CN110175924A - A kind of risk network establishing method and device - Google Patents
A kind of risk network establishing method and device Download PDFInfo
- Publication number
- CN110175924A CN110175924A CN201910284392.1A CN201910284392A CN110175924A CN 110175924 A CN110175924 A CN 110175924A CN 201910284392 A CN201910284392 A CN 201910284392A CN 110175924 A CN110175924 A CN 110175924A
- Authority
- CN
- China
- Prior art keywords
- risk
- information
- feature
- buyer
- advance
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
This specification provides a kind of risk network establishing method and device, first compares the order information compensated and predefined feature of risk information, filters out risk order according to comparing result；Order with the aggregation feature is determined as black sample order by the aggregation feature that buyer and seller are determined further according to different risk order informations；The illegal profit model for system of indemnitying in advance is extracted using the black sample order, trade mode is met into the buyer of the illegal profit model and seller is configured to risk network.So as to, for the air control processing mode indemnitied in advance, illegal person be avoided to extract compensation fund according to the risk network upgrade.
Description
Technical field
This specification is related to internet area more particularly to a kind of risk network establishing method and device.
Background technique
In order to guarantee the equity of consumer, transaction platform is proposed the service of indemnitying in advance, for example: order is nearly a kind of
The service of indemnitying in advance that transaction platform co-insurance mechanism releases, has purchased the transaction of order danger, if initiating dimension when buyer's reimbursement
Process is weighed, and seller does not complete this reimbursement in the given time, then indemnities in advance the pen with order danger clothes by insurance institution
The reimbursement that business ensures, then recovery is carried out to seller.And if this reimbursement is in vendor recovery success, it will cause transaction is flat
The property loss of platform or insurance institution.
It is currently, there are criminal while grasping buyer, seller both sides' account, illegally extracted in the service of indemnitying in advance
Fund, and still such risk behavior is identified and handled without a kind of preferable method at present.
Summary of the invention
In view of the above technical problems, this specification embodiment provides a kind of risk network establishing method and device, technical side
Case is as follows:
According to this specification embodiment in a first aspect, provide a kind of risk network establishing method, applied to indemnitying in advance
System, it is described indemnity in advance system for replace seller indemnity in advance reimbursement for qualified buyer, this method comprises:
After receiving global loss ratio exception information, in the order list indemnity in advance, according to time field
Acquisition of information meets the order of predetermined time condition；
Feature extraction, the buyer's feature that will be extracted are carried out to acquired order, seller's feature and product features are distinguished
It is matched in predefined feature of risk library, risk order is filtered out according to matching result；
The trading activity information and the generation of compensation stage generated according to the both parties of different risk orders in transactional stage
Compensation behavioural information determine the aggregation feature of buyer and seller, the order with the aggregation feature is determined as black sample
This order；
At least one illegal profit model for system of indemnitying in advance is extracted using the black sample order, with transaction
Mode meets the Buyer ID of the illegal profit model and seller's account is node, is with the illegal profit relationship of both parties
Side constructs risk network.
According to the second aspect of this specification embodiment, a kind of compensation risk inspection based on risk network establishing method is provided
Survey method, applied to the system of indemnitying in advance, it is described indemnity in advance system for replace seller pay in advance for qualified buyer
Reimbursement is paid, this method comprises:
After receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, the Bidder Information and vendor information of corresponding transaction are obtained；
The Bidder Information is matched in risk network with vendor information, according to the buyer and seller in risk
Correlation degree and degree of risk in network calculate single risk probability of currently reporting a case to the security authorities.
According to the third aspect of this specification embodiment, a kind of risk network struction device is provided, applied to indemnitying in advance
System, it is described indemnity in advance system for replace seller indemnity in advance reimbursement for qualified buyer, which includes:
Order obtains module: after receiving global loss ratio exception information, in the order column indemnity in advance
In table, the order for meeting predetermined time condition is obtained according to time field information；
Risk screening module: for carrying out feature extraction, the buyer's feature that will be extracted, Mai Jiate to acquired order
Sign is matched in predefined feature of risk library respectively with product features, filters out risk order according to matching result；
Sample acquisition module: for being believed according to the both parties of different risk orders in the trading activity that transactional stage generates
Breath and the compensation behavioural information for compensating stage generation determine the aggregation feature of buyer and seller, will have the aggregation feature
Order be determined as black sample order；
Network struction module: at least one for the non-of system of indemnitying in advance for being extracted using the black sample order
Method profit model, the Buyer ID for meeting the illegal profit model using trade mode and seller's account are double to buy and sell as node
The illegal profit relationship of side is side, constructs risk network.
According to the fourth aspect of this specification embodiment, a kind of compensation risk inspection based on risk network struction device is provided
Survey device, applied to the system of indemnitying in advance, it is described indemnity in advance system for replace seller pay in advance for qualified buyer
Reimbursement is paid, which includes:
Data obtaining module: after receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, the buyer of corresponding transaction is obtained
Information and vendor information；
Risk Calculation module: for matching the Bidder Information in risk network with vendor information, according to institute
It states the correlation degree and degree of risk of buyer and seller in risk network and calculates single risk probability of currently reporting a case to the security authorities.
According to the 5th of this specification embodiment aspect, a kind of computer equipment is provided, including memory, processor and deposit
Store up the computer program that can be run on a memory and on a processor, wherein the processor is realized when executing described program
A kind of risk network establishing method, applied to the system of indemnitying in advance, it is described indemnity in advance system for replace seller to meet item
The buyer of part indemnities in advance reimbursement, this method comprises:
After receiving global loss ratio exception information, in the order list indemnity in advance, according to time field
Acquisition of information meets the order of predetermined time condition；
Feature extraction, the buyer's feature that will be extracted are carried out to acquired order, seller's feature and product features are distinguished
It is matched in predefined feature of risk library, risk order is filtered out according to matching result；
The trading activity information and the generation of compensation stage generated according to the both parties of different risk orders in transactional stage
Compensation behavioural information determine the aggregation feature of buyer and seller, the order with the aggregation feature is determined as black sample
This order；
At least one illegal profit model for system of indemnitying in advance is extracted using the black sample order, with transaction
Mode meets the Buyer ID of the illegal profit model and seller's account is node, is with the illegal profit relationship of both parties
Side constructs risk network.
Technical solution provided by this specification embodiment first believes the order information compensated and predefined feature of risk
Breath compares, and filters out risk order according to comparing result；Buyer and seller are determined further according to different risk order informations
Order with the aggregation feature is determined as black sample order by aggregation feature；It is extracted using the black sample order
Out for the illegal profit model for system of indemnitying in advance, trade mode is met to buyer and the seller's structure of the illegal profit model
It builds as risk network.So as to, for the air control processing mode indemnitied in advance, avoid illegally dividing according to the risk network upgrade
Sub-set takes compensation fund.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
This specification embodiment can be limited.
In addition, any embodiment in this specification embodiment does not need to reach above-mentioned whole effects.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification embodiment for those of ordinary skill in the art can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is a kind of flow chart of the risk network establishing method shown in one exemplary embodiment of this specification；
Fig. 2 is a kind of schematic diagram of the illegal profit model shown in one exemplary embodiment of this specification；
Fig. 3 is a kind of schematic diagram of the risk network shown in one exemplary embodiment of this specification；
Fig. 4 is a kind of schematic diagram of the spread risk network shown in one exemplary embodiment of this specification；
Fig. 5 is another flow chart of the compensation risk checking method shown in one exemplary embodiment of this specification；
Fig. 6 is a kind of schematic diagram of the risk network struction device shown in one exemplary embodiment of this specification；
Fig. 7 is a kind of schematic diagram of the compensation risk supervision device shown in one exemplary embodiment of this specification；
Fig. 8 is a kind of schematic diagram for buyer seller's method for digging shown in one exemplary embodiment of this specification；
Fig. 9 is a kind of structural schematic diagram of computer equipment shown in one exemplary embodiment of this specification.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with this specification.On the contrary, they are only and such as institute
The example of the consistent device and method of some aspects be described in detail in attached claims, this specification.
It is only to be not intended to be limiting this explanation merely for for the purpose of describing particular embodiments in the term that this specification uses
Book.The "an" of used singular, " described " and "the" are also intended to packet in this specification and in the appended claims
Most forms are included, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein is
Refer to and includes that one or more associated any or all of project listed may combine.
It will be appreciated that though various information may be described using term first, second, third, etc. in this specification, but
These information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not taking off
In the case where this specification range, the first information can also be referred to as the second information, and similarly, the second information can also be claimed
For the first information.Depending on context, word as used in this " if " can be construed to " ... when " or
" when ... " or " in response to determination ".
In order to guarantee the equity of consumer, transaction platform is proposed the service of indemnitying in advance, for example: order is nearly a kind of
The service of indemnitying in advance that transaction platform co-insurance mechanism releases, has purchased the transaction of order danger, if initiating dimension when buyer's reimbursement
Process is weighed, and seller does not complete this reimbursement in the given time, then indemnities in advance the pen with order danger clothes by insurance institution
The reimbursement that business ensures, then recovery is carried out to seller.And if this reimbursement is in vendor recovery success, it will cause transaction is flat
The property loss of platform or insurance institution.
It is currently, there are criminal while grasping buyer, seller both sides' account, illegally extracted in the service of indemnitying in advance
Fund, and still such risk behavior is identified and handled without a kind of preferable method at present.
In view of the above problems, this specification embodiment provides a kind of risk network establishing method, and a kind of for executing
The risk network struction device of this method.The method that this specification embodiment is mentioned is mainly used in the system of indemnitying in advance, described
System of indemnitying in advance is used to replace seller to be that qualified buyer indemnities in advance reimbursement.
The risk network establishing method that the present embodiment is related to is described in detail below, shown in Figure 1, this method can
With the following steps are included:
S101, after receiving global loss ratio exception information, in the order list indemnity in advance, according to the time
Field information obtains the order for meeting predetermined time condition；
The service of indemnitying in advance is usually to be ensured in the form of insurance to transaction, is nearly lifted with the order of Taobao's platform
Example explanation: after Taobao buyer is traded with the seller with " consumer protection's service " by Alipay service, if because of this
Transaction leads to buyer's damage of the rights and interests, and in the case where buyer directly requires seller's processing to have no resolution, buyer has the right trading successfully
The right-safeguarding that backward Taobao initiates the transaction is complained, and proposes to compensate application.When Taobao determines that buyer compensates according to dependency rule
After application is set up, then reimbursement is directly compensated to the waiting that buyer is avoided to buyer, better user experience.Compensation while unlatching pair
In the recovery of seller.If seller is not the black production molecule for illegally extracting fund, guarantee fund that can be provided from seller etc. recovery
Success, but illegally extract the black production vendor of fund usually can not recovery success, cause the loss of compensation fund.
Usually, in the process of indemnitying in advance of transaction platform, the integrated information for both parties is needed to generate three
A main audit stage, be respectively using indemnity in advance to transaction ensured by the audit (money of seller's purchase order danger
Matter audit), buyer initiate right-safeguarding by audit, compensation audit after checking to right-safeguarding information, detailed process is as follows:
1) it is appraised and decided for the transaction for buying service of indemnitying in advance, according to the self information and Transaction Information of purchase user
Judge that the user's services purchase condition when whether transaction meets to indemnity in advance, if eligible, generates declaration form；
2) request of reporting a case to the security authorities that buyer surprisingly initiates for transaction is received, judges whether the buyer meets the condition of reporting a case to the security authorities, if
It is eligible, then receive described in report a case to the security authorities request and generating report a case to the security authorities list；
3) whether leading compensation is met according to order information, logistics information and buying request of reporting a case to the security authorities described in vendor information comprehensive descision
The condition of paying is compensated if eligible and generates Claims Resolution list.
Specifically, the present embodiment is monitored global loss ratio, i.e., calculates primary global loss ratio at predetermined time intervals,
Whether it is abnormal with the real-time loss ratio of determination.
Under normal circumstances, loss ratio refers to that loss ratio is higher than average level or preset threshold extremely, this showed in the past
Behavior of indemnitying in advance in a period of time is more, and the calculating of loss ratio is possible, and there are many modes, such as:
Global loss ratio=(indemnity expenditure ÷ premium incomes) × 100%, or,
Global loss ratio=(compensating order numbers ÷ trade order number) × 100%, etc.
S102 carries out feature extraction, the buyer's feature that will be extracted, seller's feature and product features to acquired order
It is matched in predefined feature of risk library respectively, risk order is filtered out according to matching result；
After leading loss ratio is abnormal, system starts to carry out data extraction to order.Order herein refers to sending out
Gave birth to the trade order indemnitied in advance.Buyer's feature in these orders is compared with predefined risk buyer feature,
Seller's feature in these orders is compared with predefined risk seller feature, by these orders product features with
Predefined risk product features compare.And then the risky order of tool can be filtered out according to comparing result.
To each feature for example:
Predefined risk buyer feature can include: buyer has the lower single act of batch, lower single time of buyer is gathered in together
One period, the right-safeguarding reason that the return of goods right-safeguarding rate of buyer is filled in higher than preset threshold and/or buyer have repeatability etc..
Predefined risk seller feature can include: the seller shop title that same time period is indemnitied in advance is close, sells
Inflow and outflow of too simple, seller shop the commodity amount less than preset threshold and/or seller shop fund is fitted up in shop by family
Frequency is higher than preset threshold etc..
Predefined risk product features can include: there are rarely used word and/or the description of commodity details page are excessively simple for commodity title
It is single.
Wherein, predefined risk buyer feature, risk seller feature and product features can be according to historical datas and warp
Test and summarize and add, the present embodiment to specific feature type without limitation.
After features described above and predefined feature of risk are compared, determine have risky order according to comparing result
And it is determined further.Wherein, determine that having risky order can be accomplished in several ways, and illustrate according to comparing result
Illustrate two of them:
A) buyer in single order, seller, when the feature of risk that commodity meet in total is on predetermined number, by this pen
Order is determined as risky order；
B) weighted value of different feature of risk is set, if the Risk rated ratio value that single order adds up is on preset threshold
When, this order is determined as risky order.
S103, the trading activity information generated according to the both parties of different risk orders in transactional stage and is compensated the stage
The compensation behavioural information of generation determines the aggregation feature of buyer and seller, and the order with the aggregation feature is determined as
Black sample order；
Specifically, after obtaining risk order, it can extract the document letter that different risk orders generate in process of indemnitying in advance
Breath, in the present embodiment, the document information may include insurance document information, document information of reporting a case to the security authorities and Claims Resolution document information；
Specifically, means of payment information can be extracted from insurance document information, time of payment information, logistics information and in advance
The service of compensation comes into force temporal information etc.；The right-safeguarding temporal information that buyer submits, right-safeguarding reason letter are extracted from document information of reporting a case to the security authorities
Whether breath, right-safeguarding amount information and need information etc. of returning goods；Right-safeguarding, which is extracted, from Claims Resolution document information passes through temporal information and reason
Pay for amount information etc.；
By the common trait of the available illegal compensation order of these indication informations extracted, for example: exist
The aggregation feature of generation of multiple and different buyer sellers on same commodity, there are multiple and different buyer sellers in the Claims Resolution time
The aggregation feature of upper generation, the aggregation feature generated on amount for which loss settled there are multiple and different buyer sellers etc., and sell
The exception of logistics information present in abnormal behavior, transaction, trading activity track exception are paid out existing for family, seller's account activity is different
Often etc..Risk order with these common traits is drawn a circle to approve as black sample order.
S104 extracts at least one illegal profit model for system of indemnitying in advance using the black sample order,
The Buyer ID and seller's account for meeting the illegal profit model using trade mode is nodes, with the illegal profit of both parties
Relationship is side, constructs risk network.
After drawing a circle to approve black sample order, needle is extracted using these behavioural informations of black sample order in process of indemnitying in advance
To the illegal profit model for the system of indemnitying in advance, generally there are many forms for such illegal profit model.The present embodiment is to wherein
A kind of illegal profit model is illustrated: with reference to Fig. 2, which is divided into four steps, as follows:
1) black production buyer lifts right-safeguarding request for black production seller；
2) the black reimbursement for producing seller's request of the right-safeguarding simultaneously and proposing；
3) black production seller keeps account balance insufficient, and can not withhold state, and the duration is more than 24 hours；
4) order danger side (ant insurance) after 24 hours, indemnities in advance to black production buyer.
As can be seen that the present embodiment is to be extracted in the past period illegally to divide according to the risk order of the past period
The main illegal profit model to be used of son can be monitored summary for the real-time sexual behaviour of illegal person behavior.And according to
The current illegal profit model real-time upgrading risk control system.
Referring to Fig. 3, after extracting illegal profit model, the buyer of the illegal profit model is met with trade mode
Account and seller's account are node, using the illegal profit relationship of both parties as side, construct risk network.Further, in addition to
Outside illegal profit model characteristic information, other characteristic informations of buyer seller also can be used as the building element of risk network.Such as:
If seller buyer is connected to the same WIFI, the illegal relationship weight that can increase this two side can behave as in risk network
Increase the weight on the side connected between buyer seller's node.
Fig. 4 is participated in, after constructing risk network, further the risk network spread with the number of acknowledging a debt, i.e., to risk net
Buyer ID and seller's account carry out information excavating in network, determine other accounts that the holder of the account is registered, are based on
Other described accounts are diffused the risk network.It specifically, can be for any account in risk network, described in acquisition
Other described accounts are determined as the new node of the risk network by other accounts that the holder of account is registered.
Based on the above-mentioned risk network constructed, this specification also provides a kind of compensation risk inspection based on the risk network
Survey method, applied to the system of indemnitying in advance, it is described indemnity in advance system for replace seller pay in advance for qualified buyer
Reimbursement is paid, referring to Fig. 5, the method includes
S501 after receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, obtains the Bidder Information of corresponding transaction and sells letter from home
Breath；
S502 matches the Bidder Information with vendor information, according to the buyer and seller in risk network
Correlation degree and degree of risk in risk network calculate single risk probability of currently reporting a case to the security authorities.
If calculated risk probability is higher than preset threshold, can take to single progress intercept process of reporting a case to the security authorities, or limitation
The service function of indemnitying in advance etc. of single both parties of reporting a case to the security authorities.
Specifically, when carrying out risk control, DistRep algorithm can be introduced.
It is existing between the two to protect if seller and buyer are abstracted as node by we based on the business characteristic of order danger
It is singly abstracted as side, with reference to Fig. 8, the relationship between seller and buyer can be indicated with graph model, it can be seen that order danger
Air control can be converted into side forecasting problem.Judge whether this transaction can be risky based on the dealing man of a transaction.
The interactive relation that graph model not only can effectively depict buyer and seller passes through centre referring to Fig. 8
Node, moreover it is possible to which, well buyer and buyer, the hidden relationship between seller and seller is disclosed.Therefore, graph model
It can be used for coping with the hidden crime of Hei Chan clique to be difficult to be found, means often convert the characteristics of updating.
Specifically, G=<N can be enabled, E>, wherein N indicates that the node set of figure G, E indicate the set on the side of link node,For side eij∈E,eij=< yij,ni,nj>, wherein niIndicate node i, njIndicate node j, yijIndicate eij
It whether is arbitrage side, value is 0 or 1.According to the figure G at current t0 moment, predict to increase side e in future t1 moment G newlyijWhether
For arbitrage side yijLikelihood probability, that is, give deckle eij, seek p (yij∣eij).Joined using the method solving model of maximal possibility estimation
Number estimation problem, i.e. the side e for observingij, the log probability of maximized y^, specifically, which can indicate such as
Under:
Corresponding to above method embodiment, this specification embodiment also provides a kind of risk network struction device, referring to Fig. 6
It is shown, the apparatus may include: relationship determination module 610, account screening module 620 and group determination module 630；
Order obtains module 610: after receiving global loss ratio exception information, in the order indemnity in advance
In list, the order for meeting predetermined time condition is obtained according to time field information；
Risk screening module 620: for carrying out feature extraction to acquired order, the buyer's feature that will be extracted is sold
Family's feature is matched in predefined feature of risk library respectively with product features, is filtered out risk according to matching result and is ordered
It is single；
Sample acquisition module 630: the transaction row generated for the both parties according to different risk orders in transactional stage
The aggregation feature that buyer and seller are determined for the compensation behavioural information that information and compensation stage generate, will have the aggregation
The order of feature is determined as black sample order；
Network struction module 640: at least one for system of indemnitying in advance for being extracted using the black sample order
Illegal profit model, the Buyer ID for meeting the illegal profit model using trade mode and seller's account is nodes, to buy
The illegal profit relationship for selling both sides is side, constructs risk network.
Based on the above-mentioned risk network constructed, this specification also provides a kind of compensation risk inspection based on the risk network
Survey device, applied to the system of indemnitying in advance, it is described indemnity in advance system for replace seller pay in advance for qualified buyer
Reimbursement is paid, referring to Fig. 7, described device includes:
Data obtaining module 710: after receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, buying for corresponding transaction is obtained
Family's information and vendor information；
Risk Calculation module 720: for the Bidder Information to be matched in risk network with vendor information, according to
The correlation degree and degree of risk of the buyer and seller in risk network calculate single risk probability of currently reporting a case to the security authorities.
This specification embodiment also provides a kind of computer equipment, includes at least memory, processor and is stored in
On reservoir and the computer program that can run on a processor, wherein processor realizes aforementioned risk net when executing described program
Network construction method, the method include at least:
After receiving global loss ratio exception information, in the order list indemnity in advance, according to time field
Acquisition of information meets the order of predetermined time condition；
Feature extraction, the buyer's feature that will be extracted are carried out to acquired order, seller's feature and product features are distinguished
It is matched in predefined feature of risk library, risk order is filtered out according to matching result；
The trading activity information and the generation of compensation stage generated according to the both parties of different risk orders in transactional stage
Compensation behavioural information determine the aggregation feature of buyer and seller, the order with the aggregation feature is determined as black sample
This order；
At least one illegal profit model for system of indemnitying in advance is extracted using the black sample order, with transaction
Mode meets the Buyer ID of the illegal profit model and seller's account is node, is with the illegal profit relationship of both parties
Side constructs risk network.
This specification embodiment also provides a kind of computer equipment, includes at least memory, processor and is stored in
On reservoir and the computer program that can run on a processor, wherein processor is realized when executing described program is based on aforementioned wind
The compensation risk checking method of dangerous network establishing method, the method include at least:
After receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, the Bidder Information and vendor information of corresponding transaction are obtained；
The Bidder Information is matched in risk network with vendor information, according to the buyer and seller in risk
Correlation degree and degree of risk in network calculate single risk probability of currently reporting a case to the security authorities.
Fig. 9 shows one kind provided by this specification embodiment and more specifically calculates device hardware structural schematic diagram,
The equipment may include: processor 1010, memory 1020, input/output interface 1030, communication interface 1040 and bus
1050.Wherein processor 1010, memory 1020, input/output interface 1030 and communication interface 1040 are real by bus 1050
The now communication connection inside equipment each other.
Processor 1010 can use general CPU (Central Processing Unit, central processing unit), micro- place
Reason device, application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or one
Or the modes such as multiple integrated circuits are realized, for executing relative program, to realize technical side provided by this specification embodiment
Case.
Memory 1020 can use ROM (Read Only Memory, read-only memory), RAM (Random Access
Memory, random access memory), static storage device, the forms such as dynamic memory realize.Memory 1020 can store
Operating system and other applications are realizing technical solution provided by this specification embodiment by software or firmware
When, relevant program code is stored in memory 1020, and execution is called by processor 1010.
Input/output interface 1030 is for connecting input/output module, to realize information input and output.Input and output/
Module can be used as component Configuration (not shown) in a device, can also be external in equipment to provide corresponding function.Wherein
Input equipment may include keyboard, mouse, touch screen, microphone, various kinds of sensors etc., output equipment may include display,
Loudspeaker, vibrator, indicator light etc..
Communication interface 1040 is used for connection communication module (not shown), to realize the communication of this equipment and other equipment
Interaction.Wherein communication module can be realized by wired mode (such as USB, cable etc.) and be communicated, can also be wirelessly
(such as mobile network, WIFI, bluetooth etc.) realizes communication.
Bus 1050 include an access, equipment various components (such as processor 1010, memory 1020, input/it is defeated
Outgoing interface 1030 and communication interface 1040) between transmit information.
It should be noted that although above equipment illustrates only processor 1010, memory 1020, input/output interface
1030, communication interface 1040 and bus 1050, but in the specific implementation process, which can also include realizing normal fortune
Other assemblies necessary to row.In addition, it will be appreciated by those skilled in the art that, it can also be only comprising real in above equipment
Component necessary to existing this specification example scheme, without including all components shown in figure.
This specification embodiment also provides a kind of computer readable storage medium, is stored thereon with computer program, the journey
Risk network establishing method above-mentioned is realized when sequence is executed by processor, the method includes at least:
After receiving global loss ratio exception information, in the order list indemnity in advance, according to time field
Acquisition of information meets the order of predetermined time condition；
Feature extraction, the buyer's feature that will be extracted are carried out to acquired order, seller's feature and product features are distinguished
It is matched in predefined feature of risk library, risk order is filtered out according to matching result；
The trading activity information and the generation of compensation stage generated according to the both parties of different risk orders in transactional stage
Compensation behavioural information determine the aggregation feature of buyer and seller, the order with the aggregation feature is determined as black sample
This order；
At least one illegal profit model for system of indemnitying in advance is extracted using the black sample order, with transaction
Mode meets the Buyer ID of the illegal profit model and seller's account is node, is with the illegal profit relationship of both parties
Side constructs risk network.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize this specification scheme.Those of ordinary skill in the art are not
In the case where making the creative labor, it can understand and implement.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.A kind of typically to realize that equipment is computer, the concrete form of computer can
To be personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
In device, navigation equipment, E-mail receiver/send equipment, game console, tablet computer, wearable device or these equipment
The combination of any several equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.The apparatus embodiments described above are merely exemplary, wherein described be used as separate part description
Module may or may not be physically separated, can be each module when implementing this specification example scheme
Function realize in the same or multiple software and or hardware.Can also select according to the actual needs part therein or
Person's whole module achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not the case where making the creative labor
Under, it can it understands and implements.
The above is only the specific embodiment of this specification embodiment, it is noted that for the general of the art
For logical technical staff, under the premise of not departing from this specification embodiment principle, several improvements and modifications can also be made, this
A little improvements and modifications also should be regarded as the protection scope of this specification embodiment.
Claims (23)
1. a kind of risk network establishing method, applied to the system of indemnitying in advance, the system of indemnitying in advance for being instead of seller
Qualified buyer indemnities in advance reimbursement, which comprises
After receiving global loss ratio exception information, in the order list indemnity in advance, according to time field information
Obtain the order for meeting predetermined time condition；
Feature extraction is carried out to acquired order, the buyer's feature that will be extracted, seller's feature is with product features respectively pre-
It is matched in the feature of risk library of definition, risk order is filtered out according to matching result；
According to the compensation of trading activity information and the generation of compensation stage that the both parties of different risk orders generate in transactional stage
Behavioural information is paid, the aggregation feature that both parties have on same commodity is extracted, by ordering with the aggregation feature
Singly it is determined as black sample order；
At least one illegal profit model for system of indemnitying in advance is extracted using the black sample order, with trade mode
The Buyer ID and seller's account for meeting the illegal profit model are node, using the illegal profit relationship of both parties as side,
Construct risk network.
2. the method as described in claim 1, after the construction risk network, further includes:
For any account in risk network, obtain other accounts that the holder of the account is registered, will it is described other
Account is determined as the new node of the risk network.
3. the method as described in claim 1, described to detect that global loss ratio is abnormal, comprising:
The situation of change of monitoring indemnity expenditure information and premium incomes information, calculates global loss ratio according to the information monitored；
If the overall situation loss ratio is higher than preset threshold, it is determined that the overall situation loss ratio is abnormal.
4. the method as described in claim 1, the buyer's feature that will be extracted carries out in predefined feature of risk library
Matching, comprising:
The buyer's feature extracted is matched in predefined feature of risk library, the buyer's feature extracted described in determination
With the matching degree of risk buyer's feature, the risk buyer feature includes: that buyer has batch lower single act, buyer places an order
The right-safeguarding reason that time is gathered in the same period, the return of goods right-safeguarding rate of buyer is higher than preset threshold and/or buyer fills in has repetition
Property.
5. the method as described in claim 1, the seller's feature that will be extracted carries out in predefined feature of risk library
Matching, comprising:
The seller's feature extracted is matched in predefined feature of risk library, the seller's feature extracted described in determination
With the matching degree of risk seller's feature, the risk seller feature includes: the seller shop that same time period is indemnitied in advance
Paving title is close, seller shop is fitted up too simple, seller shop commodity amount and provided less than preset threshold and/or seller shop
The inflow and outflow frequency of gold is higher than preset threshold.
6. the method as described in claim 1, the product features that will be extracted carry out in predefined feature of risk library
Matching, comprising:
The product features extracted are matched in predefined feature of risk library, the product features extracted described in determination
With the matching degree of risk product features, the risk product features include: that there are rarely used word and/or commodity details for commodity title
Page description is too simple.
7. the method as described in claim 1, the process of indemnitying in advance, comprising:
It is appraised and decided for the transaction for buying service of indemnitying in advance, institute is judged according to the self information of purchase user and Transaction Information
That states user services purchase condition when whether transaction meets to indemnity in advance, if eligible, generates declaration form；
The request of reporting a case to the security authorities that user surprisingly initiates for transaction is received, judges whether the user meets the condition of reporting a case to the security authorities, if meeting item
Part, then receive described in report a case to the security authorities request and generating report a case to the security authorities list；
According to order information, logistics information and buy whether request of reporting a case to the security authorities described in vendor information comprehensive descision meets item of indemnitying in advance
Part is compensated if eligible and generates Claims Resolution list.
8. the method as described in claim 1, the friendship that the both parties according to different risk orders generate in transactional stage
Easy behavioural information and the compensation behavioural information for compensating stage generation, it is special to extract the aggregation that both parties have on same commodity
Sign, comprising:
Extract the document information that different risk orders generate in process of indemnitying in advance, the document information include insurance policy it is believed that
Breath, document information of reporting a case to the security authorities and Claims Resolution document information；
Means of payment information, time of payment information are extracted from insurance document information, logistics information and the service of indemnitying in advance come into force
Temporal information；
The right-safeguarding temporal information that buyer submits is extracted from document information of reporting a case to the security authorities, right-safeguarding cause information and is at right-safeguarding amount information
It is no to need information of returning goods；
Right-safeguarding, which is extracted, from Claims Resolution document information passes through temporal information and amount for which loss settled information；
According to the every terms of information extracted, aggregation feature that firm bargain both sides have on same commodity.
9. a kind of compensation risk checking method based on risk network establishing method described in claim 1, applied to indemnitying in advance
System, it is described indemnity in advance system for replace seller indemnity in advance reimbursement for qualified buyer, which comprises
After receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, the Bidder Information and vendor information of corresponding transaction are obtained；
The Bidder Information is matched in risk network with vendor information, according to the buyer and seller in risk network
In correlation degree and degree of risk calculating currently report a case to the security authorities single risk probability.
10. method as claimed in claim 9, after the risk probability for calculating current insurance policy, further includes:
If calculated risk probability is higher than preset threshold, to single progress intercept process of reporting a case to the security authorities.
11. method as claimed in claim 10, after the risk probability for calculating current insurance policy, further includes:
If calculated risk probability is higher than preset threshold, indemnitying in advance for single both parties of reporting a case to the security authorities described in limitation services function
Energy.
12. a kind of risk network struction device, applied to the system of indemnitying in advance, the system of indemnitying in advance for being instead of seller
Qualified buyer indemnities in advance reimbursement, and described device includes:
Order obtains module: after receiving global loss ratio exception information, in the order list indemnity in advance,
The order for meeting predetermined time condition is obtained according to time field information；
Risk screening module: for carrying out feature extraction to acquired order, the buyer's feature that will be extracted, seller's feature with
Product features are matched in predefined feature of risk library respectively, filter out risk order according to matching result；
Sample acquisition module: trading activity information for being generated according to the both parties of different risk orders in transactional stage and
The compensation behavioural information that the compensation stage generates extracts the aggregation feature that both parties have on same commodity, will have institute
The order for stating aggregation feature is determined as black sample order；
Network struction module: for extracting at least one being illegally full of for system of indemnitying in advance using the black sample order
Sharp mode, the Buyer ID for meeting the illegal profit model using trade mode and seller's account is nodes, with both parties
Illegal profit relationship is side, constructs risk network.
13. device as claimed in claim 12, after the construction risk network, further includes:
For any account in risk network, obtain other accounts that the holder of the account is registered, will it is described other
Account is determined as the new node of the risk network.
14. device as claimed in claim 12, described to detect that global loss ratio is abnormal, comprising:
The situation of change of monitoring indemnity expenditure information and premium incomes information, calculates global loss ratio according to the information monitored；
If the overall situation loss ratio is higher than preset threshold, it is determined that the overall situation loss ratio is abnormal.
15. device as claimed in claim 12, the buyer's feature that will be extracted in predefined feature of risk library into
Row matching, comprising:
The buyer's feature extracted is matched in predefined feature of risk library, the buyer's feature extracted described in determination
With the matching degree of risk buyer's feature, the risk buyer feature includes: that buyer has batch lower single act, buyer places an order
The right-safeguarding reason that time is gathered in the same period, the return of goods right-safeguarding rate of buyer is higher than preset threshold and/or buyer fills in has repetition
Property.
16. device as claimed in claim 12, the seller's feature that will be extracted in predefined feature of risk library into
Row matching, comprising:
The seller's feature extracted is matched in predefined feature of risk library, the seller's feature extracted described in determination
With the matching degree of risk seller's feature, the risk seller feature includes: the seller shop that same time period is indemnitied in advance
Paving title is close, seller shop is fitted up too simple, seller shop commodity amount and provided less than preset threshold and/or seller shop
The inflow and outflow frequency of gold is higher than preset threshold.
17. device as claimed in claim 12, the product features that will be extracted in predefined feature of risk library into
Row matching, comprising:
The product features extracted are matched in predefined feature of risk library, the product features extracted described in determination
With the matching degree of risk product features, the risk product features include: that there are rarely used word and/or commodity details for commodity title
Page description is too simple.
18. device as claimed in claim 12, the process of indemnitying in advance, comprising:
It is appraised and decided for the transaction for buying service of indemnitying in advance, institute is judged according to the self information of purchase user and Transaction Information
That states user services purchase condition when whether transaction meets to indemnity in advance, if eligible, generates declaration form；
The request of reporting a case to the security authorities that user surprisingly initiates for transaction is received, judges whether the user meets the condition of reporting a case to the security authorities, if meeting item
Part, then receive described in report a case to the security authorities request and generating report a case to the security authorities list；
According to order information, logistics information and buy whether request of reporting a case to the security authorities described in vendor information comprehensive descision meets item of indemnitying in advance
Part is compensated if eligible and generates Claims Resolution list.
19. device as claimed in claim 12, what the both parties according to different risk orders generated in transactional stage
Trading activity information and the compensation behavioural information for compensating stage generation extract the aggregation that both parties have on same commodity
Feature, comprising:
Extract the document information that different risk orders generate in process of indemnitying in advance, the document information include insurance policy it is believed that
Breath, document information of reporting a case to the security authorities and Claims Resolution document information；
Means of payment information, time of payment information are extracted from insurance document information, logistics information and the service of indemnitying in advance come into force
Temporal information；
The right-safeguarding temporal information that buyer submits is extracted from document information of reporting a case to the security authorities, right-safeguarding cause information and is at right-safeguarding amount information
It is no to need information of returning goods；
Right-safeguarding, which is extracted, from Claims Resolution document information passes through temporal information and amount for which loss settled information；
According to the every terms of information extracted, aggregation feature that firm bargain both sides have on same commodity.
20. a kind of compensation risk supervision device based on risk network struction device described in claim 12 is applied to pay in advance
The system of paying, it is described indemnity in advance system for replace seller indemnity in advance reimbursement for qualified buyer, described device includes:
Data obtaining module: after receiving the list of reporting a case to the security authorities that buyer submits for reimbursement, the Bidder Information of corresponding transaction is obtained
With vendor information；
Risk Calculation module: it for matching the Bidder Information in risk network with vendor information, is bought according to described
The correlation degree and degree of risk of family and seller in risk network calculate single risk probability of currently reporting a case to the security authorities.
21. device as claimed in claim 20, after the risk probability for calculating current insurance policy, further includes:
If calculated risk probability is higher than preset threshold, to single progress intercept process of reporting a case to the security authorities.
22. device as claimed in claim 21, after the risk probability for calculating current insurance policy, further includes:
If calculated risk probability is higher than preset threshold, what single both parties of reporting a case to the security authorities described in limitation obtained, which indemnity in advance, services function
Energy.
23. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, wherein the processor realizes the method as described in claim 1 when executing described program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910284392.1A CN110175924B (en) | 2019-04-10 | 2019-04-10 | Risk network construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910284392.1A CN110175924B (en) | 2019-04-10 | 2019-04-10 | Risk network construction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110175924A true CN110175924A (en) | 2019-08-27 |
| CN110175924B CN110175924B (en) | 2023-01-20 |
Family
ID=67689591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910284392.1A Active CN110175924B (en) | 2019-04-10 | 2019-04-10 | Risk network construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175924B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743697A (en) * | 2020-08-21 | 2021-12-03 | 西安京迅递供应链科技有限公司 | Risk alarm method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987919A (en) * | 2006-10-30 | 2007-06-27 | 孙启亮 | Exciting method and system for enterprise credit in electronic business |
| WO2016172938A1 (en) * | 2015-04-30 | 2016-11-03 | 深圳市银信网银科技有限公司 | Network transaction refunding method and system |
| CN106600353A (en) * | 2015-10-19 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Online transaction settlement processing method and device |
-
2019
- 2019-04-10 CN CN201910284392.1A patent/CN110175924B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987919A (en) * | 2006-10-30 | 2007-06-27 | 孙启亮 | Exciting method and system for enterprise credit in electronic business |
| WO2016172938A1 (en) * | 2015-04-30 | 2016-11-03 | 深圳市银信网银科技有限公司 | Network transaction refunding method and system |
| CN106600353A (en) * | 2015-10-19 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Online transaction settlement processing method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743697A (en) * | 2020-08-21 | 2021-12-03 | 西安京迅递供应链科技有限公司 | Risk alarm method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175924B (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11443324B1 (en) | Systems and method for providing card account controls and purchase impact information | |
| US11727407B2 (en) | Systems and methods for detecting out-of-pattern transactions | |
| US20220027915A1 (en) | Systems and methods for processing transactions using customized transaction classifiers | |
| US20160267406A1 (en) | Systems and Methods for Rating Merchants | |
| US20090018955A1 (en) | Method and apparatus for providing user access to payment methods | |
| US20090018923A1 (en) | Method and apparatus for recommending a payment method in a transaction | |
| KR101794221B1 (en) | System and method for providing calculation of online sellers | |
| US20220188801A1 (en) | Cryptocurrency payment and distribution platform | |
| US11386488B2 (en) | System and method for combining product specific data with customer and merchant specific data | |
| CN110009365B (en) | User group detection method, device and equipment for abnormally transferring electronic assets | |
| CN112118116A (en) | System and method for recommending merchant discussion groups based on settings in an e-commerce platform | |
| US20240070236A1 (en) | Asset-class backed tokenization platform | |
| EP4149046A1 (en) | Systems and methods for blockchain network congestion-adaptive digital asset event handling | |
| JP2019185595A (en) | Information processor, method for processing information, information processing program, determination device, method for determination, and determination program | |
| JP2011159225A (en) | Credit transaction system and method of the same | |
| US20210142316A1 (en) | Gift card management system | |
| JP6294193B2 (en) | Transaction management system and transaction management method | |
| JP2002092328A (en) | Stock dealing system and stock dealing method | |
| CN110175924A (en) | A kind of risk network establishing method and device | |
| CN110633966A (en) | Block chain-based contract securitization method and device | |
| US20220230178A1 (en) | Computer-implemented systems and methods for detecting fraudulent activity | |
| CN111222924A (en) | Internet trading platform uncertainty evaluation filtering system based on normal distribution probability density function | |
| CN116596665B (en) | Data processing method, device, equipment and storage medium | |
| US20240144654A1 (en) | System and method for automated construction of data sets for retraining a machine learning model | |
| US11756057B2 (en) | Method and system for estimating vulnerability and systemic importance in transaction networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |