CN110533525A - For assessing the method and device of entity risk - Google Patents
For assessing the method and device of entity risk Download PDFInfo
- Publication number
- CN110533525A CN110533525A CN201910693035.0A CN201910693035A CN110533525A CN 110533525 A CN110533525 A CN 110533525A CN 201910693035 A CN201910693035 A CN 201910693035A CN 110533525 A CN110533525 A CN 110533525A
- Authority
- CN
- China
- Prior art keywords
- entity
- risk
- class
- data
- dimension
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000006399 behavior Effects 0.000 claims description 13
- 230000015654 memory Effects 0.000 claims description 11
- 230000015556 catabolic process Effects 0.000 claims description 8
- 238000006731 degradation reaction Methods 0.000 claims description 8
- 238000013481 data capture Methods 0.000 claims description 7
- 241001269238 Data Species 0.000 claims description 5
- 238000007726 management method Methods 0.000 description 61
- 238000011156 evaluation Methods 0.000 description 23
- 238000012502 risk assessment Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000000926 separation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000006549 dyspepsia Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Present disclose provides a kind of for assessing the method and device of entity risk, wherein the method for assessing entity risk includes: to assess data from the entity including at least one dimension data that third party's service end receives entity to be assessed, risk score model is called to determine risk score corresponding to entity assessment data, then judge to make it possible to determine the risk class of entity to be assessed according to judging result and risk score with the presence or absence of the Risk Dimensions data being used to indicate there are entity risk in entity assessment data.Using this method, the Risk Dimensions data in risk score and entity assessment data is comprehensively considered, have ensured the reliability of identified risk class, can be more applicable under application scenes.
Description
Technical field
This disclosure relates to Internet technical field, and in particular, to a kind of for assessing the method and dress of entity risk
It sets.
Background technique
With the fast development of internet finance, the application service (example of evaluation for credit degree is carried out for individual or enterprise
Such as roc expedition letter, preceding extra large reference) it is widely used and refers to.
The credit etc. that the credit appraisal system of current individual or enterprise are carried out generally be directed to the enterprise under business scenario
Grade evaluation, that is, assessment is personal or whether enterprise can complete business according to quantity on time and arrange (such as whether repayment of bank loans on time),
But due to, there are more random complicated factor, leading to prediction result not in the model calculating process of existing credit appraisal system
Stablize.For example, enterprise is without the objective negative fact of any one, but through model obtain for the enterprise
Scoring is also possible to can be lower, leads to not be suitable for the applied business field more demanding to the reliability of evaluation result
Scape, and also result in the fairness that enterprise customer queries appraisement system.
Summary of the invention
In view of the above problems, present disclose provides a kind of for assessing the method and device of entity risk, utilizes this method
And device, it is real with the presence or absence of indicating to exist in risk score and comprehensive entity assessment data to determine that application entity assesses data
The result of the dimension data of body risk assesses the risk class of entity, avoids and entity devoid of risk dimension data occurs and mistake
The case where entity is belonged to high-risk grade ensures the reliability of identified entity risk class, in some applied business
It is more applicable in scene (such as credit legal system application scenarios).
According to one aspect of the disclosure, a kind of method for assessing entity risk is provided, comprising: obtain to be evaluated
Estimate the entity assessment data of entity, the entity assessment data have at least one dimension data；Number is assessed based on the entity
According to determining the risk score of the entity to be assessed；Judging, which whether there is in the entity assessment data, is used to indicate in the presence of real
The dimension data of body risk；And according to the judging result and the risk score, determine the risk of the entity to be assessed
Grade.
Optionally, in an example of above-mentioned aspect, according to the judging result and the risk score, institute is determined
The risk class for stating entity includes: the initial risks grade that the entity to be assessed is determined according to the risk score；Described
The dimension data for being used to indicate entity risk is not present in entity assessment data and the initial risks grade belongs to low-risk class
When grade, the initial risks grade is determined as to the risk class of the entity；It is not present in entity assessment data
It is used to indicate the dimension data of entity risk and when the initial risks grade belongs to high risk class hierarchy, is degraded based on predetermined
Rule degrades to the initial risks grade, and the initial risks grade after degradation is determined as to the risk of the entity
Grade；Or when in entity assessment data in the presence of the dimension data for being used to indicate entity risk, by the initial risks
Grade is determined as the risk class of the entity.
Optionally, in an example of above-mentioned aspect, the predetermined collapsing rule includes: by described initial risks etc.
Grade is downgraded to the highest risk class of risk class in the low-risk class hierarchy；Or the initial risks grade is dropped
Grade intended level span.
Optionally, in an example of above-mentioned aspect, the reality to be assessed is being determined based on entity assessment data
Before the risk score of body, the method also includes: judge to classify in the entity assessment data with the presence or absence of with risk class
The dimension data of rule match；And when there is dimension data matched with risk class classifying rules, it is based on the risk
Grade separation rule determines the risk class of the entity to be assessed.
Optionally, in an example of above-mentioned aspect, data is assessed based on the entity, determine the reality to be assessed
The risk score of body includes: application risk Rating Model to determine the entity to be assessed based on entity assessment data
Risk score.
Optionally, in an example of above-mentioned aspect, the risk score model includes scorecard model.
Optionally, in an example of above-mentioned aspect, the dimension of the entity assessment data is true based on application scenarios
It is fixed.
Optionally, in an example of above-mentioned aspect, the application scenarios include entity credit legal system.
Optionally, in an example of above-mentioned aspect, the dimension of the entity assessment data includes: management issue class
Dimension；Manage object base info class dimension；Administration behaviour class dimension；Management selective examination plan information class dimension；Physical operating letter
Cease class dimension.
Optionally, in an example of above-mentioned aspect, the entity assessment packet for obtaining entity to be assessed is included: from
Tripartite's server-side obtains the entity assessment data of the entity to be assessed, the method also includes: it is more than in the risk class
The grade of risk class when predetermined level threshold value, or when the risk class is relative to previous assessment cycle rises span
When greater than default span threshold value, Xiang Suoshu third party's service end sending entity Risk-warning notice.
According to another aspect of the present disclosure, a kind of method for assessing entity risk is provided, comprising: obtain to be assessed
The entity of entity assesses data, and the entity assessment data have at least one dimension data, and the entity assesses data
Dimension data be dimension data associated with entity credit management risk；The entity is based on using scorecard model
Assessment data determine that the risk score of the entity to be assessed, the target variable of the scorecard model are based on entity credit
What managing risk event set determined；Judge that there are entity credit managements with the presence or absence of being used to indicate in the entity assessment data
The dimension data of risk；According to the judging result and the risk score, the risk class of the entity to be assessed is determined.
Optionally, in an example of above-mentioned aspect, the dimension of the entity assessment data includes: management issue class
Dimension；Manage object base info class dimension；Administration behaviour class dimension；Management selective examination plan information class dimension；Physical operating letter
Cease class dimension.
According to another aspect of the present disclosure, it provides a kind of for assessing the device of entity risk, comprising: assessment data obtain
Unit is taken, the entity assessment data of entity to be assessed are obtained, the entity assessment data have at least one dimension data；Wind
Danger scoring determination unit, assesses data based on the entity, determines the risk score of the entity to be assessed；Risk data is sentenced
Disconnected unit judges that there are the dimension datas of entity risk with the presence or absence of being used to indicate in the entity assessment data；And risk
Level de-termination unit determines the risk class of the entity to be assessed according to the judging result and the risk score.
Optionally, in an example of above-mentioned aspect, the risk class determination unit includes: initial risks grade
Determining module determines the initial risks grade of the entity to be assessed according to the risk score；Risk class determining module,
The entity assessment data in there is no be used to indicate entity risk dimension data and the initial risks grade belong to it is low
When risk class hierarchy, the initial risks grade is determined as to the risk class of the entity；In entity assessment data
There is no the dimension data for being used to indicate entity risk and when the initial risks grade belongs to high risk class hierarchy, based on pre-
Determine collapsing rule to degrade to the initial risks grade, and the initial risks grade after degradation is determined as the entity
Risk class；It, will be described first or when in entity assessment data in the presence of the dimension data for being used to indicate entity risk
Beginning risk class is determined as the risk class of the entity.
Optionally, in an example of above-mentioned aspect, further includes: classifying rules matching unit is being based on the entity
Before the risk score that assessment data determine the entity to be assessed, judge to whether there is in the entity assessment data and wind
The dimension data of dangerous grade separation rule match；And when there is dimension data matched with risk class classifying rules, institute
It states risk class determination unit and is based further on the risk etc. that the risk class classifying rules determines the entity to be assessed
Grade.
Optionally, in an example of above-mentioned aspect, the risk score unit further uses risk score model
To determine the risk score of the entity to be assessed based on entity assessment data.
Optionally, in an example of above-mentioned aspect, the dimension of the entity assessment data is true based on application scenarios
It is fixed.
Optionally, in an example of above-mentioned aspect, the application scenarios include entity credit legal system.
Optionally, in an example of above-mentioned aspect, the dimension of the entity assessment data includes: management issue class
Dimension；Manage object base info class dimension；Administration behaviour class dimension；Management selective examination plan information class dimension；Physical operating letter
Cease class dimension.
Optionally, the assessment data capture unit is further, obtain the entity to be assessed from third party's service end
Entity assesses data, described device further include: Risk-warning notification unit is more than predetermined level threshold value in the risk class
When, or the grade of risk class when the risk class is relative to previous assessment cycle rises span and is greater than default span
When threshold value, Xiang Suoshu third party's service end sending entity Risk-warning notice.
According to another aspect of the present disclosure, a kind of calculating equipment is provided, comprising: at least one processor；And storage
Device, the memory store instruction, when described instruction is executed by least one described processor so that it is described at least one
Processor executes the method for assessing entity risk as described above.
According to another aspect of the present disclosure, a kind of machine readable storage medium is provided, executable instruction is stored with, institute
State instruction makes the machine execute the method for assessing entity risk as described above upon being performed.
Detailed description of the invention
By referring to following attached drawing, may be implemented to further understand the nature and advantages of present disclosure.In
In attached drawing, similar assembly or feature can have identical attached drawing mark.Attached drawing be for provide to the embodiment of the present invention into
One step understands, and constitutes part of specification, is used to explain the implementation of the disclosure together with following specific embodiment
Example, but do not constitute the limitation to embodiment of the disclosure.In the accompanying drawings:
Fig. 1 shows according to an embodiment of the present disclosure for assessing the system architecture schematic diagram of the system of entity risk；
Fig. 2 shows the flow charts according to the method for assessing entity risk of an embodiment of the disclosure；
Fig. 3 shows the flow chart of the determination risk class process according to an embodiment of the disclosure；
Fig. 4 shows the method for assessing entity risk according to an embodiment of the disclosure in entity credit risk
Manage the flow chart under application scenarios；
Fig. 5 shows according to an embodiment of the present disclosure for assessing the structural block diagram of the device of entity risk；
Fig. 6 shows according to an embodiment of the present disclosure for assessing the block diagram of the calculating equipment of entity risk.
Specific embodiment
Theme described herein is discussed below with reference to example embodiment.It should be understood that discussing these embodiments only
It is in order to enable those skilled in the art can better understand that realize theme described herein being wanted to right
Ask the protection scope illustrated in book, applicability or exemplary limitation.It can be in the protection scope for not departing from present disclosure
In the case where, the function and arrangement of the element discussed are changed.Each example can according to need, omit, substitute or
Person adds various processes or component.In addition, feature described in relatively some examples can also be combined in other examples.
As used in this article, term " includes " and its modification indicate open term, be meant that " including but it is unlimited
In ".Term "based" indicates " being based at least partially on ".Term " one embodiment " and " embodiment " expression " at least one
Embodiment ".Term " another embodiment " expression " at least one other embodiment ".Term " first ", " second " etc. can refer to
For different or identical object.Here may include other definition, either specific or implicit.Unless up and down
It is clearly indicated in text, otherwise the definition of a term is consistent throughout the specification.
In addition, as used in this article, term " entity " indicates enterprise, and (or under application scenes, entity can also be wrapped
Include individual).Term " entity credit management risk " indicates the wind involved in credit management (such as Credit Regulation) field
Danger is different from general Commercial Credit Risk, in order to ensure that enterprise is not in material risk accident and leads to society
Meeting problem, and be not intended to and investigate whether enterprise can such as from about fulfil business agreement.
Herein, term " scorecard model " is the risk score model modeled using logistic regression algorithm,
Have the characteristics that interpretation is strong and model result is stable.Term " target variable " indicates in scorecard model for defeated to institute
The evaluation criterion that the variable data entered is measured, such as target variable under commercial credit scene includes that user is in the recent period
It is no to have overdue behavior.
The method and device for being used to assess entity risk of the disclosure is described presently in connection with attached drawing.
Shown in fig. 1 is embodiment of the disclosure for assessing system (the hereinafter also referred to entity risk of entity risk
Assessment system) system architecture schematic diagram.
As shown in Figure 1, entity risk evaluating system 10 includes client 101,102 and 103 and server 106,108.
Wherein, client 101, client 102 and client 103 can be the end of such as desktop computer, laptop and mobile phone etc
End equipment.Also, it can be between terminal device and server and communication interconnection carried out by network.One in the disclosure is shown
In example, each entity needs periodically to report respective entity assessment data, in order to which each entity timely learning is respectively corresponding
Risk class.In another example of the disclosure, the entity that server-side can periodically or non-periodically collect each entity is commented
Data are estimated, so that server-side can actively assess risk class present in each entity.In some applied business
In scene, server 106 can indicate third party's service end (or supervision end), and the entity for collecting each entity assesses number
According to, and server 108 can indicate risk assessment service device, for by assessing data to entity collected by server 106
Entity risk analysis is carried out to evaluate corresponding risk class.Although 106 and 108 type described in Fig. 1 is clothes
Business device, but its terminal that also can have or be replaced by such as computer or mobile phone etc.
It should be understood that the quantity of terminal device shown in figure 1 or server is not intended to embodiment of the disclosure
It is limited.In addition, server 106 and server 108 can indicate the server cluster formed by multiple server combinations,
Such as server 106 can indicate that the server cluster at corresponding supervision end and server 108 can indicate that corresponding implement general plan is commented
Estimate the server cluster of operation.Here, server 106, which is collected, assesses data about the entity of different entities, and in real time or fixed
Phase these entities assessment data are transmitted with entity risk corresponding to each entity of determination, to cooperate with to server 108
Complete the Risk Supervision to entity.Here, server 108 (or risk assessment service device) can be configured with various algorithms or mould
Type, to provide the risk assessment service for being directed to entity.
Fig. 2 shows according to an embodiment of the disclosure for assessing method (the hereinafter also referred to entity of entity risk
Methods of risk assessment) flow chart.
Process 200 as shown in Figure 2 obtains the entity assessment data of entity to be assessed, entity assessment in block 210
Data have at least one dimension data.
As described above, risk assessment service device can assess data from third party's service end receiving entity, and
Data dimension in entity assessment data can change with the difference of applied business scene, such as in credit legal system (example
Such as supervision) entity assessment packet includes and such as relates to the multiple number of dimensions for telling information and administration information etc under business scenario
According to.In an example of the disclosure, after obtaining entity assessment data, it is pre- also data progress data can be assessed entity
Processing operation, such as entity is assessed into the characteristic of specific format by data conversion by data preprocessing operation.
Then, in block 220, data is assessed based on entity, determine the risk score of entity to be assessed.Here, it can apply
Various algorithms or model carry out risk score corresponding to computational entity assessment data.
Specifically, risk score model can be used to determine that the risk of entity to be assessed is commented based on entity assessment data
Point.Here, the type of risk score model can be diversified, such as Random Forest model, gradient promotion decision can be used
Tree-model, deep learning model and scorecard model etc. come determine entity assessment data corresponding to risk score.As showing
Example, under credit legal system application scenarios, credit management risk be for entity (can than more sensitive air control index
Whether presentation-entity is by key-point management), demand is directed to the assessment result reliability with higher of credit management risk and can solve
The property released.Therefore, high stability and the strong model of result interpretation, such as scorecard model can be recommended to use.It should be understood that
, above-mentioned credit management application scenarios are only the one of applied business scene for being directed to embodiment of the disclosure, the disclosure
Embodiment be applicable to more applied business scenes.
Then, in block 230, judge that there are the dimensions of entity risk with the presence or absence of being used to indicate in entity assessment data
Data (hereinafter also referred to as Risk Dimensions data).In this way, the verification completed to entity assessment data for entity risk is grasped
Make.Illustratively, under credit management application scenarios, such as dimension " administration information " institute in sporocarp assessment data
Corresponding dimension data is " being performed management ", then it represents that it is instruction risk that the dimension data, which is there are risk or greater probability,
, conversely, if dimension data corresponding to " administration information " is " not being performed management ", then it represents that the dimension data is
It is instruction risk there is no risk or compared with small probability.
Then, according to judging result and risk score, the risk class of entity to be assessed is determined.At one of the disclosure
In example, the entity risk class of multiple and different ranks is preset, and according to judging result and risk score come above-mentioned multiple
Selection is directed to the risk class of entity to be assessed in entity risk class.Here, whether entity assessment data include dimension data
It will have a direct impact on final identified risk class.Specifically, in block 241, if there are risk dimensions in entity assessment data
Degree evidence, it is determined that entity is the first risk class.And in block 242, if there is no risks to tie up in entity assessment data
Degree evidence, it is determined that entity is the second risk class.Here, the second risk class is (for example, at least in some applied business scenes
Or under some cases) can be less than the first risk class.
In contrast, it if directly determining entity risk class using risk score, is then likely to appear in entity and comments
Estimate and do not indicate risk (such as without any punishment information) in dimension data all under data, but because of risk score model
Risk score determined by model is lower and the case where entity has still been included into high-risk grade, therefore be easy to cause entity pair
The query of the fairness of identified risk class.
In embodiment of the disclosure, the judging result and risk score of Risk Dimensions data are directed to by comprehensively considering
It determines risk class, avoids because the random complicated factor in model calculating process leads to risk score or risk rating not
Stable situation, improve determined by risk class reliability, in application scenes (such as credit management applied field
Scape) under more be applicable in.
Fig. 3 shows the flow chart of the determination risk class process according to an embodiment of the disclosure.
Process 300 as shown in Figure 3 determines the initial risks etc. of entity to be assessed according to risk score in a block 310
Grade.Illustratively, it can refer to grading system mapping table as shown in Table 1 to determine risk class (or the wind for risk score
Dangerous classification).
Table 1
As shown in table 1, lower for the risk score of entity, corresponding risk class is higher, and illustrates entity in future
The probability that entity risk case occurs for certain time is higher.It should be understood that content shown in table 1 is used only as example, risk
Scoring and risk class can be existed in the form of other.Illustratively, the reciprocal fraction section of risk score can be with
It is 1-10, A and B is merged and becomes four class risk class or is extended to ten class risk class altogether etc., this should be not added limit
System.
Then, in a block 320, judge in entity assessment data with the presence or absence of the dimension data for being used to indicate entity risk.
Operation about block 320 is referred to the operation in the block 230 with reference to Fig. 2.
In block 330, if there are Risk Dimensions data in entity assessment data, initial risks grade is determined as reality
The risk class of body.
In addition, if Risk Dimensions data are not present in entity assessment data, judging initial risks grade in block 341
Whether low-risk class hierarchy is belonged to.Here, low-risk class hierarchy and high risk class hierarchy can be it is scheduled at least one etc.
Grade.In conjunction with the example of such as table 1, low-risk class hierarchy can be the risk class of A-C, and high risk class hierarchy can be D or E
Risk class.
Then, in block 342, if initial risks grade belongs to low-risk class hierarchy, initial risks grade is determined as
The risk class of entity.
Alternatively, if initial risks grade belongs to high risk class hierarchy, being dropped to initial risks grade in block 343
Grade.
Then, in block 344, the initial risks grade after degradation is determined as to the risk class of entity.
It is illustrated continuing with the example of such as table 1, if the initial risks grade according to determined by risk score is D
Grade, and there is no the dimension datas for being used to indicate entity risk in entity assessment data, then should carry out downgrade processing, example
Such as it is reduced to one of risk class of A-C.Specifically, in an example of the disclosure, initial risks grade can be dropped
Grade is the highest risk class of risk class in low-risk class hierarchy, correspondingly, can assess data by above-mentioned entity and determine in fact
Risk class corresponding to body is C.It, can also be by initial risks grade degradation intended level in another example of the disclosure
Span then correspondingly, can assess data as above-mentioned entity and determine risk corresponding to entity if intended level span is 2 grades
Grade is B.Therefore, when Risk Dimensions data are not present in entity assessment data, even if entity assessment data are with very low
Risk score (or higher initial risks grade), also can reduce risk corresponding to entity etc. by above-mentioned downgrade processing
Grade, has ensured the reliability of prediction result.
It, can be by code fo practice matching operation without the use of risk score, to directly determine entity in some embodiments
Assess risk class corresponding to data.Specifically, after the entity for obtaining entity to be assessed assesses data, it can determine whether reality
Body, which is assessed in data, whether there is and the matched dimension data of risk class classifying rules.Here, risk class classifying rules can
To include pre-set one or more Risk Dimensions data for corresponding to setting risk class, and data are assessed in entity
When middle presence dimension data matched with risk class classifying rules, reality to be assessed can be determined based on risk class classifying rules
The risk class of body, such as determine that the risk class of entity to be assessed is setting risk corresponding to risk class classifying rules
Grade, or determine that the risk class of entity to be assessed cannot belong to low-risk class hierarchy.Illustratively, in credit management
Under application scenarios, risk class classifying rules is " being put into entity blacklist of breaking one's promise " corresponding to E grades of risk class, and such as
Fruit determines that correspondent entity has been put into entity blacklist of breaking one's promise by the information that analysis entities assess data, then can determine entity
Corresponding risk class is E grades.
As the preferred embodiment of embodiment of the disclosure, risk assessment service device is from (or the supervision of third party's service end
End) receive entity assessment data and determine the risk class of corresponding entity based on entity assessment data after, risk
Evaluating server can determine whether to execute the Risk-warning operation about one or more entities according to risk class.Specifically
Ground, when the risk class of entity is more than predetermined level threshold value, or the risk when risk class is relative to previous assessment cycle
When the grade of grade rises span greater than default span threshold value, risk assessment service device is directed to the transmission of third party's service end should
The entity Risk-warning of entity notifies, to prompt third party's service end which special entity emphasis should carry out wind mainly for
Control measure.In conjunction with the example of table 1, the risk class corresponding to entity a be D or E when, can to third server-side send about
The entity Risk-warning notice of entity a, or when entity b risk class corresponding to a upper assessment cycle is A and is currently commented
Estimating risk class corresponding to the period is C, and it is 2 (it is assumed that predetermined level threshold values 1) that risk class, which rises span, then can also be to the
Three server-sides are sent to be notified about the entity Risk-warning of entity b.It should be understood that the duration of assessment cycle can be one
The moon or other times, are answered without restriction herein.
It should be noted that embodiment of the disclosure can be applied to a variety of applied business scenes, and used entity is commented
The dimension of estimating data can be based on application scenarios and determination.Illustratively, under commercial credit scene, entity assesses number
According to dimension can be dimension associated with entity Commercial Credit Risk, such as social security information and annual report assertions etc..In addition,
Under the application scenarios of credit legal system (such as supervision), the dimension of entity assessment data be can be and entity credit management
The associated data dimension of risk.
In an example of the disclosure, the dimension of the entity assessment data under credit legal system application scenarios can
It include: management issue class dimension, management object base info class dimension, administration behaviour class dimension, management selective examination plan information class
Dimension and physical operating info class dimension.In turn, risk assessment service device can call risk score model or risk score algorithm
It determines corresponding risk score, and determines the risk etc. of entity to be assessed in conjunction with the judging result for Risk Dimensions data
Grade is conducive to the credit legal system operation that differentiated is carried out for the entity of different credit management risk class.
Fig. 4 shows the entity methods of risk assessment of an embodiment of the disclosure in entity credit legal system applied field
Flow chart under scape.
Under the application scenarios of entity credit legal system, by assessing the respective risk class of different entities, with entity
Being managed based on credit, the purpose of credit management (such as Credit Regulation) is can be according to possessed by different entities
Risk class carries out differential Supervision Measures, and to realize, the entity of low risk level is less to be bothered to having, and to high-risk grade
Entity key-point management.It should be noted that entity, which is limited to business entity, in Fig. 4 has carried out illustrative expansion description,
But it is not regarded as the limitation to the type of entity.
Process 400 as shown in Figure 4 obtains the enterprise evaluation data of enterprise to be assessed in block 410.Wherein, it assesses
Data have at least one dimension data, and the dimension data of the assessment data is related to enterprise credit management risk
The dimension data of connection.
As described above, enterprise credit management risk is different from general Commercial Credit Risk.In business standing wind
The dimension of enterprise evaluation data under danger management application scenarios can include: management issue class dimension, management object base info class
Dimension, administration behaviour class dimension, management selective examination plan information class dimension and enterprise operation info class dimension.
Here, management issue class dimension includes management issue inventory information dimension and management reports information dimension (such as to supervise
Pipe calling information or report information).Management thing in management issue inventory information dimension including each administrative department or each department
The base directory inventory and management issue of item check implementation checklist.In addition, management object base info class dimension includes administrative phase
To people's basic information, special equipment basic information, specific products basic information and place Locale information etc..In addition, administration behaviour
Class dimension includes information such as administrative inspection behavioural information, administrative penalty behavioural information and administrative arbitrariness behavior etc..In addition, management
Selective examination plan information class dimension may include the plan information etc. of " double random disclosures ".In addition, enterprise operation info class dimension packet
Include customs information, tax information, the administration of justice relate to and tell that information, intellectual property information, annual report assertions, social security common reserve fund information, finance are borrowed
Borrow information, black list information and internet public feelings information etc..
Then, in block 420, the risk of enterprise to be assessed is determined based on enterprise evaluation data using scorecard model
Scoring, the target variable of the scorecard model is determined based on enterprise credit management risk case collection.
In the example of the disclosure, using the scorecard model for having the characteristics that performance is stable and result height is interpretable,
It can allow third party's service end (or supervision end) can not only knowledge of result, moreover it is possible to which the calculating process for lucidly understanding result is met
Supervise the individual demand experience at end.Here, as the scorecard model of monitor model, target variable be can be based on enterprise
Industry credit management risk case collection and determination.
It should be understood that business administration risk case can indicate that the representative event of credit management risk, In occur for enterprise
Under some cases, enterprise credit management risk case collection is also possible to enterprise's violation operation item collection.Illustratively, enterprise believes
With managing risk event include business failure event, business taxation anomalous event, case-involving event, equity freezes event, enterprise arranges
A single event, enterprise stop doing business event, the setting finance of event, enterprise of having their business licenses revoked that enters to break one's promise borrow or lend money overdue event and setting
Business event of default.Here, list of breaking one's promise may include that customs breaks one's promise list, and setting finance and borrowing or lending money overdue event can indicate serious
Finance borrow or lend money overdue event (such as overdue more than 6 months), and setting business event of default can indicate that serious business is disobeyed
About event (such as business promise breaking target volume is huge).
In the example of the disclosure, scorecard model uses the supervised learning of two classification, whether to there is target variable institute
The enterprise credit management risk case of instruction is target, determines that each dimension data is directed to target respectively in enterprise evaluation data
The corresponding probability of variable, and then obtain the risk score for enterprise evaluation data.Therefore, data dimension in enterprise evaluation data
The rich and varied property of degree is conducive to the pinpoint accuracy for the risk score that scorecard model obtains.
Then, in block 430, judge that there are enterprise credit management wind with the presence or absence of being used to indicate in enterprise evaluation data
The dimension data (also referred to as credit management Risk Dimensions data) of danger.It specifically, can will be each in enterprise evaluation data
There are the negative factual data collection of enterprise credit management risk to be matched with instruction for dimension data, and when matching, it determines
There are credit management Risk Dimensions data in enterprise evaluation data.Here, the definition of negative factual data collection and scoring card mold
The definition of enterprise credit management risk case collection corresponding to the target variable of type is similar, and in one example, enterprise
Industry credit management risk case collection is a subset of negative factual data collection.Illustratively, enterprise credit management risk case
Can be it is serious borrow or lend money overdue event more than 6 months finance, and the corresponding negative fact can be finance and borrow or lend money overdue thing
Part and be not intended to limit the overdue time.
Then, according to judging result and risk score, the risk class of enterprise to be assessed is determined.Specifically, in block 441
In, if there are Risk Dimensions data in enterprise evaluation data, it is determined that enterprise is the first credit management risk class.And
In block 442, if Risk Dimensions data are not present in enterprise evaluation data, it is determined that enterprise is the second credit management risk class.
Specifically, different risk scores has corresponding risk class, but is not to come according to risk score directly really
Determine risk class, it is also necessary to consider to the presence or absence of the risk fact.If enterprise evaluation data do not have any one
Corresponding negative true dimension data not should be the evaluation high-risk grade of enterprise corresponding to the enterprise evaluation data then.Example
Property, when enterprise is classified because of risk score to high risk class hierarchy, enterprise must have objective negative true just successfully will
The enterprise is sorted out to high risk class rank, and low-risk class rank otherwise can only be just determined as by it.
Then, it in block 450, is commented when risk class is more than predetermined level threshold value, or in risk class relative to previous
When the grade of risk class when estimating the period rises span greater than default span threshold value, business risk early warning is sent to supervision end
Notice.In this way, being based on business risk pre-alert notification output credit management Risk-warning clue, enterprise is based on convenient for supervision department
Risk-warning notice makes targeted business standing monitor strategy.
In some embodiments, determine that enterprise exists by analyzing enterprise evaluation data when risk assessment service device
When there is dimension data matched with risk class classifying rules in the specific negative fact or enterprise evaluation data, wind can be based on
Dangerous grade separation rule determines the risk class of enterprise to be assessed.
Specifically, in conjunction with the example of such as table 1, in an example of the disclosure, following three kinds of risk class point are provided
Rule-like.
First risk class classifying rules.There is following either case in enterprise, will not be judged as A rank: the past 2 years
There are objective negative true, set up not year and a day and a upper assessment cycle in be judged as D rank or E rank.
Second risk class classifying rules.There is following either case in enterprise, can directly be judged as D rank: past two
Equity occurs year and freezes event, past 2 years generation tax anomalous event (such as the improper family of the tax or tax arrear), and past
The event that enterprise is executed person and non-implement obligation occurs within 2 years.
Third risk class classifying rules.There is following either case in enterprise, can directly be determined E rank: declare brokenly
It produces, great tax revenue violation event occurred within the past 5 years, was put into break one's promise enterprise's list (blacklist) of breaking the law on a serious scale within the past 5 years
And do not remove, it is break one's promise executed person and non-implement obligation, the generation of past Liang Nian enterprise that enterprise, which occurred within the past 5 years,
Crime dramas is adjudicated, and event of breaking one's promise is assert by the customs of Liang Nian enterprise generation in the past.
Further, if enterprise to be assessed had not only met the second risk class classifying rules but also met third risk class point
The enterprise then can be still determined as E rank by rule-like.It should be understood that being wrapped in above-mentioned each risk class classifying rules
The content contained is the description of unrestricted example, and the letter to made by the content of above-mentioned each risk class classifying rules
Single modification or deformation should also be considered as in the range of embodiment of the disclosure.
In addition, the following objective negative fact does not influence credit appraisal: the objective negative fact is regarded as missing through associated mechanisms
Sentence, mistake, clerical mistake etc. it is devious with truth；Or the objective negative fact has cancelled, invalid or plot is especially slight
's.So may be updated being directed to enterprise to be assessed when periodically acquiring enterprise evaluation data and determining the risk class of enterprise
Under the objective negative true or objective negative fact state, and update accordingly the risk class of the enterprise.
It should be noted that evaluation system both domestic and external is all the application in business scenario at present, emphasize that enterprise whether can
It honours an agreement.However, in prediction enterprise in great accident risk or the enterprise that whether will appear such as bankruptcy or violation operation etc in the future
When industry credit management risk, it is desirable that prediction result has very high reliability, and existing appraisement system can not be fitted
With.In addition, once appearance of enterprise enterprise credit management risk case (such as P2P platform thunderclaps event), then may result in
More serious social concern influences the harmonious development of industry order.
In consideration of it, in embodiment of the disclosure, proposing suitable for scorecard model in the effective of Credit Regulation field
Data dimension and target variable definition, and operated in conjunction with the identification for credit management Risk Dimensions data and determine enterprise
Risk class so that risk evaluation results are relatively reliable also more intuitive.In addition, proposing effective credit risk early-warning
Venture business can respond with as supervision clue to supervision end, take and be directed to convenient for supervision department by scheme in time
The Supervision Measures of property.
Fig. 5 shows according to an embodiment of the present disclosure for assessing device (the hereinafter also referred to as entity of entity risk
Risk assessment device) structural block diagram.
As shown in figure 5, entity risk assessment device 500 includes assessment data capture unit 510, the determining list of risk score
Member 520, risk data judging unit 530, risk class determination unit 540, classifying rules matching unit 550 and Risk-warning
Notification unit 560.
Assessment data capture unit 510 obtains the entity assessment data of entity to be assessed, and the entity assessment data have
At least one dimension data.The operation of assessment data capture unit 510 is referred to the behaviour above with reference to Fig. 2 block 210 described
Make.
Risk score determination unit 520 is based on the entity and assesses data, determines that the risk of the entity to be assessed is commented
Point.The operation of risk score determination unit 520 is referred to the operation above with reference to Fig. 2 block 220 described.
Risk data judging unit 530 judges that there are entity wind with the presence or absence of being used to indicate in the entity assessment data
The dimension data of danger.The operation of risk score determination unit 530 is referred to the operation above with reference to Fig. 2 block 230 described.
Risk class determination unit 540 determines the entity to be assessed according to the judging result and the risk score
Risk class.The operation of risk score determination unit 540 is referred to above with reference to Fig. 2 block 241 described and block 242
Relevant operation.
Classifying rules matching unit 550 is determining that the risk of the entity to be assessed is commented based on entity assessment data
/ preceding, judge to whether there is and the matched dimension data of risk class classifying rules in the entity assessment data.In this way,
When there is dimension data matched with risk class classifying rules, risk class determination unit 540 is based further on the wind
Dangerous grade separation rule determines the risk class of the entity to be assessed.The operation of classifying rules matching unit 550 can refer to
Face is directed to the relevant operation of risk class classifying rules.
Further, assessment data capture unit 510 is commented from the entity that third party's service end obtains the entity to be assessed
Estimate data, Risk-warning notification unit 560 is when the risk class is more than predetermined level threshold value, or in the risk class
When the grade of risk class when relative to previous assessment cycle rises span greater than default span threshold value, Xiang Suoshu third party
Server-side sending entity Risk-warning notice.The operation of Risk-warning notification unit 560 can refer to above with reference to Fig. 4 description
The operation of block 450.
It will be clear that the partial block of the description in Fig. 5 is also possible to optionally, such as block 550 and block 560 etc..
Some or all of in the other examples of the disclosure, can also delete in above-mentioned optional piece.In addition, in the other of the disclosure
In example, it can also modify to the operation indicated by block described in Fig. 5.
Further, risk class determination unit 540 includes: initial risks level determination module (not shown), according to institute
State the initial risks grade that risk score determines the entity to be assessed；Risk class determining module (not shown), in the reality
The dimension data for being used to indicate entity risk is not present in body assessment data and the initial risks grade belongs to low-risk class etc.
When grade, the initial risks grade is determined as to the risk class of the entity；There is no use in entity assessment data
When the dimension data and the initial risks grade for indicating entity risk belong to high risk class hierarchy, based on the predetermined rule that degrade
Then degrade to the initial risks grade, and the initial risks grade after degradation is determined as to the risk etc. of the entity
Grade；Or when in entity assessment data in the presence of the dimension data for being used to indicate entity risk, by described initial risks etc.
Grade is determined as the risk class of the entity.The operation of initial risks level determination module and risk class determining module can be joined
According to the operation of the block described above with reference to Fig. 3.
Further, risk score unit 520 goes back application risk Rating Model to determine based on entity assessment data
The risk score of the entity to be assessed.It specifically can refer to the operation above with reference to reference block 420 in Fig. 4.
Further, the dimension of the entity assessment data is determined based on application scenarios.
Further, the application scenarios include entity credit legal system.
Further, the dimension of the entity assessment data includes: management issue class dimension；Manage object base information
Class dimension；Administration behaviour class dimension；Management selective examination plan information class dimension；And physical operating info class dimension.Specifically,
It can refer to the relevant operation that credit management risk is directed to above in conjunction with Fig. 4.
Above with reference to Fig. 1 to Fig. 5, to the embodiment according to the method and device for assessing entity risk of the disclosure
It is described.To the details mentioned in the description of embodiment of the method, it is being equally applicable to the reality of the device of the disclosure above
Apply example.The device for assessing entity risk above can be using hardware realization, can also be using software or hardware and soft
The combination of part is realized.
Fig. 6 shows according to an embodiment of the present disclosure for assessing the hardware configuration of the calculating equipment 600 of entity risk
Figure.As shown in fig. 6, calculating equipment 600 may include at least one processor 610, memory (for example, non-volatile memories
Device) 620, memory 630 and communication interface 640, and at least one processor 610, memory 620, memory 630 and communication connect
Mouth 640 links together via bus 660.At least one processor 610 executes at least one for storing or encoding in memory
A computer-readable instruction (that is, above-mentioned element realized in a software form).
In one embodiment, computer executable instructions are stored in memory, make at least one when implemented
Processor 610: obtaining the entity assessment data of entity to be assessed, and the entity assessment data have at least one dimension data；
Data are assessed based on the entity, determine the risk score of the entity to be assessed；Judge in entity assessment data whether
In the presence of being used to indicate, there are the dimension datas of entity risk；And according to the judging result and the risk score, determine institute
State the risk class of entity to be assessed.
It should be understood that the computer executable instructions stored in memory 620 make at least one processing when implemented
Device 610 carries out the above various operations and functions described in conjunction with Fig. 1-5 in each embodiment of the disclosure.
In the disclosure, calculating equipment 600 can include but is not limited to: personal computer, server computer, work
Stand, desktop computer, laptop computer, notebook computer, mobile computing device, smart phone, tablet computer,
Cellular phone, personal digital assistant (PDA), hand-held device, messaging devices, wearable calculating equipment, consumer-elcetronics devices
Etc..
According to one embodiment, a kind of program product of such as machine readable media is provided.Machine readable media can be with
With instruction (that is, above-mentioned element realized in a software form), the instruction when executed by a machine so that machine executes this public affairs
The above various operations and functions described in conjunction with Fig. 1-6 in each embodiment opened.Specifically, it can provide and be deposited equipped with readable
The system or device of storage media store the function for realizing any embodiment in above-described embodiment on the readable storage medium storing program for executing
Can software program code, and read and execute the computer of the system or device or processor and be stored in this and readable deposit
Instruction in storage media.
In this case, any one of above-described embodiment can be achieved in the program code itself read from readable medium
The function of embodiment, thus machine readable code and storage machine readable code readable storage medium storing program for executing constitute it is of the invention
A part.
The embodiment of readable storage medium storing program for executing include floppy disk, hard disk, magneto-optic disk, CD (such as CD-ROM, CD-R, CD-RW,
DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), tape, non-volatile memory card and ROM.It selectively, can be by communicating
Network download program code from server computer or on cloud.
It will be appreciated by those skilled in the art that each embodiment disclosed above can be in the feelings without departing from invention essence
Various changes and modifications are made under condition.Therefore, protection scope of the present invention should be defined by the appended claims.
It should be noted that step and unit not all in above-mentioned each process and each system construction drawing is all necessary
, certain step or units can be ignored according to the actual needs.Each step execution sequence be not it is fixed, can basis
It needs to be determined.Apparatus structure described in the various embodiments described above can be physical structure, be also possible to logical construction, that is,
Some units may be realized by same physical entity, be realized alternatively, some units may divide by multiple physical entities, alternatively, can
To be realized jointly by certain components in multiple autonomous devices.
In the above various embodiments, hardware cell or module mechanically or can be realized electrically.For example, one
A hardware cell, module or processor may include permanent dedicated circuit or logic (such as special processor, FPGA or
ASIC) corresponding operating is completed.Hardware cell or processor can also include programmable logic or circuit (such as general processor
Or other programmable processors), interim setting can be carried out by software to complete corresponding operating.Concrete implementation mode (machine
Tool mode or dedicated permanent circuit or the circuit being temporarily arranged) it can be based on cost and temporal consideration come really
It is fixed.
The specific embodiment illustrated above in conjunction with attached drawing describes exemplary embodiment, it is not intended that may be implemented
Or the protection scope that falls into claims all embodiments.Term " the example used in entire this specification
Property " mean " being used as example, example or illustration ", it is not meant to than other embodiments " preferably " or " there is advantage ".For
The purpose of the understanding to described technology is provided, specific embodiment includes detail.However, it is possible in these no tools
Implement these technologies in the case where body details.In some instances, in order to avoid the concept to described embodiment causes
Indigestion, well known construction and device are shown in block diagram form.
The foregoing description of present disclosure is provided so that any those of ordinary skill in this field can be realized or make
Use present disclosure.To those skilled in the art, the various modifications carried out to present disclosure are apparent
, also, can also be in the case where not departing from the protection scope of present disclosure, by generic principles defined herein
Applied to other modifications.Therefore, present disclosure is not limited to examples described herein and design, but with meet herein
The widest scope of principle disclosed and novel features is consistent.
Claims (22)
1. a kind of method for assessing entity risk, comprising:
The entity assessment data of entity to be assessed are obtained, the entity assessment data have at least one dimension data；
Data are assessed based on the entity, determine the risk score of the entity to be assessed；
Judge that there are the dimension datas of entity risk with the presence or absence of being used to indicate in the entity assessment data；And
According to the judging result and the risk score, the risk class of the entity to be assessed is determined.
2. the method for claim 1, wherein determining the entity according to the judging result and the risk score
Risk class include:
The initial risks grade of the entity to be assessed is determined according to the risk score；
There is no the dimension data for being used to indicate entity risk and the initial risks grade categories in entity assessment data
When low-risk class hierarchy, the initial risks grade is determined as to the risk class of the entity；
There is no the dimension data for being used to indicate entity risk and the initial risks grade categories in entity assessment data
When high risk class hierarchy, degraded based on predetermined collapsing rule to the initial risks grade, and will be initial after degradation
Risk class is determined as the risk class of the entity；Or
It is when there is the dimension data for being used to indicate entity risk in entity assessment data, the initial risks grade is true
It is set to the risk class of the entity.
3. method according to claim 2, wherein the predetermined collapsing rule includes:
The highest risk class of the risk class initial risks grade being downgraded in the low-risk class hierarchy；Or
By the initial risks grade degradation intended level span.
4. the method for claim 1, wherein in the wind for determining the entity to be assessed based on entity assessment data
Before the scoring of danger, the method also includes:
Judge to whether there is and the matched dimension data of risk class classifying rules in the entity assessment data；And
In presence dimension data matched with risk class classifying rules, based on described in risk class classifying rules determination
The risk class of entity to be assessed.
5. the method for claim 1, wherein assessing data based on the entity, the wind of the entity to be assessed is determined
It scores danger
Application risk Rating Model based on entity assessment data determines the risk score of the entity to be assessed.
6. method as claimed in claim 5, wherein the risk score model includes scorecard model.
7. the method for claim 1, wherein the dimension of the entity assessment data is determined based on application scenarios.
8. the method for claim 7, wherein the application scenarios include entity credit legal system.
9. method according to claim 8, wherein the dimension of entity assessment data includes:
Management issue class dimension；
Manage object base info class dimension；
Administration behaviour class dimension；
Management selective examination plan information class dimension；
Physical operating info class dimension.
10. the method as described in any in claims 1 to 9, wherein the entity assessment packet for obtaining entity to be assessed includes:
The entity for obtaining the entity to be assessed from third party's service end assesses data,
The method also includes:
When the risk class is more than predetermined level threshold value, or the wind when the risk class is relative to previous assessment cycle
When the grade of dangerous grade rises span greater than default span threshold value, Xiang Suoshu third party's service end sending entity Risk-warning is logical
Know.
11. a method of for assessing entity risk, comprising:
The entity assessment data of entity to be assessed are obtained, the entity assessment data have at least one dimension data, and institute
The dimension data for stating entity assessment data is dimension data associated with entity credit management risk；
The risk score of the entity to be assessed, the scoring are determined based on entity assessment data using scorecard model
The target variable of card mold type is determined based on entity credit management risk case collection；
Judge that there are the dimension datas of entity credit management risk with the presence or absence of being used to indicate in the entity assessment data；
According to the judging result and the risk score, the risk class of the entity to be assessed is determined.
12. method as claimed in claim 11, wherein the dimension of entity assessment data includes:
Management issue class dimension；
Manage object base info class dimension；
Administration behaviour class dimension；
Management selective examination plan information class dimension；
Physical operating info class dimension.
13. a kind of for assessing the device of entity risk, comprising:
Data capture unit is assessed, the entity assessment data of entity to be assessed are obtained, the entity assessment data have at least one
A dimension data；
Risk score determination unit assesses data based on the entity, determines the risk score of the entity to be assessed；
Risk data judging unit judges that there are the dimensions of entity risk with the presence or absence of being used to indicate in the entity assessment data
Data；And
Risk class determination unit determines the risk of the entity to be assessed according to the judging result and the risk score
Grade.
14. device as claimed in claim 13, wherein the risk class determination unit includes:
Initial risks level determination module determines the initial risks grade of the entity to be assessed according to the risk score；
Risk class determining module, there is no the dimension data and the institutes that are used to indicate entity risk in entity assessment data
When stating initial risks grade and belonging to low-risk class hierarchy, the initial risks grade is determined as to the risk class of the entity；
The dimension data for being used to indicate entity risk is not present in entity assessment data and the initial risks grade belongs to height
When risk class hierarchy, degraded based on predetermined collapsing rule to the initial risks grade, and by the initial risks after degradation
Grade is determined as the risk class of the entity；Or there is the dimension for being used to indicate entity risk in entity assessment data
Degree according to when, the initial risks grade is determined as to the risk class of the entity.
15. device as claimed in claim 13, further includes:
Classifying rules matching unit, before determining the risk score of the entity to be assessed based on entity assessment data,
Judge to whether there is and the matched dimension data of risk class classifying rules in the entity assessment data；And
When there is dimension data matched with risk class classifying rules, the risk class determination unit is based further on institute
State the risk class that risk class classifying rules determines the entity to be assessed.
16. device as claimed in claim 13, wherein the risk score unit further,
Application risk Rating Model based on entity assessment data determines the risk score of the entity to be assessed.
17. device as claimed in claim 13, wherein the dimension of the entity assessment data is determined based on application scenarios.
18. device as claimed in claim 17, wherein the application scenarios include entity credit legal system.
19. device as claimed in claim 18, wherein the dimension of entity assessment data includes:
Management issue class dimension；
Manage object base info class dimension；
Administration behaviour class dimension；
Management selective examination plan information class dimension；And
Physical operating info class dimension.
20. the device as described in any in claim 13 to 19, wherein the assessment data capture unit is further, from
Tripartite's server-side obtains the entity assessment data of the entity to be assessed,
Described device further include:
Risk-warning notification unit, the risk class be more than predetermined level threshold value when, or the risk class relative to
When the grade of risk class when previous assessment cycle rises span greater than default span threshold value, Xiang Suoshu third party's service end hair
Entity Risk-warning is sent to notify.
21. a kind of calculating equipment, comprising:
At least one processor；And
Memory, the memory store instruction, when described instruction is executed by least one described processor so that it is described extremely
A few processor executes the method as described in any in claims 1 to 10.
22. a kind of machine readable storage medium, is stored with executable instruction, described instruction makes the machine upon being performed
Execute the method as described in any in claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910693035.0A CN110533525A (en) | 2019-07-30 | 2019-07-30 | For assessing the method and device of entity risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910693035.0A CN110533525A (en) | 2019-07-30 | 2019-07-30 | For assessing the method and device of entity risk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110533525A true CN110533525A (en) | 2019-12-03 |
Family
ID=68661018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910693035.0A Pending CN110533525A (en) | 2019-07-30 | 2019-07-30 | For assessing the method and device of entity risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533525A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583037A (en) * | 2020-04-30 | 2020-08-25 | 支付宝(杭州)信息技术有限公司 | Method and device for determining risk associated object and server |
| CN113554248A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Risk dynamic early warning assessment method and device for hazardous chemical substance transport vehicle |
| CN113673870A (en) * | 2021-08-23 | 2021-11-19 | 杭州安恒信息技术股份有限公司 | Enterprise data analysis method and related components |
| CN114049054A (en) * | 2022-01-13 | 2022-02-15 | 江苏通付盾科技有限公司 | Decision method and system applied to risk management and control |
-
2019
- 2019-07-30 CN CN201910693035.0A patent/CN110533525A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554248A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Risk dynamic early warning assessment method and device for hazardous chemical substance transport vehicle |
| CN111583037A (en) * | 2020-04-30 | 2020-08-25 | 支付宝(杭州)信息技术有限公司 | Method and device for determining risk associated object and server |
| CN113673870A (en) * | 2021-08-23 | 2021-11-19 | 杭州安恒信息技术股份有限公司 | Enterprise data analysis method and related components |
| CN113673870B (en) * | 2021-08-23 | 2024-04-30 | 杭州安恒信息技术股份有限公司 | Enterprise data analysis method and related components |
| CN114049054A (en) * | 2022-01-13 | 2022-02-15 | 江苏通付盾科技有限公司 | Decision method and system applied to risk management and control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fourcade et al. | Seeing like a market | |
| CN110533525A (en) | For assessing the method and device of entity risk | |
| US9294497B1 (en) | Method and system for behavioral and risk prediction in networks using automatic feature generation and selection using network topolgies | |
| CN110689438A (en) | Enterprise financial risk scoring method and device, computer equipment and storage medium | |
| US20080133552A1 (en) | Information Processor Arrangement | |
| US20140303993A1 (en) | Systems and methods for identifying fraud in transactions committed by a cohort of fraudsters | |
| CN104321794A (en) | A system and method using multi-dimensional rating to determine an entity's future commercial viability | |
| US20190354993A1 (en) | System and method for generation of case-based data for training machine learning classifiers | |
| Noviandy et al. | Credit Card Fraud Detection for Contemporary Financial Management Using XGBoost-Driven Machine Learning and Data Augmentation Techniques | |
| CN110795574A (en) | Knowledge graph construction method based on finance anti-fraud | |
| CN109670933A (en) | Identify method, user equipment, storage medium and the device of user role | |
| CN111639690A (en) | Fraud analysis method, system, medium, and apparatus based on relational graph learning | |
| CN111143665A (en) | Fraud qualitative method, device and equipment | |
| Yu et al. | Credit scoring with AHP and fuzzy comprehensive evaluation based on behavioural data from weibo platform | |
| CN113434575A (en) | Data attribution processing method and device based on data warehouse and storage medium | |
| CN113762703A (en) | Method and device for determining enterprise portrait, computing equipment and storage medium | |
| CN112950350B (en) | Loan product recommendation method and system based on machine learning | |
| Hou et al. | A trial of student self-sponsored peer-to-peer lending based on credit evaluation using big data analysis | |
| CN115115322A (en) | Target group identification method, risk assessment method, apparatus, device and medium | |
| CN112907308B (en) | Data detection method and device, and computer readable storage medium | |
| Parthasarathy et al. | A framework for managing ethics in data science projects | |
| Islam | An efficient technique for mining bad credit accounts from both olap and oltp | |
| CN112581042B (en) | Performance capability evaluation system and method and electronic equipment | |
| Shihembetsa | Use of artificial intelligence algorithms to enhance fraud detection in the Banking Industry | |
| Negre | Towards a knowledge (experience)-based recommender system for crisis management |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200927 Address after: English genus Applicant after: Innovative advanced technology Co.,Ltd. Address before: English genus Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200927 Address after: English genus Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |