CN107644098A - A kind of fraud recognition methods, device, equipment and storage medium - Google Patents
A kind of fraud recognition methods, device, equipment and storage medium Download PDFInfo
- Publication number
- CN107644098A CN107644098A CN201710909930.2A CN201710909930A CN107644098A CN 107644098 A CN107644098 A CN 107644098A CN 201710909930 A CN201710909930 A CN 201710909930A CN 107644098 A CN107644098 A CN 107644098A
- Authority
- CN
- China
- Prior art keywords
- targeted customer
- contract
- fraud
- key message
- abnormality degree
- 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
Abstract
The invention discloses a kind of fraud recognition methods, this method comprises the following steps:Receive the service request that targeted customer submits, the user data of targeted customer is extracted in the chart database being obtained ahead of time, determine key message corresponding to targeted customer, calculate the abnormality degree of key message, determine whether service request is fraud, wherein, the user data of multiple registered users is stored with chart database, for each registered user, the user data of the registered user is:Based on default relational network structure, the data that the user profile for the registered user being obtained ahead of time is converted to, relational network structure includes side, summit and corresponding attribute, and targeted customer is any one registered user.The technical scheme provided using the embodiment of the present invention, the accuracy of fraud identification is improved, reduces the loss brought by fraud.The invention also discloses a kind of fraud identification device, equipment and storage medium, has relevant art effect.
Description
Technical field
The present invention relates to security technology area, more particularly to a kind of fraud recognition methods, device, equipment and storage
Medium.
Background technology
As internet is financial and the development of the consumer finance, on many continuous transfer services of financial institution to line.Therewith
Come, because the fraud cost on network is cheap, financial platform fraud recognition capability is weaker, fraud is shown in repeatly
It is not fresh.
In recent years, fraud identification technology mainly has three kinds:The first, according to simple hit rule, blacklist and
Personal experience carries out analysing whether to belong to fraud;Second, statistical analysis is carried out using substantial amounts of fraud sample, is established
Fraud identification model;The third, based on historical data, including normal and fraud data are obtained by machine learning
One optimal model, go to predict and analyze fraud.
The dimension of existing fraud identification technology is often more single, poor to mass data real-time analytical capability, companion
With the appearance of the variation of network fraud, clique's division of labor refinement, brilliant fraudulent mean etc., it is difficult to efficiently identify out fraud
Behavior, it is possible to which risk control guarantee can not be provided in time.
The content of the invention
It is an object of the invention to provide a kind of fraud recognition methods, device, equipment and storage medium, to improve fraud
The accuracy rate of Activity recognition, reduce the loss brought by fraud.
In order to solve the above technical problems, the present invention provides following technical scheme:
A kind of fraud recognition methods, including:
Receive the service request that targeted customer submits;
The user data of the targeted customer is extracted in the chart database being obtained ahead of time;
Key message corresponding to the targeted customer is determined in the user data of the targeted customer;
Calculate the abnormality degree of the key message;
According to the abnormality degree, determine whether the service request is fraud;
Wherein, the user data of multiple registered users is stored with the chart database, for each registered user, the note
Volume user user data be:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is turned
The data got in return, the relational network structure include side, summit and corresponding attribute, the targeted customer and registered for any one
User.
Preferably, the key message includes the contract information of the targeted customer, the calculating key message
Abnormality degree, including:
According to the contract information of the targeted customer, the overdue rate of the first contract is calculated;
According to the overdue rate of the first contract, the abnormality degree of the key message is determined.
Preferably, the key message also includes the associated person information of the targeted customer, described to be closed according to described first
With overdue rate, the abnormality degree of the key message is determined, including:
According to the associated person information of the targeted customer, the registration ratio of the contact person of the targeted customer is calculated;
According to the overdue rate of first contract and the registration ratio, the abnormality degree of the key message is determined.
Preferably, the contract information of the key message also contact person including the targeted customer, described in the basis
The overdue rate of first contract and the registration ratio, the abnormality degree of the key message is determined, including:
According to the contract information of the contact person of the targeted customer, the overdue rate of the second contract is calculated;
According to the overdue rate of first contract, the registration ratio and the overdue rate of the second contract, the key is determined
The abnormality degree of information.
Preferably, it is described according to the abnormality degree, determine whether the service request is fraud, including:
If the abnormality degree is more than predetermined threshold value, it is determined that the service request is fraud.
A kind of fraud identification device, including:
Service request receiving module, for receiving the service request of targeted customer's submission;
User data extraction module, for extracting the number of users of the targeted customer in the chart database being obtained ahead of time
According to;
Key message determining module, for being determined in the user data of the targeted customer corresponding to the targeted customer
Key message;
Abnormality degree computing module, for calculating the abnormality degree of the key message;
Fraud determining module, for according to the abnormality degree, determining whether the service request is fraud;
Wherein, the user data of multiple registered users is stored with the chart database, for each registered user, the note
Volume user user data be:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is turned
The data got in return, the relational network structure include side, summit and corresponding attribute, the targeted customer and registered for any one
User.
Preferably, the key message includes the contract information of the targeted customer, the abnormality degree computing module, specifically
For:
According to the contract information of the targeted customer, the overdue rate of the first contract is calculated;
According to the overdue rate of the first contract, the abnormality degree of the key message is determined.
Preferably, the key message also includes the associated person information of the targeted customer, the abnormality degree computing module,
It is specifically used for:
According to the associated person information of the targeted customer, the registration ratio of the contact person of the targeted customer is calculated;
According to the overdue rate of first contract and the registration ratio, the abnormality degree of the key message is determined.
A kind of fraud identification equipment, including:
Memory, for storing computer program;
Processor, the step of realizing above-mentioned fraud recognition methods during for performing the computer program.
A kind of computer-readable recording medium, computer program is stored with the computer-readable recording medium, it is described
The step of fraud recognition methods is realized when computer program is executed by processor.
The technical scheme provided using the embodiment of the present invention, the service request that targeted customer submits is received, is obtained in advance
The user data of targeted customer is extracted in the chart database obtained, is determined in the user data of targeted customer corresponding to targeted customer
Key message, the abnormality degree of key message is calculated, according to abnormality degree, determine whether service request is fraud, wherein, figure number
According to the user data that multiple registered users are stored with storehouse, for each registered user, the user data of the registered user is:Base
In default relational network structure, the data that the user profile for the registered user being obtained ahead of time is converted to, relational network
Structure includes side, summit and corresponding attribute, and targeted customer is any one registered user.According to relational network structure in diagram data
User data is prestored in storehouse, the analysis of various dimensions can be carried out to user data, can improve and determine service request behavior
Analyze speed when whether being fraud, the accuracy of fraud identification is improved, reduces the loss brought by fraud.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of implementing procedure figure of fraud recognition methods in the embodiment of the present invention;
Fig. 2 is user's credit applications relational network structure chart in the embodiment of the present invention;
Fig. 3 is the overdue relational network structure chart of user contact's contract in the embodiment of the present invention;
Fig. 4 is a kind of structural representation of fraud identification device in the embodiment of the present invention;
Fig. 5 is a kind of structural representation of fraud identification equipment in the embodiment of the present invention.
Embodiment
The core of the present invention is to provide a kind of fraud recognition methods, receives the service request that targeted customer submits,
The user data of targeted customer is extracted in the chart database being obtained ahead of time, targeted customer is determined in the user data of targeted customer
Corresponding key message, the abnormality degree of key message is calculated, according to abnormality degree, determine whether service request is fraud, its
In, the user data of multiple registered users is stored with chart database, for each registered user, the number of users of the registered user
According to for:Based on default relational network structure, the data that the user profile for the registered user being obtained ahead of time is converted to, close
It is that network structure includes side, summit and corresponding attribute, targeted customer is any one registered user.Existed according to relational network structure
User data is prestored in chart database, the analysis of various dimensions can be carried out to user data, can improve determination business please
Analyze speed when whether ask behavior be fraud, the accuracy of fraud identification is improved, is reduced because fraud is brought
Loss.
Carried out with reference to the present invention based on relational network structure for the starting point of fraud identification, a normal note
The overdue number of contract or the overdue rate of contract of volume user should be not more than corresponding given threshold, if more than corresponding setting threshold
Value, can tentatively judge that the registered user there may be personal fraud;The contact person of one normal registered user is also
The possibility of registered user is smaller, and in other words, the number of the artificial registered user of contact of registered user should be less than a certain
Individual upper limit number, therefore, according to associated person information, it is determined that registration large percentage or more than it is default registration threshold value when, can
Tentatively to judge that the registered user there may be the fraud of clique's crime;Under normal circumstances, the contact of a registered user
The likelihood ratio that people turns into registered user is relatively low, and contact person corresponding to the registered user registers and the overdue probability of contract occurs more
It is low.So when the overdue number of contract or overdue rate exceed the corresponding upper limit, it is believed that the registered user is with the registered user's
The member that other overdue registered users of contract may be some fraud clique in contact person be present.Can be to the registered user
Implement to stop the measures such as service request authority with other corresponding registered users, to reduce the loss that fraud is brought, to reduce wind
Danger.
In order that those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiment is only part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
It refer to Fig. 1, Fig. 1 is the implementing procedure figure of fraud recognition methods in the embodiment of the present invention, including following step
Suddenly:
S101, receive the service request that targeted customer submits.
The service request submitted for targeted customer, wherein, targeted customer can be any one in all registered users
It is individual.The service request of targeted customer submission is received, the service request can be to be asked for application for registration, loan requests, deposit
Seek or change the service requests such as log-on message.
S102, in the chart database being obtained ahead of time extract targeted customer user data.
Wherein, the user data of multiple registered users is stored with chart database, for each registered user, the registration is used
The user data at family is:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is changed
The data arrived, relational network structure include side, summit and corresponding attribute, and targeted customer is any one registered user.
In the present embodiment, Fig. 2 is refer to, a chart database can be pre-established, is prestored in chart database big
Measure user profile.By taking Fig. 2 as an example, the chart database can be the topological diagram centered on registered user, specifically, registered user
Corresponding equipment, APP contact persons, registration cell-phone number, change and tie up phone number and be connected with real-name authentication information.Wherein, equipment
With facility information and international mobile subscriber identity (International Mobile Subscriber Identification
Number, Imsi) it is connected;Real-name authentication information includes:Request slip, contract, request slip therein and home contact, other connection
It is people, firm telephone, application phone, home phone number.
According to the service request of the targeted customer received, targeted customer can be extracted in the chart database being obtained ahead of time
User data, wherein, the user data of multiple registered users is stored with chart database.For each registered user, the note
Volume user user data be:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is turned
The data got in return, that is to say, that the user data stored in chart database is will according to the relational network structure pre-set
The data obtained after user profile conversion.
It should be noted that relational network structure can include side, summit and corresponding attribute, targeted customer is any one
Registered user., it is necessary to be analyzed in advance for the various social propertys and behavior of user before opening relationships network structure,
The characteristics of obtaining user, then classified, according to a variety of classification dimensions of user, summit, side in design relation network structure,
And both attributes.For designed relational network structure, select suitable chart database data storage such as Neo4j,
GraphX etc., to accelerate to determine the analyze speed of the service request for targeted customer's submission.
S103, key message corresponding to targeted customer is determined in the user data of targeted customer.
In the user data of targeted customer, it can determine to close corresponding to targeted customer according to the keyword pre-set
Key information.Wherein, according to the keyword pre-set, identified key message can be contract information, the mesh of targeted customer
Mark at least one of contract information etc. information corresponding to the associated person information of user or the associated person information of targeted customer.
S104, the abnormality degree for calculating key message.
For the key message in the user data of targeted customer, the abnormality degree of the key message is calculated.Specifically, can be with
Corresponding data cases in key message, carry out abnormality degree calculating or and pre-set reference key
Information is compared, and finally determines abnormality degree.Wherein, abnormality degree is the business for being used to weigh targeted customer's submission in the present embodiment
The intensity of anomaly of request.
In one embodiment of the invention, key message includes the contract information of targeted customer, and step S104 can be wrapped
Include following steps:
Step 1: according to the contract information of targeted customer, the overdue rate of the first contract is calculated;
Step 2: according to the overdue rate of the first contract, the abnormality degree of key message is determined.
For the ease of description, above-mentioned two step is combined illustrated below.
When the contract information of key message including targeted customer, the can be calculated according to the contract information of targeted customer
The overdue rate of one contract.Specifically, the overdue contract number of targeted customer and all contract numbers of targeted customer can be calculated
Ratio, and by the ratio be defined as the overdue rate of the first contract or according to one pre-set overdue contract number with
The corresponding relation of overdue rate determines, such as is added to obtain by all overdue rates of the overdue correspondence of contract.For example, when targeted customer shares
6 contracts, wherein overdue contract has 2, then the overdue rate of the first contract is 40%, if or, overdue contract it is corresponding
Overdue rate is 20%, 3 overdue contracts occurs, i.e. the overdue rate of the first contract is 60%.
According to the overdue rate of the first contract, it may be determined that the abnormality degree of key message, specifically, can be directly by the first contract
Overdue rate is defined as the abnormality degree of key message, can also be overdue by the proportion of the default overdue rate of first contract and the first contract
Rate carries out the abnormality degree that result of product is defined as key message, can also be overdue by the overdue rate of the first contract and default first contract
The difference of rate threshold value is defined as the abnormality degree of key message.
In one embodiment of the invention, key message also includes the associated person information of targeted customer, and step S104 can
To comprise the following steps:
Step 1: according to the associated person information of targeted customer, the registration ratio of the contact person of targeted customer is calculated;
Step 2: according to the overdue rate of the first contract and registering ratio, the abnormality degree of key message is determined.
For the ease of description, above-mentioned two step is combined illustrated below.
, can also be according to mesh when contract information of the key message including targeted customer and the associated person information of targeted customer
The associated person information of user is marked, the contact person for calculating targeted customer registers ratio.Specifically, when the associated person information of targeted customer
The contact person provided when being registered for targeted customer, in the case of registered user being present simultaneously in the contact person, by contact person
Registered user's number and targeted customer contact person's number between ratio, be defined as the registration ratio of the contact person of targeted customer
Example.For example, if the contact person of targeted customer shares 10 people, wherein 5 people are registered user, then register ratio as 50%.
The registration ratio obtained after calculating and the overdue rate of the first contract can be combined, determine the exception of key message
Degree.For example, the result after registration ratio being directly added, subtract each other, be multiplied or be divided by with the overdue rate of the first contract is defined as
The abnormality degree of key message, key message can also be calculated by registration ratio and the overdue rate of the first contract according to default weight
Abnormality degree.
It should be noted that in other embodiments of the invention, key message can be only the contact person of targeted customer
Information, that is to say, that the abnormality degree of key message according only to the registration ratio of the contact person of targeted customer, can be determined.
In one embodiment of the invention, the contract information of the key message also contact person including targeted customer, step
S104 may comprise steps of:
Step 1: according to the contract information of the contact person of targeted customer, the overdue rate of the second contract is calculated;
Step 2: according to the overdue rate of the first contract, registering ratio and the overdue rate of the second contract, the exception of key message is determined
Degree.
For the ease of description, above-mentioned two step is combined illustrated below.
When key message includes contract information, the associated person information of targeted customer and the contact of targeted customer of targeted customer
During the contract information of people, the overdue rate of the second contract, the second contract can be calculated according to the contract information of the contact person of targeted customer
The calculation of overdue rate can be identical with the calculation of the overdue rate of the first contract, on the other hand, the embodiment of the present invention repeats no more.
It is calculated after the overdue rate of the second contract, can be according to the overdue rate of the first contract, the overdue rate of the second contract and note
The volume default weighted value of ratio three, determine the abnormality degree of key message.For example, the weights of the overdue rate of the first contract can be
0.4, the weights of the overdue rate of the second contract are 0.3, register the weights of ratio as 0.3, according to the overdue rate of specific first contract, the
The overdue rate of two contracts and registration ratio, determine the abnormality degree of key message.
It should be noted that in other embodiments of the invention, key message can be only the contact person of targeted customer
Contract information, that is to say, that the abnormality degree of key message can be determined according only to the overdue rate of the second contract.
In one particular embodiment of the present invention, when key message is only the contract information of the contact person of targeted customer
When, the abnormality degree of key message is determined according only to the overdue rate of the second contract.Fig. 3 is may be referred to, wherein, A1, A2, A3, A4 are note
Volume user node;B1, B2, B3 are telephone number node;C1, C2, C3, C4 are application single node;D1, D2, D3, D4 are contract section
Point.Specifically, in targeted customer A1 cell phone address book, contact number B1, B2, B3, while notes of the B1 as A2 user be present
Volume number and the contact number of A3 user, herd numbers of the B2 as user A4, B3 use as the contact number and A3 of A1 user
The herd number at family.A1, A2, A3, A4 user's SEPARATE APPLICATION C1, C2, C3, C4 request slip, caused contract correspond to D1,
D2, D3, D4, wherein contract D2, D3 are overdue state.
By scheming to calculate, based on this relational network, in the contact person that can quickly calculate targeted customer A1, other accounts be present
The phone number of number binding, and has 3 corresponding contracts, wherein the overdue account quantity of contract is 2, can calculate the second contract
Overdue rate.The overdue rate of the second contract calculated is 66.7%, in the present embodiment, directly can be made the overdue rate of the second contract
For abnormality degree, i.e. abnormality degree is 66.7%.
After the abnormality degree for determining key message, step S105 operation can be performed.
S105, according to abnormality degree, determine whether service request is fraud.
According to abnormality degree, it may be determined that whether service request is fraud.
In one embodiment of the invention, step S105 may comprise steps of:
If abnormality degree is more than predetermined threshold value, it is determined that service request is fraud.
In the present embodiment, a threshold value can be pre-set, the specific size of the threshold value can be pre-set, can also
It is determined and is adjusted according to actual conditions, the embodiment of the present invention is not intended to limit.
In the present embodiment, if abnormality degree is more than default threshold value, it is fraud that can determine the service request, if
Abnormality degree is less than or equal to default threshold value, then it is normal business conduct that can determine the service request behavior.
The method provided using the embodiment of the present invention, the service request that targeted customer submits is received, what is be obtained ahead of time
The user data of targeted customer is extracted in chart database, is determined in the user data of targeted customer crucial corresponding to targeted customer
Information, the abnormality degree of key message is calculated, according to abnormality degree, determine whether service request is fraud, wherein, chart database
In be stored with the user data of multiple registered users, for each registered user, the user data of the registered user is:Based on pre-
If relational network structure, the data that the user profile for the registered user being obtained ahead of time is converted to, relational network structure
Including side, summit and corresponding attribute, targeted customer is any one registered user.According to relational network structure in chart database
User data is prestored, the analysis of various dimensions can be carried out to user data, can improve and whether determine service request behavior
For fraud when analyze speed, improve fraud identification accuracy, reduce the loss brought by fraud.
Corresponding to above method embodiment, the embodiment of the present invention additionally provides a kind of fraud identification device, hereafter
A kind of fraud identification device of description can be mutually to should refer to a kind of above-described fraud recognition methods.
Shown in Figure 4, the device is included with lower module:
Service request receiving module 201, for receiving the service request of targeted customer's submission;
User data extraction module 202, for extracting the user data of targeted customer in the chart database being obtained ahead of time;
Key message determining module 203, it is crucial corresponding to targeted customer for being determined in the user data of targeted customer
Information;
Abnormality degree computing module 204, for calculating the abnormality degree of key message;
Fraud determining module 205, for according to abnormality degree, determining whether service request is fraud;
Wherein, the user data of multiple registered users is stored with chart database, for each registered user, the registration is used
The user data at family is:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is changed
The data arrived, relational network structure include side, summit and corresponding attribute, and targeted customer is any one registered user.
The device provided using the embodiment of the present invention, the service request that targeted customer submits is received, what is be obtained ahead of time
The user data of targeted customer is extracted in chart database, is determined in the user data of targeted customer crucial corresponding to targeted customer
Information, the abnormality degree of key message is calculated, according to abnormality degree, determine whether service request is fraud, wherein, chart database
In be stored with the user data of multiple registered users, for each registered user, the user data of the registered user is:Based on pre-
If relational network structure, the data that the user profile for the registered user being obtained ahead of time is converted to, relational network structure
Including side, summit and corresponding attribute, targeted customer is any one registered user.According to relational network structure in chart database
User data is prestored, the analysis of various dimensions can be carried out to user data, can improve and whether determine service request behavior
For fraud when analyze speed, improve fraud identification accuracy, reduce the loss brought by fraud.
In a kind of embodiment of the present invention, key message includes the contract information of targeted customer, abnormality degree meter
Module 204 is calculated, is specifically used for:
According to the contract information of targeted customer, the overdue rate of the first contract is calculated;
According to the overdue rate of the first contract, the abnormality degree of key message is determined.
In a kind of embodiment of the present invention, key message also includes the associated person information of targeted customer, abnormal
Computing module 204 is spent, is specifically used for:
According to the associated person information of targeted customer, the registration ratio of the contact person of targeted customer is calculated;
According to the overdue rate of the first contract and ratio is registered, determines the abnormality degree of key message.
In a kind of embodiment of the present invention, the contract letter of the key message also contact person including targeted customer
Breath, abnormality degree computing module 204, is specifically used for:
According to the contract information of the contact person of targeted customer, the overdue rate of the second contract is calculated;
According to the overdue rate of the first contract, ratio and the overdue rate of the second contract are registered, determines the abnormality degree of key message.
In a kind of embodiment of the present invention, fraud determining module 205, it is specifically used for:
If abnormality degree is more than predetermined threshold value, it is determined that service request is fraud.
Corresponding to above method embodiment, the embodiment of the present invention additionally provides a kind of fraud identification equipment, hereafter
A kind of fraud identification equipment of description can be mutually to should refer to a kind of above-described fraud recognition methods.
Shown in Figure 5, the fraud identification equipment includes:
Memory D1, for storing computer program;
Processor D2, the step of the fraud recognition methods of above method embodiment is realized during for performing computer program
Suddenly.
Corresponding to above method embodiment, the embodiment of the present invention additionally provides a kind of computer-readable recording medium, under
A kind of computer-readable recording medium of text description can be mutually to should refer to a kind of above-described fraud recognition methods.
A kind of computer-readable recording medium, computer program, computer journey are stored with computer-readable recording medium
The step of fraud recognition methods of above method embodiment is realized when sequence is executed by processor.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be with it is other
The difference of embodiment, between each embodiment same or similar part mutually referring to.For dress disclosed in embodiment
For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part
Explanation.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, the composition and step of each example are generally described according to function in the above description.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specialty
Technical staff can realize described function using distinct methods to each specific application, but this realization should not
Think beyond the scope of this invention.
Directly it can be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Specific case used herein is set forth to the principle and embodiment of the present invention, and above example is said
It is bright to be only intended to help and understand technical scheme and its core concept.It should be pointed out that for the common of the art
For technical staff, under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these
Improve and modification is also fallen into the protection domain of the claims in the present invention.
Claims (10)
- A kind of 1. fraud recognition methods, it is characterised in that including:Receive the service request that targeted customer submits;The user data of the targeted customer is extracted in the chart database being obtained ahead of time;Key message corresponding to the targeted customer is determined in the user data of the targeted customer;Calculate the abnormality degree of the key message;According to the abnormality degree, determine whether the service request is fraud;Wherein, the user data of multiple registered users is stored with the chart database, for each registered user, the registration is used The user data at family is:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is changed The data arrived, the relational network structure include side, summit and corresponding attribute, and the targeted customer uses for any one registration Family.
- 2. fraud recognition methods according to claim 1, it is characterised in that the key message includes the target The contract information of user, the abnormality degree for calculating the key message, including:According to the contract information of the targeted customer, the overdue rate of the first contract is calculated;According to the overdue rate of the first contract, the abnormality degree of the key message is determined.
- 3. fraud recognition methods according to claim 2, it is characterised in that the key message also includes the mesh The associated person information of user is marked, it is described according to the overdue rate of the first contract, the abnormality degree of the key message is determined, including:According to the associated person information of the targeted customer, the registration ratio of the contact person of the targeted customer is calculated;According to the overdue rate of first contract and the registration ratio, the abnormality degree of the key message is determined.
- 4. fraud recognition methods according to claim 3, it is characterised in that the key message also includes the mesh The contract information of the contact person of user is marked, it is described according to the overdue rate of first contract and the registration ratio, determine the pass The abnormality degree of key information, including:According to the contract information of the contact person of the targeted customer, the overdue rate of the second contract is calculated;According to the overdue rate of first contract, the registration ratio and the overdue rate of the second contract, the key message is determined Abnormality degree.
- 5. the fraud recognition methods according to any one of Claims 1-4, it is characterised in that described according to institute Abnormality degree is stated, determines whether the service request is fraud, including:If the abnormality degree is more than predetermined threshold value, it is determined that the service request is fraud.
- A kind of 6. fraud identification device, it is characterised in that including:Service request receiving module, for receiving the service request of targeted customer's submission;User data extraction module, for extracting the user data of the targeted customer in the chart database being obtained ahead of time;Key message determining module, it is crucial corresponding to the targeted customer for being determined in the user data of the targeted customer Information;Abnormality degree computing module, for calculating the abnormality degree of the key message;Fraud determining module, for according to the abnormality degree, determining whether the service request is fraud;Wherein, the user data of multiple registered users is stored with the chart database, for each registered user, the registration is used The user data at family is:Based on default relational network structure, the user profile for the registered user being obtained ahead of time is changed The data arrived, the relational network structure include side, summit and corresponding attribute, and the targeted customer uses for any one registration Family.
- 7. fraud identification device according to claim 6, it is characterised in that the key message includes the target The contract information of user, the abnormality degree computing module, is specifically used for:According to the contract information of the targeted customer, the overdue rate of the first contract is calculated;According to the overdue rate of the first contract, the abnormality degree of the key message is determined.
- 8. fraud identification device according to claim 7, it is characterised in that the key message also includes the mesh The associated person information of user is marked, the abnormality degree computing module, is specifically used for:According to the associated person information of the targeted customer, the registration ratio of the contact person of the targeted customer is calculated;According to the overdue rate of first contract and the registration ratio, the abnormality degree of the key message is determined.
- A kind of 9. fraud identification equipment, it is characterised in that including:Memory, for storing computer program;Processor, the fraud identification side as described in any one of claim 1 to 5 is realized during for performing the computer program The step of method.
- 10. a kind of computer-readable recording medium, it is characterised in that be stored with computer on the computer-readable recording medium Program, the fraud recognition methods as described in any one of claim 1 to 5 is realized when the computer program is executed by processor The step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710909930.2A CN107644098A (en) | 2017-09-29 | 2017-09-29 | A kind of fraud recognition methods, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710909930.2A CN107644098A (en) | 2017-09-29 | 2017-09-29 | A kind of fraud recognition methods, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107644098A true CN107644098A (en) | 2018-01-30 |
Family
ID=61111701
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710909930.2A Pending CN107644098A (en) | 2017-09-29 | 2017-09-29 | A kind of fraud recognition methods, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107644098A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108334647A (en) * | 2018-04-12 | 2018-07-27 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
CN108984773A (en) * | 2018-07-23 | 2018-12-11 | 杭州呯嘭智能技术有限公司 | Blacklist multidimensional information verification method and system and readable storage medium storing program for executing and equipment in the case of shortage of data |
CN109086317A (en) * | 2018-06-28 | 2018-12-25 | 招联消费金融有限公司 | Risk control method and relevant apparatus |
CN109409502A (en) * | 2018-09-26 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Generation method, device, equipment and the storage medium of anti-fraud model |
CN109670933A (en) * | 2018-09-26 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Identify method, user equipment, storage medium and the device of user role |
WO2020186789A1 (en) * | 2019-03-15 | 2020-09-24 | 平安科技(深圳)有限公司 | User anti-fraud realization method and apparatus, computer device, and storage medium |
CN114020795A (en) * | 2021-10-14 | 2022-02-08 | 深圳华云信息系统有限公司 | Business processing method and device, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102496073A (en) * | 2011-12-20 | 2012-06-13 | 南京审计学院 | Financial fraud audit assisting system and audit assisting method |
CN105701704A (en) * | 2015-12-31 | 2016-06-22 | 先花信息技术(北京)有限公司 | Method for processing user credibility social network data |
CN106296343A (en) * | 2016-08-01 | 2017-01-04 | 王四春 | A kind of e-commerce transaction monitoring method based on the Internet and big data |
CN106373006A (en) * | 2016-09-07 | 2017-02-01 | 派生科技集团股份有限公司 | Method for evaluating user credit and repayment willingness through big-data modeling |
US20170155675A1 (en) * | 2015-11-30 | 2017-06-01 | Justin Xavier Howe | Login credential alert system |
CN107153847A (en) * | 2017-05-31 | 2017-09-12 | 北京知道创宇信息技术有限公司 | Predict method and computing device of the user with the presence or absence of malicious act |
-
2017
- 2017-09-29 CN CN201710909930.2A patent/CN107644098A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102496073A (en) * | 2011-12-20 | 2012-06-13 | 南京审计学院 | Financial fraud audit assisting system and audit assisting method |
US20170155675A1 (en) * | 2015-11-30 | 2017-06-01 | Justin Xavier Howe | Login credential alert system |
CN105701704A (en) * | 2015-12-31 | 2016-06-22 | 先花信息技术(北京)有限公司 | Method for processing user credibility social network data |
CN106296343A (en) * | 2016-08-01 | 2017-01-04 | 王四春 | A kind of e-commerce transaction monitoring method based on the Internet and big data |
CN106373006A (en) * | 2016-09-07 | 2017-02-01 | 派生科技集团股份有限公司 | Method for evaluating user credit and repayment willingness through big-data modeling |
CN107153847A (en) * | 2017-05-31 | 2017-09-12 | 北京知道创宇信息技术有限公司 | Predict method and computing device of the user with the presence or absence of malicious act |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108334647A (en) * | 2018-04-12 | 2018-07-27 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
WO2019196552A1 (en) * | 2018-04-12 | 2019-10-17 | 阿里巴巴集团控股有限公司 | Data processing method, apparatus and device for insurance fraud identification, and server |
CN109086317A (en) * | 2018-06-28 | 2018-12-25 | 招联消费金融有限公司 | Risk control method and relevant apparatus |
CN109086317B (en) * | 2018-06-28 | 2020-07-21 | 招联消费金融有限公司 | Risk control method and related device |
CN108984773A (en) * | 2018-07-23 | 2018-12-11 | 杭州呯嘭智能技术有限公司 | Blacklist multidimensional information verification method and system and readable storage medium storing program for executing and equipment in the case of shortage of data |
CN108984773B (en) * | 2018-07-23 | 2020-09-04 | 杭州呯嘭智能技术有限公司 | Method and system for verifying blacklist multidimensional information under data missing condition, readable storage medium and device |
CN109409502A (en) * | 2018-09-26 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Generation method, device, equipment and the storage medium of anti-fraud model |
CN109670933A (en) * | 2018-09-26 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Identify method, user equipment, storage medium and the device of user role |
WO2020186789A1 (en) * | 2019-03-15 | 2020-09-24 | 平安科技(深圳)有限公司 | User anti-fraud realization method and apparatus, computer device, and storage medium |
CN114020795A (en) * | 2021-10-14 | 2022-02-08 | 深圳华云信息系统有限公司 | Business processing method and device, electronic equipment and storage medium |
CN114020795B (en) * | 2021-10-14 | 2022-06-24 | 深圳华云信息系统有限公司 | Business processing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107644098A (en) | A kind of fraud recognition methods, device, equipment and storage medium | |
CN108492104B (en) | Resource transfer monitoring method and device | |
CN109409896B (en) | Bank fraud recognition model training method, bank fraud recognition method and device | |
CN106780012A (en) | A kind of internet credit methods and system | |
CN109461070A (en) | A kind of risk measures and procedures for the examination and approval, device, storage medium and server | |
CN108229963A (en) | The Risk Identification Method and device of user's operation behavior | |
CN108416670A (en) | Credit matches folk prescription method and server | |
CN105389488B (en) | Identity identifying method and device | |
CN109086317B (en) | Risk control method and related device | |
CN106603327B (en) | Behavioral data analysis method and device | |
CN108961032A (en) | Borrow or lend money processing method, device and server | |
CN105243566A (en) | Method and apparatus for evaluating credit of users through different mobile phone number information from operators | |
CN109670835A (en) | Air control method, apparatus, equipment and readable storage medium storing program for executing based on service node | |
CN108090831A (en) | Credit Risk Assessment method, application server and computer readable storage medium | |
CN110659961A (en) | Method and device for identifying off-line commercial tenant | |
CN109658256A (en) | Risk control method, device, equipment and readable storage medium storing program for executing | |
CN110414914A (en) | Business datum monitoring method and device | |
CN109461069A (en) | Air control method, apparatus, equipment and readable storage medium storing program for executing based on service node | |
CN106779271A (en) | Determine the method and device and account risk score method and device of feature of risk | |
CN106651368A (en) | Order-scalping-preventing payment mode control method and control system | |
CN107346310A (en) | A kind of account complaint processing method and server | |
CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
CN105741161A (en) | Method and system for recognizing click farming users in taxi businesses on basis of driver credit | |
CN109670933A (en) | Identify method, user equipment, storage medium and the device of user role | |
CN111882140A (en) | Risk evaluation method, model training method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180130 |
|
RJ01 | Rejection of invention patent application after publication |