CN108596638A - Anti- fraud recognition methods and system based on big data, terminal and storage medium - Google Patents
Anti- fraud recognition methods and system based on big data, terminal and storage medium Download PDFInfo
- Publication number
- CN108596638A CN108596638A CN201810393697.1A CN201810393697A CN108596638A CN 108596638 A CN108596638 A CN 108596638A CN 201810393697 A CN201810393697 A CN 201810393697A CN 108596638 A CN108596638 A CN 108596638A
- Authority
- CN
- China
- Prior art keywords
- loaning bill
- fraud
- bill side
- related information
- big data
- 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.)
- Withdrawn
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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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
Abstract
The anti-fraud recognition methods and system that the invention discloses a kind of based on big data, terminal and storage medium, the method includes：When receiving the loaning bill request that loaning bill side is sent, according to the essential information of the side of loaning bill described in the loaning bill acquisition request；Loaning bill side's identity is determined according to the essential information, obtains the relation data block of the loaning bill side from relational database based on loaning bill side's identity；The essential information and corresponding node in the relation data block are compared, judge whether unmatched risk point；If there are unmatched risk point, there are risk of fraud for judgement.The present invention can reduce the credit risk of creditor, safeguard loan order.
Description
Technical field
The present invention relates to financial system technical field more particularly to a kind of anti-fraud recognition methods based on big data and it is
System, terminal and storage medium.
Background technology
With the combination of computer networking technology and financial service, remote financial service is more and more universal, the thing followed
It is the protrusion of financial security problem, therefore, financial security problem becomes the research hotspot of this field.
It is the fraud problems in credit that credit financial field, which needs the most important safety problems solved,.It is existing common anti-
Fraud mode has carries out fraud identification by obtaining device-fingerprint or IP address of equipment, such as：Device-fingerprint is obtained, if same equipment
Repeatedly application, there are fraud suspicion；If same equipment application credit card simultaneously applies for loan etc. in a loan, there are fraud suspicion；If
Multiple equipment carries out credit applications in same IP address, then there is fraud suspicion.Fraud identification is only carried out through the above way to deposit
In the inaccurate problem of identification.
Invention content
The anti-fraud recognition methods based on big data that the main purpose of the present invention is to provide a kind of, purport solve above-mentioned fraud
The inaccurate technical problem of identification method identification.
To achieve the above object, the present invention provides a kind of anti-fraud recognition methods based on big data, described based on big number
According to anti-fraud recognition methods include：
When receiving the loaning bill request that loaning bill side is sent, according to the basic letter of the side of loaning bill described in the loaning bill acquisition request
Breath；
Loaning bill side's identity is determined according to the essential information, and institute is obtained from relational database based on loaning bill side's identity
State the relation data block of loaning bill side；
The essential information and corresponding node in the relation data block are compared, judged whether unmatched
Risk point；
If there are unmatched risk point, there are risk of fraud for judgement.
In a kind of optional embodiment, it is described based on loaning bill side's identity obtained from relational database described in borrow
The step of relation data block of money side includes：
According to loaning bill side's ID inquiring relational database, judge to whether there is the loaning bill in the relational database
The relation data block of side；
If in the presence of the relation data block of the loaning bill side is obtained from relational database；
If being not present, the related information of the loaning bill side is acquired, the loaning bill side is generated according to the related information
The relation data block of the loaning bill side is stored in the relational database by relation data block, obtains the relationship of the loaning bill side
Data block.
In a kind of optional embodiment, include after described the step of judging whether unmatched risk point：
If unmatched risk point is not present, according to the relation data block production Methods validation problem of the loaning bill side；
The answer for receiving the relationship validation problem that the loaning bill side inputs judges whether the answer is all correct；
If wrong answer accounting is more than preset ratio in the answer, there are risk of fraud for judgement.
In a kind of optional embodiment, the related information of the acquisition loaning bill side, according to the related information
The step of relation data block for generating the loaning bill side includes：
Acquisition has the first related information set of direct correlation with the loaning bill side, obtains the first related information set
In each first related information link type；
The extension rank of each first related information is determined according to the link type, is acquired based on the extension rank
Corresponding second related information of each first related information, wherein the corresponding first association letter of the second related information
Cease the incidence relation having in the extension rank；
Described in incidence relation composition between the loaning bill side, the first related information, the second related information and former three
The relation data block of loaning bill side.
In a kind of optional embodiment, the loaning bill side, the first related information, the second related information and preceding
Incidence relation between three formed after the step of relation data block of the loaning bill side：
There is the association more than the first predetermined number in detecting first related information and the second related information to borrow
After money user, the fraud scoring of the related party loans user is obtained, wherein association of the fraud scoring less than predetermined threshold value is borrowed
Money user is fraudulent user；
If there is the fraudulent user more than the second predetermined number in the related party loans user, judge there is fraud wind
Danger.
In a kind of optional embodiment, the judgement includes later the step of there are risk of fraud：
Fraud label is added for the loaning bill side；
It is more than preset times when detecting that the loaning bill side refunds to record on time, and the fraud scoring of the loaning bill side is higher than
When predetermined threshold value, the fraud label of the loaning bill side is deleted.
In a kind of optional embodiment, the anti-fraud recognition methods based on big data includes：
User behavior data, personal information data and the third party's credit data of the loaning bill side are obtained, the use is based on
Family behavioral data, personal information data and third party's credit data determine the fraud scoring of the loaning bill side.
To achieve the above object, the present invention provides a kind of anti-fraud identifying system based on big data, described based on big number
According to anti-fraud identifying system include：
Data acquisition module, for when receiving the loaning bill request that loaning bill side sends, according to the loaning bill acquisition request
The essential information of the loaning bill side；
Relation data block acquisition module is based on the loaning bill side for determining loaning bill side's identity according to the essential information
Identity obtains the relation data block of the loaning bill side from relational database；
Risk analysis module is sentenced for comparing the essential information and corresponding node in the relation data block
It is disconnected to whether there is unmatched risk point；
Determination module is cheated, for when there are unmatched risk point, there are risk of fraud for judgement.
To achieve the above object, the present invention also provides a kind of anti-fraud identification terminal based on big data, it is described based on big
The anti-fraud identification terminal of data includes：It memory, processor and is stored on the memory and can be on the processor
The anti-fraud recognizer based on big data of operation, the anti-fraud recognizer based on big data are held by the processor
The step as described in the anti-fraud recognition methods based on big data above-mentioned is realized when row.
In addition, to achieve the above object, the present invention also provides a kind of storage medium, being stored with and being based on the storage medium
The anti-fraud recognizer of big data is realized when the anti-fraud recognizer based on big data is executed by processor as above-mentioned
Step described in anti-fraud recognition methods based on big data.
A kind of anti-fraud recognition methods based on big data that the embodiment of the present invention proposes, by receiving loaning bill side's hair
When the loaning bill request sent, according to the essential information of the side of loaning bill described in the loaning bill acquisition request；It is determined according to the essential information
Loaning bill side's identity obtains the relation data block of the loaning bill side based on loaning bill side's identity from relational database；It will be described
Essential information is compared with corresponding node in the relation data block, judges whether unmatched risk point；If in the presence of
Unmatched risk point, then judgement is there are risk of fraud, the case where may recognize that forged identity information, and occurring, information comparison is different
Often, that is, when there is risk point, there are risk of fraud for judgement, remind lending platforms or creditor that there may be risk of fraud, reduce
The credit risk of creditor maintains loan order.
Description of the drawings
Fig. 1 is the anti-fraud identification terminal hardware architecture diagram involved in the embodiment of the present invention；
Fig. 2 is anti-one example structure schematic diagram of fraud identifying system involved in the embodiment of the present invention；
Fig. 3 is the flow diagram of the anti-fraud recognition methods first embodiment the present invention is based on big data；
Fig. 4 is that the present invention is based on anti-one example schematics of fraud recognition methods of big data；
Fig. 5 is that the present invention is based on another example schematics of anti-fraud recognition methods of big data.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In subsequent description, if using the suffix of such as " module ", " component " or " unit " for indicating element, only for having
Conducive to the explanation of the present invention, itself there is no specific meaning.Therefore, " module ", " component " or " unit " can mixedly make
With.
The present embodiments relate to the anti-fraud recognition methods based on big data be mainly used in based on the anti-of big data
Cheat identification terminal, this instead cheat identification terminal can be PC, pocket computer, mobile terminal etc. have show and processing function
Equipment.
Referring to Fig.1, Fig. 1 is the anti-fraud identification terminal hardware architecture diagram involved in the embodiment of the present invention.This
In inventive embodiments, the anti-fraud identification terminal based on big data may include processor 1001, such as CPU, network interface
1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 for realizing these components it
Between connection communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard),
Touch screen, camera (including AR/VR equipment), optional user interface 1003 can also include the wireline interface of standard, wirelessly connect
Mouthful.Network interface 1004 may include optionally standard wireline interface and wireless interface (such as WI-FI interfaces, blue tooth interface, spy
Needle interface, 3G/4G/5G connected network communication interfaces etc.).Memory 1005 can be high-speed RAM memory, can also be stable deposit
Reservoir (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned place
Manage the storage device of device 1001.It will be understood by those skilled in the art that hardware configuration shown in Fig. 1 is not constituted to the present invention
Restriction, may include either combining certain components or different components arrangement than illustrating more or fewer components.
With continued reference to Fig. 1, in Fig. 1 as a kind of memory 1005 of computer readable storage medium may include operation system
System, network communication module and counter cheat recognizer.In Fig. 1, network communication module is mainly used for Connection Service device, with clothes
Device be engaged in into row data communication；And processor 1001 can call the anti-fraud recognizer stored in memory 1005, and execute
Anti- fraud recognition methods provided in an embodiment of the present invention based on big data.
The embodiment of the present invention also provides a kind of anti-fraud identifying system based on big data.
With reference to the function module signal that Fig. 2, Fig. 2 are anti-fraud one embodiment of identifying system the present invention is based on big data
Figure.
In the present embodiment, the anti-fraud identifying system based on big data includes：
Data acquisition module, for when receiving the loaning bill request that loaning bill side sends, according to the loaning bill acquisition request
The essential information of the loaning bill side；
Relation data block acquisition module is based on the loaning bill side for determining loaning bill side's identity according to the essential information
Identity obtains the relation data block of the loaning bill side from relational database；
Risk analysis module is sentenced for comparing the essential information and corresponding node in the relation data block
It is disconnected to whether there is unmatched risk point；
Determination module is cheated, for when there are unmatched risk point, there are risk of fraud for judgement.
The anti-fraud recognition methods based on big data that an embodiment of the present invention provides a kind of.
With reference to the flow diagram that Fig. 3, Fig. 3 are the anti-fraud recognition methods first embodiment the present invention is based on big data.
In the present embodiment, the anti-fraud recognition methods includes the following steps：
Step S10, when receiving the loaning bill request that loaning bill side is sent, according to loaning bill side described in the loaning bill acquisition request
Essential information；
In the present embodiment the anti-fraud recognition methods based on big data be applied to lending platforms, in credit flow into
The anti-fraud identification of row, carries out demand docking in order to facilitate debtor and creditor, constructs a lending platforms, there is the loaning bill of borrowing demand
Loan application can be carried out in lending platforms, have making loans for the ability of making loans that can make loans in lending platforms.
The actual identity of the side of loaning bill is natural person, can also be enterprise in the present embodiment.When loaning bill side borrows money
When, lending platforms can be accessed by network；Then loan application option is selected at the credit interface of lending platforms, with to credit
Platform sends corresponding loaning bill request.Lending platforms need identity information/note to loaning bill side when receiving loaning bill request
The essential informations such as volume information are collected, to carry out anti-fraud identification.In one embodiment, loaning bill side sends request of borrowing money
Before, the anti-fraud identification terminal where anti-fraud recognizer detects that loaning bill side starts the loaning bill in anti-fraud recognizer
When instruction is initiated in request, essential information supplementary instructions are exported by anti-identification terminal of cheating, it is desirable that loaning bill side's supplement is relevant basic
Information, if loaning bill side is natural person, required for the content of essential information supplemented may include basic identity information (including surname
Name, photo, fingerprint, identification card number, kinsfolk etc.), contact method (phone, home address, unit address etc.), proprietary information
(borrow money and it is expected amount, house property, deposit, income, bank transaction flowing water, educational background etc.), creditor-debtor entry etc., if loaning bill side is enterprise,
The content for the essential information supplemented needed for then may include that log-on message (step on by registered address, legal person/representative, certificate of registration etc.
Remember testimonial material), proprietary information, affiliate's information etc., may also require that loanings bill side supplements others information certainly.Loaning bill side
When receiving the supplementary instructions, essential information will be supplemented according to the supplementary instructions.It is worth noting that loaning bill side is in supplement base
When this information, not necessarily need to be supplemented fully according to the content in the supplementary instructions.Specifically, being wrapped in the supplementary instructions
Including required information and optional information, it is necessary to information includes basic identity information and contact method/log-on message and proprietary information,
Optional information includes proprietary information and creditor-debtor entry/affiliate's information；Loaning bill side needs required information in supplemental information
It to be supplemented as required, and the supplement of selectivity can be carried out according to actual conditions for optional information.
Optionally, for loaning bill side, essential information can be to lending platforms propose loan application when again
Supplement provides, and can also be to be provided when lending platforms carry out account creation (registration).For example, loaning bill side is registered in lending platforms
When account, can in account profile interface the relevant essential information of typing so that lending platforms get the essential information.
Step S20 determines loaning bill side's identity according to the essential information, is based on loaning bill side's identity from relational database
The middle relation data block for obtaining the loaning bill side；
Loaning bill side's identity in the present embodiment is to be exclusively used in the single message identification or information aggregate of mark loaning bill side's identity
Mark can navigate to unique specific individual/enterprise, for natural person, information aggregate mark by loaning bill side's identity
Can be the arbitrary combination of basic identity information, such as name+address+birthday/name+address+fingerprint, single message identification can be with
It is such as to be executed to name+address+birthday based on the unique identity that one or more information generate in loaning bill side's essential information
Hash algorithm generates a unique character string and is used as loaning bill side's identity.Loaning bill side's identity in the present embodiment, can be in loaning bill side
It generates, can also be generated when relation data block generates when registering typing essential information, after the generation of loaning bill side's identity, i.e., will
Loaning bill side's identity is associated with loaning bill side's relation data block in deposit relation data block, so that anti-identification terminal of cheating is according to loaning bill side
Identity inquires the relation data block of loaning bill side in relational database.
In the present embodiment " according to the essential information determine loaning bill side's identity " the step for can specifically include：
After the essential information of loaning bill acquisition request loaning bill side, according to loaning bill side's identity create-rule based on loaning bill side
Essential information generates loaning bill side's identity.For example, if loaning bill side's identity create-rule is this three of loaning bill side's name+address+birthday
Information aggregate, then the side's of loaning bill identity can be：Name：Zhang San；Address：Unit three, the Changsha, Hunan Yuhua District communities Yu Hua；
Birthday：December 1 nineteen ninety.
Or may include：
The correspondence of basic identity information and loaning bill side's identity is stored in anti-fraud identification terminal, the correspondence is such as
Following table：
After obtaining basic identity information, loaning bill side's identity can be determined according to correspondence as shown above.
Relational database refers to the database of storage loaning bill side's relation data block, can be that anti-fraud identification terminal is locally stored
Database, can also be long-distance on-line database.Loaning bill side's identity and loaning bill side's relation data are stored in relational database
Incidence relation or loaning bill side's identity between block and loaning bill side's relation data block associated storage in relational database, therefore,
The relation data block of loaning bill side can be obtained from relational database according to loaning bill side's identity.
Specifically, the loaning bill side is obtained from relational database based on loaning bill side's identity described in step S20
The step of relation data block includes：
Step S21 judges to whether there is in the relational database according to loaning bill side's ID inquiring relational database
The relation data block of the loaning bill side；If in the presence of step S22 is executed；If being not present, step S23 is executed；
Loaning bill side's information may be stored in relational database, it is also possible to not yet store loaning bill side's information, or not generate
The relation data block of loaning bill side.
Step S22 obtains the relation data block of the loaning bill side from relational database；
Step S23 acquires the related information of the loaning bill side, the relationship of the loaning bill side is generated according to the related information
The relation data block of the loaning bill side is stored in the relational database by data block, obtains the relation data of the loaning bill side
Block.
Related information refers to anti-fraud identification terminal is obtained from the various channels and relevant letter in loaning bill side in the present embodiment
Breath, can be the related information captured from network by web crawlers, can also be from social software, reference center, public product
The related information of the acquisitions such as golden data center, related information include the essential informations classification such as basic identity information, proprietary information.
Relation data block refers to the data acquisition system of the composition of the incidence relation between information entity and information entity, specific to this reality
It applies in example, relation data block refers to loaning bill side's (information entity), the related information (information entity) of loaning bill side and loaning bill side and its closes
The data acquisition system for joining the incidence relation composition between information, can be stored with RDF graph (resource description framework) or attribute graph structure.
Meanwhile relation data information entity in the block is known as node by the present embodiment, the related information of such as loaning bill side, loaning bill side is borrowed money
Square relation data node in the block.Such as Fig. 4, " Zhang San ", " address 1 ", " school 1 ", " company 1 ", " Li Si ", " phone 1 " are section
Point.
The essential information and corresponding node in the relation data block are compared, are judged whether by step S30
Unmatched risk point；If in the presence of S40 is thened follow the steps；If being not present, S50 is thened follow the steps.
For ease of understanding, an example is provided：
Loaning bill side's name is Zhang San, and the essential information of the loaning bill side based on its loaning bill acquisition request includes：Name-
Three, address：Address 1, school：School 1, company：Company 1, telephone number：Phone 1；Based on loaning bill side's identity from relational database
The middle relation data block for obtaining loaning bill side is as shown in figure 4, also include name, address, school, company and telephone number four respectively
Node saves addressed nodes, school and Tu4Zhong schools in name node, address and Fig. 4 in the name and Fig. 4 in essential information
Telephone number node is compared one by one in point, company and Tu4Zhong companies node, telephone number and Fig. 4, judge whether with
The inconsistent essential information of corresponding node information in Fig. 4 relation data blocks.
If in the presence of the inconsistent essential information is and the unmatched risk point of relation data block.
If being not present, can preliminary judgement essential information it is errorless, reduction falsely use information, the risk of forged identity information.
Step S40, if there are unmatched risk point, there are risk of fraud for judgement.
If there are risk point, then illustrate being associated with for the loaning bill side that essential information that the side of loaning bill inputs and lending platforms are collected
Information is inconsistent, and there are the risks of the false identities information/information that claims the identity of others fraudulently, that is, there is risk of fraud.
Further, if loaning bill side is only to slip up to input individual information by mistake, possible risk of fraud is little, to promote user
Experience then further judges whether risk point number is more than first threshold if there are unmatched risk points, if risk point
Number is greater than or equal to first threshold, then there are risk of fraud for judgement；If risk point number is less than first threshold, judgement is not present
Risk of fraud can carry out fraud in next step and judge flow.
If unmatched risk point is not present, that is, the loaning bill side that the essential information that the side of loaning bill inputs is collected with lending platforms
Related information is consistent, then reduces the risk of the false identities information/information that claims the identity of others fraudulently, then can carry out cheating in next step and sentence
Stop journey.
The present embodiment according to described in the loaning bill acquisition request by when receiving the loaning bill request that loaning bill side is sent, borrowing
The essential information of money side；Loaning bill side's identity is determined according to the essential information, is based on loaning bill side's identity from relational database
The middle relation data block for obtaining the loaning bill side；Corresponding node in the essential information and the relation data block is carried out pair
Than judging whether unmatched risk point；If there are unmatched risk point, there are risk of fraud for judgement, can recognize that
The case where going out forged identity information, occurring, information comparison is abnormal, that is, when there is risk point, there are risk of fraud for judgement, remind
There may be risk of fraud by lending platforms or creditor, reduce the credit risk of creditor, maintain loan order.
Further, in one embodiment, include after the step S30：
Step S50 is tested if unmatched risk point is not present according to the relation data block production Methods of the loaning bill side
Card problem；
Step S51 receives the answer for the relationship validation problem that the loaning bill side inputs, judges whether the answer is complete
Portion is correct；
Step S52, if wrong answer accounting is more than preset ratio in the answer, there are risk of fraud for judgement.
There is no risk points, then essential information is all correct, reduce forged identity Information Risk.Further to exclude to falsely use
The risk of identity information is judging there is no after risk of fraud, can carrying out cheating in next step judging flow, in the present embodiment, institute
It states fraud in next step and judges that flow executes step S50.
Relationship validation problem be according in relation data block loanings bill side related information generation be used for verify identity the problem of,
Particularly, relationship validation problem is unrelated with loaning bill side's essential information.
In the present embodiment, preset ratio refers to the preset ratio of anti-fraud identifying system based on big data, for example, default ratio
Example is 5%, if wrong answer accounting is 10%, judges, there are risk of fraud, if wrong answer accounting is 0%, to judge not
There are risk of fraud.
The present embodiment by determining there is no after unmatched risk point, according in the relation data block for the side of loaninging bill substantially
Related information production Methods validation problem other than information can further exclude the risk for falsely using identity information, reduce fraud wind
Danger.
Further, it is based on above-described embodiment and proposes the second embodiment of the present invention.
In the present embodiment, the related information of the loaning bill side is acquired in step S23, according to related information generation
The step for relation data block of loaning bill side includes：
Step S231, acquisition have the first related information set of direct correlation with the loaning bill side, obtain described first and close
Join the link type of each first related information in information aggregate；
Step S232 is determined the extension rank of each first related information according to the link type, is prolonged based on described
It stretches rank and acquires corresponding second related information of each first related information, wherein second related information is corresponding
First related information has the incidence relation in the extension rank；
Step S233, the incidence relation between the loaning bill side, the first related information, the second related information and former three
Form the relation data block of the loaning bill side.
It is directly linked the incidence relation referred to based on loaning bill side, the name of such as loaning bill side is XX, school where loaning bill side
YY, loaning bill side's address is ZZ, and loaning bill side wife is QQ etc., therefore, the addresses ZZ there are one large-scale gymnasium be not with by means of
There is the first related information of direct correlation relationship in money side, and the principal of YY schools is nor there is the of direct correlation relationship with loaning bill side
One related information.
Link type refers to the information category of each related information in relation data block, for example, such as Fig. 4, Zhang San's address 1
Link type is " family " class, and the link type of school 1 where Zhang San is " education " class, the link type of company 1 where Zhang San
Link type for " work " class, the phone 1 of Zhang San is " contact method " class.
Extend rank and refers to association rank, for example, such as Fig. 5, the extension rank between Zhang San's address 1 and Zhang San is 1 grade,
Extension rank between the event 1 occurred in address 1 and Zhang San is 2 grades, and the extension rank between Zhang San and its brother Zhang Si is 1
Grade, the extension rank where Zhang Si between company 1 and Zhang San are 2 grades.
The information of different linking type is different from the strength of association of loaning bill side, and therefore, different linking type corresponds to difference
Extension rank.Correspondence between link type and extension rank is that the anti-fraud identifying system based on big data prestores
Correspondence, such as：
| Link type | Extend rank |
| " family " class | 15 grades |
| " education " class | 6 grades |
| " work " class | 15 grades |
| " assets " class | 18 grades |
In step S231, there is the first related information of direct correlation to have with the loaning bill side multiple, wherein the first association letter
Breath set is the set of first related information, and each first related information has link type, directly acquires link type i.e.
It can.When relation data block generates, the anti-fraud identifying system based on big data is the chain to each related information and loaning bill side
It connects type and makes mark, subsequently to obtain at any time.
Corresponding second related information of each first related information is acquired based on the extension rank, shown in upper table
Between link type and extension rank for correspondence, if first related information of " family " class, then obtain in 15 grades
Related information (i.e. the second related information) then obtains the related information in 6 grades if first related information of " education " class, if
It is first related information of " work " class, then obtains using first related information as the related information in 15 grades of basic point.
Incidence relation in the extension rank includes " 1 grade+2 grades+3 grades ... .. extend rank incidence relation ", for example,
It is 2 grades to extend rank, then it includes 1 grade of+2 grades of related information that 2 grades, which extend rank incidence relation, and it is n grades to extend rank, then prolongs for n grades
It includes 1+2+3 ...+n grades of related informations to stretch rank incidence relation.
The present embodiment is by obtaining the first related information set for having direct correlation with the loaning bill side and each first pass
The link type for joining information, the extension rank of each first related information is determined according to the link type, is prolonged based on described
Corresponding second related information of each first related information of rank acquisition is stretched, based on the loaning bill side, the first related information, the
Incidence relation between two related informations and former three forms the relation data block of the loaning bill side, can be formed and is with loaning bill side
The information aggregate at center can be identified by the analysis to loaning bill side's relation data block from the various relevant informations of loaning bill side hiding
Risk of fraud, reduce credit risk.
Further, it is based on second embodiment and proposes the third embodiment of the present invention.
Include after step S233：
Step S234 exists in detecting first related information and the second related information and is more than the first predetermined number
Related party loans user after, obtain the fraud scoring of the related party loans user, wherein the fraud scoring be less than predetermined threshold value
Related party loans user be fraudulent user；
Step S235, if there is the fraudulent user more than the second predetermined number in the related party loans user, judgement is deposited
In risk of fraud.
Related party loans user is to be present in user in the first related information and the second related information, having record of borrowing money,
It is present in the first related information and the second related information, illustrates related party loans user and loaning bill side there are certain incidence relation,
Clique is cheated for identification, to there is certain associated loaning bill user to pay special attention to.In the present embodiment, the first predetermined number is by base
It is default in the anti-fraud identifying system of big data.
Lending platforms are when carrying out user information collection, the user information based on collection, as reference information, debt information,
Multi-platform loaning bill situation, overdue refund situation carry out fraud scoring to each user, with the personal risk of fraud brought of mark.
In one embodiment, the determination step of the fraud scoring includes：
Step S2341 obtains user behavior data, personal information data and the third party's credit data of the loaning bill side,
The fraud scoring of the loaning bill side is determined based on the user behavior data, personal information data and third party's credit data.
User behavior data, it is main include browsing of the user in website and mobile applications (APP)/click/post/
The behaviors such as editor；Personal information data refer mainly to ID card information, academic information, winning information, information on social activities, employment
Information, common reserve fund information etc.；Third party's credit data refers mainly to main strategies data etc..
By the way that user behavior data, personal information data and third party's credit data to be inputted to preset fraud scoring mould
Type obtains fraud scoring as a result, can get with specific aim, accurate appraisal result.
If the fraud scoring of certain loaning bill user is less than predetermined threshold value, then loaning bill user is fraudulent user, if borrowing money
There is the fraudulent user more than the second predetermined number in the related party loans user of side, then illustrates that loaning bill side is likely to swindling gang
A member, to reduce fraud risk, there are risk of fraud for judgement loaning bill side.
Further, there are include after risk of fraud for the judgement：
Step S236, for loaning bill side addition fraud label；
Step S237, when detecting that loaning bill side record of refunding on time is more than preset times, and the loaning bill side takes advantage of
When swindleness scoring is higher than predetermined threshold value, the fraud label of the loaning bill side is deleted.
After judgement is there are risk of fraud, fraud label is added for loaning bill side, there is fraud wind to identify the loaning bill side
Danger, to remind creditor/lending platforms more to be investigated work, reduction is spoofed risk.
If loaning bill side, which refunds to record on time, is more than preset times, illustrate that the loan of loaning bill side is accustomed to and is intended to preferably, if
Loaning bill side meets fraud scoring higher than this condition of predetermined threshold value simultaneously, illustrates that the risk of fraud of loaning bill side is smaller, the intended use of the loan
Normally, then the fraud label of the loaning bill side can be deleted, the fraud to loaning bill side is reduced and investigates dynamics, rational allocation fraud is adjusted
Look into resource.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is stored with based on big data on the storage medium
Anti- fraud recognizer, is realized when the anti-fraud recognizer based on big data is executed by processor such as above-described embodiment institute
The step of stating, particular content is as detailed above, and details are not described herein again.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements include not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
There is also other identical elements in the process of element, method, article or system.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment executes the present invention respectively
Method described in a embodiment.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of anti-fraud recognition methods based on big data, which is characterized in that the anti-fraud identification side based on big data
Method includes the following steps：
When receiving the loaning bill request that loaning bill side is sent, according to the essential information of the side of loaning bill described in the loaning bill acquisition request；
According to the essential information determine loaning bill side's identity, based on loaning bill side's identity obtained from relational database described in borrow
The relation data block of money side；
The essential information and corresponding node in the relation data block are compared, judge whether unmatched risk
Point；
If there are unmatched risk point, there are risk of fraud for judgement.
2. the anti-fraud recognition methods based on big data as described in claim 1, which is characterized in that described to be based on the loaning bill
Square identity obtains the step of relation data block of the loaning bill side from relational database and includes：
According to loaning bill side's ID inquiring relational database, judge in the relational database with the presence or absence of the loaning bill side
Relation data block；
If in the presence of the relation data block of the loaning bill side is obtained from relational database；
If being not present, the related information of the loaning bill side is acquired, the relationship of the loaning bill side is generated according to the related information
The relation data block of the loaning bill side is stored in the relational database by data block, obtains the relation data of the loaning bill side
Block.
3. the anti-fraud recognition methods based on big data as described in claim 1, which is characterized in that described to judge whether
Include after the step of unmatched risk point：
If unmatched risk point is not present, according to the relation data block production Methods validation problem of the loaning bill side；
The answer for receiving the relationship validation problem that the loaning bill side inputs judges whether the answer is all correct；
If wrong answer accounting is more than preset ratio in the answer, there are risk of fraud for judgement.
4. the anti-fraud recognition methods based on big data as claimed in claim 2, which is characterized in that the acquisition loaning bill
The related information of side, the step of relation data block that the loaning bill side is generated according to the related information include：
Acquisition has the first related information set of direct correlation with the loaning bill side, obtains each in the first related information set
The link type of first related information；
The extension rank of each first related information is determined according to the link type, and each institute is acquired based on the extension rank
State corresponding second related information of the first related information, wherein the corresponding first related information tool of the second related information
There is the incidence relation in the extension rank；
Incidence relation between the loaning bill side, the first related information, the second related information and former three forms the loaning bill
The relation data block of side.
5. the anti-fraud recognition methods based on big data as claimed in claim 4, which is characterized in that the loaning bill side,
Incidence relation between first related information, the second related information and former three forms the relation data block of the loaning bill side
Include after step：
The related party loans existed in detecting first related information and the second related information more than the first predetermined number are used
Behind family, the fraud scoring of the related party loans user is obtained, wherein the fraud scoring is used less than the related party loans of predetermined threshold value
Family is fraudulent user；
If there is the fraudulent user more than the second predetermined number in the related party loans user, there are risk of fraud for judgement.
6. the anti-fraud recognition methods based on big data as claimed in claim 5, which is characterized in that the judgement has fraud
Include after the step of risk：
Fraud label is added for the loaning bill side；
It is more than preset times when detecting that the loaning bill side refunds to record on time, and the fraud scoring of the loaning bill side is higher than default
When threshold value, the fraud label of the loaning bill side is deleted.
7. the anti-fraud recognition methods based on big data as described in any one of claim 5 to 6, which is characterized in that described
Anti- fraud recognition methods based on big data includes：
User behavior data, personal information data and the third party's credit data of the loaning bill side are obtained, user's row is based on
The fraud scoring of the loaning bill side is determined for data, personal information data and third party's credit data.
8. a kind of anti-fraud identifying system based on big data, which is characterized in that the anti-fraud identification system based on big data
System includes：
Data acquisition module, for when receiving the loaning bill request that loaning bill side sends, according to the loaning bill acquisition request
The essential information of loaning bill side；
Relation data block acquisition module is based on loaning bill side's identity for determining loaning bill side's identity according to the essential information
The relation data block of the loaning bill side is obtained from relational database；
Risk analysis module, for comparing the essential information and corresponding node in the relation data block, judgement is
It is no that there are unmatched risk points；
Determination module is cheated, for when there are unmatched risk point, there are risk of fraud for judgement.
9. a kind of anti-fraud identification terminal based on big data, which is characterized in that the anti-fraud identification based on big data is eventually
End include processor, memory and be stored on the memory and can be executed by the processor based on big data
Anti- fraud recognizer is realized wherein when the anti-fraud recognizer based on big data is executed by the processor as weighed
Profit requires the step of anti-fraud recognition methods based on big data described in any one of 1 to 7.
10. a kind of storage medium, which is characterized in that be stored with the anti-fraud identification journey based on big data on the storage medium
Sequence is realized when the anti-fraud recognizer based on big data is executed by processor as described in any one of claim 1 to 7
The anti-fraud recognition methods based on big data the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810393697.1A CN108596638A (en) | 2018-04-27 | 2018-04-27 | Anti- fraud recognition methods and system based on big data, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810393697.1A CN108596638A (en) | 2018-04-27 | 2018-04-27 | Anti- fraud recognition methods and system based on big data, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596638A true CN108596638A (en) | 2018-09-28 |
Family
ID=63610276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810393697.1A Withdrawn CN108596638A (en) | 2018-04-27 | 2018-04-27 | Anti- fraud recognition methods and system based on big data, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596638A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109413687A (en) * | 2018-10-25 | 2019-03-01 | 深圳壹账通智能科技有限公司 | WI-FI network analysis method, device, equipment and readable storage medium storing program for executing |
| CN109584048A (en) * | 2018-11-30 | 2019-04-05 | 上海点融信息科技有限责任公司 | The method and apparatus that risk rating is carried out to applicant based on artificial intelligence |
| CN109584041A (en) * | 2018-10-25 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Credit fraud analysis method, apparatus, equipment and computer readable storage medium |
| CN109636570A (en) * | 2018-10-25 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, equipment and the readable storage medium storing program for executing of cell-phone number |
| CN109636574A (en) * | 2018-10-25 | 2019-04-16 | 平安科技（深圳）有限公司 | Risk checking method, device, equipment and the storage medium of credit information |
| CN109636568A (en) * | 2018-10-25 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Risk checking method, device, equipment and the storage medium of telephone number |
| CN109660507A (en) * | 2018-10-16 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, equipment and the readable storage medium storing program for executing communicated with user terminal |
| CN109658222A (en) * | 2018-10-16 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, equipment and computer readable storage medium |
| CN109711982A (en) * | 2019-01-04 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Face core questioning method, device, computer equipment and readable storage medium storing program for executing |
| CN111882330A (en) * | 2020-07-27 | 2020-11-03 | 山东协和学院 | Financial fraud prevention analysis method, device, equipment and storage medium |
| CN111915109A (en) * | 2019-05-07 | 2020-11-10 | 北京水滴互保科技有限公司 | Medical financing device, system and method |
| CN112258315A (en) * | 2020-10-20 | 2021-01-22 | 南京三百云信息科技有限公司 | Vehicle loan pre-loan data inspection method and device based on identity tag |
| CN112348524A (en) * | 2020-10-27 | 2021-02-09 | 深圳前海微众银行股份有限公司 | Anti-fraud decision method, device, equipment and computer storage medium |
| CN116245546A (en) * | 2023-05-11 | 2023-06-09 | 广州格鲁信息技术有限公司 | Data processing system and method based on device fingerprint |
-
2018
- 2018-04-27 CN CN201810393697.1A patent/CN108596638A/en not_active Withdrawn
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109660507B (en) * | 2018-10-16 | 2022-05-17 | 深圳壹账通智能科技有限公司 | Method, device and equipment for communicating with user side and readable storage medium |
| CN109660507A (en) * | 2018-10-16 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, equipment and the readable storage medium storing program for executing communicated with user terminal |
| CN109658222A (en) * | 2018-10-16 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, equipment and computer readable storage medium |
| CN109584041A (en) * | 2018-10-25 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Credit fraud analysis method, apparatus, equipment and computer readable storage medium |
| CN109636570A (en) * | 2018-10-25 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, equipment and the readable storage medium storing program for executing of cell-phone number |
| CN109636574A (en) * | 2018-10-25 | 2019-04-16 | 平安科技（深圳）有限公司 | Risk checking method, device, equipment and the storage medium of credit information |
| CN109636568A (en) * | 2018-10-25 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Risk checking method, device, equipment and the storage medium of telephone number |
| CN109413687A (en) * | 2018-10-25 | 2019-03-01 | 深圳壹账通智能科技有限公司 | WI-FI network analysis method, device, equipment and readable storage medium storing program for executing |
| CN109413687B (en) * | 2018-10-25 | 2022-09-06 | 深圳壹账通智能科技有限公司 | WI-FI network analysis method, device, equipment and readable storage medium |
| CN109584048A (en) * | 2018-11-30 | 2019-04-05 | 上海点融信息科技有限责任公司 | The method and apparatus that risk rating is carried out to applicant based on artificial intelligence |
| CN109711982A (en) * | 2019-01-04 | 2019-05-03 | 深圳壹账通智能科技有限公司 | Face core questioning method, device, computer equipment and readable storage medium storing program for executing |
| CN111915109A (en) * | 2019-05-07 | 2020-11-10 | 北京水滴互保科技有限公司 | Medical financing device, system and method |
| CN111915109B (en) * | 2019-05-07 | 2024-04-02 | 北京水滴科技集团有限公司 | Medical funding device, system and method |
| CN111882330A (en) * | 2020-07-27 | 2020-11-03 | 山东协和学院 | Financial fraud prevention analysis method, device, equipment and storage medium |
| CN112258315A (en) * | 2020-10-20 | 2021-01-22 | 南京三百云信息科技有限公司 | Vehicle loan pre-loan data inspection method and device based on identity tag |
| CN112258315B (en) * | 2020-10-20 | 2024-02-02 | 南京三百云信息科技有限公司 | Method and device for checking vehicle credit pre-credit data based on identity tag |
| CN112348524A (en) * | 2020-10-27 | 2021-02-09 | 深圳前海微众银行股份有限公司 | Anti-fraud decision method, device, equipment and computer storage medium |
| CN116245546A (en) * | 2023-05-11 | 2023-06-09 | 广州格鲁信息技术有限公司 | Data processing system and method based on device fingerprint |
| CN116245546B (en) * | 2023-05-11 | 2023-08-25 | 广州格鲁信息技术有限公司 | Data processing system and method based on device fingerprint |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596638A (en) | Anti- fraud recognition methods and system based on big data, terminal and storage medium | |
| CN109670936A (en) | Loan examination & approval processing method, platform, equipment and computer readable storage medium | |
| Rhine et al. | The determinants of being unbanked for US immigrants | |
| US7853493B2 (en) | Personal finance integration system and method | |
| WO2020051154A1 (en) | Authenticated access and aggregation database platform | |
| US20120123959A1 (en) | Methods and Systems to Help Detect Identity Fraud | |
| US20110238566A1 (en) | System and methods for determining and reporting risk associated with financial instruments | |
| Oluyinka et al. | A study of electronic commerce adoption factors in Nigeria | |
| CN106296389A (en) | The appraisal procedure of a kind of user credit degree and device | |
| CN105894380A (en) | Digital currency credit investigation system and method | |
| CN110738558B (en) | Information restoration method, device, electronic equipment and computer readable medium | |
| CN108230151A (en) | A kind of suspicious transaction detection method, apparatus, equipment and storage medium | |
| CN108711101A (en) | A kind of loan transaction method, apparatus, system and electronic equipment | |
| CN109472683A (en) | Customer lending qualification generation method, server and readable storage medium storing program for executing | |
| CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
| Wang et al. | Seeing is important: the usefulness of video information in P2P | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| CN101295388A (en) | Credit estimation method and system | |
| CN112308698B (en) | WeChat end loan product management method and system supporting second-level legal person | |
| KR20010044544A (en) | A service mothod of internet credit | |
| CN109410035B (en) | Method and tool for assisting anti-fraud analysis of group structure | |
| CN111489255A (en) | Data credit granting method, device, equipment and computer readable storage medium | |
| CN107808339A (en) | A kind of data acquisition and analysis system | |
| CN113327161A (en) | Intelligent wind control decision system for credit business | |
| CN113362156A (en) | Financial fraud detection and identification system based on Internet of things |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180928 |