CN109858737A - Rating Model method of adjustment, device and computer equipment based on model deployment - Google Patents
Rating Model method of adjustment, device and computer equipment based on model deployment Download PDFInfo
- Publication number
- CN109858737A CN109858737A CN201811552012.XA CN201811552012A CN109858737A CN 109858737 A CN109858737 A CN 109858737A CN 201811552012 A CN201811552012 A CN 201811552012A CN 109858737 A CN109858737 A CN 109858737A
- Authority
- CN
- China
- Prior art keywords
- assumptions
- data
- risks
- rating model
- model
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of Rating Model method of adjustment, device and computer equipments based on model deployment.The described method includes: the corresponding multiple user data of type of service, business datum and historical behavior data are obtained from database according to predeterminated frequency；Preset air control model is obtained according to type of service, the user data, business datum and historical behavior data are analyzed by air control model, obtain analysis result data；When there are when risk label, carrying out feature extraction in analysis result data to analysis result data, extract multiple risks and assumptions；Calculate the weight and feature dimensions angle value of multiple risks and assumptions；Rating Model is obtained according to type of service, Rating Model is adjusted according to the weight of multiple risks and assumptions and feature dimensions angle value, the Rating Model updated.The assessment accuracy rate of Rating Model can be effectively improved using this method.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of Rating Model adjustment side based on model deployment
Method, device and computer equipment.
Background technique
With the continuous development of computer technology, internet financial industry also rapidly develops therewith.Internet finance at present
Industry has penetrated into the every field such as clothing, food, lodging and transportion -- basic necessities of life, occurs some including the functions such as payment, financing, insurance, trip, consumption
All kinds of internet financial products and platform.However internet finance needs to establish good risk pipe there are certain risk
Reason system, to be managed to the risk in internet financial transaction.Therefore occur it is some by Rating Model to user's
The mode that consumer behavior is assessed carries out early warning to risk present in transaction.
However, traditional mode is carried out by history consumer behavior data of the preset Rating Model to user mostly
Analysis and scoring.And the dimensional comparison of Rating Model is single, Rating Model Yi Dan established, compare by the part that can be modified and adjust
Few, the flexibility of Rating Model is relatively low, and then causes the scoring accuracy of Rating Model lower.Therefore, how effectively to mention
The assessment accuracy rate of high Rating Model becomes the current technical issues that need to address.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, it is quasi- to provide a kind of assessment that can effectively improve Rating Model
Rating Model method of adjustment, device and the computer equipment based on model deployment of true rate.
A kind of Rating Model method of adjustment based on model deployment, comprising:
The corresponding multiple user data of type of service, business datum and history row are obtained from database according to predeterminated frequency
For data；
Preset air control model is obtained according to the type of service, by the air control model to the user data, industry
Business data and historical behavior data are analyzed, and analysis result data is obtained；
When there are when risk label, carrying out feature extraction in the analysis result data to the analysis result data, mention
Take out multiple risks and assumptions；
Calculate the weight and feature dimensions angle value of the multiple risks and assumptions；
Rating Model is obtained according to the type of service, according to the weight of the multiple risks and assumptions and feature dimensions angle value pair
The Rating Model is adjusted, the Rating Model updated.
In one of the embodiments, before the preset Rating Model according to type of service acquisition, further includes:
Obtain multiple user data, business datum and historical behavior data；To multiple user data, business datum and historical behavior data
Clustering is carried out, cluster result is obtained；Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；According to default
Algorithm calculates the corresponding weight of multiple risks and assumptions and feature dimensions angle value；According to the weight of multiple risks and assumptions and feature dimensions angle value
Rating Model is established according to predetermined manner.
The Rating Model includes multiple preset risks and assumptions in one of the embodiments, described according to described more
The weight and feature dimensions angle value of a risks and assumptions are adjusted the Rating Model, comprising: obtain in the Rating Model
The weight and feature dimensions angle value of risks and assumptions；According to multiple risks and assumptions of extraction and corresponding weight and feature dimensions angle value pair
The weight and feature dimensions angle value of risks and assumptions in the Rating Model are adjusted, risks and assumptions and correspondence after being adjusted
Weight and feature dimensions angle value；According to risks and assumptions adjusted and corresponding weight and feature dimensions angle value according to predetermined manner pair
The Rating Model is reconstructed, the Rating Model updated.
In one of the embodiments, the method also includes: receive user terminal send service request, the business
Request includes user identifier, type of service and business datum；Corresponding user's history behavior number is obtained according to the user identifier
According to；The Rating Model updated is obtained according to the type of service, by the Rating Model to the user's history behavioral data
It scores with business datum, obtains the appraisal result of the service request；It is right when the appraisal result is lower than default scoring
The service request is intercepted, and sends early warning information to corresponding monitor terminal.
In one of the embodiments, the method also includes: the corresponding user of user identifier is obtained according to predeterminated frequency
Historical behavior data and business datum；The Rating Model updated is obtained, by the Rating Model to the user's history behavior
Data and business datum score, and obtain the appraisal result of the user identifier；According to the appraisal result to the user
Mark adds corresponding scoring label, and is stored according to the user identifier.
A kind of Rating Model adjustment device based on model deployment, comprising:
Data acquisition module, for obtaining the corresponding multiple numbers of users of type of service from database according to predeterminated frequency
According to, business datum and historical behavior data；
Risk analysis module passes through the air control model for obtaining preset air control model according to the type of service
The user data, business datum and historical behavior data are analyzed, analysis result data is obtained；
Characteristic extracting module, for when in the analysis result data there are when risk label, to the analysis number of results
According to feature extraction is carried out, multiple risks and assumptions are extracted；
Computing module, for calculating the weight and feature dimensions angle value of the multiple risks and assumptions；
Model adjusts module, for obtaining Rating Model according to the type of service, according to the multiple risks and assumptions
Weight and feature dimensions angle value are adjusted the Rating Model, the Rating Model updated.
Described device further includes model building module in one of the embodiments, for obtaining multiple user data, industry
Data of being engaged in and historical behavior data；Clustering is carried out to multiple user data, business datum and historical behavior data, is gathered
Class result；Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；Multiple risks and assumptions are calculated according to preset algorithm
Corresponding weight and feature dimensions angle value；It is established and is scored according to predetermined manner according to the weight of multiple risks and assumptions and feature dimensions angle value
Model.
The Rating Model includes multiple preset risks and assumptions in one of the embodiments, and the model adjusts mould
Block is also used to obtain the weight and feature dimensions angle value of the risks and assumptions in the Rating Model；According to multiple risks and assumptions of extraction
And corresponding weight and feature dimensions angle value adjust the weight and feature dimensions angle value of the risks and assumptions in the Rating Model
It is whole, risks and assumptions and corresponding weight and feature dimensions angle value after being adjusted；According to risks and assumptions adjusted and corresponding
Weight and feature dimensions angle value are reconstructed the Rating Model according to predetermined manner, the Rating Model updated.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
The corresponding multiple user data of type of service, business datum and history row are obtained from database according to predeterminated frequency
For data；
Preset air control model is obtained according to the type of service, by the air control model to the user data, industry
Business data and historical behavior data are analyzed, and analysis result data is obtained；
When there are when risk label, carrying out feature extraction in the analysis result data to the analysis result data, mention
Take out multiple risks and assumptions；
Calculate the weight and feature dimensions angle value of the multiple risks and assumptions；
Rating Model is obtained according to the type of service, according to the weight of the multiple risks and assumptions and feature dimensions angle value pair
The Rating Model is adjusted, the Rating Model updated.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
The corresponding multiple user data of type of service, business datum and history row are obtained from database according to predeterminated frequency
For data；
Preset air control model is obtained according to the type of service, by the air control model to the user data, industry
Business data and historical behavior data are analyzed, and analysis result data is obtained；
When there are when risk label, carrying out feature extraction in the analysis result data to the analysis result data, mention
Take out multiple risks and assumptions；
Calculate the weight and feature dimensions angle value of the multiple risks and assumptions；
Rating Model is obtained according to the type of service, according to the weight of the multiple risks and assumptions and feature dimensions angle value pair
The Rating Model is adjusted, the Rating Model updated.
Above-mentioned Rating Model method of adjustment, device and computer equipment based on model deployment, according to predeterminated frequency from number
According to the corresponding multiple user data of acquisition type of service, business datum and historical behavior data in library.Obtain preset air control mould
Type analyzes user data, business datum and historical behavior data by air control model, obtains analysis result data, leads to
It crosses air control model to analyze a large number of users data, business datum and historical behavior data, can effectively analyze every kind
Risk factors present in type of service.When there are when risk label, being carried out to analysis result data special in analysis result data
Sign is extracted, and multiple risks and assumptions are extracted；Calculate the weight and feature dimensions angle value of multiple risks and assumptions.It is obtained according to type of service
Preset Rating Model is adjusted Rating Model according to the weight of multiple risks and assumptions and feature dimensions angle value, is updated
Rating Model.A large number of users data, business datum and historical behavior data are analyzed by air control model, it can be effective
Ground analyzes risks and assumptions present in every kind of type of service, and then the risks and assumptions by analyzing are corresponding to type of service
Rating Model is adjusted, and thus, it is possible to effectively carry out dynamic adjustment to Rating Model, and then can effectively improve scoring
The assessment accuracy of model.
Detailed description of the invention
Fig. 1 is the application scenario diagram of the Rating Model method of adjustment based on model deployment in one embodiment；
Fig. 2 is the flow diagram of the Rating Model method of adjustment based on model deployment in one embodiment；
Fig. 3 is the flow diagram of Rating Model establishment step in one embodiment；
Fig. 4 is the flow diagram of Rating Model set-up procedure in one embodiment；
Fig. 5 is the structural block diagram of the Rating Model adjustment device in one embodiment based on model deployment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Rating Model method of adjustment provided by the present application based on model deployment, can be applied to application as shown in Figure 1
In environment.Wherein, user terminal 102 is communicated with server 104 by network by network.Wherein, user terminal 102 can
With but be not limited to various personal computers, laptop, smart phone, tablet computer and portable wearable device, take
Business device 104 can be realized with the server cluster of the either multiple server compositions of independent server.104 basis of server
Predeterminated frequency obtains the corresponding multiple user data of type of service, business datum and historical behavior data from database.Wherein,
User data, business datum and historical behavior data can be multiple user terminals 102 and send service request, service to server
The data that the service request that device 104 sends multiple terminals generates after handling.Server 104 obtains preset air control in turn
Model analyzes user data, business datum and historical behavior data by air control model, obtains analysis result data,
A large number of users data, business datum and historical behavior data are analyzed by air control model, can effectively be analyzed every
Risk factors present in kind type of service.When there are when risk label, being carried out to analysis result data in analysis result data
Feature extraction extracts multiple risks and assumptions；Calculate the weight and feature dimensions angle value of multiple risks and assumptions.104 basis of server
Type of service obtains preset Rating Model, is adjusted according to the weight of multiple risks and assumptions and feature dimensions angle value to Rating Model
Rating Model that is whole, being updated.A large number of users data, business datum and historical behavior data are divided by air control model
Analysis can effectively analyze risks and assumptions present in every kind of type of service, and then the risks and assumptions by analyzing are to industry
The corresponding Rating Model of service type is adjusted, and thus, it is possible to effectively carry out dynamic adjustment to Rating Model, and then can be had
Improve the assessment accuracy of Rating Model in effect ground.
In one embodiment, as shown in Fig. 2, providing a kind of Rating Model method of adjustment based on model deployment, with
This method is applied to be illustrated for the server in Fig. 1, comprising the following steps:
Step 202, the corresponding multiple user data of type of service, business datum are obtained from database according to predeterminated frequency
With historical behavior data.
Operation system is deployed in server, includes multiple subservice systems in operation system.User terminal can pass through
Operation system initiating business request, includes user data and business information in service request, and server sends out multiple user terminals
After the service request sent is handled, corresponding business datum is generated, and stored according to user identifier.
Server can then obtain the corresponding a large number of users data of type of service according to predeterminated frequency from local data base
And business datum, the user data and history of multiple user identifiers can also be obtained from local data base or third party database
Behavioral data.Wherein, user data may include essential information and collage-credit data of user etc., and historical behavior data may include
Consumer behavior data and history service data of user etc..
Step 204, preset air control model is obtained according to type of service, by air control model to user data, business number
It is analyzed according to historical behavior data, obtains analysis result data.
After server obtains the corresponding user data of type of service, business datum and historical behavior data, obtain preset
Air control model.Wherein, air control model can be obtains corresponding rule template according to different types of service from template library, into
And air control model corresponding with type of service is generated according to multiple rule templates.Server then pass through the air control model of acquisition to
User data, business datum and historical behavior data are analyzed, it is possible thereby to corresponding analysis result data is effectively obtained, with
The service request is analyzed with the presence or absence of risk.It wherein, may include multinomial data and corresponding analysis knot in analysis result data
Fruit.
Step 206, when there are when risk label, carrying out feature extraction in analysis result data to analysis result data, mention
Take out multiple risks and assumptions.
Step 208, the weight and feature dimensions angle value of multiple risks and assumptions are calculated.
When there are when risk label, carrying out feature extraction to analysis result data in analysis result data.Specifically, it services
Multinomial data and corresponding analysis in device acquisition analysis result data are as a result, carry out multinomial data and corresponding analysis result
Feature extraction, whether server can meet default result value according to the corresponding analysis result of multinomial data carries out multinomial data
Screening, and the characteristic variable of the multinomial data filtered out is extracted, the characteristic variable after feature extraction is then risks and assumptions.
For example, risks and assumptions may include trade company source, network entry time, billing cycle, nature of account, business license whether
Expire with check list quantity accounting etc..Wherein, risks and assumptions may include static behavior parameter and dynamic behaviour parameter.Such as it is quiet
State behavioral parameters may include whether trade company source, network entry time, nature of account, business license expire；Dynamic behaviour parameter
It may include nearly 2 months card number moons repetitive rate, check list quantity accounting, nearly 3 months credit cards transaction accounting and 6 months nearly
Monthly turnover etc..
After server extracts corresponding multiple risks and assumptions according to multinomial data, according to multinomial data and corresponding analysis
As a result the weight and feature dimensions angle value of multiple risks and assumptions are calculated by preset algorithm.Wherein, risks and assumptions may include more
A dimension, feature dimensions angle value are the characteristic dimension belonging to each risks and assumptions are corresponding.By air control model to user data, business
Data and historical behavior data carry out risk analysis, can effectively utilize mass data and analyze present in present type of service
Risk factors.
Step 210, Rating Model is obtained according to type of service, according to the weight of multiple risks and assumptions and feature dimensions angle value pair
Rating Model is adjusted, the Rating Model updated.
After server calculates the weight and feature dimensions angle value of multiple risks and assumptions, preset comment is obtained according to type of service
Sub-model.Wherein, Rating Model can be Rating Model corresponding with type of service, and the Rating Model that server obtains can be with
It is adjusted updated Rating Model.It may include multiple scoring types in Rating Model, for example, scoring type can wrap
Include networking scoring, transaction scoring, credit scoring and comprehensive score etc..
After server calculates the weight and feature dimensions angle value of multiple risks and assumptions, then according to the weight of multiple risks and assumptions
Rating Model is adjusted with feature dimensions angle value.Specifically, Rating Model includes multiple preset risks and assumptions, and server obtains
The weight and feature dimensions angle value for taking the risks and assumptions in Rating Model, according to multiple risks and assumptions of extraction and corresponding weight
It is adjusted with weight and feature dimensions angle value of the feature dimensions angle value to the risks and assumptions in Rating Model, the risk after being adjusted
The factor and corresponding weight and feature dimensions angle value.Server is in turn according to risks and assumptions adjusted and corresponding weight and feature
Dimension values are reconstructed Rating Model according to predetermined manner, the Rating Model updated.It is used by air control model a large amount of
User data, business datum and historical behavior data are analyzed, and wind present in every kind of type of service can be effectively analyzed
The dangerous factor, and then the risks and assumptions by analyzing are adjusted the corresponding Rating Model of type of service, thus, it is possible to effective
Ground carries out dynamic adjustment to Rating Model, and then can effectively improve the assessment accuracy of Rating Model.
Further, after server is adjusted Rating Model, then it can use updated Rating Model to user
Consumer behavior score, user may include personal user and trade company.For example, server can be obtained according to user identifier
Corresponding user data and consumer behavior data may include static behavior parameter and dynamic behaviour ginseng in consumer behavior data
Number.Such as static behavior parameter may include whether trade company source, network entry time, nature of account, business license expire；Dynamically
Behavioral parameters may include nearly 2 months card number moons repetitive rate, check list quantity accounting, nearly 3 months credit cards transaction accounting and
Nearly 6 months monthly turnovers etc..The user data of the user and consumer behavior data are then input to Rating Model by server
In, obtain the appraisal result of the user.It wherein, can also include subitem scoring and comprehensive score in appraisal result.When scoring is tied
When fruit is not up to preset threshold, then risk label is added to the user, and send early warning information to corresponding monitor terminal,
So that corresponding monitoring personnel is monitored and manages to the user using monitor terminal.Rating Model pair by adjusting after
User scores, and thus, it is possible to effectively assess the user with the presence or absence of risk, and then can effectively ensure business or friendship
Easy safety.
In the above-mentioned Rating Model method of adjustment based on model deployment, server is obtained from database according to predeterminated frequency
The corresponding multiple user data of type of service, business datum and historical behavior data.Server obtains preset air control mould in turn
Type analyzes user data, business datum and historical behavior data by air control model, obtains analysis result data, leads to
It crosses air control model to analyze a large number of users data, business datum and historical behavior data, can effectively analyze every kind
Risk factors present in type of service.When there are when risk label, being carried out to analysis result data special in analysis result data
Sign is extracted, and multiple risks and assumptions are extracted；Calculate the weight and feature dimensions angle value of multiple risks and assumptions.Server is according to service class
Type obtains preset Rating Model, is adjusted, is obtained to Rating Model according to the weight of multiple risks and assumptions and feature dimensions angle value
To the Rating Model of update.A large number of users data, business datum and historical behavior data are analyzed by air control model, energy
It is enough effectively to analyze risks and assumptions present in every kind of type of service, and then the risks and assumptions by analyzing are to type of service
Corresponding Rating Model is adjusted, and thus, it is possible to effectively carry out dynamic adjustment to Rating Model, and then can effectively be mentioned
The assessment accuracy of high Rating Model.
In one embodiment, as shown in figure 3, further including building before obtaining preset Rating Model according to type of service
The step of vertical Rating Model, which specifically includes the following contents:
Step 302, multiple user data, business datum and historical behavior data are obtained.
Step 304, clustering is carried out to multiple user data, business datum and historical behavior data, obtains cluster knot
Fruit.
Step 306, feature selecting is carried out according to cluster result, obtains multiple risks and assumptions.
Before obtaining preset Rating Model according to type of service, server can be from local data base or third number formulary
According to a large amount of user data, business datum and historical behavior data are obtained in library, server is in turn to a large number of users number of acquisition
Clustering is carried out according to, business datum and historical behavior data.Specifically, server to a large number of users data, business datum and
Historical behavior data carry out feature extraction, extract corresponding characteristic variable.Server extracts a large number of users data, business number
After characteristic variable corresponding with historical behavior data, clustering is carried out using preset clustering algorithm characteristic variable.For example,
Preset clustering algorithm can be the method for k-means (k- mean algorithm) cluster.Server is more by carrying out to characteristic variable
Multiple cluster results are obtained after secondary cluster.
Server is further respectively combined the characteristic variable in multiple cluster results, obtains multiple assemblage characteristics and becomes
Amount.Target variable is obtained, correlation test is carried out to multiple assemblage characteristic variables using target variable.When upchecking, to group
It closes characteristic variable and adds interactive tag.Utilize the corresponding characteristic variable of assemblage characteristic variable resolution after addition interactive tag.Add
Assemblage characteristic variable after adding interactive tag can be the characteristic variable for reaching preset threshold, and server, which then extracts, reaches default
Threshold trait variable, the characteristic variable for reaching threshold value is risks and assumptions.
Step 308, the corresponding weight of multiple risks and assumptions and feature dimensions angle value are calculated according to preset algorithm.
Step 310, Rating Model is established according to predetermined manner according to the weight of multiple risks and assumptions and feature dimensions angle value.
Server carries out spy by carrying out clustering to multiple user data, business datum and historical behavior data
Sign selection, after obtaining multiple risks and assumptions, further calculates the corresponding weight of multiple risks and assumptions and spy according to preset algorithm
Levy dimension values.After server calculates the corresponding weight of multiple risks and assumptions and feature dimensions angle value, then according to multiple risks and assumptions
Corresponding weight and feature dimensions angle value establish Rating Model according to predetermined manner.Wherein, Rating Model can be based on decision tree
Or model neural network based.
Further, a large amount of user data, business datum and the historical behavior data that server can also will acquire are raw
At trained and data and verifying collection data.Server carries out clustering to the mass data in training set, obtains cluster result
Afterwards, feature selecting is carried out according to cluster result, obtains multiple risks and assumptions.Server then calculates multiple risks according to preset algorithm
The corresponding weight of the factor and feature dimensions angle value, and then according to the corresponding weight of multiple risks and assumptions and feature dimensions angle value according to default
Mode establishes raw score model.
After server establishes raw score model, raw score model is carried out into one using the mass data that verifying is concentrated
Step training and verifying, when the data for the default assessed value of satisfaction that verifying is concentrated reach default ratio, the scoring mould established
Type.After being analyzed to a large amount of user data, business datum and historical behavior data and selecting risks and assumptions, utilize
Risks and assumptions establish Rating Model according to predetermined manner, and thus, it is possible to be effectively constructed out Rating Model.
In one embodiment, as shown in figure 4, Rating Model includes multiple preset risks and assumptions, according to multiple risks
The step of weight and feature dimensions angle value of the factor are adjusted Rating Model, specifically includes the following contents:
Step 402, the weight and feature dimensions angle value of the risks and assumptions in Rating Model are obtained；
Step 404, according to multiple risks and assumptions of extraction and corresponding weight and feature dimensions angle value in Rating Model
Risks and assumptions weight and feature dimensions angle value be adjusted, risks and assumptions and corresponding weight and feature dimensions after being adjusted
Angle value.
Step 406, according to risks and assumptions adjusted and corresponding weight and feature dimensions angle value according to predetermined manner to commenting
Sub-model is reconstructed, the Rating Model updated.
Server obtained from database according to predeterminated frequency the corresponding multiple user data of type of service, business datum and
After historical behavior data, preset air control model is obtained according to type of service, by air control model to user data, business datum
It is analyzed with historical behavior data, obtains analysis result data.When in analysis result data there are when risk label, to analysis
Result data carries out feature extraction, extracts multiple risks and assumptions.Server calculates multiple risks according to preset algorithm in turn
The weight and feature dimensions angle value of the factor.
After server calculates the weight and feature dimensions angle value of multiple risks and assumptions, preset comment is obtained according to type of service
Sub-model.Wherein, Rating Model can be Rating Model corresponding with type of service.It may include multiple comment in Rating Model
Classifying type, for example, scoring type may include network scoring, transaction scoring, credit scoring and comprehensive score etc..
Server is further adjusted Rating Model according to the weight of multiple risks and assumptions and feature dimensions angle value, specifically
Ground, Rating Model include multiple preset risks and assumptions, and server obtains the weight and feature of the risks and assumptions in Rating Model
Dimension values, according to multiple risks and assumptions of extraction and corresponding weight and feature dimensions angle value to the risks and assumptions in Rating Model
Weight and feature dimensions angle value be adjusted, risks and assumptions and corresponding weight and feature dimensions angle value after being adjusted.For example,
When, there is no when the risks and assumptions extracted, the risks and assumptions that will be not present are added in Rating Model in Rating Model；When commenting
When the weight and dimensional characteristics difference of the risks and assumptions of the weight and dimensional characteristics and extraction of the risks and assumptions in sub-model, by wind
The original weight of the dangerous factor and dimensional characteristics are revised as extracting again and the weight and dimensional characteristics of calculated risks and assumptions.
Server is in turn according to risks and assumptions adjusted and corresponding weight and feature dimensions angle value according to predetermined manner pair
Rating Model is reconstructed, the Rating Model updated.By utilizing the risks and assumptions analyzed to industry according to predeterminated frequency
The corresponding Rating Model of service type is adjusted, and thus, it is possible to effectively carry out dynamic adjustment to Rating Model, and then can be had
Improve the assessment accuracy of Rating Model in effect ground.
In one embodiment, this method further include: receive the service request that user terminal is sent, service request includes using
Family mark, type of service and business datum；Corresponding user's history behavioral data is obtained according to user identifier；According to type of service
The Rating Model updated is obtained, is scored by Rating Model user's history behavioral data and business datum, obtains business
The appraisal result of request；When appraisal result is lower than default scoring, service request is intercepted, and to corresponding monitor terminal
Send early warning information.
Server obtained from database according to predeterminated frequency the corresponding multiple user data of type of service, business datum and
After historical behavior data, preset air control model is obtained according to type of service, by air control model to user data, business datum
It is analyzed with historical behavior data, obtains analysis result data.When in analysis result data there are when risk label, to analysis
Result data carries out feature extraction, extracts multiple risks and assumptions.Server calculates multiple risks according to preset algorithm in turn
The weight and feature dimensions angle value of the factor obtain preset Rating Model according to type of service, according to the weight of multiple risks and assumptions
Rating Model is adjusted with feature dimensions angle value, the Rating Model updated.
After server is adjusted update to Rating Model, then it can receive the service request of user terminal transmission, business
Request includes user identifier, type of service and business datum.Server obtains corresponding user's history according to user identifier in turn
Behavioral data, and the Rating Model updated is obtained according to type of service, by Rating Model to user's history behavioral data and industry
Business data score.Specifically, server in turn carries out user's history behavioral data and business datum according to predetermined manner
Feature extraction extracts user's history behavioral data and the corresponding characteristic variable of business datum.Server is then by the feature of extraction
Variable is input in Rating Model, carries out risk analysis to user's history behavioral data and business datum by Rating Model, and
Export corresponding appraisal result.
It may include the corresponding result information of multiple scoring types in obtained appraisal result.When appraisal result reaches default
When scoring, server is then further handled the service request, generates corresponding business processing data, and mark according to user
Knowledge stores business processing data.
When appraisal result is lower than default scoring, service request is intercepted, and is sent in advance to corresponding monitor terminal
Alert prompt information, to prompt corresponding monitoring personnel to carry out early warning and audit to the service request.By being commented using updated
Sub-model carries out risk assessment to the service request of user, can effectively assess the user or the service request with the presence or absence of wind
Danger, and then can effectively ensure the safety in business processing or process of exchange.
In one embodiment, this method further include: the corresponding user's history row of user identifier is obtained according to predeterminated frequency
For data and business datum；The Rating Model updated is obtained, by Rating Model to user's history behavioral data and business datum
It scores, obtains the appraisal result of user identifier；Corresponding scoring label, and root are added to user identifier according to appraisal result
It is stored according to user identifier.
Server obtained from database according to predeterminated frequency the corresponding multiple user data of type of service, business datum and
After historical behavior data, preset air control model is obtained according to type of service, by air control model to user data, business datum
It is analyzed with historical behavior data, obtains analysis result data.When in analysis result data there are when risk label, to analysis
Result data carries out feature extraction, extracts multiple risks and assumptions.Server calculates multiple risks according to preset algorithm in turn
The weight and feature dimensions angle value of the factor obtain preset Rating Model according to type of service, according to the weight of multiple risks and assumptions
Rating Model is adjusted with feature dimensions angle value, the Rating Model updated.
After server is adjusted update to Rating Model, user terminal can by operation system initiating business request,
Service request includes user identifier, type of service and business datum.After server receives the service request that user terminal is sent, root
Corresponding user's history behavioral data is obtained according to user identifier, and obtains the Rating Model updated according to type of service, by commenting
Sub-model scores to user's history behavioral data and business datum, obtains the appraisal result of the service request.When scoring is tied
When fruit reaches default scoring, service request is handled, generates corresponding business datum after processing, and according to user identifier into
Row storage.
Server can obtain the corresponding user's history behavioral data of user identifier and business further according to predeterminated frequency
Data and business processing data, such as predeterminated frequency can be the frequencys such as one day, one week, two weeks or one month.Server is then
Updated Rating Model is obtained, is scored by Rating Model user's history behavioral data and business datum.Specifically,
Server carries out feature extraction to user's history behavioral data, business datum and business processing data according to predetermined manner, mentions
Take out user's history behavioral data, business datum and the corresponding characteristic variable of business processing data.Server is then by extraction
Characteristic variable is input in Rating Model, carries out risk point to user's history behavioral data and business datum by Rating Model
Analysis, and corresponding appraisal result is exported, thus obtain the appraisal result of user identifier.Server so according to appraisal result to
Family mark adds corresponding scoring label, and is stored according to user identifier to appraisal result and scoring label.By real-time
Updated Rating Model is analyzed according to user's history behavioral data and business datum of the preset frequency to user identifier,
Thus, it is possible to the risks accurately and effectively to user to carry out dynamic evaluation, so as to effectively improve the efficiency of risk assessment, into
And early warning effectively can be carried out to risk existing for user.
Further, monitor terminal can inquire the appraisal result of multiple users.Specifically, monitor terminal can be to service
Device sends inquiry request, carries user identifier in inquiry request, the history appraisal result of the user is obtained according to user identifier.
Further, monitor terminal can according to the appraisal result of user to the relevant service authority of user setting, or to server send out
It send and comments request again, scored again the user.It is monitored by risk status of the monitor terminal to user, Neng Gouyou
Effect ground carries out early warning to risk existing for user.
It should be understood that although each step in the flow chart of Fig. 2-4 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-4
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 5, providing a kind of Rating Model adjustment device based on model deployment, packet
It includes: data acquisition module 502, risk analysis module 504, characteristic extracting module 506, computing module 508 and model adjustment module
510, in which:
Data acquisition module 502, for obtaining the corresponding multiple users of type of service from database according to predeterminated frequency
Data, business datum and historical behavior data；
Risk analysis module 504, for obtaining preset air control model according to type of service, by air control model to user
Data, business datum and historical behavior data are analyzed, and analysis result data is obtained；
Characteristic extracting module 506, for when there are when risk label, being carried out to analysis result data in analysis result data
Feature extraction extracts multiple risks and assumptions；
Computing module 508, for calculating the weight and feature dimensions angle value of multiple risks and assumptions；
Model adjusts module 510, for obtaining Rating Model according to type of service, according to the weight of multiple risks and assumptions and
Feature dimensions angle value is adjusted the Rating Model, the Rating Model updated.
The device further includes model building module in one of the embodiments, for obtaining multiple user data, business
Data and historical behavior data；Clustering is carried out to multiple user data, business datum and historical behavior data, is clustered
As a result；Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；Multiple risks and assumptions pair are calculated according to preset algorithm
The weight and feature dimensions angle value answered；Scoring mould is established according to predetermined manner according to the weight of multiple risks and assumptions and feature dimensions angle value
Type.
Rating Model includes multiple preset risks and assumptions in one of the embodiments, and model adjustment module 510 is also used
In the weight and feature dimensions angle value that obtain the risks and assumptions in Rating Model；According to multiple risks and assumptions of extraction and corresponding
Weight and feature dimensions angle value are adjusted the weight and feature dimensions angle value of the risks and assumptions in Rating Model, after being adjusted
Risks and assumptions and corresponding weight and feature dimensions angle value；According to risks and assumptions adjusted and corresponding weight and feature dimensions angle value
Rating Model is reconstructed according to predetermined manner, the Rating Model updated.
The device further includes service request grading module in one of the embodiments, is sent for receiving user terminal
Service request, service request includes user identifier, type of service and business datum；Corresponding user is obtained according to user identifier
Historical behavior data；The Rating Model updated is obtained according to type of service, by Rating Model to user's history behavioral data and
Business datum scores, and obtains the appraisal result of service request；When appraisal result is lower than default scoring, to service request into
Row intercepts, and sends early warning information to corresponding monitor terminal.
The device further includes user's grading module in one of the embodiments, for obtaining user according to predeterminated frequency
Identify corresponding user's history behavioral data and business datum；The Rating Model updated is obtained, by Rating Model to the use
Family historical behavior data and business datum score, and obtain the appraisal result of user identifier；User is marked according to appraisal result
Know and add corresponding scoring label, and is stored according to user identifier.
Specific restriction about the Rating Model adjustment device disposed based on model may refer to above for based on mould
The restriction of the Rating Model method of adjustment of type deployment, details are not described herein.The above-mentioned Rating Model based on model deployment adjusts dress
Modules in setting can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be in the form of hardware
It is embedded in or independently of the storage that in the processor in computer equipment, can also be stored in a software form in computer equipment
In device, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing the data such as user data, business datum and historical behavior data.The net of the computer equipment
Network interface is used to communicate with external terminal by network connection.To realize a kind of base when the computer program is executed by processor
In the Rating Model method of adjustment of model deployment.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
The corresponding multiple user data of type of service, business datum and history row are obtained from database according to predeterminated frequency
For data；
Obtain preset air control model according to type of service, by air control model to the user data, business datum and
Historical behavior data are analyzed, and analysis result data is obtained；
When there are when risk label, carrying out feature extraction in analysis result data to analysis result data, extract multiple
Risks and assumptions；
Calculate the weight and feature dimensions angle value of multiple risks and assumptions；
Rating Model is obtained according to type of service, according to the weight of multiple risks and assumptions and feature dimensions angle value to Rating Model
It is adjusted, the Rating Model updated.
In one embodiment, also performed the steps of when processor executes computer program obtain multiple user data,
Business datum and historical behavior data；Clustering is carried out to multiple user data, business datum and historical behavior data, is obtained
Cluster result；Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；According to preset algorithm calculate multiple risks because
The corresponding weight of son and feature dimensions angle value；It is commented according to the weight of multiple risks and assumptions and feature dimensions angle value according to predetermined manner foundation
Sub-model.
In one embodiment, Rating Model includes multiple preset risks and assumptions, when processor executes computer program
Also perform the steps of the weight and feature dimensions angle value for obtaining the risks and assumptions in Rating Model；According to multiple risks of extraction
The factor and corresponding weight and feature dimensions angle value adjust the weight and feature dimensions angle value of the risks and assumptions in Rating Model
It is whole, risks and assumptions and corresponding weight and feature dimensions angle value after being adjusted；According to risks and assumptions adjusted and corresponding
Weight and feature dimensions angle value are reconstructed Rating Model according to predetermined manner, the Rating Model updated.
In one embodiment, it is also performed the steps of when processor executes computer program and receives user terminal transmission
Service request, service request includes user identifier, type of service and business datum；Corresponding user is obtained according to user identifier
Historical behavior data；The Rating Model updated is obtained according to type of service, by Rating Model to user's history behavioral data and
Business datum scores, and obtains the appraisal result of service request；When appraisal result is lower than default scoring, to service request into
Row intercepts, and sends early warning information to corresponding monitor terminal.
In one embodiment, it also performs the steps of when processor executes computer program and is obtained according to predeterminated frequency
The corresponding user's history behavioral data of user identifier and business datum；The Rating Model updated is obtained, by Rating Model to institute
It states user's history behavioral data and business datum scores, obtain the appraisal result of user identifier；According to appraisal result to
Family mark adds corresponding scoring label, and is stored according to user identifier.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
The corresponding multiple user data of type of service, business datum and history row are obtained from database according to predeterminated frequency
For data；
Obtain preset air control model according to type of service, by air control model to the user data, business datum and
Historical behavior data are analyzed, and analysis result data is obtained；
When there are when risk label, carrying out feature extraction in analysis result data to analysis result data, extract multiple
Risks and assumptions；
Calculate the weight and feature dimensions angle value of multiple risks and assumptions；
Rating Model is obtained according to type of service, according to the weight of multiple risks and assumptions and feature dimensions angle value to Rating Model
It is adjusted, the Rating Model updated.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains multiple numbers of users
According to, business datum and historical behavior data；Clustering is carried out to multiple user data, business datum and historical behavior data,
Obtain cluster result；Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；Multiple wind are calculated according to preset algorithm
The corresponding weight of the dangerous factor and feature dimensions angle value；It is built according to the weight of multiple risks and assumptions and feature dimensions angle value according to predetermined manner
Vertical Rating Model.
In one embodiment, Rating Model includes multiple preset risks and assumptions, and computer program is executed by processor
When also perform the steps of obtain Rating Model in risks and assumptions weight and feature dimensions angle value；According to multiple wind of extraction
The dangerous factor and corresponding weight and feature dimensions angle value carry out the weight and feature dimensions angle value of the risks and assumptions in Rating Model
Adjustment, risks and assumptions and corresponding weight and feature dimensions angle value after being adjusted；According to risks and assumptions adjusted and correspondence
Weight and feature dimensions angle value Rating Model is reconstructed according to predetermined manner, the Rating Model updated.
In one embodiment, it is also performed the steps of when computer program is executed by processor and receives user terminal hair
The service request sent, service request include user identifier, type of service and business datum；Corresponding use is obtained according to user identifier
Family historical behavior data；The Rating Model updated is obtained according to type of service, by Rating Model to user's history behavioral data
It scores with business datum, obtains the appraisal result of service request；When appraisal result is lower than default scoring, to service request
It is intercepted, and sends early warning information to corresponding monitor terminal.
In one embodiment, it also performs the steps of when computer program is executed by processor and is obtained according to predeterminated frequency
Take the corresponding user's history behavioral data of user identifier and business datum；The Rating Model updated is obtained, Rating Model pair is passed through
The user's history behavioral data and business datum score, and obtain the appraisal result of user identifier；According to appraisal result pair
User identifier adds corresponding scoring label, and is stored according to user identifier.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of Rating Model method of adjustment based on model deployment, comprising:
The corresponding multiple user data of type of service, business datum and historical behavior number are obtained from database according to predeterminated frequency
According to；
Preset air control model is obtained according to the type of service, by the air control model to the user data, business number
It is analyzed according to historical behavior data, obtains analysis result data；
When there are when risk label, carrying out feature extraction in the analysis result data to the analysis result data, extract
Multiple risks and assumptions；
Calculate the weight and feature dimensions angle value of the multiple risks and assumptions；
Rating Model is obtained according to the type of service, according to the weight of the multiple risks and assumptions and feature dimensions angle value to described
Rating Model is adjusted, the Rating Model updated.
2. the method according to claim 1, wherein described obtain preset scoring mould according to the type of service
Before type, further includes:
Obtain multiple user data, business datum and historical behavior data；
Clustering is carried out to multiple user data, business datum and historical behavior data, obtains cluster result；
Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；
The corresponding weight of multiple risks and assumptions and feature dimensions angle value are calculated according to preset algorithm；
Rating Model is established according to predetermined manner according to the weight of multiple risks and assumptions and feature dimensions angle value.
3. the method according to claim 1, wherein the Rating Model includes multiple preset risks and assumptions,
It is described that the Rating Model is adjusted according to the weight and feature dimensions angle value of the multiple risks and assumptions, comprising:
Obtain the weight and feature dimensions angle value of the risks and assumptions in the Rating Model；
According to multiple risks and assumptions of extraction and corresponding weight and feature dimensions angle value to the risk in the Rating Model because
The weight and feature dimensions angle value of son are adjusted, risks and assumptions and corresponding weight and feature dimensions angle value after being adjusted；
According to risks and assumptions adjusted and corresponding weight and feature dimensions angle value according to predetermined manner to the Rating Model into
Row reconstruct, the Rating Model updated.
4. according to claim 1 to method described in 3 any one, which is characterized in that the method also includes:
The service request that user terminal is sent is received, the service request includes user identifier, type of service and business datum；
Corresponding user's history behavioral data is obtained according to the user identifier；
The Rating Model updated is obtained according to the type of service, by the Rating Model to the user's history behavioral data
It scores with business datum, obtains the appraisal result of the service request；
When the appraisal result is lower than default scoring, the service request is intercepted, and is sent out to corresponding monitor terminal
Send early warning information.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
The corresponding user's history behavioral data of user identifier and business datum are obtained according to predeterminated frequency；
The Rating Model updated is obtained, the user's history behavioral data and business datum are commented by the Rating Model
Point, obtain the appraisal result of the user identifier；
Corresponding scoring label is added to the user identifier according to the appraisal result, and is deposited according to the user identifier
Storage.
6. a kind of Rating Model based on model deployment adjusts device, comprising:
Data acquisition module, for obtaining the corresponding multiple user data of type of service, industry from database according to predeterminated frequency
Data of being engaged in and historical behavior data；
Risk analysis module, for obtaining preset air control model according to the type of service, by the air control model to institute
It states user data, business datum and historical behavior data to be analyzed, obtains analysis result data；
Characteristic extracting module, for when in the analysis result data there are when risk label, to the analysis result data into
Row feature extraction extracts multiple risks and assumptions；
Computing module, for calculating the weight and feature dimensions angle value of the multiple risks and assumptions；
Model adjusts module, for obtaining Rating Model according to the type of service, according to the weight of the multiple risks and assumptions
The Rating Model is adjusted with feature dimensions angle value, the Rating Model updated.
7. device according to claim 6, which is characterized in that described device further includes model building module, for obtaining
Multiple user data, business datum and historical behavior data；Multiple user data, business datum and historical behavior data are carried out
Clustering obtains cluster result；Feature selecting is carried out according to cluster result, obtains multiple risks and assumptions；According to preset algorithm
Calculate the corresponding weight of multiple risks and assumptions and feature dimensions angle value；According to the weight of multiple risks and assumptions and feature dimensions angle value according to
Predetermined manner establishes Rating Model.
8. device according to claim 6, which is characterized in that the Rating Model includes multiple preset risks and assumptions,
The model adjustment module is also used to obtain the weight and feature dimensions angle value of the risks and assumptions in the Rating Model；According to extraction
Weight and spy to the risks and assumptions in the Rating Model of multiple risks and assumptions and corresponding weight and feature dimensions angle value
Sign dimension values are adjusted, risks and assumptions and corresponding weight and feature dimensions angle value after being adjusted；According to wind adjusted
The dangerous factor and corresponding weight and feature dimensions angle value are reconstructed the Rating Model according to predetermined manner, and what is updated comments
Sub-model.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 5 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552012.XA CN109858737B (en) | 2018-12-18 | 2018-12-18 | Grading model adjustment method and device based on model deployment and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552012.XA CN109858737B (en) | 2018-12-18 | 2018-12-18 | Grading model adjustment method and device based on model deployment and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109858737A true CN109858737A (en) | 2019-06-07 |
| CN109858737B CN109858737B (en) | 2023-04-25 |
Family
ID=66891510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811552012.XA Active CN109858737B (en) | 2018-12-18 | 2018-12-18 | Grading model adjustment method and device based on model deployment and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858737B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322349A (en) * | 2019-06-25 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of processing method of data, device and equipment |
| CN110428087A (en) * | 2019-06-25 | 2019-11-08 | 万翼科技有限公司 | Business stability prediction technique, device, computer equipment and storage medium |
| CN110493190A (en) * | 2019-07-15 | 2019-11-22 | 平安科技（深圳）有限公司 | Processing method, device, computer equipment and the storage medium of data information |
| CN110493181A (en) * | 2019-07-05 | 2019-11-22 | 中国平安财产保险股份有限公司 | User behavior detection method, device, computer equipment and storage medium |
| CN110659800A (en) * | 2019-08-15 | 2020-01-07 | 平安科技（深圳）有限公司 | Risk monitoring processing method and device, computer equipment and storage medium |
| CN110765127A (en) * | 2019-09-16 | 2020-02-07 | 平安科技（深圳）有限公司 | Method, device and equipment for scoring fact data and storage medium |
| CN110874743A (en) * | 2019-10-11 | 2020-03-10 | 支付宝(杭州)信息技术有限公司 | Method and device for determining account transaction risk |
| CN110909384A (en) * | 2019-11-19 | 2020-03-24 | 支付宝(杭州)信息技术有限公司 | Method and device for determining business party revealing user information |
| CN111047417A (en) * | 2019-12-24 | 2020-04-21 | 北京每日优鲜电子商务有限公司 | Service monitoring method, device, equipment and storage medium |
| CN111078880A (en) * | 2019-12-12 | 2020-04-28 | 支付宝(杭州)信息技术有限公司 | Risk identification method and device for sub-application |
| CN111523826A (en) * | 2020-05-11 | 2020-08-11 | 支付宝(杭州)信息技术有限公司 | Data acquisition method, device and equipment |
| CN112200586A (en) * | 2020-11-16 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Identity authentication method and device |
| TWI739432B (en) * | 2019-09-26 | 2021-09-11 | 大陸商支付寶（杭州）信息技術有限公司 | Intelligent risk control decision-making method and system, business processing method and system |
| CN114861939A (en) * | 2022-07-07 | 2022-08-05 | 浙江邦业科技股份有限公司 | AHP model self-learning-based energy consumption analysis method and device |
| CN115496553A (en) * | 2022-09-20 | 2022-12-20 | 青岛畅联科技有限公司 | User credit evaluation system and method based on trusted computing under edge computing |
| CN116977062A (en) * | 2023-08-04 | 2023-10-31 | 江苏臻云技术有限公司 | Risk label management system and method for financial business |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110137704A1 (en) * | 2009-12-09 | 2011-06-09 | Infosys Technologies Limited | System and method for calculating a comprehensive pipeline integrity business risk score |
| CN108615190A (en) * | 2018-04-27 | 2018-10-02 | 深圳市分期乐网络科技有限公司 | Air control model verification method, device, equipment and storage medium |
-
2018
- 2018-12-18 CN CN201811552012.XA patent/CN109858737B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110137704A1 (en) * | 2009-12-09 | 2011-06-09 | Infosys Technologies Limited | System and method for calculating a comprehensive pipeline integrity business risk score |
| CN108615190A (en) * | 2018-04-27 | 2018-10-02 | 深圳市分期乐网络科技有限公司 | Air control model verification method, device, equipment and storage medium |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428087A (en) * | 2019-06-25 | 2019-11-08 | 万翼科技有限公司 | Business stability prediction technique, device, computer equipment and storage medium |
| CN110322349A (en) * | 2019-06-25 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of processing method of data, device and equipment |
| CN110322349B (en) * | 2019-06-25 | 2023-08-22 | 创新先进技术有限公司 | Data processing method, device and equipment |
| CN110493181A (en) * | 2019-07-05 | 2019-11-22 | 中国平安财产保险股份有限公司 | User behavior detection method, device, computer equipment and storage medium |
| CN110493181B (en) * | 2019-07-05 | 2023-04-07 | 中国平安财产保险股份有限公司 | User behavior detection method and device, computer equipment and storage medium |
| CN110493190A (en) * | 2019-07-15 | 2019-11-22 | 平安科技（深圳）有限公司 | Processing method, device, computer equipment and the storage medium of data information |
| CN110493190B (en) * | 2019-07-15 | 2022-07-08 | 平安科技（深圳）有限公司 | Data information processing method and device, computer equipment and storage medium |
| CN110659800A (en) * | 2019-08-15 | 2020-01-07 | 平安科技（深圳）有限公司 | Risk monitoring processing method and device, computer equipment and storage medium |
| CN110765127A (en) * | 2019-09-16 | 2020-02-07 | 平安科技（深圳）有限公司 | Method, device and equipment for scoring fact data and storage medium |
| CN110765127B (en) * | 2019-09-16 | 2024-05-14 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for scoring fact data |
| TWI739432B (en) * | 2019-09-26 | 2021-09-11 | 大陸商支付寶（杭州）信息技術有限公司 | Intelligent risk control decision-making method and system, business processing method and system |
| CN110874743A (en) * | 2019-10-11 | 2020-03-10 | 支付宝(杭州)信息技术有限公司 | Method and device for determining account transaction risk |
| CN110874743B (en) * | 2019-10-11 | 2023-04-07 | 支付宝(杭州)信息技术有限公司 | Method and device for determining account transaction risk |
| CN110909384A (en) * | 2019-11-19 | 2020-03-24 | 支付宝(杭州)信息技术有限公司 | Method and device for determining business party revealing user information |
| CN111078880A (en) * | 2019-12-12 | 2020-04-28 | 支付宝(杭州)信息技术有限公司 | Risk identification method and device for sub-application |
| CN111047417A (en) * | 2019-12-24 | 2020-04-21 | 北京每日优鲜电子商务有限公司 | Service monitoring method, device, equipment and storage medium |
| CN111523826A (en) * | 2020-05-11 | 2020-08-11 | 支付宝(杭州)信息技术有限公司 | Data acquisition method, device and equipment |
| CN111523826B (en) * | 2020-05-11 | 2022-06-24 | 支付宝(杭州)信息技术有限公司 | Data acquisition method, device and equipment |
| CN112200586A (en) * | 2020-11-16 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Identity authentication method and device |
| CN112200586B (en) * | 2020-11-16 | 2022-07-08 | 支付宝(杭州)信息技术有限公司 | Identity authentication method and device |
| CN114861939B (en) * | 2022-07-07 | 2022-10-18 | 浙江邦业科技股份有限公司 | AHP model self-learning-based energy consumption analysis method and device |
| CN114861939A (en) * | 2022-07-07 | 2022-08-05 | 浙江邦业科技股份有限公司 | AHP model self-learning-based energy consumption analysis method and device |
| CN115496553A (en) * | 2022-09-20 | 2022-12-20 | 青岛畅联科技有限公司 | User credit evaluation system and method based on trusted computing under edge computing |
| CN115496553B (en) * | 2022-09-20 | 2023-10-17 | 青岛畅联科技有限公司 | User credit evaluation system and method based on trusted computing under edge computing |
| CN116977062A (en) * | 2023-08-04 | 2023-10-31 | 江苏臻云技术有限公司 | Risk label management system and method for financial business |
| CN116977062B (en) * | 2023-08-04 | 2024-01-23 | 江苏臻云技术有限公司 | Risk label management system and method for financial business |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109858737B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858737A (en) | Rating Model method of adjustment, device and computer equipment based on model deployment | |
| CN109636607A (en) | Business data processing method, device and computer equipment based on model deployment | |
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| US11734692B2 (en) | Data breach detection | |
| WO2020253358A1 (en) | Service data risk control analysis processing method, apparatus and computer device | |
| CN110929879A (en) | Business decision logic updating method based on decision engine and model platform | |
| CN110490720A (en) | Financial data analysis and early warning method, apparatus, computer equipment and storage medium | |
| CN109345374A (en) | Risk control method, device, computer equipment and storage medium | |
| CN109783338A (en) | Recording method, device and computer equipment based on business information | |
| CN109087208B (en) | Pre-loan data processing method, pre-loan data processing device, computer equipment and storage medium | |
| CN109120429B (en) | Risk identification method and system | |
| CN110866820A (en) | Real-time monitoring system, method, equipment and storage medium for banking business | |
| CN110009225A (en) | Risk evaluating system construction method, device, computer equipment and storage medium | |
| CN109949154A (en) | Customer information classification method, device, computer equipment and storage medium | |
| CN110474871A (en) | A kind of exception account detection method, device, computer equipment and storage medium | |
| CN110363645A (en) | Asset data processing method, device, computer equipment and storage medium | |
| CN109767226A (en) | Suspicious transaction statistical views generation method and device based on big data | |
| CN109871445A (en) | Fraudulent user recognition methods, device, computer equipment and storage medium | |
| CN109857373A (en) | Business data processing method, device, computer equipment and storage medium | |
| Kolodiziev et al. | Automatic machine learning algorithms for fraud detection in digital payment systems | |
| CN112612813A (en) | Test data generation method and device | |
| CN110084606A (en) | Risk control method, device, computer equipment and storage medium | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN109523124A (en) | Asset data processing method, device, computer equipment and storage medium | |
| CN113888299A (en) | Wind control decision method and device, computer equipment and storage medium |
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 |