CN110175924B - Risk network construction method and device - Google Patents
Risk network construction method and device Download PDFInfo
- Publication number
- CN110175924B CN110175924B CN201910284392.1A CN201910284392A CN110175924B CN 110175924 B CN110175924 B CN 110175924B CN 201910284392 A CN201910284392 A CN 201910284392A CN 110175924 B CN110175924 B CN 110175924B
- Authority
- CN
- China
- Prior art keywords
- risk
- information
- seller
- buyer
- features
- 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.)
- Active
Links
Images
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present specification provides a risk network construction method and device, firstly comparing the paid order information with the predefined risk characteristic information, and screening out the risk order according to the comparison result; determining the aggregative characteristics of the buyer and the seller according to different risk order information, and determining the order with the aggregative characteristics as a black sample order; and extracting an illegal profit mode aiming at the advanced payment system by using the black sample order, and constructing buyers and sellers of which the transaction modes accord with the illegal profit mode into a risk network. Therefore, the wind control processing mode for the prior claims can be upgraded according to the risk network, and illegal sub-groups are prevented from collecting the claims and paying funds.
Description
Technical Field
The present disclosure relates to the field of internet, and in particular, to a method and an apparatus for constructing a risk network.
Background
In order to guarantee the rights and interests of consumers, the transaction platform releases a first-line claim service, which exemplifies: the order insurance is a prior compensation service promoted by a transaction platform combined insurance mechanism, the transaction of the order insurance is purchased, if a buyer initiates a right maintaining process when refunding and a seller does not complete the refunding within a preset time, the insurance mechanism performs the compensation of the refunding with the guarantee of the order insurance service in advance and then performs the compensation on the seller. If the refund is not successfully reimbursed at the seller, property loss of the transaction platform or insurance agency will result.
At present, lawless persons master the account numbers of both buyers and sellers at the same time, and illegally collect funds in the advance claim payment service, but no better method for identifying and processing the risky behaviors exists at present.
Disclosure of Invention
In view of the above technical problems, embodiments of the present specification provide a method and an apparatus for constructing a risk network, and a technical solution is as follows:
according to a first aspect of embodiments of the present specification, there is provided a risk network construction method applied to a pay-ahead system for paying a refund in advance for a qualified buyer in place of a seller, the method including:
after receiving the abnormal information of the global odds ratio, obtaining orders meeting the preset time condition according to the time field information in an order list subjected to the prior odds;
performing feature extraction on the obtained order, respectively matching the extracted buyer features, seller features and commodity features in a predefined risk feature library, and screening out risk orders according to matching results;
determining the aggregative characteristics of a buyer and a seller according to the transaction behavior information generated by the buyer and the seller in the transaction stage and the indemnity behavior information generated in the indemnity stage, and determining the order with the aggregative characteristics as a black sample order;
and extracting at least one illegal profit mode aiming at the advanced payment system by using the black sample order, and constructing a risk network by taking the buyer account and the seller account which have the transaction modes conforming to the illegal profit modes as nodes and taking the illegal profit relationship of the buyer and the seller as sides.
According to a second aspect of the embodiments of the present specification, there is provided a reimbursement risk detection method based on a risk network construction method, applied to an advanced reimbursement system for reimbursing a eligible buyer in place of a seller, the method including:
after receiving a report submitted by a buyer for refund, acquiring buyer information and seller information of a corresponding transaction;
and matching the buyer information and the seller information in a risk network, and calculating the risk probability of the current report according to the association degree and the risk degree of the buyer and the seller in the risk network.
According to a third aspect of the embodiments of the present specification, there is provided a risk network construction apparatus applied to an antecedent payment system for antecedent payment of refunds for eligible buyers in place of a seller, the apparatus comprising:
an order acquisition module: the order form processing system is used for acquiring an order form meeting a preset time condition according to time field information in an order form list subjected to prior claims after receiving the global claims rate abnormal information;
a risk screening module: the system is used for extracting the characteristics of the obtained orders, respectively matching the extracted buyer characteristics, seller characteristics and commodity characteristics in a predefined risk characteristic library, and screening out risk orders according to the matching result;
a sample acquisition module: the system comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for determining the aggregative characteristics of buyers and sellers according to transaction behavior information generated in a transaction stage and claim payment behavior information generated in a claim payment stage by buyers and sellers of different risk orders, and determining orders with the aggregative characteristics as black sample orders;
a network construction module: the system comprises a black sample order, a buyer account and a seller account, wherein the black sample order is used for extracting at least one illegal profit mode aiming at a pay-ahead system, the buyer account and the seller account which have transaction modes conforming to the illegal profit modes are taken as nodes, and the illegal profit relationship of the buyer and the seller is taken as an edge to construct a risk network.
According to a fourth aspect of the embodiments of the present specification, there is provided a reimbursement risk detection apparatus based on a risk network construction apparatus, applied to an advanced reimbursement system for reimbursing a eligible buyer in place of a seller, the apparatus including:
an information acquisition module: the system is used for acquiring buyer information and seller information corresponding to the transaction after receiving an application form submitted by a buyer for refund;
a risk calculation module: and the risk probability of the current report is calculated according to the association degree and the risk degree of the buyer and the seller in the risk network.
According to a fifth aspect of embodiments of the present specification, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement a risk network construction method applied to an advanced claim system for advanced claim reimbursement for a qualified buyer in place of a seller, the method comprising:
after receiving the abnormal information of the global claims rate, obtaining orders meeting the preset time condition according to the time field information in an order list subjected to the prior claims;
extracting the characteristics of the obtained orders, respectively matching the extracted buyer characteristics, seller characteristics and commodity characteristics in a predefined risk characteristic library, and screening out risk orders according to the matching result;
determining the aggregative characteristics of buyers and sellers according to transaction behavior information generated by buyers and sellers of different risk orders in a transaction stage and claim behavior information generated by a claim stage, and determining orders with the aggregative characteristics as black sample orders;
and extracting at least one illegal profit mode aiming at the advanced payment system by using the black sample order, taking the buyer account and the seller account of which the transaction modes conform to the illegal profit modes as nodes, and taking the illegal profit relationship of the buyer and the seller as an edge to construct a risk network.
According to the technical scheme provided by the embodiment of the specification, firstly, the paid order information is compared with the predefined risk characteristic information, and the risk order is screened out according to the comparison result; determining the aggregative characteristics of the buyer and the seller according to different risk order information, and determining the order with the aggregative characteristics as a black sample order; and extracting an illegal profit mode aiming at the advanced payment system by using the black sample order, and constructing buyers and sellers of which the transaction modes conform to the illegal profit mode into a risk network. Therefore, the wind control processing mode for the prior claims can be upgraded according to the risk network, and illegal sub-groups are prevented from collecting the claims and paying funds.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of embodiments of the invention.
In addition, any one of the embodiments in the present specification is not required to achieve all of the effects described above.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present specification, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a flow diagram of a risk network construction method shown in an exemplary embodiment of the present description;
FIG. 2 is a schematic illustration of an illegal profit model shown in an exemplary embodiment of the present description;
FIG. 3 is a schematic diagram of a risk network shown in an exemplary embodiment of the present description;
FIG. 4 is a schematic diagram of a diffusion risk network shown in an exemplary embodiment of the present description;
FIG. 5 is another flow diagram of a method of risk of reimbursement detection shown in an exemplary embodiment of the present description;
FIG. 6 is a schematic diagram of a risk network building apparatus shown in an exemplary embodiment of the present description;
FIG. 7 is a schematic diagram of a claim risk detection apparatus, shown in an exemplary embodiment of the present description;
FIG. 8 is a schematic diagram illustrating a mining method for buyer sellers, according to an exemplary embodiment of the present description;
fig. 9 is a schematic structural diagram of a computer device according to an exemplary embodiment of the present specification.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the specification, as detailed in the appended claims.
The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present specification. The word "if" as used herein may be interpreted as "at" \8230; "or" when 8230; \8230; "or" in response to a determination ", depending on the context.
In order to guarantee the rights and interests of consumers, the transaction platform releases a first-line claim service, which exemplifies: the order insurance is a payment-in-advance service released by a transaction platform and a joint insurance institution, the transaction of the order insurance is purchased, if a buyer initiates a right-maintaining process when refunding, and a seller does not complete the refund within a preset time, the insurance institution pays the refund with the guarantee of the order insurance service in advance, and then the seller is compensated. If the refund is not successfully reimbursed at the seller, the property loss of the transaction platform or insurance institution will be caused.
At present, lawless persons master account numbers of a buyer and a seller at the same time, and illegally collect funds in the pay-first-aid service, but no better method for identifying and processing the risk behaviors exists at present.
In view of the above problems, embodiments of the present specification provide a risk network construction method and a risk network construction device for executing the method. The method mentioned in the embodiments of the present specification is mainly applied to an advanced claim payment system, which is used to pay a refund for a qualified buyer in place of a seller.
The method for constructing a risk network according to the present embodiment is described in detail below, and as shown in fig. 1, the method may include the following steps:
s101, after receiving the global odds rate abnormal information, obtaining an order meeting a preset time condition according to the time field information in an order list subjected to antecedent claim payment;
the first pay service generally guarantees the transaction in the form of insurance, and is exemplified by the order insurance of the Taobao platform: after the Taobao buyer and the seller with the 'consumer security service' transact through the Paobao service, if the right of the buyer is damaged due to the transaction and the buyer directly requires the seller to deal with the failure, the buyer has the right to initiate a right-maintaining complaint of the transaction after the transaction is successful to the Taobao and proposes a claim application. When the Taobao judges that the buyer claims and pays application is established according to the relevant rules, the buyer is paid with refund payment directly, waiting of the buyer is avoided, and user experience is good. The compensation opens up a compensation for the seller at the same time. If the seller is not the black product seller who illegally collects the funds, the seller can successfully recoup the deposit and the like provided by the seller, but the seller of the black product who illegally collects the funds usually cannot recoup the deposit and the loss of the reimbursement funds is caused.
Generally speaking, in the prior claim payment process of the transaction platform, three main auditing stages need to be generated for the comprehensive information of both the buyer and the seller, which are respectively the verification of passing the guarantee of the transaction by using the prior claim payment (the qualification verification of the seller purchasing order risk), the buyer issues the verification of passing the right of maintenance, and the claim payment verification after checking the right of maintenance information, and the specific process is as follows:
1) The method comprises the steps of checking the transaction of purchasing the advanced claim payment service, judging whether the current transaction of a user accords with the purchase condition of the advanced claim payment service or not according to the self information and the transaction information of the purchasing user, and generating a policy if the current transaction accords with the condition;
2) Receiving a case report request initiated by a buyer aiming at a transaction accident, judging whether the buyer accords with a case report condition, and if so, receiving the case report request and generating a case report form;
3) And comprehensively judging whether the application request meets the advanced claim condition or not according to the order information, the logistics information and the buyer and seller information, and if so, performing claim and generating a claim settlement sheet.
Specifically, the present embodiment monitors the global payout rate, that is, calculates the global payout rate every predetermined time to determine whether the real-time payout rate is abnormal.
Generally, the abnormal odds refer to the odds being higher than the average or preset threshold, which indicates that the prior odds are more frequently paid in the past period, and the odds may be calculated in various ways, for example:
global payout rate = (payout of claims ÷ premium revenue) × 100%, or,
global payout rate = (payout order number ÷ transaction order number) × 100%, etc
S102, extracting the characteristics of the obtained order, respectively matching the extracted buyer characteristics, seller characteristics and commodity characteristics in a predefined risk characteristic library, and screening out the risk order according to the matching result;
when the antecedent payment rate is abnormal, the system starts to extract data of the order. The order here refers to a trade order in which a claim has been made. Comparing buyer characteristics in the orders with predefined risky buyer characteristics, comparing seller characteristics in the orders with predefined risky seller characteristics, and comparing commodity characteristics in the orders with predefined risky commodity characteristics. And then the orders with risks can be screened according to the comparison result.
For each of the features, by way of example:
the predefined risk buyer characteristics may include: the method comprises the following steps that a buyer has batch ordering behaviors, the ordering time of the buyer is gathered in the same time period, the return right rate of the buyer is higher than a preset threshold value, and/or the right reason filled by the buyer has repeatability and the like.
The predefined risky seller characteristics may include: the seller stores with the prior claims in the same time period are similar in name, the seller stores are too simple to decorate, the number of commodities of the seller stores is less than a preset threshold value, and/or the inflow and outflow frequency of funds of the seller stores is higher than a preset threshold value.
The predefined risky merchandise characteristics may include: the title of the product has obscure words and/or the detailed page of the product is too simple to describe.
The predefined risky buyer characteristics, the risky seller characteristics and the commodity characteristics can be summarized and added according to historical data and experience, and the specific characteristic types are not limited in the embodiment.
And after the characteristics are compared with the predefined risk characteristics, determining the orders with risks according to the comparison result and carrying out the next judgment. Wherein the determination of the at-risk order based on the comparison may be accomplished in a variety of ways, two of which are illustrated:
a) Judging the order as a risky order when the risk characteristics of the buyers, the sellers and the commodities in the single order are met above a preset number;
b) And setting weight values of different risk characteristics, and judging the order as a risky order if the risk weight value accumulated by the single order is above a preset threshold value.
S103, determining the aggregative characteristics of the buyer and the seller according to the transaction behavior information generated by the buyer and the seller of different risk orders in the transaction stage and the claim payment behavior information generated by the claim payment stage, and determining the order with the aggregative characteristics as a black sample order;
specifically, after the risk orders are acquired, the document information generated in the prior claim paying process of different risk orders can be extracted, and in this embodiment, the document information may include insurance document information, entry document information and claim settlement document information;
specifically, payment mode information, payment time information, logistics information, effective time information of advanced claim payment service and the like can be extracted from the insurance document information; extracting right maintaining time information, right maintaining reason information, right maintaining amount information, information on whether goods return is needed and the like submitted by a buyer from the report document information; extracting the information of the right passing time, the claim settlement amount and the like from the claim settlement document information;
the extracted index information can obtain common characteristics of illegal pay orders, such as: the method comprises the steps of generating aggregative characteristics on the same commodity by a plurality of different buyer and sellers, generating aggregative characteristics on claim settlement time by a plurality of different buyer and sellers, generating aggregative characteristics on claim settlement amount by a plurality of different buyer and sellers and the like, and generating abnormal payment withholding behavior, abnormal logistics information in transaction, abnormal transaction behavior track, abnormal seller account activity and the like by sellers. Risk orders with these common characteristics are circled as black sample orders.
And S104, extracting at least one illegal profit mode aiming at the advanced payment system by using the black sample order, taking a buyer account and a seller account of which the transaction modes conform to the illegal profit modes as nodes, and taking the illegal profit relationship of a buyer and a seller as sides to construct a risk network.
After the black sample orders are circled, an illegal profit mode for the advanced claim payment system is extracted by utilizing the behavior information of the black sample orders in the advanced claim payment process, and the illegal profit mode generally has various forms. This embodiment exemplifies one of the illegal profit patterns: referring to fig. 2, the illegal profit model is divided into four steps, as follows:
1) The black product buyer lifts a right-keeping request for the black product seller;
2) The black-yielding seller simultaneously requests the refund provided by the right-to-maintain request;
3) The black product seller keeps the account with insufficient balance and cannot deduct money, and the duration time exceeds 24 hours;
4) After 24 hours, the order insurance party (ant insurance) pays the black product buyer in advance.
It can be seen that, in the embodiment, the illegal profit patterns mainly used by the illegal molecules in the past period are extracted according to the risk orders in the past period, and the real-time behavior of the illegal molecule behavior can be monitored and summarized. And upgrading the risk control system in real time according to the current illegal profit mode.
Referring to fig. 3, after the illegal profit pattern is extracted, a risk network is constructed by taking a buyer account and a seller account, of which the transaction patterns conform to the illegal profit pattern, as nodes and taking an illegal profit relationship between a buyer and a seller as an edge. Further, in addition to the illegal profit model feature information, other feature information of the buyer seller can also be used as a construction element of the risk network. For example: if the buyer of the seller is connected with the same WIFI, the weight of the illegal relationship between the two parties can be increased, and in the risk network, the weight of the edges connected between the nodes of the buyer and the seller can be increased.
Referring to fig. 4, after a risk network is constructed, the risk network is further subjected to account diffusion of the same person, that is, information mining is performed on a buyer account and a seller account in the risk network, other accounts registered by a holder of the accounts are determined, and the risk network is diffused based on the other accounts. Specifically, for any account in the risk network, other accounts registered by the holder of the account may be acquired, and the other accounts may be determined as new nodes of the risk network.
Based on the risk network constructed as above, the present specification further provides a method for detecting reimbursement risk based on the risk network, which is applied to an advanced reimbursement system for reimbursing a eligible buyer in place of a seller, as shown in fig. 5, and the method includes
S501, after receiving an application form submitted by a buyer for refund, acquiring buyer information and seller information corresponding to transaction;
s502, matching the buyer information and the seller information in a risk network, and calculating the risk probability of the current report according to the association degree and the risk degree of the buyer and the seller in the risk network.
If the calculated risk probability is higher than a preset threshold value, the report sheet can be intercepted, or the advanced claim paying service function of the buyer and the seller of the report sheet can be limited.
Specifically, in performing risk control, a DistRep algorithm may be introduced.
Based on the business characteristics of the order insurance, if the seller and the buyer are abstracted as nodes and the policy existing between the seller and the buyer is abstracted as an edge, referring to fig. 8, the relationship between the seller and the buyer can be represented by a graph model, and it can be seen that the order insurance pneumatic control can be converted into an edge prediction problem. I.e., to determine whether a transaction is risky based on the buyer or seller of the transaction.
The graph model can not only effectively depict the interaction relationship between the buyer and the seller, see fig. 8, but also can well reveal the hidden relationship between the buyer and the seller and between the buyer and the seller through the intermediate nodes. Therefore, the graph model can be used for dealing with the characteristics that the black product group hidden plan is difficult to discover, and the updating is frequently changed.
Specifically, let G =<N,E>Where N represents the set of nodes of graph G, E represents the set of edges connecting the nodes,
for edge e ij ∈E,e ij ＝<y ij ,n i ,n j >Wherein n is i Represents node i, n j Represents node j, y ij Denotes e ij And if the current edge is the overlap edge, the value is 0 or 1. Predicting a newly added edge e in the future t1 moment G according to the graph G at the current t0 moment ij Whether it is a registered edge y ij Likelihood probability of, i.e. given edge e ij Calculating p (y) ij ∣e ij ). Solving the model parameter estimation problem using a method of maximum likelihood estimation, i.e. for the observed edge e ij The maximized log probability of y ^ and in particular, the probability formula can be expressed as follows:
corresponding to the above method embodiment, an embodiment of the present specification further provides a risk network constructing apparatus, and referring to fig. 6, the apparatus may include: a relationship determination module 610, an account screening module 620, and a group determination module 630;
the order acquisition module 610: the order form processing system is used for acquiring an order form meeting a preset time condition according to time field information in an order form list subjected to prior claims after receiving the global claims rate abnormal information;
the risk screening module 620: the risk order screening system is used for extracting the characteristics of the obtained order, respectively matching the extracted buyer characteristics, seller characteristics and commodity characteristics in a predefined risk characteristic library, and screening a risk order according to the matching result;
the sample acquisition module 630: the system comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for determining the aggregative characteristics of a buyer and a seller according to transaction behavior information generated by the buyer and the seller in a transaction stage and claim behavior information generated by the claim stage of different risk orders, and determining the order with the aggregative characteristics as a black sample order;
the network construction module 640: the system comprises a black sample order, a buyer account and a seller account, wherein the black sample order is used for extracting at least one illegal profit mode aiming at a pay-ahead system, the buyer account and the seller account which have transaction modes conforming to the illegal profit modes are taken as nodes, and the illegal profit relationship of the buyer and the seller is taken as an edge to construct a risk network.
Based on the risk network constructed as above, the present specification further provides a reimbursement risk detection apparatus based on the risk network, which is applied to an advanced reimbursement system for reimbursing a eligible buyer in place of a seller, referring to fig. 7, the apparatus includes:
the information acquisition module 710: the system is used for acquiring buyer information and seller information corresponding to the transaction after receiving an application form submitted by a buyer for refund;
the risk calculation module 720: and the risk probability of the current report is calculated according to the association degree and the risk degree of the buyer and the seller in the risk network.
Embodiments of the present specification further provide a computer device, which at least includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the risk network construction method when executing the program, and the method at least includes:
after receiving the abnormal information of the global claims rate, obtaining orders meeting the preset time condition according to the time field information in an order list subjected to the prior claims;
performing feature extraction on the obtained order, respectively matching the extracted buyer features, seller features and commodity features in a predefined risk feature library, and screening out risk orders according to matching results;
determining the aggregative characteristics of a buyer and a seller according to the transaction behavior information generated by the buyer and the seller in the transaction stage and the indemnity behavior information generated in the indemnity stage, and determining the order with the aggregative characteristics as a black sample order;
and extracting at least one illegal profit mode aiming at the advanced payment system by using the black sample order, and constructing a risk network by taking the buyer account and the seller account which have the transaction modes conforming to the illegal profit modes as nodes and taking the illegal profit relationship of the buyer and the seller as sides.
The embodiments of the present specification further provide a computer device, which at least includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for detecting a reimbursement risk based on the risk network construction method, the method at least includes:
after receiving an application form submitted by a buyer for refund, acquiring buyer information and seller information corresponding to the transaction;
and matching the buyer information and the seller information in a risk network, and calculating the risk probability of the current report according to the association degree and the risk degree of the buyer and the seller in the risk network.
Fig. 9 is a schematic diagram illustrating a more specific hardware structure of a computing device according to an embodiment of the present disclosure, where the computing device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component within the device (not shown) or may be external to the device to provide corresponding functionality. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (for example, USB, network cable, etc.), and can also realize communication in a wireless mode (for example, mobile network, WIFI, bluetooth, etc.).
The bus 1050 includes a path to transfer information between various components of the device, such as the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040.
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
Embodiments of the present specification further provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor, and the method for constructing a risk network includes at least:
after receiving the abnormal information of the global odds ratio, obtaining orders meeting the preset time condition according to the time field information in an order list subjected to the prior odds;
performing feature extraction on the obtained order, respectively matching the extracted buyer features, seller features and commodity features in a predefined risk feature library, and screening out risk orders according to matching results;
determining the aggregative characteristics of buyers and sellers according to transaction behavior information generated by buyers and sellers of different risk orders in a transaction stage and claim behavior information generated by a claim stage, and determining orders with the aggregative characteristics as black sample orders;
and extracting at least one illegal profit mode aiming at the advanced payment system by using the black sample order, taking the buyer account and the seller account of which the transaction modes conform to the illegal profit modes as nodes, and taking the illegal profit relationship of the buyer and the seller as an edge to construct a risk network.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
For the device embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in the specification. One of ordinary skill in the art can understand and implement it without inventive effort.
The systems, apparatuses, modules or units described in the above embodiments may be specifically implemented by a computer chip or an entity, or implemented by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, the apparatus embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the description of the method embodiments for relevant points. The above-described apparatus embodiments are merely illustrative, and the modules described as separate components may or may not be physically separate, and the functions of the modules may be implemented in one or more software and/or hardware when implementing the embodiments of the present disclosure. And part or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing is only a specific embodiment of the embodiments of the present disclosure, and it should be noted that, for those skilled in the art, a plurality of modifications and decorations can be made without departing from the principle of the embodiments of the present disclosure, and these modifications and decorations should also be regarded as the protection scope of the embodiments of the present disclosure.
Claims (23)
1. A risk network construction method is applied to a pay-ahead system, the pay-ahead system is used for paying refunds for eligible buyers in place of sellers in advance, and the method comprises the following steps:
after receiving the abnormal information of the global claims rate, obtaining orders meeting the preset time condition according to the time field information in an order list subjected to the prior claims;
extracting the characteristics of the obtained orders, respectively matching the extracted buyer characteristics, seller characteristics and commodity characteristics in a predefined risk characteristic library, and screening out risk orders according to the matching result;
extracting the aggregative characteristics of the buyer and the seller on the same commodity according to the trading behavior information generated by the buyer and the seller in the trading stage and the claim behavior information generated by the claim stage of different risk orders, and judging the order with the aggregative characteristics as a black sample order;
and extracting at least one illegal profit mode aiming at the advanced payment system by using the black sample order, taking the buyer account and the seller account of which the transaction modes conform to the illegal profit modes as nodes, and taking the illegal profit relationship of the buyer and the seller as an edge to construct a risk network.
2. The method of claim 1, after constructing the risk network, further comprising:
aiming at any account number in the risk network, acquiring other account numbers registered by a holder of the account number, and determining the other account numbers as new nodes of the risk network.
3. The method of claim 1, the detecting that global odds are anomalous comprises:
monitoring the change condition of the claim expenditure information and the premium income information, and calculating the global claim rate according to the monitored information;
and if the global odds ratio is higher than a preset threshold value, determining that the global odds ratio is abnormal.
4. The method of claim 1, wherein the matching the extracted buyer characteristics in a predefined risk characteristics repository comprises:
matching the extracted buyer features in a predefined risk feature library, and determining the matching degree of the extracted buyer features and the risk buyer features, wherein the risk buyer features comprise: the method comprises the following steps that the buyers have batch ordering behaviors, ordering time of the buyers is gathered in the same time period, the returned goods right-keeping rate of the buyers is higher than a preset threshold value, and/or right-keeping reasons filled by the buyers have repeatability.
5. The method of claim 1, said matching the extracted seller characteristics in a predefined risk characteristics repository, comprising:
matching the extracted seller features in a predefined risk feature library, and determining the matching degree of the extracted seller features and risk seller features, wherein the risk seller features comprise: the seller stores with the same time period for which the antecedent payment occurs are similar in name, the seller stores are too simple to finish, the number of commodities of the seller stores is less than a preset threshold value, and/or the inflow and outflow frequency of funds of the seller stores is higher than a preset threshold value.
6. The method of claim 1, wherein matching the extracted commodity features in a predefined risk feature library comprises:
matching the extracted commodity features in a predefined risk feature library, and determining the matching degree of the extracted commodity features and the risk commodity features, wherein the risk commodity features comprise: the title of the product has obscure words and/or the detailed page of the product is too simple to describe.
7. The method of claim 1, the antecedent claim process, comprising:
the method comprises the steps of checking the transaction of purchasing the advanced claim payment service, judging whether the current transaction of a user accords with the purchase condition of the advanced claim payment service or not according to the self information and the transaction information of the purchasing user, and generating a policy if the current transaction accords with the condition;
receiving a case report request initiated by a user aiming at a transaction accident, judging whether the user accords with a case report condition, and if so, receiving the case report request and generating a case report sheet;
and comprehensively judging whether the application request meets the advanced claim condition or not according to the order information, the logistics information and the buyer and seller information, and if so, performing claim and generating a claim settlement sheet.
8. The method according to claim 1, wherein the extracting of the aggregative features of the buyer and the seller on the same commodity according to the transaction behavior information generated by the buyer and the seller in the transaction stage and the reimbursement behavior information generated by the reimbursement stage comprises:
extracting bill information generated in a prior claim paying process of different risk orders, wherein the bill information comprises insurance bill information, declaration bill information and claim settlement bill information;
extracting payment mode information, payment time information, logistics information and effective time information of advanced claim payment service from the insurance document information;
extracting right maintaining time information, right maintaining reason information, right maintaining amount information and information on whether goods return is required, which are submitted by buyers, from the report document information;
extracting the information of the right passing time and the claim amount from the information of the claim document;
and determining the aggregation characteristics of the buyer and the seller on the same commodity according to the extracted information.
9. A claims risk detection method based on the risk network construction method of claim 1, applied to an advanced claims system for advanced claims refund for eligible buyers in place of sellers, the method comprising:
after receiving an application form submitted by a buyer for refund, acquiring buyer information and seller information corresponding to the transaction;
and matching the buyer information and the seller information in a risk network, and calculating the risk probability of the current report according to the association degree and the risk degree of the buyer and the seller in the risk network.
10. The method of claim 9, after calculating the risk probability for the current insurance policy, further comprising:
and if the calculated risk probability is higher than a preset threshold value, intercepting the report.
11. The method of claim 10, after calculating the risk probability of the current insurance policy, further comprising:
and if the calculated risk probability is higher than a preset threshold value, limiting the advanced claim paying service function of the buyer and the seller of the report form.
12. A risk network construction apparatus applied to a pay-ahead system for paying a refund in place of a seller for a qualified buyer, the apparatus comprising:
an order acquisition module: the order form acquisition module is used for acquiring an order form meeting a preset time condition according to the time field information in an order form list subjected to antecedent claims after receiving the global odds rate abnormal information;
a risk screening module: the system is used for extracting the characteristics of the obtained orders, respectively matching the extracted buyer characteristics, seller characteristics and commodity characteristics in a predefined risk characteristic library, and screening out risk orders according to the matching result;
a sample acquisition module: the system comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for extracting the aggregative characteristics of buyers and sellers on the same commodity according to trading behavior information generated by the buyers and the sellers in a trading stage and claim behavior information generated by a claim stage of different risk orders, and judging the orders with the aggregative characteristics as black sample orders;
a network construction module: the system comprises a black sample order, a buyer account and a seller account, wherein the black sample order is used for extracting at least one illegal profit mode aiming at a pay-ahead system, the buyer account and the seller account which have transaction modes conforming to the illegal profit modes are taken as nodes, and the illegal profit relationship of the buyer and the seller is taken as an edge to construct a risk network.
13. The apparatus of claim 12, said constructing a risk network further comprising:
aiming at any account number in the risk network, acquiring other account numbers registered by a holder of the account number, and determining the other account numbers as new nodes of the risk network.
14. The apparatus of claim 12, the detecting that global odds are anomalous comprises:
monitoring the change condition of the claim expenditure information and the premium income information, and calculating the global claim rate according to the monitored information;
and if the global payout rate is higher than a preset threshold value, determining that the global payout rate is abnormal.
15. The apparatus of claim 12, the matching of the extracted buyer characteristics in a predefined risk characteristics repository, comprising:
matching the extracted buyer features in a predefined risk feature library, and determining the matching degree of the extracted buyer features and the risk buyer features, wherein the risk buyer features comprise: the method comprises the following steps that the buyers have batch ordering behaviors, ordering time of the buyers is gathered in the same time period, the returned goods right-keeping rate of the buyers is higher than a preset threshold value, and/or right-keeping reasons filled by the buyers have repeatability.
16. The apparatus of claim 12, said matching the extracted seller features in a predefined risk feature library, comprising:
matching the extracted seller features in a predefined risk feature library, and determining the matching degree of the extracted seller features and risk seller features, wherein the risk seller features comprise: the seller stores which pay in advance in the same time period are close in name, the seller stores are too simple to decorate, the number of commodities of the seller stores is less than a preset threshold value, and/or the inflow and outflow frequency of funds of the seller stores is higher than the preset threshold value.
17. The apparatus of claim 12, the matching of the extracted commodity features in a predefined risk feature library, comprising:
matching the extracted commodity features in a predefined risk feature library, and determining the matching degree of the extracted commodity features and the risk commodity features, wherein the risk commodity features comprise: the title of the product has obscure words and/or the detailed page of the product is too simple to describe.
18. The apparatus of claim 12, the antecedent claim process, comprising:
the method comprises the steps of checking the transaction of purchasing the advanced claim payment service, judging whether the current transaction of a user accords with the purchase condition of the advanced claim payment service or not according to the self information and the transaction information of the purchasing user, and generating a policy if the current transaction accords with the condition;
receiving a case report request initiated by a user aiming at a transaction accident, judging whether the user accords with a case report condition, and if so, receiving the case report request and generating a case report sheet;
and comprehensively judging whether the application request meets the advanced claim condition or not according to the order information, the logistics information and the buyer and seller information, and if so, performing claim and generating a claim settlement sheet.
19. The apparatus according to claim 12, wherein the extracting of the aggregative features of the buyer and the seller on the same commodity according to the transaction behavior information generated by the buyer and the seller in the transaction stage and the reimbursement behavior information generated by the reimbursement stage comprises:
extracting bill information generated in a prior claim paying process of different risk orders, wherein the bill information comprises insurance bill information, declaration bill information and claim settlement bill information;
extracting payment mode information, payment time information, logistics information and first-aid claim service effective time information from insurance document information;
extracting right maintaining time information, right maintaining reason information, right maintaining amount information and information on whether goods return is required, which are submitted by a buyer, from the report document information;
extracting the information of the right passing time and the claim amount from the information of the claim document;
and determining the aggregation characteristics of the buyer and the seller on the same commodity according to the extracted information.
20. A claim risk detection device based on the risk network construction device of claim 12, applied to an antecedent claim system for antecedent claim reimbursement for eligible buyers in place of sellers, the device comprising:
an information acquisition module: the system is used for acquiring buyer information and seller information corresponding to the transaction after receiving an application form submitted by a buyer for refund;
a risk calculation module: and the risk probability of the current report form is calculated according to the association degree and the risk degree of the buyer and the seller in the risk network.
21. The apparatus of claim 20, after calculating the risk probability of the current insurance policy, further comprising:
and if the calculated risk probability is higher than a preset threshold value, intercepting the report.
22. The apparatus of claim 21, said calculating the risk probability of the current insurance policy further comprising:
and if the calculated risk probability is higher than a preset threshold value, limiting the prior claim payment service function obtained by the buyer and the seller of the report form.
23. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of claim 1 when executing the 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 CN110175924A (en) | 2019-08-27 |
| CN110175924B true 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) |
Families Citing this family (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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175924A (en) | 2019-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9661012B2 (en) | Systems and methods for identifying information related to payment card breaches | |
| US10423962B2 (en) | Pre-authorization of a transaction using predictive modeling | |
| TWI729474B (en) | Claim business processing method and device | |
| US20170024828A1 (en) | Systems and methods for identifying information related to payment card testing | |
| US20140172697A1 (en) | Systems and methods for detecting fraud in retail return transactions | |
| US11403645B2 (en) | Systems and methods for cross-border ATM fraud detection | |
| US20160196615A1 (en) | Cross-channel fraud detection | |
| CN108876188B (en) | Inter-connected service provider risk assessment method and device | |
| US20170053278A1 (en) | Systems and Methods for Processing Charges for Disputed Transactions | |
| US20170116674A1 (en) | Processing electronic signals to determine insurance risk | |
| US11605014B2 (en) | Systems and methods for short identifier behavioral analytics | |
| US20210326978A1 (en) | Real estate product related finance system and management method thereof | |
| WO2021176762A1 (en) | Fraud detection device, foreigner employment system, program, and method for detecting illicit labor by foreign worker | |
| CN110175924B (en) | Risk network construction method and device | |
| US8078529B1 (en) | Evaluating customers' ability to manage revolving credit | |
| JP7001640B2 (en) | Real estate related economic system and its management method | |
| CN110633966A (en) | Block chain-based contract securitization method and device | |
| US12008573B2 (en) | Computer-implemented systems and methods for detecting fraudulent activity | |
| US8595114B2 (en) | Account level interchange effectiveness determination | |
| CN113962817A (en) | Abnormal person identification method and device, electronic equipment and storage medium | |
| CN113129127A (en) | Early warning method and device | |
| KR20210039603A (en) | Method and system for preventing payment error using block chain | |
| US11822959B2 (en) | Methods and systems for processing requests using load-dependent throttling | |
| JP2002197268A (en) | Loan managing system, its method, and computer software program product which makes computer system manage loan | |
| TWI783387B (en) | Management support device, management support system, management support program, and management support method |
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 | ||
| 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |