CN106203808A - Enterprise Credit Risk Evaluation method and apparatus - Google Patents
Enterprise Credit Risk Evaluation method and apparatus Download PDFInfo
- Publication number
- CN106203808A CN106203808A CN201610515164.7A CN201610515164A CN106203808A CN 106203808 A CN106203808 A CN 106203808A CN 201610515164 A CN201610515164 A CN 201610515164A CN 106203808 A CN106203808 A CN 106203808A
- Authority
- CN
- China
- Prior art keywords
- abnormal index
- enterprise
- weight
- case
- index
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of Enterprise Credit Risk Evaluation method and apparatus, the method includes: extract multiple abnormal index from the survey data intending trusted enterprise, and the abnormal index extracted from survey data is the first abnormal index；With the second abnormal index in each case in the instruction case library built in advance, the first abnormal index being carried out matching primitives, obtains the matching degree case more than preset matching degree, matching degree is coupling case more than the case of preset matching degree；Determine the weight that each second abnormal index matched in coupling case is corresponding；Calculate weight that in coupling case, each second abnormal index of matching is corresponding and, and compare by weight with default weight threshold；If weight and more than presetting weight threshold, it is determined that intending trusted enterprise is the trusted enterprise of high default risk.Make the method be applicable to carry out the risk assessment intending trusted enterprise that index is beautified, and improve the accuracy rate of risk evaluation result.
Description
Technical field
The present embodiments relate to technical field of data processing, particularly relate to a kind of Enterprise Credit Risk Evaluation method and dress
Put.
Background technology
Along with the market competition being growing more intense, this foundation of product is sold on the basis of credit economy with method of open account by enterprise
Mode of doing business a lot of fields the most worldwide become the principal mode of enterprise marketing.And the thing followed is looked forward to exactly
The credit risk of industry.The credit risk of enterprise is to sell product in credit mode or provide the enterprise of service to face, its
Be client likely cannot full-payout loan, or after the time of original promise could payment on account of credit to credit enterprise or
The risk that bank is brought.
Method and artificial judgment method are commented in being mainly the methods of risk assessment of trusted enterprise by bank at present.It is right for inside commenting method
A series of risk indicator sets respective weights and score value, and is comprehensively scored evaluation method by scoring card mode.Manually
Determination methods is that the enterprise operation correlative factor provided in the report of the responsible investigation to trusted enterprise carries out Comprehensive Evaluation, and then sentences
The method of disconnected Credit Risk Assessment of Enterprise.
Owing to both the above method all refers to each operation, Comprehensive Evaluation of risk elements to trusted enterprise, so being subject to
Believe a whole set of index of correlation beautification method of Corporation R & D, to tackle bank's wind control examination & verification, cause traditional trusted enterprise
The assessment result accuracy rate of assessing credit risks method is relatively low.
Summary of the invention
The embodiment of the present invention provides a kind of Enterprise Credit Risk Evaluation method, in order to solve trusted Corporation R & D a whole set of
Index of correlation beautification method, make the skill that the assessment result accuracy rate of the assessing credit risks method of traditional trusted enterprise is relatively low
Art problem.
The embodiment of the present invention provides a kind of Enterprise Credit Risk Evaluation method, including:
Multiple abnormal index is extracted, from the survey data of described plan trusted enterprise from the survey data intending trusted enterprise
The abnormal index extracted is the first abnormal index；
By described first abnormal index and the second abnormal index in each case in the instruction case library built in advance
Carrying out matching primitives, obtain the matching degree case more than preset matching degree, described matching degree more than the case of preset matching degree is
Coupling case；
Determine the weight that each second abnormal index matched in described coupling case is corresponding；
Calculate weight corresponding to each second abnormal index matched in described coupling case and, and by described weight and
Compare with default weight threshold；
If described weight and more than described default weight threshold, it is determined that described plan trusted enterprise is being subject to of high default risk
Letter enterprise.
The embodiment of the present invention provides a kind of Enterprise Credit Risk Evaluation device, including:
Extraction module, for extracting multiple abnormal index from the survey data intending trusted enterprise, looks forward to from described plan trusted
The abnormal index extracted in the survey data of industry is the first abnormal index；
Computing module, for indicating described first abnormal index in each case in case library with build in advance
Second abnormal index carries out matching primitives, obtains the matching degree case more than preset matching degree, and described matching degree is more than default
The case of degree of joining is coupling case；
Determine module, for determining the weight that each second abnormal index matched in described coupling case is corresponding；
Described computing module, is additionally operable to calculate the power that each second abnormal index matched in described coupling case is corresponding
Weight and, and compare by described weight with default weight threshold；
Described determine module, if being additionally operable to described weight and more than described default weight threshold, it is determined that described plan trusted
Enterprise is the trusted enterprise of high default risk.
The embodiment of the present invention provides a kind of Enterprise Credit Risk Evaluation method and apparatus, by from the investigation intending trusted enterprise
Extracting multiple abnormal index in data, the abnormal index extracted from the survey data intending trusted enterprise is the first abnormal index；
First abnormal index is carried out matching primitives with the second abnormal index in each case in the instruction case library built in advance,
Obtaining the matching degree case more than preset matching degree, matching degree is coupling case more than the case of preset matching degree；Determine coupling
The weight that each second abnormal index of matching in case is corresponding；Calculate each second matched in coupling case extremely to refer to
Weight that mark is corresponding and, and compare by weight with default weight threshold；If weight and more than preset weight threshold, the most really
Ding Ni trusted enterprise is the trusted enterprise of high default risk.Due in the instruction case library that builds in advance, there is multiple enterprise of having broken a contract
The abnormal index of industry, contains comprehensively, is no lack of to have and carries out the abnormal index after index is beautified, so being applicable not only to normally intend being subject to
The risk assessment of letter enterprise, is also applied for carrying out the risk assessment intending trusted enterprise that index is beautified, and improves risk assessment
The accuracy rate of result.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is this
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is the flow chart of Enterprise Credit Risk Evaluation embodiment of the method one of the present invention；
Fig. 2 is the flow chart of Enterprise Credit Risk Evaluation embodiment of the method two of the present invention；
Fig. 3 is the flow chart of step 203 in the embodiment of the present invention two；
Fig. 4 is the structural representation of Enterprise Credit Risk Evaluation device embodiment one of the present invention；
Fig. 5 is the structural representation of Enterprise Credit Risk Evaluation device embodiment two of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
Should be appreciated that term "and/or" used herein is only a kind of incidence relation describing affiliated partner, represent
Three kinds of relations, such as, A and/or B can be there are, can represent: individualism A, there is A and B, individualism B these three simultaneously
Situation.It addition, character "/" herein, typically represent forward-backward correlation to as if the relation of a kind of "or".
Depend on linguistic context, word as used in this " if " can be construed to " ... time " or " when ...
Time " or " in response to determining " or " in response to detection ".Similarly, depend on linguistic context, phrase " if it is determined that " or " if detection
(condition of statement or event) " " when determining " or " in response to determining " can be construed to or " when the detection (condition of statement
Or event) time " or " in response to detection (condition of statement or event) ".
Fig. 1 is the flow chart of Enterprise Credit Risk Evaluation embodiment of the method one of the present invention, as it is shown in figure 1, the present embodiment
Executive agent is Enterprise Credit Risk Evaluation device, and this Enterprise Credit Risk Evaluation device may be located at the application of local terminal,
Or can also be to be located locally the plug-in unit in the application of terminal or SDK (Software Development
Kit, SDK) etc. functional unit, this is not particularly limited by the embodiment of the present invention.
It is understood that the application program (nativeApp) that application can be mounted in terminal, or can also is that
One web page program (webApp) of the browser in terminal, this is not defined by the embodiment of the present invention.Terminal is the most permissible
For computer, notebook computer or server etc..
The Enterprise Credit Risk Evaluation method that then the present embodiment provides includes following step.
Step 101, extracts multiple abnormal index from the survey data intending trusted enterprise, from the investigation money intending trusted enterprise
The abnormal index extracted in material is the first abnormal index.
Wherein, intending trusted enterprise is to borrow prosomite to carry out the enterprise of assessing credit risks.Intending the investigation money of trusted enterprise
Material includes the result that the objective circumstances of trusted enterprise are investigated by all departments.This survey data can include this plan trusted
The corporate structure of enterprise, financing situation, investments abroad situation, financial situation, working capital situation, sales situation etc..
In the present embodiment, multiple exception can be extracted according to abnormal index identification model from the survey data intending trusted enterprise
Index.The abnormal index extracted from the survey data intending trusted enterprise is the first abnormal index.First abnormal index can be
Quantization type abnormal index, qualitative abnormal index or cluster type abnormal index.
Extraction quantization type abnormal index and the extraction plan of cluster type abnormal index is stored in abnormal index identification model
Slightly, according to extraction strategy, the first abnormal index is extracted.
Step 102, by abnormal with second in each case in the instruction case library built in advance for the first abnormal index
Index carries out matching primitives, obtains the matching degree case more than preset matching degree, and matching degree more than the case of preset matching degree is
Coupling case.
In the present embodiment, include, at the instruction case library built in advance, the exception that the enterprise of breaking a contract of predetermined number is corresponding
Index, abnormal index corresponding to each enterprise of having broken a contract is the second abnormal index.The second exception that each enterprise of having broken a contract is corresponding
Index can be multiple.A case in instruction case library is constituted by the second abnormal index that each enterprise of having broken a contract is corresponding.
High risk content according to each enterprise of having broken a contract is different, and content and the number of the second abnormal index are also not quite similar.
In the present embodiment, can be by whether occurring event of default to determine this trusted during the follow-up loan of trusted enterprise
Whether enterprise is enterprise of having broken a contract.
Specifically, in the present embodiment, each first abnormal index can be indicated in case library with build in advance respectively
The second abnormal index in each case carries out matching primitives, determines and the matching degree of each case, by with each case
Degree of joining is ranked up, and obtains the matching degree case more than preset matching degree.In the present embodiment, the numerical value of preset matching degree can be
80%, it is also possible to be 85%, or other suitable numerical value, be not construed as limiting this in the present embodiment.
Wherein, the case that matching degree is more than preset matching degree is coupling case.In the present embodiment, can be abnormal according to first
Index and the size of the matching degree of the second abnormal index matching primitives of each case, mate case and can be one, it is also possible to
For multiple.Also can be very much like to the second abnormal index in instruction case library in advance, the case that registration is higher carries out merger, this
Time coupling case be one.
Step 103, determines the weight that each second abnormal index matched in coupling case is corresponding.
Specifically, in the present embodiment, prestore the weight that each second abnormal index of instruction case library is corresponding, if
First abnormal index matches with the second abnormal index in a certain case, then corresponding according to the second abnormal index prestored
Weight corresponding to the first abnormal index that weight finds with the second abnormal index matches.
Wherein, weight corresponding to the second abnormal index prestored setting means can according to the second abnormal index with
The degree of association of event of default of enterprise of having broken a contract is set, it is possible to the second abnormal index in the enterprise of promise breaking of predetermined number
Responsible investigation report in occur the frequency add up, according to occur the frequency set the weight that the second abnormal index is corresponding,
Or adopt in other ways, the present embodiment does not limits.
Step 104, calculate weight that in coupling case, each second abnormal index of matching is corresponding and, and by weight and
Compare with default weight threshold.
Wherein, the weight sum that in instruction case library, all second abnormal indexes of each case are corresponding, pin can first be calculated
Each case is all preset a weight threshold, and each second abnormal index matched in the coupling case that will calculate is corresponding
Weight and compare, according to comparative result with corresponding default weight threshold, it is judged that intend trusted enterprise credit risk.Also
A weight threshold can be set according to the weight situation of abnormal index of all cases in instruction case library, by calculate
Join weight corresponding to each second abnormal index matched in case and compare with this default weight threshold, the present embodiment
In this is not limited.
Step 105, if weight and more than preset weight threshold, it is determined that intend trusted enterprise be high default risk trusted enterprise
Industry.
Specifically, in the present embodiment, if weight and more than preset weight threshold, then explanation intend trusted enterprise Risk Content
All case is mated with this similar, it is determined that intend the trusted enterprise that trusted enterprise is high default risk with risk height.
If it should be noted that weight and be not more than preset weight threshold, then explanation intend trusted enterprise Risk Content with
Coupling case is similar, but the height intending the credit risk of trusted enterprise needs to be determined further.
The Enterprise Credit Risk Evaluation method that the present embodiment provides is many by extracting from the survey data intending trusted enterprise
Individual abnormal index, the abnormal index extracted from the survey data intending trusted enterprise is the first abnormal index；Extremely refer to first
Mark carries out matching primitives with the second abnormal index in each case in the instruction case library built in advance, obtains matching degree big
In the case of preset matching degree, matching degree is coupling case more than the case of preset matching degree；Determine in coupling case and match
Weight corresponding to each second abnormal index；Calculate the weight that each second abnormal index matched in coupling case is corresponding
With, and compare by weight with default weight threshold；If weight and more than preset weight threshold, it is determined that intend trusted enterprise
Trusted enterprise for high default risk.There is the multiple exception having broken a contract enterprise refer to due in the instruction case library that builds in advance
Mark, contains comprehensively, is no lack of to have and carries out the abnormal index after index is beautified, so being applicable not only to normally intend the wind of trusted enterprise
Danger assessment, is also applied for carrying out the risk assessment intending trusted enterprise that index is beautified, and improves the accurate of risk evaluation result
Rate.
Fig. 2 is the flow chart of Enterprise Credit Risk Evaluation embodiment of the method two of the present invention, as in figure 2 it is shown, the present embodiment carries
The Enterprise Credit Risk Evaluation method of confession, compared to embodiment one, is a particularly preferred embodiment, then the present embodiment provides
Enterprise Credit Risk Evaluation method comprises the following steps.
Step 201, it may be judged whether storage has the instruction case library built in advance, the most then perform step 206, otherwise, then
Perform step 202.
In the present embodiment, the instruction case library built in advance can be stored in default memory area or storage chip,
Preset in memory area or storage chip and search whether that there is the instruction case library built in advance.
Step 202, extracts abnormal index from the responsible investigation of the enterprise of breaking a contract of predetermined number is reported respectively, from presetting
The abnormal index extracted in the responsible investigation report of the enterprise of breaking a contract of quantity is the second abnormal index.
Further, in the present embodiment, from the responsible investigation of the enterprise of breaking a contract of predetermined number is reported, extract the respectively
Two abnormal indexes are any one of following abnormal index: quantization type abnormal index, qualitative abnormal index, cluster type refer to extremely
Mark.Include the multiple features forming abnormal index at cluster type abnormal index, there are this multiple features the most simultaneously, could structure
Become cluster type abnormal index.
In the present embodiment, abnormal index identification model stores extraction quantization type abnormal index, qualitative abnormal index
With the extraction strategy of cluster type abnormal index, according to extracting strategy, the second abnormal index is extracted.
Wherein, when extracting the quantization type abnormal index in the second abnormal index, by the responsible investigation report of enterprise of breaking a contract
Accusing the extracting rule extracted in strategy with each quantization type abnormal index prestored to contrast, extracting rule if meeting
Then, then from the responsible investigation of enterprise of breaking a contract is reported, extract the quantization type index of correspondence.When extracting qualitative abnormal index,
Extraction strategy according to qualitative index, receives the qualitative abnormal index of user's income, extracts qualitative abnormal index.Extracting second
During cluster type abnormal index in abnormal index, according to the extraction strategy of every kind of poly-index of classification, check which feature needs
Being inputted by user, which feature can automatically extract, and when needs user inputs, can show to user by the way of window or menu
Show, and receive the feature that user is inputted by window or menu, when if desired automatically extracting, it is possible to according to quantization type abnormal index
Similar extracting method extracts.If there are all features of cluster type abnormal index, then by cluster type abnormal index simultaneously
Extract from the responsible investigation of enterprise of breaking a contract is reported.
Step 203, is set the weight of each second abnormal index.
Further, Fig. 3 is the flow chart of step 203 in the embodiment of the present invention two, as it is shown on figure 3, in the present embodiment, step
Rapid 203 can be divided into following step to carry out.
Step 203a, it is judged that whether the second abnormal index is to preset abnormal index, and default abnormal index is rare and important
Abnormal index, the most then perform step 203b, otherwise, then perform step 203c.
Specifically, in the present embodiment, the extracted respectively in the responsible investigation report of the enterprise of breaking a contract of predetermined number
Two abnormal indexes do not ensure that the important abnormal index existing for the enterprise relating to all industries, so in advance to seldom
See and important abnormal index stores, and receive the power that each rare and important abnormal index is set of user's input
Weight, when the weight setting each rare and important abnormal index, the weight of the most important setting of abnormal index is the biggest.
Further, in the present embodiment, default abnormal index is respectively any one of following abnormal index: quantization type is different
Chang Zhibiao, qualitative abnormal index, cluster type abnormal index.
In the present embodiment, it is expressed as rare and important abnormal index presetting abnormal index.Can be by contrasting one by one
Mode judges whether to have in the second abnormal index default abnormal index, it is possible to judge that second refers to extremely by other control methods
Whether mark is to preset abnormal index.
Step 203b, according to the corresponding relation of the default abnormal index prestored Yu weight, determines the second abnormal index
Weight.
Specifically, in the present embodiment, prestore user's input each rare and important abnormal index is set
Weight, if the second abnormal index for preset abnormal index, then the weight of this second abnormal index be correspondence default exception
The weight of index.
Step 203c, calculates the degree of association of the second abnormal index and the event of default of enterprise of breaking a contract, sets according to the degree of association
The weight that fixed second abnormal index is corresponding, or, the frequency of the second abnormal index is added up, sets second according to the frequency different
The weight that Chang Zhibiao is corresponding.
Specifically, in the present embodiment, if the second abnormal index is not for presetting abnormal index, then the Return Law is used to calculate second
Abnormal index and the degree of association of the event of default of enterprise of breaking a contract, set, according to the degree of association, the weight that the second abnormal index is corresponding.
The i.e. degree of association is the biggest, and the weight that corresponding second abnormal index is corresponding is the biggest, and the degree of association is the least, and corresponding second abnormal index is corresponding
Weight is the least.In advance the degree of association and weight can be arranged mapping relations, according to these mapping relations, determine that this degree of association is corresponding
The weight of two abnormal indexes.
Or, in the present embodiment, it is possible to abnormal to second in the responsible investigation report of the enterprise of breaking a contract of predetermined number
The frequency of index is added up, and sets, according to the frequency, the weight that the second abnormal index is corresponding.
Specifically, prestore the frequency of the second abnormal index and the mapping relations of weight, count each second
After the frequency of abnormal index, according to the frequency and the mapping relations of weight of the second abnormal index, determine the weight of correspondence.Second is different
The frequency of Chang Zhibiao is the biggest, and corresponding weight is the biggest, and the frequency of the second abnormal index is the least, and corresponding weight is the least.
Table 1: the signal after the weight of each second abnormal index is set
Table 1 is the signal table after the weight to each second abnormal index is set, as shown in table 1, different to cluster type
The weight setting of Chang Zhibiao 1 and cluster type abnormal index 2 is respectively 1.5, to quantization type abnormal index 3, quantization type abnormal index
The weight setting of 4, quantization type abnormal index 5 is respectively 0.3,0.7,0.4.
Step 204, carries out pretreatment to the second abnormal index that enterprise of breaking a contract is corresponding, forms instruction case library.
Wherein, the second abnormal index that each enterprise of having broken a contract is corresponding is a case in instruction case library.
Specifically, in this enforcement, the institute of enterprise of breaking a contract that can be very few to the second abnormal index number in enterprise of breaking a contract
The second abnormal index is had to delete.Also can owning enterprise of breaking a contract too small for weight sum corresponding for the second abnormal index
Second abnormal index is deleted.Can also enter by the second abnormal index very much like to the second abnormal index, that registration is higher
Row merges, and forms a case.
Step 205, stores the instruction case library built, and weight corresponding for the second abnormal index is deposited
Storage.
In the present embodiment, the weight of the second abnormal index and the second being associated property of abnormal index can be stored.
Step 206, extracts multiple abnormal index from the survey data intending trusted enterprise, from the investigation money intending trusted enterprise
The abnormal index extracted in material is the first abnormal index.
Further, the first abnormal index is respectively any one of following abnormal index: quantization type abnormal index, qualitative
Abnormal index, cluster type abnormal index.
Step 207, by abnormal with second in each case in the instruction case library built in advance for the first abnormal index
Index carries out matching primitives, obtains the matching degree case more than preset matching degree, and matching degree more than the case of preset matching degree is
Coupling case.
Step 208, determines the weight that each second abnormal index matched in coupling case is corresponding.
Step 209, calculate weight that in coupling case, each second abnormal index of matching is corresponding and, and by weight and
Compare with default weight threshold, if weight and more than preset weight threshold, it is determined that intend trusted enterprise be high default risk
Trusted enterprise.
Step 101-step in the present embodiment, in the implementation of step 206-step 209 and the embodiment of the present invention one
The implementation of 105 is identical, and this is no longer going to repeat them.
If it should be noted that weight and be not more than and preset weight threshold, the credit risk of Ze Ni trusted enterprise need into
One step determines.
Step 210, according to the second abnormal index and the corresponding relation of Risk Content of pre-stored, searches and extremely refers to first
Mark the Risk Content that the second abnormal index matched is corresponding；And export the second abnormal index matched with the first abnormal index
Corresponding Risk Content.
Further, in the present embodiment, can be by each second abnormal index and corresponding Risk Content in instruction case library
Being associated property stores.Also can be as shown in table 1, the Risk Content of each second abnormal index, corresponding weight and correspondence is entered
Row relatedness stores, and searches the Risk Content corresponding with the second abnormal index that the first abnormal index matches, and by display
Screen exports this Risk Content corresponding with the second abnormal index that the first abnormal index matches.
Wherein, the form of the Risk Content that output is corresponding with the second abnormal index that the first abnormal index matches does not limits
Fixed.
The Enterprise Credit Risk Evaluation method that the present embodiment provides, stores the instruction case built in advance by judging whether
Example storehouse, if it is not, then extract abnormal index respectively, from predetermined number from the responsible investigation of the enterprise of breaking a contract of predetermined number is reported
Enterprise of breaking a contract responsible investigation report in extract abnormal index be the second abnormal index, to each second abnormal index
Weight is set, and the second abnormal index that enterprise of breaking a contract is corresponding carries out pretreatment, forms instruction case library, to build
Instruction case library stores, and weight corresponding for the second abnormal index is stored, from the survey data intending trusted enterprise
The multiple abnormal index of middle extraction, the abnormal index extracted from the survey data intending trusted enterprise is the first abnormal index, by the
One abnormal index carries out matching primitives with the second abnormal index in each case in the instruction case library built in advance, obtains
Matching degree is coupling case more than the case of preset matching degree, matching degree more than the case of preset matching degree, determines coupling case
In weight corresponding to each second abnormal index of matching, calculate each second abnormal index pair matched in coupling case
The weight answered and, and compare by weight with default weight threshold, if weight and more than presetting weight threshold, it is determined that intend
Trusted enterprise is the trusted enterprise of high default risk, according to the second abnormal index and the corresponding relation of Risk Content of pre-stored,
Search the Risk Content corresponding with the second abnormal index that the first abnormal index matches；And export and the first abnormal index phase
The Risk Content that the second abnormal index of joining is corresponding, can obtain risk after judging the credit risk intending trusted enterprise
Content, improves determining whether to intend whether trusted enterprise has the guide of risk.
Fig. 4 is the structural representation of Enterprise Credit Risk Evaluation device embodiment one of the present invention, as shown in Figure 4, this enforcement
The Enterprise Credit Risk Evaluation device that example provides includes: extraction module 41, computing module 42 and determine module 43.
Wherein, extraction module 41, for extracting multiple abnormal index, from intending trusted from the survey data intending trusted enterprise
The abnormal index extracted in the survey data of enterprise is the first abnormal index.Computing module 42, for by the first abnormal index with
The second abnormal index in each case in the instruction case library built in advance carries out matching primitives, obtains matching degree more than pre-
If the case of matching degree, matching degree is coupling case more than the case of preset matching degree.Determine module 43, be used for determining coupling case
The weight that each second abnormal index of matching in example is corresponding.Computing module 42, is additionally operable in calculating coupling case match
Weight corresponding to each second abnormal index and, and compare by weight with default weight threshold.Determine module 43, also
If for weight with more than presetting weight threshold, it is determined that intend the trusted enterprise that trusted enterprise is high default risk.
The device that the present embodiment provides can perform the technical scheme of embodiment of the method shown in Fig. 1, and it realizes principle and skill
Art effect is similar to, and here is omitted.
Fig. 5 is the structural representation of Enterprise Credit Risk Evaluation device embodiment two of the present invention；As it is shown in figure 5, this enforcement
Example, on the basis of Enterprise Credit Risk Evaluation device embodiment one of the present invention, also includes: setting module 51, pretreatment module
52, module 53 and output module 54 are searched.
Further, extraction module 41, for computing module 42 by the first abnormal index and the instruction case built in advance
The second abnormal index in each case in storehouse carries out matching primitives, obtain matching degree more than preset matching degree case it
Before, from the responsible investigation of the enterprise of breaking a contract of predetermined number is reported, extract abnormal index respectively, from the promise breaking of predetermined number
The abnormal index extracted in the responsible investigation report of enterprise is the second abnormal index.Setting module 51, for each second different
The weight of Chang Zhibiao is set.Pretreatment module 52, for carrying out pre-place to the second abnormal index that enterprise of breaking a contract is corresponding
Reason, forms instruction case library, and the second abnormal index corresponding to each enterprise of having broken a contract is a case in instruction case library.
Further, search module 53, after being used for determining that module determines that plan trusted enterprise is high risk trusted enterprise,
The second abnormal index according to pre-stored and the corresponding relation of Risk Content, search second matched with the first abnormal index different
The Risk Content that Chang Zhibiao is corresponding.Output module 54, the second abnormal index pair matched with the first abnormal index for output
The Risk Content answered.
Further, in the Enterprise Credit Risk Evaluation device that the present embodiment provides, the first abnormal index, second extremely refer to
Mark and default abnormal index are respectively any one of following abnormal index: quantization type abnormal index, qualitative abnormal index, cluster
Type abnormal index.
The device that the present embodiment provides can perform the technical scheme of embodiment of the method shown in Fig. 2 and Fig. 3, and it realizes principle
Similar with technique effect, here is omitted.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each method embodiment can be led to
The hardware crossing programmed instruction relevant completes.Aforesaid program can be stored in a computer read/write memory medium.This journey
Sequence upon execution, performs to include the step of above-mentioned each method embodiment；And aforesaid storage medium includes: ROM, RAM, magnetic disc or
The various media that can store program code such as person's CD.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit；To the greatest extent
The present invention has been described in detail by pipe with reference to foregoing embodiments, it will be understood by those within the art that: it depends on
So the technical scheme described in foregoing embodiments can be modified, or the most some or all of technical characteristic is entered
Row equivalent；And these amendments or replacement, do not make the essence of appropriate technical solution depart from various embodiments of the present invention technology
The scope of scheme.
Claims (10)
1. an Enterprise Credit Risk Evaluation method, it is characterised in that including:
From the survey data intending trusted enterprise, extract multiple abnormal index, extract from the survey data of described plan trusted enterprise
Abnormal index be the first abnormal index；
Described first abnormal index is carried out with the second abnormal index in each case in the instruction case library built in advance
Matching primitives, obtains the matching degree case more than preset matching degree, and described matching degree is coupling more than the case of preset matching degree
Case；
Determine the weight that each second abnormal index matched in described coupling case is corresponding；
Calculate weight corresponding to each second abnormal index matched in described coupling case and, and by described weight and with in advance
If weight threshold compares；
If described weight and more than described default weight threshold, it is determined that described plan trusted enterprise is the trusted enterprise of high default risk
Industry.
Method the most according to claim 1, it is characterised in that described by described first abnormal index and the finger built in advance
Show that the second abnormal index in each case in case library carries out matching primitives, obtain the matching degree case more than preset matching degree
Before example, also include:
From the responsible investigation of the enterprise of breaking a contract of predetermined number is reported, extract abnormal index respectively, described from predetermined number
The abnormal index extracted in the responsible investigation report of promise breaking enterprise is the second abnormal index；
The weight of each second abnormal index is set；
The second abnormal index that enterprise of breaking a contract is corresponding is carried out pretreatment, forms instruction case library, described each enterprise of having broken a contract
Second abnormal index corresponding to industry is a case in described instruction case library.
Method the most according to claim 2, it is characterised in that the described weight to each second abnormal index is set
Specifically include:
Judging whether described second abnormal index is to preset abnormal index, described default abnormal index is rare and important exception
Index；
If described second abnormal index is for presetting abnormal index, then corresponding with weight according to the default abnormal index prestored
Relation, determines the weight of described second abnormal index；
If described second abnormal index for presetting abnormal index, does not then calculate the promise breaking thing of the second abnormal index and enterprise of breaking a contract
The degree of association of part, sets, according to the degree of association, the weight that described second abnormal index is corresponding, or, the frequency to the second abnormal index
Add up, set, according to the described frequency, the weight that described second abnormal index is corresponding.
Method the most according to claim 1, it is characterised in that described determine that described plan trusted enterprise is high risk trusted
After enterprise, also include:
The second abnormal index according to pre-stored and the corresponding relation of Risk Content, search and match with described first abnormal index
Risk Content corresponding to the second abnormal index；
Export the Risk Content corresponding with the second abnormal index that described first abnormal index matches.
5. according to the method described in claim 3 or 4, it is characterised in that described first abnormal index, described second abnormal index
It is respectively any one of following abnormal index: quantization type abnormal index, qualitative abnormal index, poly-with described default abnormal index
Type abnormal index.
6. an Enterprise Credit Risk Evaluation device, it is characterised in that including:
Extraction module, for extracting multiple abnormal index, from described plan trusted enterprise from the survey data intending trusted enterprise
The abnormal index extracted in survey data is the first abnormal index；
Computing module, for by described first abnormal index and second in each case in the instruction case library built in advance
Abnormal index carries out matching primitives, obtains the matching degree case more than preset matching degree, and described matching degree is more than preset matching degree
Case for coupling case；
Determine module, for determining the weight that each second abnormal index matched in described coupling case is corresponding；
Described computing module, is additionally operable to calculate the weight that each second abnormal index matched in described coupling case is corresponding
With, and compare by described weight with default weight threshold；
Described determine module, if being additionally operable to described weight and more than described default weight threshold, it is determined that described plan trusted enterprise
Trusted enterprise for high default risk.
Device the most according to claim 6, it is characterised in that also include: setting module and pretreatment module,
Described extraction module, indicates described first abnormal index in case library with build in advance for described computing module
The second abnormal index in each case carries out matching primitives, before obtaining the case that matching degree is more than preset matching degree, from advance
If abnormal index, the described enterprise of promise breaking from predetermined number are extracted in the responsible investigation report of the enterprise of breaking a contract of quantity respectively
Responsible investigation report in extract abnormal index be the second abnormal index；
Described setting module, for being set the weight of each second abnormal index；
Described pretreatment module, for the second abnormal index that enterprise of breaking a contract is corresponding carries out pretreatment, forms instruction case
Storehouse, the second abnormal index corresponding to described each enterprise of having broken a contract is a case in described instruction case library.
Device the most according to claim 7, it is characterised in that described setting module, specifically for:
Judging whether described second abnormal index is to preset abnormal index, described default abnormal index is rare and important exception
Index；If described second abnormal index is for presetting abnormal index, then the default abnormal index that basis prestores is right with weight
Should be related to, determine the weight of described second abnormal index；If described second abnormal index is for presetting abnormal index, then calculate the
Two abnormal indexes and the degree of association of the event of default of enterprise of breaking a contract, set described second abnormal index according to the degree of association corresponding
Weight, or, the frequency of the second abnormal index is added up, sets described second abnormal index according to the described frequency corresponding
Weight.
Device the most according to claim 6, it is characterised in that also include: search module and output module,
Described lookup module, for described determine that module determines that described plan trusted enterprise is high risk trusted enterprise after, root
According to the second abnormal index and the corresponding relation of Risk Content of pre-stored, search second matched with described first abnormal index
The Risk Content that abnormal index is corresponding；
Described output module, in the risk that output is corresponding with the second abnormal index that described first abnormal index matches
Hold.
Device the most according to claim 8 or claim 9, it is characterised in that described first abnormal index, described second extremely refer to
Mark and described default abnormal index are respectively any one of following abnormal index: quantization type abnormal index, qualitative abnormal index,
Cluster type abnormal index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610515164.7A CN106203808A (en) | 2016-07-01 | 2016-07-01 | Enterprise Credit Risk Evaluation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610515164.7A CN106203808A (en) | 2016-07-01 | 2016-07-01 | Enterprise Credit Risk Evaluation method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106203808A true CN106203808A (en) | 2016-12-07 |
Family
ID=57464790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610515164.7A Pending CN106203808A (en) | 2016-07-01 | 2016-07-01 | Enterprise Credit Risk Evaluation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106203808A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106802916A (en) * | 2016-12-09 | 2017-06-06 | 国网北京市电力公司 | Method of calibration, the apparatus and system of the transaction record data of electric automobile |
| CN107909274A (en) * | 2017-11-17 | 2018-04-13 | 平安科技（深圳）有限公司 | Enterprise investment methods of risk assessment, device and storage medium |
| CN108509491A (en) * | 2018-02-12 | 2018-09-07 | 阿方提法律咨询（上海）有限公司 | A kind of enterprise's responsible investigation data processing system and method |
| CN109523116A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Business risk analysis method, device, computer equipment and storage medium |
| CN109829640A (en) * | 2019-01-23 | 2019-05-31 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of enterprise's default risk |
| CN109858762A (en) * | 2018-12-29 | 2019-06-07 | 重庆誉存大数据科技有限公司 | A kind of business risk prediction technique and device |
| CN110264022A (en) * | 2018-10-23 | 2019-09-20 | 爱信诺征信有限公司 | Enterprise vitality evaluation method and its device |
| CN110659841A (en) * | 2019-09-29 | 2020-01-07 | 深圳前海环融联易信息科技服务有限公司 | Risk asset screening method and device, computer equipment and storage medium |
| CN110782327A (en) * | 2018-07-12 | 2020-02-11 | 阿里巴巴集团控股有限公司 | Abnormal information discovery method, device and equipment |
| CN115936830A (en) * | 2022-12-27 | 2023-04-07 | 企查查科技有限公司 | Enterprise credit risk assessment method and device |
-
2016
- 2016-07-01 CN CN201610515164.7A patent/CN106203808A/en active Pending
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106802916B (en) * | 2016-12-09 | 2020-02-07 | 国网北京市电力公司 | Method, device and system for verifying transaction record data of electric vehicle |
| CN106802916A (en) * | 2016-12-09 | 2017-06-06 | 国网北京市电力公司 | Method of calibration, the apparatus and system of the transaction record data of electric automobile |
| CN107909274A (en) * | 2017-11-17 | 2018-04-13 | 平安科技（深圳）有限公司 | Enterprise investment methods of risk assessment, device and storage medium |
| CN107909274B (en) * | 2017-11-17 | 2023-02-28 | 平安科技（深圳）有限公司 | Enterprise investment risk assessment method and device and storage medium |
| WO2019095572A1 (en) * | 2017-11-17 | 2019-05-23 | 平安科技（深圳）有限公司 | Enterprise investment risk assessment method, device, and storage medium |
| CN108509491A (en) * | 2018-02-12 | 2018-09-07 | 阿方提法律咨询（上海）有限公司 | A kind of enterprise's responsible investigation data processing system and method |
| CN108509491B (en) * | 2018-02-12 | 2021-10-15 | 阿方提法律咨询（上海）有限公司 | Enterprise due diligence data processing system and method |
| CN110782327B (en) * | 2018-07-12 | 2023-06-30 | 阿里巴巴集团控股有限公司 | Abnormal information discovery method, device and equipment |
| CN110782327A (en) * | 2018-07-12 | 2020-02-11 | 阿里巴巴集团控股有限公司 | Abnormal information discovery method, device and equipment |
| CN109523116A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Business risk analysis method, device, computer equipment and storage medium |
| CN110264022A (en) * | 2018-10-23 | 2019-09-20 | 爱信诺征信有限公司 | Enterprise vitality evaluation method and its device |
| CN109858762A (en) * | 2018-12-29 | 2019-06-07 | 重庆誉存大数据科技有限公司 | A kind of business risk prediction technique and device |
| CN109829640A (en) * | 2019-01-23 | 2019-05-31 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of enterprise's default risk |
| CN110659841A (en) * | 2019-09-29 | 2020-01-07 | 深圳前海环融联易信息科技服务有限公司 | Risk asset screening method and device, computer equipment and storage medium |
| CN110659841B (en) * | 2019-09-29 | 2022-08-09 | 深圳前海环融联易信息科技服务有限公司 | Risk asset screening method and device, computer equipment and storage medium |
| CN115936830A (en) * | 2022-12-27 | 2023-04-07 | 企查查科技有限公司 | Enterprise credit risk assessment method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106203808A (en) | Enterprise Credit Risk Evaluation method and apparatus | |
| US11769008B2 (en) | Predictive analysis systems and methods using machine learning | |
| CN110458697A (en) | Method and apparatus for assessing risk | |
| CN106530078A (en) | Loan risk early warning method and system based on multi-industry data | |
| KR102168198B1 (en) | Business default prediction system and operation method thereof | |
| CN105719045A (en) | Retention risk determiner | |
| CN108363717B (en) | Data security level identification and detection method and device | |
| CN108009911A (en) | A kind of method of identification P2P network loan borrower's default risks | |
| CN108492001A (en) | A method of being used for guaranteed loan network risk management | |
| CN107274291A (en) | Cross-platform valuation table analytic method, storage medium and application server | |
| US20190392295A1 (en) | Information processing device, method, and program that use deep learning | |
| CN108428178A (en) | financing risk control method, device, equipment and storage medium | |
| CN110930038A (en) | Loan demand identification method, loan demand identification device, loan demand identification terminal and loan demand identification storage medium | |
| CN110009219A (en) | Financial big data processing method, storage medium and equipment | |
| CN110348471A (en) | Exception object recognition methods, device, medium and electronic equipment | |
| CN111210321B (en) | Risk early warning method and system based on contract management | |
| CN106033455A (en) | Method and device for processing user operation information | |
| KR102110889B1 (en) | System for providing AI clause inspection | |
| CN110910002B (en) | Account receivables default risk identification method and system | |
| CN112907371A (en) | Training method of wind control model | |
| CN108830723A (en) | Electronic device, bond yield analysis method and storage medium | |
| CN105335630A (en) | Identity recognition method and identity recognition device | |
| Sapkota et al. | Fear sells: determinants of fund-raising success in the cross-section of initial coin offerings | |
| CN112330328A (en) | Credit card fraud detection method based on feature extraction | |
| CN109635289A (en) | Entry classification method and audit information abstracting method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |
|
| RJ01 | Rejection of invention patent application after publication |