CN106803168A - A kind of abnormal transfer accounts method for detecting and device - Google Patents
A kind of abnormal transfer accounts method for detecting and device Download PDFInfo
- Publication number
- CN106803168A CN106803168A CN201611264190.3A CN201611264190A CN106803168A CN 106803168 A CN106803168 A CN 106803168A CN 201611264190 A CN201611264190 A CN 201611264190A CN 106803168 A CN106803168 A CN 106803168A
- Authority
- CN
- China
- Prior art keywords
- producing
- accounts
- exception
- index
- transfer
- 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.)
- Granted
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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
- G06Q20/108—Remote banking, e.g. home banking
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present embodiments relate to internet financial field, more particularly to a kind of abnormal transfer accounts method for detecting and device, for being detected to money transfer transactions and being sent abnormity early warning.In the embodiment of the present invention, transfer transaction information is obtained, transfer transaction information includes the side's of producing information；According to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts, detection model of transferring accounts extremely is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing；The exception of the transfer transaction information input side of producing is transferred accounts detection model, the abnormal probable value of the transfer transaction information is obtained, so as to when user initiates money transfer transactions, detect to the money transfer transactions of user and sent abnormity early warning.
Description
Technical field
The present embodiments relate to internet financial field, more particularly to a kind of abnormal transfer accounts method for detecting and device.
Background technology
With internet finance and the arrival in big data epoch, user can be realized non-cash by modes such as internets
Money transfer transactions, because internet is an open network, bank system of web also causes to be opened to internet inside bank.In
It is that the security for how ensureing noncash money transfer transactions is that internet finance is vital with one of the big data epoch to ask
Topic, is related to the safety of whole internet finance, is also the major issue that each bank guarantee user fund security needs to consider.
In existing abnormal money transfer transactions detection technique, a kind of conventional method is when improving user to carry out money transfer transactions
Security authentication mechanism, this method needs that user carries out diversified verification operation mode or client and server exists
The mode verified in transaction message, but these modes can bring extra verification operation, increase money transfer transactions to prolong to user
Late, reduce customer experience and cause that transaction message is excessively complicated, increase the process time of server end；Another method is
Setting up customer relationship network by the relation between user carries out the detection of abnormal money transfer transactions, but this method only for user
Between have history transfer accounts record when could opening relationships network, if between user without history transfer accounts record when, relational network structure compared with
It is difficulty.
In sum, turn without history between money transfer transactions delay, user if existing in existing abnormal money transfer transactions detection technique
When account is recorded, then the more difficult problem of customer relationship network struction, it is, therefore, desirable to provide effective method solves above-mentioned asking
Topic.
The content of the invention
A kind of transfer accounts extremely method for detecting and device are the embodiment of the invention provides, is used to solve presence in the prior art and is turned
If between account order execution delay, user without history transfer accounts record when, relational network builds more difficult problem.
The embodiment of the present invention provides a kind of abnormal method for detecting of transferring accounts, including：
Transfer transaction information is obtained, transfer transaction information includes the side's of producing information；
According to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts, detection model of transferring accounts extremely is according to producing
The social attribute of side and the historical behavior attribute of the side of producing are obtained；
The exception of the transfer transaction information input side of producing is transferred accounts detection model, the abnormal probability of transfer transaction information is obtained
Value.
Alternatively, detection model of transferring accounts extremely is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing
Arrive, including：
The interaction attributes that the social attribute of the side of producing includes the self attributes of the side of producing and obtained from social networks；
The historical behavior attribute of the side of producing includes the payment behavior attribute of the side of producing；
The customer relationship net of the side of producing is determined according to self attributes, interaction attributes and payment behavior attribute；
According to the positive negative sample of history money transfer transactions and customer relationship network, the different of the side of producing is set up by machine learning algorithm
Normal detection model of transferring accounts.
Alternatively, the exception of the transfer transaction information input side of producing is transferred accounts detection model, obtains transfer transaction information
Abnormal probable value, including：
The exception of the transfer transaction information input side of producing is transferred accounts detection model, the self attributes of transfer transaction information are obtained
Abnormal probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value；
According to self attributes exception probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value, obtain
To the abnormal probable value of transfer transaction information.
Alternatively, according to the positive negative sample of history money transfer transactions and customer relationship network, set up by machine learning algorithm and turned
The exception of the side of going out is transferred accounts detection model, including：
Correlation analysis are carried out to the self attributes in customer relationship network, interaction attributes and payment behavior attribute；
The attribute of non-correlation is deleted from customer relationship network, revised customer relationship network is obtained；According to history
The positive negative sample of money transfer transactions and revised customer relationship network, the exception for setting up the side of producing by machine learning algorithm are transferred accounts and are detectd
Survey model.
Alternatively, self attributes include at least one of：Status indicator message, education degree index, employment status refer to
Mark, home background index, social information's index；
Payment behavior attribute includes at least one of：Transfer accounts Frequency Index, Annual distribution index of transferring accounts, the place point of transferring accounts
Cloth index, transfer amounts distribution index, mode of transferring accounts accounting index；
Interaction attributes include at least one of：Good friend's Frequency Index, contact Frequency Index, likability index.
The embodiment of the present invention also provides a kind of abnormal arrangement for detecting of transferring accounts, including：
Acquiring unit：For obtaining transfer transaction information, transfer transaction information includes the side's of producing information；
Determining unit：For according to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts, detecting of transferring accounts extremely
Model is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing；
Computing unit：For the exception of the transfer transaction information input side of producing to be transferred accounts detection model, money transfer transactions are obtained
The abnormal probable value of information.
Alternatively, the social attribute of the side of producing includes the self attributes of the side of producing and the interaction category obtained from social networks
Property；
The historical behavior attribute of the side of producing includes the payment behavior attribute of the side of producing；
Determining unit specifically for：
The customer relationship net of the side of producing is determined according to self attributes, interaction attributes and payment behavior attribute；
According to the positive negative sample of history money transfer transactions and customer relationship network, the different of the side of producing is set up by machine learning algorithm
Normal detection model of transferring accounts.
Alternatively, computing unit specifically for：
The exception of the transfer transaction information input side of producing is transferred accounts detection model, the self attributes of transfer transaction information are obtained
Abnormal probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value；
According to self attributes exception probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value, obtain
To the abnormal probable value of transfer transaction information.
Optionally it is determined that unit is specifically additionally operable to：
Correlation analysis are carried out to the self attributes in customer relationship network, interaction attributes and payment behavior attribute；
The attribute of non-correlation is deleted from customer relationship network, revised customer relationship network is obtained；According to history
The positive negative sample of money transfer transactions and revised customer relationship network, the exception for setting up the side of producing by machine learning algorithm are transferred accounts and are detectd
Survey model.
Alternatively, self attributes include at least one of：Status indicator message, education degree index, employment status refer to
Mark, home background index, social information's index；
Payment behavior attribute includes at least one of：Transfer accounts Frequency Index, Annual distribution index of transferring accounts, the place point of transferring accounts
Cloth index, transfer amounts distribution index, mode of transferring accounts accounting index；
Interaction attributes include at least one of：Good friend's Frequency Index, contact Frequency Index, likability index.
A kind of abnormal transfer accounts method for detecting and device are provided in the embodiment of the present invention, transfer transaction information is obtained, transferred accounts
Transaction Information includes the side's of producing information；According to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts is transferred accounts extremely
Detection model is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing；Transfer transaction information input is produced
The exception of side is transferred accounts detection model, obtains the abnormal probable value of transfer transaction information.By obtaining first in the embodiment of the present invention
Transfer transaction information；Then according to transfer transaction information, the detection model it is determined that exception of the side of producing is transferred accounts, wherein, transfer accounts extremely
Detection model is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing, and is easy to abnormal detecting system pair of transferring accounts
Money transfer transactions carry out detection identification, because social attribute and historical behavior attribute are diversified, therefore carry out volume without user
Outer security validation operation, so that the delay of money transfer transactions is reduced, while when being recorded without transferring accounts between user by social attribute
Can also detect whether there is abnormal situation of transferring accounts, so as to improve coverage rate and accuracy to abnormal detecting of transferring accounts；Most
The exception of the transfer transaction information input side of producing is transferred accounts detection model afterwards, obtains the abnormal probable value of transfer transaction information, can
Detected with the money transfer transactions to user and sent abnormity early warning.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will make needed for embodiment description
Accompanying drawing is briefly introduced.
Fig. 1 is that the embodiment of the invention provides a kind of abnormal detecting system overall architecture schematic diagram of transferring accounts；
Fig. 2 is that the embodiment of the invention provides a kind of abnormal method for detecting schematic flow sheet of transferring accounts；
Fig. 3 is comprehensive exception probability schematic diagram provided in an embodiment of the present invention；
Fig. 4 is the schematic diagram that the embodiment of the invention provides customer relationship network；
Fig. 5 is that the embodiment of the invention provides a kind of abnormal arrangement for detecting structural representation of transferring accounts.
Specific embodiment
In order that the purpose of the present invention, technical scheme and beneficial effect become more apparent, below in conjunction with accompanying drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used to explain this hair
It is bright, it is not intended to limit the present invention.
In order to more fully understand this programme, devise the exception in technical solution of the present invention and transfer accounts detecting system, below it is right
The exception of design detecting system of transferring accounts once illustrates that the integrated stand composition of detecting system of transferring accounts extremely is illustrated in fig. 1 shown below：
Fig. 1 illustrates a kind of abnormal detecting system overall architecture schematic diagram of transferring accounts provided in an embodiment of the present invention,
As shown in figure 1, setting up module, abnormal detection model instruction of transferring accounts including data acquisition module, DBM, customer relationship network
Practice module, abnormal detection module of transferring accounts, wherein, DBM include self attributes database, payment behavior attribute database,
Interaction attributes database, detection model training module of transferring accounts extremely docking backstage transaction system.So, transfer accounts extremely detecting system
The mentality of designing of overall architecture is such：The self attributes data of data collecting module collected user, payment behavior attribute number
According to interaction attributes data, and be stored in self attributes database, payment behavior attribute database and interaction attributes database respectively
In；Customer relationship network sets up module according to self attributes database, payment behavior attribute database and interaction attributes database
Data, set up a customer relationship network of three dimensions, wherein, self attributes dimension, paying bank that three dimensions refer to
It is attribute dimensions and interaction attributes dimension；Extremely detection model training module of transferring accounts obtains the history of user from backstage transaction system
The positive negative sample of money transfer transactions, according to the positive negative sample of the history money transfer transactions of customer relationship network and user, calculates with machine learning
Method sets up abnormal detection model of transferring accounts, and the detection model that will transfer accounts extremely is used in abnormal detection module of transferring accounts, and is when user initiates
During money transfer transactions, money transfer transactions are detected and abnormity early warning is sent.Additionally, in abnormal detecting system of transferring accounts user relation
Network is not unalterable, self attributes data, payment behavior attribute data and interaction that detecting system of transferring accounts extremely is gathered
Attribute data changes as user's external relations data change, and detection model of transferring accounts extremely is also constantly carried out periodically more
Newly.
Exception detecting system overall architecture of transferring accounts for designing has the following advantages that：First, turn when user initiates one
When account is concluded the business, various and huge customer relationship network contains the bulk information of user, therefore is carried out additionally without user
Security validation operation, so as to reduce the delay of money transfer transactions, second, when do not transferred accounts between user record when, it is also possible to
Customer relationship network is set up by the self attributes data and interaction attributes data of user, if being transferred accounts without history between solving user
During record, then the more difficult problem of customer relationship network struction, the 3rd, by various and huge customer relationship network and
The positive and negative Sample Establishing of history money transfer transactions of user is transferred accounts detection model extremely, and the model is used for into abnormal detection module of transferring accounts
In, improve the coverage rate and accuracy to abnormal detecting of transferring accounts.
Fig. 2 illustrates a kind of abnormal transfer accounts method for detecting schematic flow sheet, such as Fig. 2 provided in an embodiment of the present invention
It is shown, comprise the following steps：
Step S101：Transfer transaction information is obtained, transfer transaction information includes the side's of producing information；
Step S102：According to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts, detection model of transferring accounts extremely
The historical behavior attribute of social attribute and the side of producing according to the side of producing is obtained；
Step S103：The exception of the transfer transaction information input side of producing is transferred accounts detection model, transfer transaction information is obtained
Abnormal probable value.
Above-described embodiment specifically, when user initiates a money transfer transactions, transfer accounts detection module by the exception in system
Initiation user A to money transfer transactions is analyzed with user B is received, and obtains the money transfer transactions letter initiated user A with receive user B
Breath；User A will be initiated and be input into abnormal detection model of transferring accounts with the transfer transaction information for receiving user B, obtain money transfer transactions letter
The abnormal probable value of breath.Wherein, in specific implementation, user A will be initiated with the transfer transaction information for receiving user B and will be input into exception
After transferring accounts in detection model, it is possible to use machine learning algorithm obtains the abnormal probable value of transfer transaction information.Transferred accounts
After the abnormal probable value of Transaction Information, it is possible to achieve the money transfer transactions of user are detected and abnormity early warning is sent.It is abnormal
Detection model of transferring accounts is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing, and is easy to the abnormal detecting system that transfers accounts
System carries out detection identification to money transfer transactions, because social attribute and historical behavior attribute are diversified, therefore enters without user
The extra security validation operation of row, so that the delay of money transfer transactions is reduced, while when being recorded without transferring accounts between user by social activity
Attribute can also detect whether there is abnormal situation of transferring accounts, so as to improve to the coverage rate of abnormal detecting of transferring accounts with it is accurate
Property.
Wherein, detection model of transferring accounts extremely can be obtained by following three kinds of modes：
Mode one：Extremely detection model of transferring accounts is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing
Arrive；Specifically, using the historical behavior attribute of the social attribute of the side of producing and the side of producing as abnormal the defeated of detection model of transferring accounts
Enter, the training to abnormal detection model of transferring accounts is realized with machine learning algorithm, after repeatedly training, finally train
Exception is transferred accounts detection model.
Mode two：Alternatively, detection model is transferred accounts extremely according to the social attribute of the side of producing and the historical behavior of the side of producing
Attribute is obtained, including：The interaction attributes that the social attribute of the side of producing includes the self attributes of the side of producing and obtained from social networks；
The historical behavior attribute of the side of producing includes the payment behavior attribute of the side of producing；According to self attributes, interaction attributes and payment behavior
Attribute determines the customer relationship net of the side of producing；According to the positive negative sample of history money transfer transactions and customer relationship network, by engineering
Practise algorithm and set up the exception of the side of producing and transfer accounts detection model；Specifically, first according to self attributes, interaction attributes and paying bank
The customer relationship net of the side of producing is determined for attribute；Then using the positive negative sample of history money transfer transactions and customer relationship network as exception
Transfer accounts the input of detection model, the training to abnormal detection model of transferring accounts is realized with machine learning algorithm, by repeatedly instruction
After white silk, abnormal detection model of transferring accounts finally is trained.
Mode three：Alternatively, according to the positive negative sample of history money transfer transactions and customer relationship network, by machine learning algorithm
The exception for setting up the side of producing is transferred accounts detection model, including：To the self attributes in customer relationship network, interaction attributes and paying bank
For attribute carries out correlation analysis；The attribute of non-correlation is deleted from customer relationship network, revised customer relationship is obtained
Network；According to the positive negative sample of history money transfer transactions and revised customer relationship network, set up by machine learning algorithm and produced
The exception of side is transferred accounts detection model.In specific implementation, self attributes, interaction attributes and the payment behavior category in customer relationship network
Property include many information or index respectively, it is assumed that self attributes, interaction attributes and payment behavior attribute are contained altogether
This 10000 indexs are carried out correlation analysis or data cleansing and screening by 10000 indexs first, for example, index 1 and finger
Mark 2 is presented linear relationship, then, in index 1 and index 2 can be retained, delete another index, it is assumed that to this
10000 indexs are by after correlation analysis or data cleansing and screening, finally remaining 1000 indexs；Then basis
1000 indexs obtain revised customer relationship network, by the positive negative sample of history money transfer transactions and revised customer relationship net
Network as abnormal detection model of transferring accounts input and with machine learning algorithm abnormal detection model of transferring accounts is trained, in instruction
During white silk, index related analysis can be carried out with reference to the positive negative sample of history money transfer transactions and correct customer relationship network again,
Such as, some positive negative samples on history money transfer transactions do not have the index of any influence in 1000 indexs, can be by
It is deleted, it is assumed that have 500 indexs not have any influence to the positive negative sample of history money transfer transactions in 1000 indexs, then
Obtain comprising 500 customer relationship networks corrected again of index, the customer relationship network and history that will be corrected again are transferred accounts
Conclude the business positive negative sample as abnormal detection model of transferring accounts input and with machine learning algorithm abnormal detection model of transferring accounts is entered
Row training, finally trains abnormal detection model of transferring accounts, wherein, the positive negative sample of history money transfer transactions is by abnormal detecting of transferring accounts
Detection model training module of being transferred accounts extremely in system docking backstage transaction system is obtained, and the positive negative sample of history money transfer transactions includes
The normal money transfer transactions record of user's history and abnormal money transfer transactions record., wherein it is desired to first point of explanation is：User is closed
It is that network has carried out modified twice, the customer relationship network corrected again can be in the training to abnormal detection model of transferring accounts
Carried out in journey, or carried out before to the training of abnormal detection model of transferring accounts, such as, to the customer relationship corrected again
1000 index combination positive negative samples of history money transfer transactions in network carry out correlation analysis or data cleansing and screening, finally
500 indexs are filtered out, by comprising 500 the customer relationship networks corrected again and the positive negative sample of history money transfer transactions of index
As the input of abnormal detection model of transferring accounts, abnormal detection model of transferring accounts is trained with machine learning algorithm；Need
Bright second point is：It is example in carrying out being input to abnormal detection model of transferring accounts in the form of rule record in specific implementation
Such as, record 1 is：Transfer accounts the time for 8 points of morning, transfer amounts be 8000, place of transferring accounts for Shanghai, mode of transferring accounts to swipe the card and
The relation for receiving user transfer accounts for colleague, money transfer transactions are positive sample；Need explanation be thirdly：In specific implementation, if
It is full positive sample in the positive negative sample of history money transfer transactions of user, then the history money transfer transactions note for extracting the user can be reduced
The quantity of record, if negative sample is far longer than the quantity of positive sample in the positive negative sample of history money transfer transactions of user, then can be with
Increase the quantity of the history money transfer transactions record for extracting the user.
Transferred accounts extremely by three of the above the determination mode of detection model, it can be seen that for abnormal detection model of transferring accounts
Determination mode there is variation and the characteristics of flexibility；Modified twice is carried out to customer relationship network, actually to user
Relational network has carried out Data Dimensionality Reduction twice, can so reduce the amount of calculation and pressure of system, which can also clearly go out and refer to
Mark can have effect to money transfer transactions.
Alternatively, the exception of the transfer transaction information input side of producing is transferred accounts detection model, obtains transfer transaction information
Abnormal probable value, including：The exception of the transfer transaction information input side of producing is transferred accounts detection model, transfer transaction information is obtained
Self attributes exception probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value；It is different according to self attributes
Normal probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value, obtain the abnormal general of transfer transaction information
Rate value.Specifically, it is assumed that user A transfers accounts to user B, detection module is transferred accounts in detecting system of transferring accounts extremely extremely to user A
It is analyzed with user B and obtains their index, index is input in abnormal detection model of transferring accounts, can show that three exceptions are general
Rate value, respectively self attributes exception probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value, it is assumed that
Respectively 0.3,0.5,0.2, appropriate weight is imposed to these three abnormal probable values respectively, each exception after weight will be applied
Probable value is added, and ultimately generates the comprehensive exception probability that the money transfer transactions are abnormal money transfer transactions, it is assumed that comprehensively exception probability is
0.25, synthesis exception probability shows that current money transfer transactions are abnormal value-at-risk.If the combined chance is very big, system is straight
Sending and receiving go out abnormity early warning.Fig. 3 schematically illustrates comprehensive exception probability schematic diagram, as shown in Figure 3.
Alternatively, self attributes include at least one of：Status indicator message, education degree index, employment status refer to
Mark, home background index, social information's index；In specific implementation, status indicator message can also include identity card, passport, property
Not, age, phone number etc. characterize the information of user identity；Education degree index shows the educational level of user；Employment status
Whether index reflection user has fixed proper occupation and work replacement frequency；Home background index includes marriage and children's situation
Deng；Social information's index includes that social security, medical insurance are converged and pays situation and social credibility situation, and social credibility is it may is that bank card
Overdue arrearage of overdue or government utility payment etc..Exception transfers accounts detecting system according to self attributes information, depicts the base of user
This situation is drawn a portrait.For example, if user has no regular occupation, identity information is imperfect or fake, social information it is not good etc., and turn
Account dealing money but than larger, then no matter as money transfer transactions initiation user or receive user, this money transfer transactions it is different
Normal probability is of a relatively high, and it may be money laundering or telecommunication fraud activity that such as the pen is transferred accounts.
Payment behavior attribute includes at least one of：Transfer accounts Frequency Index, Annual distribution index of transferring accounts, the place point of transferring accounts
Cloth index, transfer amounts distribution index, mode of transferring accounts accounting index；In specific implementation, the data of payment behavior attribute it is main from
Bank's passage, card tissue, acquisition such as Third-party payment mechanism in itself, the data of payment behavior attribute including history transfer accounts record,
History consumption details etc..In history transfers accounts record, based on but be not limited to transfer accounts object, transfer amounts, time of transferring accounts, transfer accounts
The key messages such as place, mode of transferring accounts, wherein, object of transferring accounts includes account and card number etc., object of transferring accounts, transfer amounts, transfers accounts
Time, place of transferring accounts, mode of transferring accounts transfer accounts the distribution of object to statistical analysis and frequency of transferring accounts accordingly, user are transferred accounts gold
Volume distribution, the index such as time and place distribution, mode of transferring accounts accounting of transferring accounts.In object analysis of transferring accounts, according to transfer accounts frequency by
It is high to Low to be ranked up object；In transfer amounts, time of transferring accounts, place distribution of transferring accounts, can analyze and obtain turning for user
The account amount of money is interval and with the fluctuation tendency of time, and such as user transfers accounts and rule distribution is presented and fluctuates gently, but gold of currently transferring accounts
Volume is uprushed, and the time of transferring accounts also is free on outside distribution, then abnormal probability of transferring accounts is higher；The accounting of mode of being transferred accounts to user's history
Analysis, it may be to know that user is more likely to traditional channel, and such as ATM, bank counter are still innovated channel such as computer end, mobile terminal and carried out
Money transfer transactions, such as user carry out money transfer transactions frequently by traditional channel, and currently transfer accounts is carried out by mobile terminal, then the index
Judgement weight to abnormal probability of transferring accounts increases.Additionally, in the history transfer transaction data of user, being transferred accounts by user's history
Transaction and consumer record from the information such as consuming frequency, spending amount, consumption pattern, analyze the consumptive power index and transaction canal of user
Road.Consumptive power index shows the level of consumption of the user, reflects consumptive power and the purchasing power of user, i.e., wholesale consumption often occur
Or small amount consumption.Consumption pattern shows that the user is more likely to that conventional payment mode such as POS is swiped the card etc. or innovation pays
Mode such as cloud sudden strain of a muscle pair, the payment of Quick Response Code barcode scanning etc., and then reflect fanatic degree of the user to mobile innovation payment.
Interaction attributes include at least one of：Good friend's Frequency Index, contact Frequency Index, likability index.In this hair
In bright specific implementation, except setting up user between payment behavior relation on attributes network, also set up the interaction attributes relation of user
Network, the record even if the no history of the both sides for so transferring accounts is transferred accounts also can judge that mutual relation is strong by interaction attributes
It is weak.In interaction attributes, data include wechat, QQ, microblogging, mail, telecom operators such as short message or call, network game, even win
Color data etc., each user can set up an interaction attributes relational network for complexity.In interaction attributes relational network,
Refer mainly to indicate that good friend's frequency, contact frequency, likability etc. are a series of can reflect that user associates tightness degree with other users
Index.Good friend's frequency index, reflection be friend relation between user tightness degree, such as user both sides are in wechat, qq multiclass
Friend relation is in social software, then good friend's frequency is higher between the user.Contact Frequency Index, reflection is contact between user
The height of frequency, mainly obtains the contact frequency between user from communication class social data.Likability index, reflection is user
Between relation positive and negative quality, it is possible to use natural language analysis technology user's Chat communication content is carried out participle, word frequency statisticses,
Fine or not word analysis etc., obtains the likability between user.In addition to social networking application, the data such as online game, lottery industry also can
The complicated relational network of reflection user, such as in network game, the relation in same team between team member can further supplement interaction
Relation on attributes network.
Determined according to self attributes, interaction attributes and payment behavior attribute due to customer relationship network, then, based on
On to the content of the specific introduction of self attributes, interaction attributes and payment behavior attribute, be described below based on self attributes, interaction
The customer relationship network of attribute and payment behavior attribute specifically sets up process, including three processes：
Self attributes, interaction attributes and payment behavior attribute may be considered three dimensions of customer relationship network, and 1, right
Information in self attributes, interaction attributes and payment behavior attribute is given a mark：In self attributes dimension, to the identity of user
Information index, education degree index, employment status index, home background index, social information's index are judged and beaten respectively
Point, if complete true, the professional stable, social information of the identity information of the two parties of money transfer transactions is good, it is clear that can reduce
Money transfer transactions are abnormal probability, and the fraction that status indicator message, employment status index to user, social information's index are beaten can
To beat low spot；In interaction attributes dimension, commented by good friend's Frequency Index, contact Frequency Index, likability index etc.
Sentence and give a mark, good friend's Frequency Index, contact Frequency Index, likability index whether there is social activity between can intuitively reflecting user
Front or negative emotion between relation, contact tightness degree and user, for example, the good friend user B of user A is to user A
Apply for demand of transferring accounts, but find that good friend's frequency is relatively low between user A and B in interaction attributes dimension, get in touch with seldom, also without good opinion
Degree, illustrates that user A compares weak with the social interaction attributes of B, and user B is very big may be by steal-number, then at this moment to interaction attributes
Good friend's Frequency Index, the fraction beaten of contact Frequency Index, likability index it is higher；In payment behavior attribute dimensions, will be right
The all of money transfer transactions of user and consumer record carry out going deep into mining analysis, obtain user and transfer accounts density relation, the analysis of object
User's money transfer transactions or consumption habit, portray it and pay portrait.Gone through between the initiation user and reception user of current money transfer transactions
The behaviors such as history money transfer transactions, consumption are frequent, and transfer amounts are stable, meet the consumptive power level of user, then current money transfer transactions
For abnormal probability is relatively low, then relatively low fraction can be beaten to the information in payment behavior attribute dimensions；Conversely, hair of transferring accounts
Play user and have no money transfer transactions contact with user is received, and transfer accounts receive user payment relation it is complicated and irregular, and currently
Grave fault for the relative consumptive power for initiating user of transferring accounts of transfer amounts, then abnormal probability of transferring accounts is larger, and initiation of such as transferring accounts is used
Family can suffer from telecommunication fraud activity, at this moment can beat fraction higher to the information in payment behavior attribute dimensions；2nd, to certainly
The fraction that information in body attribute, interaction attributes and payment behavior attribute is beaten generates each weighted value；3rd, in being with the user that transfers accounts
Heart node, with each weighted value as side, forms customer relationship network.Fig. 4 schematically illustrates showing for customer relationship network
It is intended to, as shown in Figure 4.
Can be seen that from the discussion above：A kind of abnormal method for detecting of transferring accounts is provided in the embodiment of the present invention, friendship of transferring accounts is obtained
Easy information, transfer transaction information includes the side's of producing information；According to the side's of producing information, the detecting mould it is determined that the exception of the side of producing is transferred accounts
Type, detection model of transferring accounts extremely is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing；By money transfer transactions
The exception of the information input side of producing is transferred accounts detection model, obtains the abnormal probable value of transfer transaction information.In the embodiment of the present invention
By obtaining transfer transaction information first；Then according to transfer transaction information, the detection model it is determined that exception of the side of producing is transferred accounts, its
In, detection model of transferring accounts extremely is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing, and is easy to system pair
Money transfer transactions carry out detection identification, because social attribute and historical behavior attribute are diversified, therefore carry out volume without user
Outer security validation operation, so that the delay of money transfer transactions is reduced, while can also be detected when nothing is transferred accounts and recorded between user
With the presence or absence of abnormal situation of transferring accounts, so as to improve coverage rate and accuracy to abnormal detecting of transferring accounts；Finally by money transfer transactions
The exception of the information input side of producing is transferred accounts detection model, obtains the abnormal probable value of transfer transaction information, and user can be turned
Account transaction is detected and is sent abnormity early warning.
Based on same idea, a kind of abnormal arrangement for detecting of transferring accounts provided in an embodiment of the present invention, Fig. 5 illustrates this
The abnormal arrangement for detecting structural representation of transferring accounts of one kind that inventive embodiments are provided, as shown in figure 5, the device includes acquiring unit
201st, determining unit 202, computing unit 203.Wherein：
Acquiring unit 201：For obtaining transfer transaction information, transfer transaction information includes the side's of producing information；
Determining unit 202：For according to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts to be transferred accounts extremely
Detection model is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing；
Computing unit 203：For the exception of the transfer transaction information input side of producing to be transferred accounts detection model, friendship of transferring accounts is obtained
The abnormal probable value of easy information.
Alternatively, the social attribute of the side of producing includes the self attributes of the side of producing and the interaction category obtained from social networks
Property；
The historical behavior attribute of the side of producing includes the payment behavior attribute of the side of producing；
Determining unit 202 specifically for：
The customer relationship net of the side of producing is determined according to self attributes, interaction attributes and payment behavior attribute；
According to the positive negative sample of history money transfer transactions and customer relationship network, the different of the side of producing is set up by machine learning algorithm
Normal detection model of transferring accounts.
Alternatively, computing unit 203 specifically for：
The exception of the transfer transaction information input side of producing is transferred accounts detection model, the self attributes of transfer transaction information are obtained
Abnormal probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value；
According to self attributes exception probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value, obtain
To the abnormal probable value of transfer transaction information.
Optionally it is determined that unit 202 is specifically additionally operable to：
Correlation analysis are carried out to the self attributes in customer relationship network, interaction attributes and payment behavior attribute；
The attribute of non-correlation is deleted from customer relationship network, revised customer relationship network is obtained；According to history
The positive negative sample of money transfer transactions and revised customer relationship network, the exception for setting up the side of producing by machine learning algorithm are transferred accounts and are detectd
Survey model.
Alternatively, self attributes include at least one of：Status indicator message, education degree index, employment status refer to
Mark, home background index, social information's index；
Payment behavior attribute includes at least one of：Transfer accounts Frequency Index, Annual distribution index of transferring accounts, the place point of transferring accounts
Cloth index, transfer amounts distribution index, mode of transferring accounts accounting index；
Interaction attributes include at least one of：Good friend's Frequency Index, contact Frequency Index, likability index.
Can be seen that from the discussion above：A kind of abnormal arrangement for detecting of transferring accounts is provided in the embodiment of the present invention, friendship of transferring accounts is obtained
Easy information, transfer transaction information includes the side's of producing information；According to the side's of producing information, the detecting mould it is determined that the exception of the side of producing is transferred accounts
Type, detection model of transferring accounts extremely is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing；By money transfer transactions
The exception of the information input side of producing is transferred accounts detection model, obtains the abnormal probable value of transfer transaction information.In the embodiment of the present invention
By obtaining transfer transaction information first；Then according to transfer transaction information, the detection model it is determined that exception of the side of producing is transferred accounts, its
In, detection model of transferring accounts extremely is obtained according to the social attribute of the side of producing and the historical behavior attribute of the side of producing, and is easy to abnormal turning
Account detecting system carries out detection identification to money transfer transactions, because social attribute and historical behavior attribute are diversified, therefore nothings
Palpus user carries out extra security validation operation, so that the delay of money transfer transactions is reduced, while when being recorded without transferring accounts between user
Can also detect whether there is abnormal situation of transferring accounts by social attribute, so as to improve the coverage rate to abnormal detecting of transferring accounts
With accuracy；Finally the exception of the transfer transaction information input side of producing is transferred accounts detection model, the different of transfer transaction information is obtained
The money transfer transactions of user can be detected and be sent abnormity early warning by normal probable value.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method or computer program product.
Therefore, the present invention can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.And, the present invention can be used to be can use in one or more computers for wherein including computer usable program code and deposited
The shape of the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that every first-class during flow chart and/or block diagram can be realized by computer program instructions
The combination of flow and/or square frame in journey and/or square frame and flow chart and/or block diagram.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The device of the function of being specified in present one flow of flow chart or multiple one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices with spy
In determining the computer-readable memory that mode works so that instruction of the storage in the computer-readable memory is produced and include finger
Make the manufacture of device, the command device realize in one flow of flow chart or multiple one square frame of flow and/or block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented treatment, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification without deviating from essence of the invention to the present invention
God and scope.So, if these modifications of the invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of abnormal method for detecting of transferring accounts, it is characterised in that including：
Transfer transaction information is obtained, the transfer transaction information includes the side's of producing information；
According to the side's of producing information, the detection model it is determined that exception of the side of producing is transferred accounts, the exception transfer accounts detection model according to
The historical behavior attribute of the social attribute of the side of producing and the side of producing is obtained；
The exception of the transfer transaction information input side of producing is transferred accounts detection model, the transfer transaction information is obtained
Abnormal probable value.
2. the method for claim 1, it is characterised in that the exception is transferred accounts the society of detection model side of producing according to
Attribute and the historical behavior attribute of the side of producing is handed over to obtain, including：
The interaction attributes that the social attribute of the side of producing includes the self attributes of the side of producing and obtained from social networks；
The historical behavior attribute of the side of producing includes the payment behavior attribute of the side of producing；
The customer relationship of the side of producing according to the self attributes, the interaction attributes and the payment behavior attribute determine
Net；
According to the positive negative sample of history money transfer transactions and the customer relationship network, the side of producing is set up by machine learning algorithm
Exception transfer accounts detection model.
3. method as claimed in claim 2, it is characterised in that described by the transfer transaction information input side of producing
Exception is transferred accounts detection model, obtains the abnormal probable value of the transfer transaction information, including：
The exception of the transfer transaction information input side of producing is transferred accounts detection model, the transfer transaction information is obtained
Self attributes exception probable value, interaction attributes exception probable value and payment behavior attribute abnormal probable value；
It is general according to self attributes exception probable value, interaction attributes exception probable value and the payment behavior attribute abnormal
Rate value, obtains the abnormal probable value of the transfer transaction information.
4. method as claimed in claim 2, it is characterised in that described according to the positive negative sample of history money transfer transactions and the user
Relational network, the exception for setting up the side of producing by machine learning algorithm is transferred accounts detection model, including：
Correlation analysis are carried out to the self attributes in the customer relationship network, interaction attributes and payment behavior attribute；
The attribute of non-correlation is deleted from the customer relationship network, revised customer relationship network is obtained；According to described
The positive negative sample of history money transfer transactions and the revised customer relationship network, the side of producing is set up by machine learning algorithm
Exception transfer accounts detection model.
5. method as claimed in claim 4, it is characterised in that the self attributes include at least one of：Identity information
Index, education degree index, employment status index, home background index, social information's index；
The payment behavior attribute includes at least one of：Transfer accounts Frequency Index, Annual distribution index of transferring accounts, the place point of transferring accounts
Cloth index, transfer amounts distribution index, mode of transferring accounts accounting index；
The interaction attributes include at least one of：Good friend's Frequency Index, contact Frequency Index, likability index.
6. a kind of abnormal arrangement for detecting of transferring accounts, it is characterised in that including：
Acquiring unit, for obtaining transfer transaction information, the transfer transaction information includes the side's of producing information；
Determining unit, for according to the side of producing information, the detection model it is determined that exception of the side of producing is transferred accounts, the exception to be transferred accounts
Detection model historical behavior attribute of the social attribute of the side of producing and the side of producing according to is obtained；
Computing unit, for the exception of the transfer transaction information input side of producing to be transferred accounts detection model, obtains described
The abnormal probable value of transfer transaction information.
7. device as claimed in claim 6, it is characterised in that
The interaction attributes that the social attribute of the side of producing includes the self attributes of the side of producing and obtained from social networks；
The historical behavior attribute of the side of producing includes the payment behavior attribute of the side of producing；
The determining unit, specifically for being determined according to the self attributes, the interaction attributes and the payment behavior attribute
The customer relationship net of the side of producing；
According to the positive negative sample of history money transfer transactions and the customer relationship network, the side of producing is set up by machine learning algorithm
Exception transfer accounts detection model.
8. device as claimed in claim 7, it is characterised in that
The computing unit, specifically for the exception of the transfer transaction information input side of producing is transferred accounts detection model,
Obtain self attributes exception probable value, interaction attributes exception probable value and the payment behavior attribute abnormal of the transfer transaction information
Probable value；
It is general according to self attributes exception probable value, interaction attributes exception probable value and the payment behavior attribute abnormal
Rate value, obtains the abnormal probable value of the transfer transaction information.
9. device as claimed in claim 7, it is characterised in that
The determining unit, is specifically additionally operable to the self attributes in the customer relationship network, interaction attributes and payment behavior
Attribute carries out correlation analysis；
The attribute of non-correlation is deleted from the customer relationship network, revised customer relationship network is obtained；According to described
The positive negative sample of history money transfer transactions and the revised customer relationship network, the side of producing is set up by machine learning algorithm
Exception transfer accounts detection model.
10. device as claimed in claim 9, it is characterised in that the self attributes include at least one of：Identity information
Index, education degree index, employment status index, home background index, social information's index；
The payment behavior attribute includes at least one of：Transfer accounts Frequency Index, Annual distribution index of transferring accounts, the place point of transferring accounts
Cloth index, transfer amounts distribution index, mode of transferring accounts accounting index；
The interaction attributes include at least one of：Good friend's Frequency Index, contact Frequency Index, likability index.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611264190.3A CN106803168B (en) | 2016-12-30 | 2016-12-30 | Abnormal transfer detection method and device |
| PCT/CN2017/111096 WO2018121113A1 (en) | 2016-12-30 | 2017-11-15 | Abnormal account transfer detection method and device |
| TW106145681A TWI690884B (en) | 2016-12-30 | 2017-12-26 | Abnormal transfer detection method, device, storage medium, electronic equipment and products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611264190.3A CN106803168B (en) | 2016-12-30 | 2016-12-30 | Abnormal transfer detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106803168A true CN106803168A (en) | 2017-06-06 |
| CN106803168B CN106803168B (en) | 2021-04-16 |
Family
ID=58985292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611264190.3A Active CN106803168B (en) | 2016-12-30 | 2016-12-30 | Abnormal transfer detection method and device |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN106803168B (en) |
| TW (1) | TWI690884B (en) |
| WO (1) | WO2018121113A1 (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358360A (en) * | 2017-07-14 | 2017-11-17 | 成都农村商业银行股份有限公司 | The abnormal traffic data screening method of anti money washing system |
| CN107437176A (en) * | 2017-07-11 | 2017-12-05 | 广东欧珀移动通信有限公司 | Method of payment and Related product |
| CN107798530A (en) * | 2017-08-09 | 2018-03-13 | 中国银联股份有限公司 | A kind of payment system and method for payment |
| CN107871213A (en) * | 2017-11-27 | 2018-04-03 | 上海众人网络安全技术有限公司 | A kind of trading activity evaluation method, device, server and storage medium |
| CN107908740A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术（北京）有限公司 | Information output method and device |
| WO2018121113A1 (en) * | 2016-12-30 | 2018-07-05 | 中国银联股份有限公司 | Abnormal account transfer detection method and device |
| 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 |
| CN108647891A (en) * | 2018-05-14 | 2018-10-12 | 口口相传(北京)网络技术有限公司 | Data exception classification, Reasons method and device |
| CN108734479A (en) * | 2018-04-12 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
| CN108769208A (en) * | 2018-05-30 | 2018-11-06 | 阿里巴巴集团控股有限公司 | Specific user's identification and information-pushing method and device |
| CN109118053A (en) * | 2018-07-17 | 2019-01-01 | 阿里巴巴集团控股有限公司 | It is a kind of steal card risk trade recognition methods and device |
| CN109165940A (en) * | 2018-06-28 | 2019-01-08 | 阿里巴巴集团控股有限公司 | A kind of theft preventing method, device and electronic equipment |
| CN109191129A (en) * | 2018-07-18 | 2019-01-11 | 阿里巴巴集团控股有限公司 | A kind of air control method, system and computer equipment |
| CN109360085A (en) * | 2018-09-27 | 2019-02-19 | 中国银行股份有限公司 | A kind of bank client responsible investigation method and system |
| CN109426960A (en) * | 2017-12-28 | 2019-03-05 | 中国平安财产保险股份有限公司 | Account authentication method, mobile device, account authentication equipment and readable storage medium storing program for executing |
| CN109472656A (en) * | 2017-09-08 | 2019-03-15 | 腾讯科技（深圳）有限公司 | A kind of methods of exhibiting of virtual objects, device and storage medium |
| CN110955842A (en) * | 2019-12-03 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Abnormal access behavior identification method and device |
| WO2020135242A1 (en) * | 2018-12-25 | 2020-07-02 | 瞬联软件科技（北京）有限公司 | Method and system for displaying security risk value of online payment by color |
| CN111401478A (en) * | 2020-04-17 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Data abnormity identification method and device |
| CN111681010A (en) * | 2020-06-11 | 2020-09-18 | 中国银行股份有限公司 | Transaction verification method and device |
| CN111860647A (en) * | 2020-07-21 | 2020-10-30 | 金陵科技学院 | Abnormal consumption mode judgment method |
| CN112491900A (en) * | 2020-11-30 | 2021-03-12 | 中国银联股份有限公司 | Abnormal node identification method, device, equipment and medium |
| CN112581283A (en) * | 2020-12-28 | 2021-03-30 | 中国建设银行股份有限公司 | Method and device for analyzing and alarming business bank employee transaction behaviors |
| CN113011889A (en) * | 2021-03-10 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Account abnormity identification method, system, device, equipment and medium |
| US11102230B2 (en) * | 2017-12-15 | 2021-08-24 | Advanced New Technologies Co., Ltd. | Graphical structure model-based prevention and control of abnormal accounts |
| CN113888153A (en) * | 2021-11-10 | 2022-01-04 | 建信金融科技有限责任公司 | Transfer abnormity prediction method, device, equipment and readable storage medium |
| CN113935738A (en) * | 2020-06-29 | 2022-01-14 | 腾讯科技（深圳）有限公司 | Transaction data processing method, device, storage medium and equipment |
| CN114154507A (en) * | 2021-11-12 | 2022-03-08 | 中国银行股份有限公司 | Abnormal transfer monitoring method, device, equipment and storage medium |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175850B (en) * | 2019-05-13 | 2023-08-01 | 中国银联股份有限公司 | Transaction information processing method and device |
| CN110363387B (en) * | 2019-06-14 | 2023-09-05 | 平安科技（深圳）有限公司 | Portrait analysis method and device based on big data, computer equipment and storage medium |
| CN110457601B (en) * | 2019-08-15 | 2023-10-24 | 腾讯科技（武汉）有限公司 | Social account identification method and device, storage medium and electronic device |
| CN110730459B (en) * | 2019-10-25 | 2021-05-28 | 支付宝(杭州)信息技术有限公司 | Method and related device for initiating near field communication authentication |
| CN112990919A (en) * | 2019-12-17 | 2021-06-18 | 中国银联股份有限公司 | Information processing method and device |
| CN112016913A (en) * | 2020-08-28 | 2020-12-01 | 中国农业银行股份有限公司湖南省分行 | Social insurance medical insurance intelligent payment system based on mobile internet |
| CN112488708B (en) * | 2020-11-30 | 2024-04-05 | 苏州黑云智能科技有限公司 | Block chain account relevance query method and false transaction screening method |
| CN117195130B (en) * | 2023-09-19 | 2024-05-10 | 深圳市东陆高新实业有限公司 | Intelligent all-purpose card management system and method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103123712A (en) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | Method and system for monitoring network behavior data |
| CN104468249A (en) * | 2013-09-17 | 2015-03-25 | 深圳市腾讯计算机系统有限公司 | Method and device for detecting abnormal account number |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060294095A1 (en) * | 2005-06-09 | 2006-12-28 | Mantas, Inc. | Runtime thresholds for behavior detection |
| TW201017569A (en) * | 2008-10-21 | 2010-05-01 | Univ Chaoyang Technology | A financial fund transferring system capable of preventing illegal events |
| CN101714273A (en) * | 2009-05-26 | 2010-05-26 | 北京银丰新融科技开发有限公司 | Rule engine-based method and system for monitoring exceptional service of bank |
| CN103379431B (en) * | 2012-04-19 | 2017-06-30 | 阿里巴巴集团控股有限公司 | A kind of guard method of account safety and device |
| DE202014011247U1 (en) * | 2013-05-15 | 2019-06-05 | Kensho Technologies, Llc | Systems for data acquisition and modeling |
| CN103716316B (en) * | 2013-12-25 | 2018-09-25 | 上海拍拍贷金融信息服务有限公司 | A kind of authenticating user identification system |
| CN105703966A (en) * | 2014-11-27 | 2016-06-22 | 阿里巴巴集团控股有限公司 | Internet behavior risk identification method and apparatus |
| CN105957271B (en) * | 2015-12-21 | 2018-12-28 | 中国银联股份有限公司 | A kind of financial terminal safety protecting method and system |
| CN106803168B (en) * | 2016-12-30 | 2021-04-16 | 中国银联股份有限公司 | Abnormal transfer detection method and device |
-
2016
- 2016-12-30 CN CN201611264190.3A patent/CN106803168B/en active Active
-
2017
- 2017-11-15 WO PCT/CN2017/111096 patent/WO2018121113A1/en active Application Filing
- 2017-12-26 TW TW106145681A patent/TWI690884B/en active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103123712A (en) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | Method and system for monitoring network behavior data |
| CN104468249A (en) * | 2013-09-17 | 2015-03-25 | 深圳市腾讯计算机系统有限公司 | Method and device for detecting abnormal account number |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018121113A1 (en) * | 2016-12-30 | 2018-07-05 | 中国银联股份有限公司 | Abnormal account transfer detection method and device |
| CN107437176A (en) * | 2017-07-11 | 2017-12-05 | 广东欧珀移动通信有限公司 | Method of payment and Related product |
| CN107358360A (en) * | 2017-07-14 | 2017-11-17 | 成都农村商业银行股份有限公司 | The abnormal traffic data screening method of anti money washing system |
| CN107798530B (en) * | 2017-08-09 | 2021-09-14 | 中国银联股份有限公司 | Payment system and payment method |
| CN107798530A (en) * | 2017-08-09 | 2018-03-13 | 中国银联股份有限公司 | A kind of payment system and method for payment |
| CN109472656A (en) * | 2017-09-08 | 2019-03-15 | 腾讯科技（深圳）有限公司 | A kind of methods of exhibiting of virtual objects, device and storage medium |
| CN109472656B (en) * | 2017-09-08 | 2022-11-29 | 腾讯科技（深圳）有限公司 | Virtual article display method and device and storage medium |
| CN107908740B (en) * | 2017-11-15 | 2022-11-22 | 百度在线网络技术（北京）有限公司 | Information output method and device |
| CN107908740A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术（北京）有限公司 | Information output method and device |
| CN107871213B (en) * | 2017-11-27 | 2021-11-12 | 上海众人网络安全技术有限公司 | Transaction behavior evaluation method, device, server and storage medium |
| CN107871213A (en) * | 2017-11-27 | 2018-04-03 | 上海众人网络安全技术有限公司 | A kind of trading activity evaluation method, device, server and storage medium |
| US11223644B2 (en) | 2017-12-15 | 2022-01-11 | Advanced New Technologies Co., Ltd. | Graphical structure model-based prevention and control of abnormal accounts |
| US11102230B2 (en) * | 2017-12-15 | 2021-08-24 | Advanced New Technologies Co., Ltd. | Graphical structure model-based prevention and control of abnormal accounts |
| CN109426960A (en) * | 2017-12-28 | 2019-03-05 | 中国平安财产保险股份有限公司 | Account authentication method, mobile device, account authentication equipment and readable storage medium storing program for executing |
| CN108734479A (en) * | 2018-04-12 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
| 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 |
| CN108647891A (en) * | 2018-05-14 | 2018-10-12 | 口口相传(北京)网络技术有限公司 | Data exception classification, Reasons method and device |
| CN108769208B (en) * | 2018-05-30 | 2022-04-22 | 创新先进技术有限公司 | Specific user identification and information push method and device |
| CN108769208A (en) * | 2018-05-30 | 2018-11-06 | 阿里巴巴集团控股有限公司 | Specific user's identification and information-pushing method and device |
| CN109165940A (en) * | 2018-06-28 | 2019-01-08 | 阿里巴巴集团控股有限公司 | A kind of theft preventing method, device and electronic equipment |
| CN109165940B (en) * | 2018-06-28 | 2022-08-09 | 创新先进技术有限公司 | Anti-theft method and device and electronic equipment |
| CN109118053B (en) * | 2018-07-17 | 2022-04-05 | 创新先进技术有限公司 | Method and device for identifying card stealing risk transaction |
| CN109118053A (en) * | 2018-07-17 | 2019-01-01 | 阿里巴巴集团控股有限公司 | It is a kind of steal card risk trade recognition methods and device |
| CN109191129A (en) * | 2018-07-18 | 2019-01-11 | 阿里巴巴集团控股有限公司 | A kind of air control method, system and computer equipment |
| CN109360085A (en) * | 2018-09-27 | 2019-02-19 | 中国银行股份有限公司 | A kind of bank client responsible investigation method and system |
| WO2020135242A1 (en) * | 2018-12-25 | 2020-07-02 | 瞬联软件科技（北京）有限公司 | Method and system for displaying security risk value of online payment by color |
| CN110955842A (en) * | 2019-12-03 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Abnormal access behavior identification method and device |
| CN111401478A (en) * | 2020-04-17 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Data abnormity identification method and device |
| CN111681010A (en) * | 2020-06-11 | 2020-09-18 | 中国银行股份有限公司 | Transaction verification method and device |
| CN113935738B (en) * | 2020-06-29 | 2024-04-19 | 腾讯科技（深圳）有限公司 | Transaction data processing method, device, storage medium and equipment |
| CN113935738A (en) * | 2020-06-29 | 2022-01-14 | 腾讯科技（深圳）有限公司 | Transaction data processing method, device, storage medium and equipment |
| CN111860647A (en) * | 2020-07-21 | 2020-10-30 | 金陵科技学院 | Abnormal consumption mode judgment method |
| CN111860647B (en) * | 2020-07-21 | 2023-11-10 | 金陵科技学院 | Abnormal consumption mode judging method |
| CN112491900A (en) * | 2020-11-30 | 2021-03-12 | 中国银联股份有限公司 | Abnormal node identification method, device, equipment and medium |
| CN112581283A (en) * | 2020-12-28 | 2021-03-30 | 中国建设银行股份有限公司 | Method and device for analyzing and alarming business bank employee transaction behaviors |
| CN113011889A (en) * | 2021-03-10 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Account abnormity identification method, system, device, equipment and medium |
| CN113011889B (en) * | 2021-03-10 | 2023-09-15 | 腾讯科技（深圳）有限公司 | Account anomaly identification method, system, device, equipment and medium |
| CN113888153A (en) * | 2021-11-10 | 2022-01-04 | 建信金融科技有限责任公司 | Transfer abnormity prediction method, device, equipment and readable storage medium |
| CN113888153B (en) * | 2021-11-10 | 2022-11-29 | 建信金融科技有限责任公司 | Transfer abnormity prediction method, device, equipment and readable storage medium |
| CN114154507A (en) * | 2021-11-12 | 2022-03-08 | 中国银行股份有限公司 | Abnormal transfer monitoring method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| TWI690884B (en) | 2020-04-11 |
| TW201824135A (en) | 2018-07-01 |
| WO2018121113A1 (en) | 2018-07-05 |
| CN106803168B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106803168A (en) | A kind of abnormal transfer accounts method for detecting and device | |
| Carlin et al. | Fintech adoption across generations: Financial fitness in the information age | |
| CN106875078B (en) | Transaction risk detection method, device and equipment | |
| CN107281755B (en) | Detection model construction method and device, storage medium and terminal | |
| CN107807941B (en) | Information processing method and device | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| CN111062808B (en) | Credit card limit evaluation method, credit card limit evaluation device, computer equipment and storage medium | |
| CN111179089B (en) | Money laundering transaction identification method, device and equipment | |
| Shambaugh et al. | A clear advantage: The benefits of transparency to crisis recovery | |
| JP2021111261A (en) | Model generation device, model generation method, and recording medium | |
| CN110363407A (en) | Risk of fraud appraisal procedure and device based on user behavior track | |
| CN110335144B (en) | Personal electronic bank account security detection method and device | |
| Liu et al. | Improving fraud detection via hierarchical attention-based graph neural network | |
| Kemboi | Effect of financial technology on the financial performance of commercial banks in Kenya | |
| CN107944851A (en) | The management method of group's fund account, apparatus and system | |
| CN112884480A (en) | Method and device for constructing abnormal transaction identification model, computer equipment and medium | |
| CN107038185A (en) | A kind of method and device of Transaction Information processing | |
| CN117668375A (en) | Construction method of user group prediction model and user group prediction method | |
| Perera et al. | Interrelations between mobile banking service quality attributes, customer satisfaction and customer loyalty in domestic commercial banks in Sri Lanka | |
| CN112967062A (en) | User identity recognition method based on cautious degree | |
| KR20210110442A (en) | Method, apparatus and computer program for clustering cryptocurrency accounts using artificial intelligence | |
| Kang | Fraud Detection in Mobile Money Transactions Using Machine Learning | |
| CN112529623B (en) | Malicious user identification method, device and equipment | |
| US12001643B1 (en) | Age prediction of end users based on input device data | |
| US11915313B2 (en) | Using email history to estimate creditworthiness for applicants having insufficient credit history |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1238766 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |