CN110533527A - A kind of credit risk dynamic assessment method, system, medium and equipment - Google Patents
A kind of credit risk dynamic assessment method, system, medium and equipment Download PDFInfo
- Publication number
- CN110533527A CN110533527A CN201910806315.8A CN201910806315A CN110533527A CN 110533527 A CN110533527 A CN 110533527A CN 201910806315 A CN201910806315 A CN 201910806315A CN 110533527 A CN110533527 A CN 110533527A
- Authority
- CN
- China
- Prior art keywords
- credit
- risk
- index
- weight
- assessment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention proposes a kind of credit risk dynamic assessment method, system, medium and equipment, comprising: the credit demand of acquisition financial business object carries out multidimensional risk assessment according to the credit demand;Comprehensive assessment result is obtained according to the multidimensional risk assessment;The present invention can effectively reduce operator's workload by intuitive evaluation mechanism, while reduce the requirement to operator's professional standards.
Description
Technical field
The present invention relates to credit financing field more particularly to a kind of credit risk dynamic assessment method, system, medium and set
It is standby.
Background technique
Nowadays big data platform has demand more and more widely, more and more banks and mechanism in financial air control field
Model is constructed using big data platform, handles data, information is provided, auxiliary user makes a policy.Even to this day, big data platform
Have become the indispensable important tool in financial field.
However, there is also certain limitations to require user high if information is not heterogeneous smart for big data platform at present.Greatly
Data platform generates a large amount of information by logical process using a large amount of data.These information are related to the side of a product
Aspect face, although comprehensively, also carrying out analysis decision to user and causing difficulty.And the bulk information that platform generates, still need
Professional is wanted to be compared and treated, expend considerable time and effort to information, finally according to the experience and knowledge of oneself
It makes a policy.Once lacking relevant professional, platform is just difficult to run, and proposes to the quality of bank practitioner higher
Requirement.
Summary of the invention
In view of the above problem of the existing technology, the present invention proposes a kind of credit risk dynamic assessment method, system, Jie
Matter and equipment mainly solve the problems, such as that many and diverse information is unfavorable for decision.
To achieve the goals above and other purposes, the technical solution adopted by the present invention are as follows.
A kind of credit risk dynamic assessment method, comprising:
The credit demand for acquiring financial business object carries out multidimensional risk assessment according to the credit demand;
Comprehensive assessment result is obtained according to the multidimensional risk assessment.
Optionally, multidimensional risk assessment index is obtained according to the credit demand of financial business object, carries out multidimensional risk and comments
Estimate.
Optionally, the multidimensional Risk Evaluation Factors include: identity, contractual capacity, credit history, Behavior preference, human connection
Relationship.
Optionally, the credit demand includes financing needs, enterprise's Loan Demand, household consumption borrowing demand.
Optionally, by obtaining the weight scoring per the one-dimensional Risk Evaluation Factors, multidimensional risk assessment is carried out.
Optionally, the weight scoring of Risk Evaluation Factors described in COMPREHENSIVE CALCULATING multidimensional, carries out comprehensive assessment to credit risk.
Optionally, credit decisions is carried out according to the result of the multidimensional risk assessment and the comprehensive assessment result.
Optionally, the weight obtained per the one-dimensional Risk Evaluation Factors scores, and includes at least:
Construct the index network per the one-dimensional Risk Evaluation Factors;
Weight is distributed for each node in the index network, obtains the weight scoring of the node;
It is scored according to the weight of the node, calculates the weight scoring of the corresponding Risk Evaluation Factors.
Optionally, the index network includes multi -index, according to the corresponding pass between upper level index and next stage index
System, establishes the connection relationship of index network.
Optionally, Rating Model is set, is each node distribution power in the index network by the Rating Model
Weight.
Optionally,
Sample database is created according to credit case data;
According to sample database training Rating Model, the Rating Model of multiple classifications is obtained.
Optionally, the Rating Model includes identity Rating Model, contractual capacity Rating Model, credit history scoring mould
Type, Behavior preference Rating Model, relationship among persons Rating Model.
Optionally, according to the corresponding relationship of the classification of the Rating Model and the Risk Evaluation Factors, for corresponding institute
State each node distribution weight in index network.
Optionally, the weight of each node in the index network is weighted and averaged, obtains the index network pair
The weight for the Risk Evaluation Factors answered scores.
Optionally, the weight scoring of the multidimensional Risk Evaluation Factors is weighted and averaged, obtains the comprehensive of credit risk
Close scoring.
Optionally, after obtaining the weight score per the one-dimensional Risk Evaluation Factors, according to expertise to the weight
Score is verified, and is modified according to check results to the weight score.
Optionally, credit decisions model is set, the multidimensional risk evaluation result and the comprehensive assessment result are inputted
The credit decisions model obtains the result of decision.
Optionally, according to credit case creation training sample set and object set;
According to the training sample set and object set training decision model.
A kind of credit risk dynamic evaluation system, comprising:
Data acquisition module, for acquiring the credit demand of financial business object;
Multidimensional risk evaluation module, for carrying out multidimensional risk assessment according to the credit demand;
Comprehensive assessment module, for obtaining comprehensive assessment result according to the multidimensional risk assessment.
Optionally, the multidimensional risk evaluation module includes:
Risk indicator acquiring unit, for obtaining multidimensional risk assessment index;
Index network generation unit constructs the index network per the one-dimensional Risk Evaluation Factors;
Score unit, is that each node in the index network distributes weight, obtains the weight scoring of the node;Root
It scores according to the weight of the node, calculates the weight scoring of the corresponding Risk Evaluation Factors.
It optionally, further include display module, the assessment result for each index of real-time display.
A kind of equipment, comprising:
One or more processors;With
One or more machine readable medias of instruction are stored thereon with, when one or more of processors execute,
So that the equipment executes the credit risk dynamic assessment method.
One or more machine readable medias are stored thereon with instruction, when executed by one or more processors, so that
Equipment executes the credit risk dynamic assessment method.
As described above, a kind of credit risk dynamic assessment method of the present invention, system, medium and equipment, have beneficial below
Effect.
The multidimensional evaluation is carried out according to user demand, targetedly appraisal procedure can effectively filter redundancy, obtain and need
Assessment data information;By evaluation mechanism, is conducive to user according to assessment result and carries out decision, simplify decision process, reduce
Dependence to user's professional ability, improves applicability.
Detailed description of the invention
Fig. 1 is the flow chart of credit risk dynamic assessment method in one embodiment of the invention.
Fig. 2 is the module map of credit risk dynamic evaluation system in one embodiment of the invention.
Fig. 3 is the hardware structural diagram of terminal device in one embodiment of the invention.
Fig. 4 is the hardware structural diagram of terminal device in another embodiment of the present invention.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
Referring to Fig. 1, the present invention provides a kind of credit risk dynamic assessment method, including step S01-S02.
In step S01, the credit demand of financial business object is acquired, multidimensional risk assessment is carried out according to credit demand:
In one embodiment, financial business object may include needing the enterprise to finance, the individual for needing to borrow or lend money etc., can also wrap
Managing Financial Institutions personnel are included, as the business personnel of bank can carry out risk assessment according to user demand typing credit demand.
In one embodiment, credit demand can be divided into financing needs, enterprise's Loan Demand, household consumption borrowing demand etc..
In one embodiment, text or voice input can be used in the demand information of financial business object.According to the text of acquisition
Key feature is compared with the feature in preset feature database, and then judges letter by this and voice messaging, extraction key feature
The classification of loan demand.Such as input " so-and-so company need to borrow or lend money M yuan ", letter can be matched according to the feature " company " of extraction and " debt-credit "
Loan demand class is enterprise's Loan Demand.
In another embodiment, it can also be provided by display interface and be selected for the credit demand of financial business Object Selection
, such as by taking household consumption borrowing demand as an example, the option of settable household consumption borrowing demand.The option can be clicked and obtain information
Input interface, the essential informations such as name, the certificate of typing borrower.
It in one embodiment, can be according to the input information Auto-matching of financial business object and the letter of the financial business object
The corresponding multidimensional Risk Evaluation Factors of loan demand.Multidimensional Risk Evaluation Factors corresponding with credit demand can be passed through by expert
It tests and is configured, multidimensional Risk Evaluation Factors are formed into cluster with corresponding user demand and are stored in index storehouse.When according to defeated
Enter information matches to when user demand, corresponding multidimensional Risk Evaluation Factors can be directly obtained from index storehouse.
By taking household consumption borrowing demand as an example, user inputs " personal credit situation ", matches with household consumption borrowing demand,
Corresponding multidimensional Risk Evaluation Factors can be obtained automatically.Multidimensional Risk Evaluation Factors may include: identity, contractual capacity, credit
This 5 dimensions of history, Behavior preference, relationship among persons.
In one embodiment, model training can also be carried out by machine learning algorithm obtain the cluster mould based on credit demand
Type, common machine learning algorithm used herein may include K mean cluster algorithm, mean shift clustering algorithm etc..It is equal with K
It is worth for clustering algorithm, credit demand and corresponding history achievement data is formed into class group data, initialize all kinds of groups of data
Central point.Each data point is calculated to the distance of central point, which kind of data point is then divided into apart from which central point recently
In, it completes after calculating, updates all kinds of central points, continuation is iterated according to abovementioned steps, until center position tends to be steady
It is fixed, obtain Clustering Model.By regularly updating Clustering Model, i.e., the renewable corresponding multidimensional Risk Evaluation Factors of credit demand,
With the variation of adaptive databases.Clustering Model can also introduce verification scheme, be adjusted in real time according to expertise.
Since the data complexity for carrying out risk assessment is usually relatively high, in order to obtain data abundant, raising is commented
The accuracy estimated can refine every one-dimensional Risk Evaluation Factors, form index network.By taking this dimension of identity as an example, certain
People can have multiple identities simultaneously, be both company clerk and the responsible person of certain association etc..It can be rule of thumb by evaluation index
Multiple levels are divided into, according to the corresponding relationship of upper level index and next stage index, establish index network.With identity, this is one-dimensional
For the Risk Evaluation Factors of degree.It may include driver, company clerk that identity, which corresponds to next level index, and lower layer of driver
Grade index may include record, driving age violating the regulations etc., and the lower level of company clerk may include post, income situation etc..It is closed with this
Connection property establishes the index network per one-dimensional Risk Evaluation Factors.
It in one embodiment, can be that Rating Model is set per one-dimensional Risk Evaluation Factors according to expertise, it will be per one-dimensional
It is each node of composing indexes network by Rating Model in the corresponding index network inputs Rating Model of Risk Evaluation Factors
Distribute weight.The weight score for all nodes possibly being present in index network is stored in Rating Model.It can also add manually
Add or modify the weight score of index network corresponding node.
In another embodiment, sample database can be created according to history credit case data, extracting data in case includes
Key feature, such as age, work, income, credit history information are scored for these key messages using neural metwork training
Model obtains the weight score of each feature in Rating Model.Here the computer learning algorithm of training pattern is not made specifically
Limitation, it may include convolutional neural networks, support vector machines, Recognition with Recurrent Neural Network etc..
According to sample database training Rating Model, the Rating Model of multiple classifications can be obtained, each classification corresponds to one-dimensional risk
Evaluation index.Rating Model may include identity Rating Model, contractual capacity Rating Model, credit history Rating Model, behavior
Predilection grade model, relationship among persons Rating Model.It will be commented per the corresponding index network inputs of one-dimensional Risk Evaluation Factors are corresponding
Sub-model assigns weight to node each in the index network.
In one embodiment, settable verification scheme verifies the weight score of each node in index network, can draw
Enter desk checking mechanism, weight score is verified according to expertise, and weight score is repaired according to check results
Just.
The weight of all nodes in index network is weighted and averaged, the power of corresponding Risk Evaluation Factors can be obtained
It scores again.In this approach, the weight scoring of each dimension Risk Evaluation Factors is calculated separately out.
In step S02, comprehensive assessment result is obtained according to multidimensional risk assessment.
The weight scoring of multidimensional Risk Evaluation Factors is weighted and averaged, synthesis corresponding with credit demand can be obtained and commented
Point.
It is corresponding that the step of creating training dataset according to credit case data, describe according to S01 obtains training dataset
The scoring of index network node weight and comprehensive score, using the scoring of the weight of each index network node and comprehensive score as defeated
Enter sample set, object set is constructed with the result of decision of credit case.Pass through input sample collection and object set training credit decisions mould
Type.Supervised learning neural network algorithm can be used and carry out model training, training data is marked by expert and concentrates training data, is mentioned
The precision of high model training.The training that other machine learning algorithms carry out decision model can also be used.
By the weight score of each index nodes obtained in step S01, corresponding every one-dimensional Risk Evaluation Factors
Weight score and comprehensive score input decision model, the result of decision is exported by decision model.
Financial business object only needs to refer to the result of decision and weight score is simply checked, and credit can be completed
Decision.
Referring to Fig. 2, the present embodiment provides a kind of credit risk dynamic evaluation systems, for executing preceding method embodiment
Described in credit risk dynamic assessment method.Since the technical principle of system embodiment and the technology of preceding method embodiment are former
It manages similar, thus repeatability no longer is done to same technical detail and is repeated.
In one embodiment, credit risk dynamic evaluation system includes data acquisition module 10, multidimensional risk evaluation module
11 and comprehensive assessment module 12.Data acquisition module 10 and multidimensional risk evaluation module 11 are for assisting execution preceding method to implement
The step S01 that example is introduced, comprehensive assessment module 11 are used to execute the step S02 of preceding method embodiment introduction.
In one embodiment, index evaluation module 12 includes risk index acquiring unit, index network generation unit and comments
Sub-unit.
Risk index acquiring unit is used for the credit demand according to financial business object, obtains corresponding multidimensional risk assessment
Index.Multidimensional Risk Evaluation Factors corresponding with credit demand can be configured by expertise, by multidimensional risk assessment
Index forms cluster with the demand of corresponding financial business object and is stored in index storehouse.When according to input information matches to finance
When the demand of business object, corresponding multidimensional Risk Evaluation Factors can be directly obtained from index storehouse.
By taking household consumption borrowing demand as an example, user inputs " personal credit situation ", matches with household consumption borrowing demand,
Corresponding multidimensional Risk Evaluation Factors can be obtained automatically.Multidimensional Risk Evaluation Factors may include: identity, contractual capacity, credit
This 5 dimensions of history, Behavior preference, relationship among persons.
In one embodiment, model training can also be carried out by machine learning algorithm obtain the cluster mould based on credit demand
Type, common machine learning algorithm used herein may include K mean cluster algorithm, mean shift clustering algorithm etc..It is equal with K
It is worth for clustering algorithm, credit demand and corresponding history achievement data is formed into class group data, initialize all kinds of groups of data
Central point.Each data point is calculated to the distance of central point, which kind of data point is then divided into apart from that central point recently
In, it completes after calculating, updates all kinds of central points, continuation is iterated according to abovementioned steps, until center position tends to be steady
It is fixed, obtain Clustering Model.By regularly updating Clustering Model, i.e., the renewable corresponding multidimensional Risk Evaluation Factors of credit demand,
With the variation of adaptive databases.The Clustering Model can also introduce verification scheme, be adjusted in real time according to expertise.
Index network generation unit forms index network for refining to every one-dimensional Risk Evaluation Factors.With identity
For this dimension, someone can have multiple identities simultaneously, be both company clerk and the responsible person of certain association etc..It can root
Evaluation index is divided into multiple levels according to experience, according to the corresponding relationship of upper level index and next stage index, establishes index
Network.By taking the Risk Evaluation Factors of this dimension of identity as an example.It may include driver, company that identity, which corresponds to next level index,
Office worker, the lower level index of driver may include violating the regulations record, driving age etc., the lower level of company clerk may include post,
Take in situation etc..The index network per one-dimensional Risk Evaluation Factors is established with this relevance.
It in one embodiment, can be that Rating Model is set per one-dimensional Risk Evaluation Factors according to expertise, by the mould that scores
Type is integrated in scoring unit.In will be per the corresponding index network inputs Rating Model of one-dimensional Risk Evaluation Factors, pass through scoring
Model is that each node of composing indexes network distributes weight.The institute possibly being present in index network is stored in Rating Model
There is the weight score of node.It can also add or modify manually the weight score of index network corresponding node.
In another embodiment, sample database can be created according to history credit case data, extracting data in case includes
Key feature, such as age, work, income, credit history information are scored for these key messages using neural metwork training
Model obtains the weight score of each feature in Rating Model.Here the computer learning algorithm of training pattern is not made specifically
Limitation, it may include convolutional neural networks, support vector machines, Recognition with Recurrent Neural Network etc..
According to sample database training Rating Model, the Rating Model of multiple classifications can be obtained, each classification corresponds to one-dimensional risk
Evaluation index.Rating Model may include identity Rating Model, contractual capacity Rating Model, credit history Rating Model, behavior
Predilection grade model, relationship among persons Rating Model.It will be commented per the corresponding index network inputs of one-dimensional Risk Evaluation Factors are corresponding
Sub-model assigns weight to node each in the index network.
In one embodiment, also settable verification scheme in scoring unit, to the weight score of each node in index network
It is verified, desk checking mechanism can be introduced, weight score is verified according to expertise, and according to check results to power
Weight score is modified.
The weight of all nodes in index network is weighted and averaged, the power of corresponding Risk Evaluation Factors can be obtained
It scores again.In this approach, the weight scoring of each dimension Risk Evaluation Factors is calculated separately out.
In one embodiment, system further includes display module, can be corresponding by each index network of display module real-time display
The weight appraisal result of node, each weight score, comprehensive score and result of decision for tieing up Risk Evaluation Factors, for financial business
Object refers to, the various aspects information that financial business object can be provided according to display module, voluntarily decision.
The embodiment of the present application also provides a kind of equipment, which may include: one or more processors;It deposits thereon
The one or more machine readable medias for containing instruction, when being executed by one or more of processors, so that the equipment
Execute method described in Fig. 1.In practical applications, which can be used as terminal device, can also be used as server, and terminal is set
Standby example may include: smart phone, tablet computer, E-book reader, MP3 (dynamic image expert's compression standard voice
Level 3, Moving Picture Experts Group Audio Layer III) player, MP4 (dynamic image expert pressure
Contracting received pronunciation level 4, Moving Picture Experts Group Audio Layer IV) it is player, on knee portable
Computer, vehicle-mounted computer, desktop computer, set-top box, intelligent TV set, wearable device etc., the embodiment of the present application for
Specific equipment is without restriction.
The embodiment of the present application also provides a kind of non-volatile readable storage medium, be stored in the storage medium one or
Multiple modules (programs) when the one or more module is used in equipment, can make the equipment execute the application reality
Apply the instruction (instructions) of the included step of credit risk dynamic assessment method in Fig. 1 of example.
Fig. 3 is the hardware structural diagram for the terminal device that one embodiment of the application provides.As shown, the terminal device
It may include: input equipment 1100, first processor 1101, output equipment 1102, first memory 1103 and at least one is logical
Believe bus 1104.Communication bus 1104 is for realizing the communication connection between element.First memory 1103 may include high speed
RAM memory, it is also possible to it further include non-volatile memories NVM, a for example, at least magnetic disk storage, in first memory 1103
It can store various programs, for completing various processing functions and realizing the method and step of the present embodiment.
Optionally, above-mentioned first processor 1101 for example can be central processing unit (Central Processing
Unit, abbreviation CPU), application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts
(DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or
Other electronic components realize that the processor 1101 is coupled to above-mentioned input equipment 1100 by wired or wireless connection and output is set
Standby 1102.
Optionally, above-mentioned input equipment 1100 may include a variety of input equipments, such as may include user oriented use
At least one of family interface, device oriented equipment interface, the programmable interface of software, camera, sensor.Optionally, should
Device oriented equipment interface can be wireline interface for carrying out data transmission between equipment and equipment, can also be and is used for
Hardware insertion interface (such as USB interface, serial ports etc.) carried out data transmission between equipment and equipment;Optionally, should towards with
The user interface at family for example can be user oriented control button, voice-input device and use for receiving voice input
The touch awareness apparatus (such as touch screen, Trackpad with touch sensing function etc.) of family reception user's touch input;It is optional
, the programmable interface of above-mentioned software for example can be the entrance for editing or modifying program for user, such as the input of chip
Pin interface or input interface etc.;Output equipment 1102 may include the output equipments such as display, sound equipment.
In the present embodiment, the processor of the terminal device includes for executing each module of speech recognition equipment in each equipment
Function, concrete function and technical effect are referring to above-described embodiment, and details are not described herein again.
Fig. 4 is the hardware structural diagram for the terminal device that another embodiment of the application provides.Fig. 4 is existed to Fig. 3
A specific embodiment during realization.As shown, the terminal device of the present embodiment may include second processor
1201 and second memory 1202.
Second processor 1201 executes the computer program code that second memory 1202 is stored, and realizes above-described embodiment
Middle Fig. 1 the method.
Second memory 1202 is configured as storing various types of data to support the operation in terminal device.These numbers
According to example include any application or method for operating on the terminal device instruction, such as message, picture, video
Deng.Second memory 1202 may include random access memory (random access memory, abbreviation RAM), it is also possible to
It further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Optionally, first processor 1201 is arranged in processing component 1200.The terminal device can also include: communication set
Part 1203, power supply module 1204, multimedia component 1205, voice component 1206, input/output interface 1207 and/or sensor
Component 1208.Component that terminal device is specifically included etc. is set according to actual demand, and the present embodiment is not construed as limiting this.
The integrated operation of the usual controlling terminal equipment of processing component 1200.Processing component 1200 may include one or more
Second processor 1201 executes instruction, to complete all or part of the steps of method shown in above-mentioned Fig. 1.In addition, processing component
1200 may include one or more modules, convenient for the interaction between processing component 1200 and other assemblies.For example, processing component
1200 may include multi-media module, to facilitate the interaction between multimedia component 1205 and processing component 1200.
Power supply module 1204 provides electric power for the various assemblies of terminal device.Power supply module 1204 may include power management
System, one or more power supplys and other with for terminal device generate, manage, and distribute the associated component of electric power.
Multimedia component 1205 includes the display screen of one output interface of offer between terminal device and user.One
In a little embodiments, display screen may include liquid crystal display (LCD) and touch panel (TP).If display screen includes touch surface
Plate, display screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touchings
Sensor is touched to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or cunning
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.
Voice component 1206 is configured as output and/or input speech signal.For example, voice component 1206 includes a wheat
Gram wind (MIC), when terminal device is in operation mode, when such as speech recognition mode, microphone is configured as receiving external voice
Signal.The received voice signal of institute can be further stored in second memory 1202 or send via communication component 1203.
In some embodiments, voice component 1206 further includes a loudspeaker, for exporting voice signal.
Input/output interface 1207 provides interface between processing component 1200 and peripheral interface module, and above-mentioned periphery connects
Mouth mold block can be click wheel, button etc..These buttons may include, but are not limited to: volume button, start button and locking press button.
Sensor module 1208 includes one or more sensors, and the state for providing various aspects for terminal device is commented
Estimate.For example, sensor module 1208 can detecte the state that opens/closes of terminal device, the relative positioning of component, Yong Huyu
The existence or non-existence of terminal device contact.Sensor module 1208 may include proximity sensor, be configured to do not having
Detected the presence of nearby objects when any physical contact, including detection user between terminal device at a distance from.In some implementations
In example, which can also be including camera etc..
Communication component 1203 is configured to facilitate the communication of wired or wireless way between terminal device and other equipment.Eventually
End equipment can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In one embodiment
In, it may include SIM card slot in the terminal device, which step on terminal device for being inserted into SIM card
GPRS network is recorded, is communicated by internet with server foundation.
From the foregoing, it will be observed that communication component 1203, voice component 1206 involved in Fig. 4 embodiment and input/output
Interface 1207, sensor module 1208 can be used as the implementation of the input equipment in Fig. 3 embodiment.
In conclusion a kind of credit risk dynamic assessment method of the present invention, system, medium and equipment, pass through Auto-matching
Risk indicator parameter greatly simplifies the process that risk indicator is manually specified, and enhances the degree of automation of platform;By
Built-in risk index dynamic evaluation mechanism in platform carries out intuitive comprehensive displaying to assessment result, is conducive to bank working people
Member scores according to various aspects and carries out decision, reduces labor workload;It only needs to carry out decision according to scoring, reduce special to user
The requirement of industry level, improves the applicability of platform;Expert's verification scheme is introduced, the accuracy of the result of decision can be enhanced.So
The present invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (23)
1. a kind of credit risk dynamic assessment method characterized by comprising
The credit demand for acquiring financial business object carries out multidimensional risk assessment according to the credit demand;
Comprehensive assessment result is obtained according to the multidimensional risk assessment.
2. credit risk dynamic assessment method according to claim 1, which is characterized in that according to the letter of financial business object
Loan demand obtains multidimensional Risk Evaluation Factors, carries out multidimensional risk assessment.
3. credit risk dynamic assessment method according to claim 2, which is characterized in that the multidimensional Risk Evaluation Factors
It include: identity, contractual capacity, credit history, Behavior preference, relationship among persons.
4. credit risk dynamic assessment method according to claim 1, which is characterized in that the credit demand includes financing
Demand, enterprise's Loan Demand, household consumption borrowing demand.
5. credit risk dynamic assessment method according to claim 2, which is characterized in that
By obtaining the weight scoring per the one-dimensional Risk Evaluation Factors, multidimensional risk assessment is carried out.
6. credit risk dynamic assessment method according to claim 4, which is characterized in that risk described in COMPREHENSIVE CALCULATING multidimensional
The weight of evaluation index scores, and carries out comprehensive assessment to credit risk.
7. credit risk dynamic assessment method according to claim 1, which is characterized in that according to the multidimensional risk assessment
Result and the comprehensive assessment result carry out credit decisions.
8. credit risk dynamic assessment method according to claim 5, which is characterized in that described to obtain per the one-dimensional wind
The weight of dangerous evaluation index scores, and includes at least:
Construct the index network per the one-dimensional Risk Evaluation Factors;
Weight is distributed for each node in the index network, obtains the weight scoring of the node;
It is scored according to the weight of the node, calculates the weight scoring of the corresponding Risk Evaluation Factors.
9. credit risk index dynamic assessment method according to claim 8, which is characterized in that the index network includes
Multi -index establishes the connection relationship of index network according to the corresponding relationship between upper level index and next stage index.
10. credit risk dynamic assessment method according to claim 8, which is characterized in that setting Rating Model passes through institute
Commentary sub-model is that each node in the index network distributes weight.
11. credit risk dynamic assessment method according to claim 10, which is characterized in that
Sample database is created according to credit case data;
According to sample database training Rating Model, the Rating Model of multiple classifications is obtained.
12. credit risk dynamic assessment method according to claim 11, which is characterized in that the Rating Model includes body
Part Rating Model, contractual capacity Rating Model, credit history Rating Model, Behavior preference Rating Model, relationship among persons scoring mould
Type.
13. credit risk dynamic assessment method according to claim 11, which is characterized in that
It is in the corresponding index network according to the corresponding relationship of the classification of the Rating Model and the Risk Evaluation Factors
Each node distribute weight.
14. credit risk dynamic assessment method according to claim 8, which is characterized in that every in the index network
The weight of a node is weighted and averaged, and obtains the weight scoring of the corresponding Risk Evaluation Factors of the index network.
15. credit risk dynamic assessment method according to claim 6, which is characterized in that the multidimensional risk assessment
The weight scoring of index is weighted and averaged, and obtains the comprehensive score of credit risk.
16. credit risk dynamic assessment method according to claim 5, which is characterized in that obtain per the one-dimensional risk
After the weight score of evaluation index, the weight score is verified according to expertise, and according to check results to described
Weight score is modified.
17. credit risk dynamic assessment method according to claim 7, which is characterized in that setting credit decisions model, it will
The multidimensional risk evaluation result and the comprehensive assessment result input the credit decisions model, obtain the result of decision.
18. credit risk dynamic assessment method according to claim 17, which is characterized in that
According to credit case creation training sample set and object set;
According to the training sample set and object set training decision model.
19. a kind of credit risk dynamic evaluation system characterized by comprising
Data acquisition module, for acquiring the credit demand of financial business object;
Multidimensional risk evaluation module, for carrying out multidimensional risk assessment according to the credit demand;
Comprehensive assessment module, for obtaining comprehensive assessment result according to the multidimensional risk assessment.
20. credit risk dynamic evaluation system according to claim 19, which is characterized in that the multidimensional risk assessment mould
Block includes:
Risk indicator acquiring unit, for obtaining multidimensional risk assessment index;
Index network generation unit constructs the index network per the one-dimensional Risk Evaluation Factors;
Score unit, is that each node in the index network distributes weight, obtains the weight scoring of the node;According to institute
The weight scoring for stating node calculates the weight scoring of the corresponding Risk Evaluation Factors.
21. credit risk dynamic evaluation system according to claim 19, which is characterized in that further include display module, use
In the assessment result of each index of real-time display.
22. a kind of equipment characterized by comprising
One or more processors;With
One or more machine readable medias of instruction are stored thereon with, when one or more of processors execute, so that
The equipment executes the method as described in one or more in claim 1-18.
23. one or more machine readable medias, which is characterized in that instruction is stored thereon with, when by one or more processors
When execution, so that equipment executes the method as described in one or more in claim 1-18.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910806315.8A CN110533527A (en) | 2019-08-29 | 2019-08-29 | A kind of credit risk dynamic assessment method, system, medium and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910806315.8A CN110533527A (en) | 2019-08-29 | 2019-08-29 | A kind of credit risk dynamic assessment method, system, medium and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110533527A true CN110533527A (en) | 2019-12-03 |
Family
ID=68664972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910806315.8A Pending CN110533527A (en) | 2019-08-29 | 2019-08-29 | A kind of credit risk dynamic assessment method, system, medium and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110533527A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111967767A (en) * | 2020-08-18 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Business risk identification method, device, equipment and medium |
CN112561337A (en) * | 2020-12-16 | 2021-03-26 | 北京明略软件***有限公司 | Method and device for determining object type |
CN114387077A (en) * | 2021-11-29 | 2022-04-22 | 阿尔法时刻科技(深圳)有限公司 | Credit qualification examination method and system |
CN115760368A (en) * | 2022-11-24 | 2023-03-07 | 中电金信软件有限公司 | Credit business approval method and device and electronic equipment |
CN118134633A (en) * | 2024-05-07 | 2024-06-04 | 深圳市拓保软件有限公司 | Bank credit asset risk analysis method and system based on AI technology |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107993143A (en) * | 2017-11-23 | 2018-05-04 | 深圳大管加软件与技术服务有限公司 | A kind of Credit Risk Assessment method and system |
CN108596495A (en) * | 2018-04-26 | 2018-09-28 | 浙江工业大学 | A kind of retail credit business points-scoring system and method |
CN108665184A (en) * | 2018-05-21 | 2018-10-16 | 国网陕西省电力公司咸阳供电公司 | A kind of power customer credit assessment method based on big data reference |
CN108921686A (en) * | 2018-06-19 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of credit-graded approach and device of personal user |
-
2019
- 2019-08-29 CN CN201910806315.8A patent/CN110533527A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107993143A (en) * | 2017-11-23 | 2018-05-04 | 深圳大管加软件与技术服务有限公司 | A kind of Credit Risk Assessment method and system |
CN108596495A (en) * | 2018-04-26 | 2018-09-28 | 浙江工业大学 | A kind of retail credit business points-scoring system and method |
CN108665184A (en) * | 2018-05-21 | 2018-10-16 | 国网陕西省电力公司咸阳供电公司 | A kind of power customer credit assessment method based on big data reference |
CN108921686A (en) * | 2018-06-19 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of credit-graded approach and device of personal user |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111967767A (en) * | 2020-08-18 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Business risk identification method, device, equipment and medium |
CN112561337A (en) * | 2020-12-16 | 2021-03-26 | 北京明略软件***有限公司 | Method and device for determining object type |
CN114387077A (en) * | 2021-11-29 | 2022-04-22 | 阿尔法时刻科技(深圳)有限公司 | Credit qualification examination method and system |
CN115760368A (en) * | 2022-11-24 | 2023-03-07 | 中电金信软件有限公司 | Credit business approval method and device and electronic equipment |
CN118134633A (en) * | 2024-05-07 | 2024-06-04 | 深圳市拓保软件有限公司 | Bank credit asset risk analysis method and system based on AI technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110533527A (en) | A kind of credit risk dynamic assessment method, system, medium and equipment | |
CN110569377B (en) | Media file processing method and device | |
CN107622432A (en) | Trade company's evaluation method and system | |
CN110135942A (en) | Products Show method, apparatus and computer readable storage medium | |
CN112287244A (en) | Product recommendation method and device based on federal learning, computer equipment and medium | |
CN107609563A (en) | Picture semantic describes method and device | |
TWI701629B (en) | Recommended method, device and electronic equipment for sharing products | |
CN112561535A (en) | Transaction dispute data processing method, device, equipment and storage medium | |
Cai et al. | MIFAD-net: multi-layer interactive feature fusion network with angular distance loss for face emotion recognition | |
CN109559218A (en) | A kind of determination method, apparatus traded extremely and storage medium | |
CN108241653A (en) | Data processing method and device | |
CN111275683B (en) | Image quality grading processing method, system, device and medium | |
CN112989210A (en) | Insurance recommendation method, system, equipment and medium based on health portrait | |
CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
CN117235633A (en) | Mechanism classification method, mechanism classification device, computer equipment and storage medium | |
CN112100491A (en) | Information recommendation method, device and equipment based on user data and storage medium | |
CN116701593A (en) | Chinese question-answering model training method based on GraphQL and related equipment thereof | |
CN116862434A (en) | Material data management system and method based on big data | |
CN116703520A (en) | Product recommendation method based on improved K-means algorithm and related equipment thereof | |
CN113890948B (en) | Resource allocation method based on voice outbound robot dialogue data and related equipment | |
CN112417197B (en) | Sorting method, sorting device, machine readable medium and equipment | |
Shin | Socio-technical design of algorithms: Fairness, accountability, and transparency | |
CN114021660A (en) | Training method, device, medium and equipment for feature mining model | |
CN114359952A (en) | Multi-modal score fusion method, device, computer-readable storage medium and equipment | |
CN110135804A (en) | Data processing method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |
|
RJ01 | Rejection of invention patent application after publication |