WO2015161746A1 - 转账交易的风险控制方法及装置 - Google Patents

转账交易的风险控制方法及装置 Download PDF

Info

Publication number
WO2015161746A1
WO2015161746A1 PCT/CN2015/076511 CN2015076511W WO2015161746A1 WO 2015161746 A1 WO2015161746 A1 WO 2015161746A1 CN 2015076511 W CN2015076511 W CN 2015076511W WO 2015161746 A1 WO2015161746 A1 WO 2015161746A1
Authority
WO
WIPO (PCT)
Prior art keywords
financial account
account
shortest distance
transfer
transferred
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.)
Ceased
Application number
PCT/CN2015/076511
Other languages
English (en)
French (fr)
Inventor
万四爽
刘国宝
尹亚伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Unionpay Co Ltd
Original Assignee
China Unionpay Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Unionpay Co Ltd filed Critical China Unionpay Co Ltd
Publication of WO2015161746A1 publication Critical patent/WO2015161746A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

Definitions

  • the invention belongs to the technical field of transfer transactions, and relates to risk control of transfer transactions, in particular to obtaining an account relationship map based on historical transfer transaction data, and then obtaining the shortest distance value between the transferred financial account and the transferred financial account to transfer the transaction.
  • the prior art adopts a technical means for the transfer process to improve the security of the transfer.
  • the method and system for improving the security of transfer are adopted.
  • the transaction data is signed, the transmitted content is encrypted or signed to protect the transfer security, and the transfer data is prevented from being tampered or intercepted by an illegal attacker. Therefore, the risk control of prior art transfer transactions is achieved through the security level of data transmission.
  • the existing transfer transaction risk control system can not provide technical judgment at all, relying entirely on the transfer of the financial account user itself. To carry out artificial identification.
  • the auditing of the credibility of the financial account is at most a manual review by collecting user identity information (such as an ID card, a photo), etc., and the manual verification of the user's identity information is not only manual work.
  • user identity information such as an ID card, a photo
  • the large amount also affects the convenience of the transaction, and the actual effect is not obvious.
  • One of the objects of the present invention is to reduce the risk of a transfer transaction from the credibility of transferring a transfer transaction into a financial account.
  • the present invention provides the following technical solutions.
  • a risk control method for a transfer transaction which includes:
  • Account relationship diagram generation step according to the historical transfer transaction data, all the financial accounts that have already undergone the transfer transaction, and the account relationship diagram with the financial account as the apex, in the account relationship diagram, any two of the transfer transactions have occurred A directed edge with weights is established between financial accounts, wherein the more directed edges point to a certain financial account, the smaller the weight of the directed edge pointing to the financial account is;
  • a shortest distance value calculation step of calculating a shortest distance value between the transferred financial account and the transferred financial account based on the account relationship map in response to the request for the transfer transaction, wherein the shortest distance value is used for direct or indirect connection Calculating the corresponding weights of the transferred financial account and one or more directed edges transferred to the financial account;
  • Transaction response step determining the risk level of the transfer transaction based on the shortest distance value, and responding to controlling the transfer transaction process according to the corresponding risk level.
  • a risk control method wherein, in the transaction response step, after a successful transfer transaction between the transfer-out financial account and the transferred financial account, the transfer transaction is recorded as history Transfer the transaction data and return to the account relationship map generation step to update the account relationship map.
  • the weights of all directed edges associated with the transferred financial account of the transfer transaction data are set to 0 to identify it as an untrustworthy financial account; and, in the shortest distance value calculation step, if the untrusted financial account is determined to be a transfer financial account of the request for the transfer transaction, the shortest distance is directly calculated The value is 0.
  • the financial account downstream of the untrusted financial account is also identified as an untrusted financial account.
  • the risk level is determined to be "serious risk” and the transfer transaction is prohibited.
  • the weights of the N directed edges are set to one of N, wherein N is greater than or An integer equal to 2.
  • the weight of the directed edge of the bar is set to one.
  • a risk control method in which a breadth-first algorithm is employed The shortest distance value between the financial account and the financial account is calculated in the account relationship diagram.
  • the query passes through the directed edge and the Transferring a plurality of adjacent financial accounts directly connected to the financial account, if the shortest distance values of the M adjacent financial accounts and the transferred financial account are less than the predetermined value, updating the transferred financial account and the financial
  • the shortest distance value between the accounts is an average of the shortest distance values of the M adjacent financial accounts and the transferred financial account, wherein M is an integer greater than or equal to 2.
  • the traversal process is stopped.
  • the direct record distance between the financial account and the financial account is directly recorded to be greater than a predetermined value.
  • At least two directed edges whose weights are not zero are directed to each of the adjacent financial accounts.
  • the risk control method of any of the preceding embodiments in the transaction response step, if the shortest distance value is greater than a predetermined value, the risk level is determined to be "high risk" and displayed to the user who transfers the financial account , while limiting the freedom of the transfer transaction.
  • the transfer transaction in the transaction response step, if the shortest distance value is greater than 0 and less than or equal to a predetermined value, the transfer transaction is restricted according to the size of the shortest distance value The degree of freedom.
  • a risk control apparatus for a transfer transaction comprising:
  • An account relationship diagram generating module configured to establish an account relationship map with a plurality of financial accounts in which all the transfer transactions have occurred according to the historical transfer transaction data, and in the account relationship diagram, the transfer has occurred
  • a directed edge with weights is established between any two financial accounts of the transaction, wherein the more directed edges point to a certain financial account, the smaller the weight of the directed edge pointing to the financial account is;
  • a shortest distance value calculation module configured to calculate a shortest distance value between the transferred financial account and the transferred financial account based on the account relationship map in response to the request for the transfer transaction, wherein the shortest distance value is used by Calculating directly or indirectly the corresponding weights of the transferred financial account and one or more directed edges transferred to the financial account;
  • a transaction response module configured to determine the transfer transaction based on the shortest distance value The risk level, and in response to controlling the transfer transaction process based on the corresponding risk level.
  • a risk control apparatus for a transfer transaction wherein, in the transaction response module, after a successful transfer transaction between the transferred financial account and the transferred financial account, the transfer transaction is recorded as The transaction data is historically transferred and returned to the account relationship map generation module to update the account relationship map.
  • the risk control apparatus of the transfer transaction wherein, in the shortest distance value calculation module, if the shortest distance value between the outgoing financial account and the financial account is greater than a predetermined value, the inquiry is passed a plurality of adjacent financial accounts directly connected to the transfer financial account, and if the shortest distance values of the M adjacent financial accounts and the transferred financial account are less than the predetermined value, the transfer is updated
  • the shortest distance value between the financial account and the financial account is an average of the shortest distance values of the M adjacent financial accounts and the transferred financial account, wherein M is an integer greater than or equal to 2.
  • a computer program product comprising computer program code means for performing the risk control method described above when the computer program code means is operated by a computer capable electronic device.
  • FIG. 1 is a flow chart showing a risk control method of a transfer transaction according to an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of a directed edge with weights established between two financial accounts in an account relationship diagram.
  • FIG. 3 is a schematic diagram of an account relationship diagram of an embodiment.
  • FIG. 4 is a schematic diagram of an account relationship diagram of still another embodiment.
  • Figure 5 is a schematic diagram of an account relationship diagram of still another embodiment.
  • Figure 6 is a schematic diagram of assessing the risk level of a transfer transaction based on the shortest distance value.
  • FIG. 1 is a flow chart showing a risk control method for a transfer transaction according to an embodiment of the present invention.
  • the process of transfer transaction generally refers to the two parties of the transfer transaction, that is, the transfer of the financial account (hereinafter referred to as F) and the transfer of the financial account (hereinafter referred to as T), the present invention judges F and the analysis by analyzing the historical transfer transaction data.
  • the risk level between T provides a reference for users of F to improve the security of the transfer transaction.
  • Each financial account represents a corresponding user, which may be, but is not limited to, represented by the card number of the bank card.
  • the risk control method of the transfer transaction mainly includes three stages, namely, an account relationship map generation 110, a shortest distance calculation 120, and a transaction response 130.
  • an account relationship diagram is mainly generated based on the historical transfer transaction data.
  • a plurality of financial users involved in the transfer transaction involving the plurality of historical transfer transaction data are distributed in the account relationship diagram.
  • each financial account and other financial accounts with which a transfer transaction has occurred establish a connection through the directed edge, and each directed edge points from the transfer party to the transfer party, that is, F points to T, Its direction reflects the direction of capital inflows from the transaction.
  • a weight value is correspondingly set on each of the directed edges, and the weight value can be used to calculate a distance value between F and T, and the smaller the weight value, the T of the corresponding directed edge is reflected. The higher the reliability.
  • Figure 2 is a schematic diagram of a directed edge with weights established between two financial accounts in an account relationship diagram.
  • a directed edge is established between A and B, and the transfer is performed.
  • the outbound party A points to the transferee B, and in the case where other transactions are not considered, the weight is set to 1 in this embodiment.
  • the weight represents the credibility of B. The greater the weight, the lower the credibility of B, and the greater the risk of transferring to B.
  • the more the F and T successfully occur the transfer transaction the smaller the weight corresponding to the Td multiple directed edges of T corresponds, and thus the reliability of the T increases.
  • FIG. 3 is a schematic diagram of an account relationship diagram of an embodiment.
  • the weight of the directed edge between C and B is 1/2.
  • the weight of the directed edge between A and B is correspondingly reduced, for example 1/2.
  • the weights of the N directed edges are set to one-N, where N is an integer greater than or equal to 2. Therefore, the larger N is, the more the financial account successfully transfers to B, and the smaller the weight of the directed edge pointing to B, the higher the credibility of representing B.
  • the specific setting method of the weight is not limited to the embodiment of the present invention.
  • the weight of the relevant directed edge of the fraudulent user can be configured based on the fraudulent transaction record. As shown in FIG. 3, in the case where a certain historical transfer transaction data is determined to be a fraudulent transaction record, B is determined to be a fraudulent transaction user, then the weights of all directed edges associated with B are set to 0 to It is identified as an untrustworthy financial account, that is, an untrustworthy financial account. Further, when B is an untrustworthy financial account, the financial accounts downstream of B, such as C, D, and E, are also identified as untrusted financial accounts, that is, the weights of the directed edges associated with C, D, and E are set to 0.
  • the upstream and downstream relationship of the financial account is defined by the flow of funds for the transfer transaction, that is, the direction of the directed edge.
  • FIG. 5 is a schematic diagram of an account relationship diagram of still another embodiment.
  • five financial accounts F, 2, 3, 4, and T constitute the vertices of the account relationship diagram, but it is necessary to understand the number of financial accounts in the account relationship diagram. It is not restrictive.
  • the financial account misbehavior changes, and the corresponding weights also change. For example, if financial account 5 successfully transfers a transaction to T, financial account 5 updates the update in the account relationship diagram, and the four directed edges of 2, 3, 4, and 5 can point to T, and their weights can be updated to 1/4.
  • the account relationship map is sent to the shortest distance value calculation module, and proceeds to the step minimum distance value calculation 120, in which, in response to the request for the transfer transaction, A shortest distance value of F and T is calculated based on the account relationship map, wherein the shortest distance value is calculated by a corresponding weight value for directly or indirectly connecting one or more directed edges of F and T.
  • the shortest distance value between F and T ie, Distance (F, T)
  • FIG. 5 is exemplified by taking the account relationship diagram of the embodiment shown in FIG. 5 as an example.
  • a voting-like strategy is adopted, such as asking through the directed edge and The F is directly connected to a plurality of adjacent financial accounts, if the M adjacent financial accounts (L 1 , L 2 , ..., L M ) and the shortest distance value of the T respectively (L 1 , T), ..., Distance (L M , T) are both less than Distance(max), then update Distance(F,T) to the average of Distance (L 1 ,T),...,Distance(L M ,T) of the M neighboring financial accounts.
  • M is an integer greater than or equal to 2.
  • At least two directed edges whose weights are not 0 directly point to each adjacent financial account, and the reliability of the adjacent financial account is less than 1; A directed edge that is not 0 directly points to an adjacent financial account, and the credibility of the adjacent financial account is higher.
  • the transaction response module may determine the risk level of the transfer transaction based on the shortest distance value and respond to control the transfer transaction process based on the corresponding risk level. For example, different responses are performed based on different risk levels, such as direct rejection, direct approval, weak verification factor approval, and strong verification factor approval.
  • Figure 6 is a diagram showing the risk level of a transfer transaction based on the shortest distance value. As shown in FIG. 6, it is exemplarily explained how to judge the risk level of the transfer transaction, that is, the degree of risk, based on the shortest distance value Distance(F, T).
  • the risk level can be divided according to the interval in which Distance(F,T) is located; when 0 ⁇ Distance(F,T) ⁇ D1, it is rated as lower risk interval; When D1 ⁇ Distance(F,T) ⁇ D2, it is assessed as a low risk interval; when D2 ⁇ Distance(F,T) ⁇ Distance(max), it is assessed as a medium risk interval; it can be determined according to the specific risk level. Whether the pen transfer transaction needs to collect more information from the financial account user to enhance the user experience and improve the success rate of the transaction;
  • the degree of freedom of the transfer transaction is limited according to the size of the shortest distance value, for example, when the value is less than or equal to D1, the user information may be collected or collected less, and the user information may be collected.
  • the transaction limit therefore, the user experience of the transfer transaction at this time is greatly improved.
  • the risk control of the transfer transaction in the embodiment of the present invention is to obtain the account relationship map through the historical transfer transaction data, and then obtain the shortest distance value between the transferred financial account and the transferred financial account to rate the risk level of the transfer transaction.
  • it can effectively reduce the probability of occurrence of risks, on the other hand, it can also improve the user experience of transfer transactions.
  • the present invention can be implemented as a method and implemented as a system and apparatus. When implemented as a system and apparatus, it includes at least an account relationship diagram generation module, a shortest distance calculation module, and a transaction corresponding module.
  • the invention can be implemented in the form of hardware and/or software (including firmware, resident software, microcode, etc.).
  • Computer program code for performing the operations of the present invention may employ an object oriented programming language (eg, Smalltalk or C++), a conventional procedural programming language (such as a "C" programming language or low-level code (such as assembly language and / or microcode).
  • the program code can be executed entirely on a single processor and / or in multiple processing Executed on the device as part of a separately running software package or another software package.
  • the program code can be executed entirely on the multimedia device or only partially on the multimedia device and partly on another device.
  • another device may be connected to the multimedia device via a wired and/or wireless local area network (LAN) and/or a wide area network (WAN), or the connection may be connected to an external computer (eg, by using an Internet service provider's Internet).
  • LAN local area network
  • WAN wide area network

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Finance (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

本发明属于转账交易技术领域，涉及转账交易的风险控制方法及装置。该转账交易的风险控制根据历史转账交易数据得到账户关系图、进而得到转出金融账户和转入金融账户之间的最短距离值来对该笔转账交易的风险等级进行评级。该转账交易的风险控制方法可以降低转账交易的风险，并且用户体验好。

Description

转账交易的风险控制方法及装置 技术领域
本发明属于转账交易技术领域，涉及转账交易的风险控制，尤其涉及根据历史转账交易数据得到账户关系图、进而得到转出金融账户和转入金融账户之间的最短距离值来对该笔转账交易的风险等级进行评级的转账交易的风险控制。
背景技术
在金融用户进行转账交易过程中，转账的安全性是每个用户在发生转账行为时首要关注的问题，但是，通常转账交易的安全性和便利性是相互矛盾的。
在转账交易的风险控制方法，现有技术都是针对转账过程采取技术手段来提高转账的安全性，例如，中国专利申请号200910086672.8的专利中，其涉及提高转账安全性的方法和系统，通过对交易数据签名、对传输的内容进行加密或者签名保护来保证转账安全,防止转账数据被非法攻击者篡改或截获取。因此，现有技术的转账交易的风险控制都是通过数据传输的安全层面来实现的。
然而，对于转入金融账户是否可信、转出金融账户是否落入被欺诈的转账交易行为中，现有的转账交易风险控制系统完全不能提供技术性的判断，完全依赖于转出金融账户用户自身来进行人为的识别。
现有技术中，对于金融账户的可信与否的审核，至多也是通过收集用户身份信息(例如身份证、照片)等人工审核的方式，这种通过人工审核用户的身份信息的方式不但人工工作量大、也影响交易的便利性，并且实际效果并不明显。
有鉴于此，有必要提出一种新型的转账交易的风险控制机制。
发明内容
本发明的目的之一在于，从对转账交易的转入金融账户的可信度出发来降低转账交易的风险。
本发明的还一目的在于，提高转账交易的用户体验。
为实现以上目的或者其他目的，本发明提供以下技术方案。
按照本发明的一方面，提供一种转账交易的风险控制方法，其包括：
账户关系图生成步骤：根据历史转账交易数据，将所有已经发生转账交易的多个金融账户、以金融账户为顶点建立账户关系图，在所述账户关系图中，在已发生转账交易的任意两个金融账户之间建立带权值的有向边，其中，越多有向边共同指向某一金融账户时，指向该金融账户的有向边的权值越小；
最短距离值计算步骤：响应于转账交易的请求，基于所述账户关系图计算转出金融账户与转入金融账户之间的最短距离值，其中，所述最短距离值通过用于直接或间接连接所述转出金融账户与转入金融账户的一条或多条有向边的相应权值计算得出；以及
交易响应步骤：基于所述最短距离值判断该转账交易的风险等级，并且根据相应的风险等级来响应控制该转账交易过程。
根据本发明一实施例的风险控制方法，其中，在所述交易响应步骤中，在所述转出金融账户与所述转入金融账户之间成功进行转账交易后，该转账交易被记录为历史转账交易数据，并返回至所述账户关系图生成步骤以更新所述账户关系图。
根据本发明又一实施例的风险控制方法，在某一历史转账交易数据被确定为欺诈交易的情况下，与该转账交易数据的转入金融账户相关的所有有向边的权值被设置为0以将其标识为不可信金融账户；并且，在所述最短距离值计算步骤中，如果该不可信金融账户被判断为转账交易的请求的转入金融账户时，则直接计算所述最短距离值为0。
在一实施例中，所述不可信金融账户的下游的金融账户也被标识为不可信金融账户。
在一实施例中在所述最短距离值为0时，风险等级被判定为“严重风险”，并禁止所述转账交易。
在之前所述任一实施例的风险控制方法中，在N个有向边共同指向某一金融账户时，该N个有向边的权值被设置为N分之一，其中N为大于或等于2的整数。
在之前所述任一实施例的风险控制方法中，在某一金融账户仅被一条有向边所指向时，该条有向边的权值被设置1。
根据本发明还一的风险控制方法，其中，采用广度优先的算法在 所述账户关系图中计算转出金融账户与金融账户之间的最短距离值。
根据本发明再一的风险控制方法，其中，在所述最短距离值计算步骤中，如果转出金融账户与金融账户之间的所述最短距离值大于预定值时，询问通过有向边与该转出金融账户直接连接的多个相邻金融账户，如果M个所述相邻金融账户分别与该转入金融账户的最短距离值小于所述预定值，则更新所述转出金融账户与金融账户之间的所述最短距离值为M个所述相邻金融账户分别与该转入金融账户的最短距离值的平均值，其中M为大于或等于2的整数。
在一实施例中，在计算所述最短距离值的过程中，如果从所述转出金融账户出发遍历的顶点的层数超过预定层数仍未到达转入金融账户，则停止所述遍历过程，直接记录转出金融账户与金融账户之间的所述最短距离值大于预定值。
在一实施例中，至少有两条权值不为0的有向边直接指向每个所述相邻金融账户。
在之前所述任一实施例的风险控制方法中，在所述交易响应步骤中，如果所述最短距离值大于预定值，风险等级被判定为“高风险”并显示给转出金融账户的用户，同时限制该转账交易的自由度。
在之前所述任一实施例的风险控制方法中，在所述交易响应步骤中，如果所述最短距离值大于0且小于或等于预定值，根据所述最短距离值的大小来限制该转账交易的自由度。
按照本发明的又一方面，提供一种转账交易的风险控制装置，其包括：
账户关系图生成模块，其被配置为根据历史转账交易数据，将所有已经发生转账交易的多个金融账户、以金融账户为顶点建立账户关系图，在所述账户关系图中，在已发生转账交易的任意两个金融账户之间建立带权值的有向边，其中，越多有向边共同指向某一金融账户时，指向该金融账户的有向边的权值越小；
最短距离值计算模块，其被配置为响应于转账交易的请求，基于所述账户关系图计算转出金融账户与转入金融账户之间的最短距离值，其中，所述最短距离值通过用于直接或间接连接所述转出金融账户与转入金融账户的一条或多条有向边的相应权值计算得出；以及
交易响应模块，其被配置为基于所述最短距离值判断该转账交易 的风险等级，并且根据相应的风险等级来响应控制该转账交易过程。
根据本发明一实施例的转账交易的风险控制装置，其中，在交易响应模块中，在所述转出金融账户与所述转入金融账户之间成功进行转账交易后，该转账交易被记录为历史转账交易数据，并返回至所述账户关系图生成模块以更新所述账户关系图。
根据本发明又一实施例的转账交易的风险控制装置，其中，在所述最短距离值计算模块中，如果转出金融账户与金融账户之间的所述最短距离值大于预定值时，询问通过有向边与该转出金融账户直接连接的多个相邻金融账户，如果M个所述相邻金融账户分别与该转入金融账户的最短距离值小于所述预定值，则更新所述转出金融账户与金融账户之间的所述最短距离值为M个所述相邻金融账户分别与该转入金融账户的最短距离值的平均值，其中M为大于或等于2的整数。
按照本发明的还一方面，提供一种包括计算机程序代码装置的计算机程序产品，用于当所述计算机程序代码装置被具有计算机能力的电子设备运行时执行以上所述及的风险控制方法。
本发明的这些和其他的优点及特征将从结合附图的以下描述中更加显而易见。
附图说明
从结合附图的以下详细说明中，将会使本发明的上述和其他目的及优点更加完整清楚，其中，相同或相似的要素采用相同的标号表示。
图1是按照本发明一实施例的转账交易的风险控制方法的流程示意图。
图2是账户关系图中的两个金融账户之间建立的带权值的有向边的示意图。
图3是一实施例的账户关系图的示意图。
图4是又一实施例账户关系图的示意图。
图5是再一实施例账户关系图的示意图。
图6是基于最短距离值评定转账交易的风险等级的示意图。
具体实施方式
下面介绍的是本发明的多个可能实施例中的一些，旨在提供对本发 明的基本了解，并不旨在确认本发明的关键或决定性的要素或限定所要保护的范围。容易理解，根据本发明的技术方案，在不变更本发明的实质精神下，本领域的一般技术人员可以提出可相互替换的其他实现方式。因此，以下具体实施方式以及附图仅是对本发明的技术方案的示例性说明，而不应当视为本发明的全部或者视为对本发明技术方案的限定或限制。
图1所示为按照本发明一实施例的转账交易的风险控制方法的流程示意图。在转账交易过程中，一般涉及转账交易的双方，即转出金融账户(以下简称为F)和转入金融账户(以下简称为T)，本发明通过对历史转账交易数据的分析来判断F与T之间的风险等级，为F的用户提供参考，提高转账交易的安全性。每个金融账户代表相应的用户，其可以但不限于以银行卡的卡号来表示。
如图1所示，该转账交易的风险控制方法过程中主要包括三个阶段，即账户关系图生成110、最短距离计算120以及交易响应130。在账户关系生成步骤110中，主要是基于历史转账交易数据来生成账户关系图，在账户关系图中，诸多历史转账交易数据中涉及的已经发生转账交易的多个金融用户被分布在账户关系图中，以每个金融账户为顶点，每个金融账户和与其发生过转账交易的其他金融账户通过有向边建立连接，每个有向边从转出方指向转入方，即F指向T，其方向反映交易的资金流入方向。在本发明中，每条有向边上对应设置有权值，该权值可以用来计算F与T之间的距离值，权值越小，反映相应的有向边所指向的T的可信度越高。
图2所示为账户关系图中的两个金融账户之间建立的带权值的有向边的示意图。以金融账户A和B为例，如果A和B发生一笔转账交易，则根据A和B的历史转账交易数据，如图2所示，在A和B之间建立有向边，其从转出方A指向转入方B，在不考虑其它交易的情况下，在该实施例中，权值设置为1。权值代表B的可信度，权值越大，B的可信度越低，向B转账的风险越大。
在本发明中，越多个F与T成功发生转账交易，T所对应的指向Td多个有向边的权值越小，这样，该T的可信度增加。
图3所示为一实施例的账户关系图的示意图。如图3所示，在金融账户C也向金融账户B成功转账后，C与B之间的有向边的权值为1/2， A与B之间的有向边的权值相应也降低，例如1/2。在该实施例中，在N个有向边共同指向某一金融账户时，该N个有向边的权值被设置为N分之一，其中N为大于或等于2的整数。因此，N越大，越多金融账户成功向B转账，指向B的有向边的权值越小，这样，代表B的可信度越高。需要理解的是，权值的具体设置方法并不限于本发明实施例。
图4所示为又一实施例账户关系图的示意图。在该实施例中，为进一步避免金融账户的用户的主观欺诈，可以根据欺诈交易记录来配置该欺诈用户的相关有向边的权值。如图3所示，在某一历史转账交易数据被确定为欺诈交易记录的情况下，B被确定为欺诈交易用户，那么与B相关的所有有向边的权值被设置为0以将其标识为不可信金融账户，即不可信的金融账户。进一步地，B为不可信金融账户时，B的下游的金融账户例如C、D和E也被标识为不可信金融账户，也即C、D和E相关的有向边的权值被设置为0。
需要理解的是，在本发明中，通过转账交易的资金的流向，也即有向边的指向方向来定义金融账户的上下游关系。
这样，如果金融账户B进行过诈骗，金融账户B以及其相关金融账户的诈骗都不能掩蔽。
图5所示为再一实施例账户关系图的示意图。在该实施例中，如图5所示，F、2、3、4和T五个金融账户构成了账户关系图的顶点，但是，需要理解的是，账户关系图中的金融账户的数量并不是限制性的，随着历史转账交易数据的增加，金融账户不端变化，并且，相应的权值也发生变化。例如，如果金融账户5向T成功发生转账交易，金融账户5将更新显示在账户关系图中，并且，2、3、4和5的四条有向边可以指向T，它们的权值可以更新为1/4。
进一步，如图1所示，在完成账户关系图生成步骤110后，账户关系图被发送至最短距离值计算模块，进入步骤最短距离值计算120，在该步骤中，响应于转账交易的请求，基于所述账户关系图计算F与T的最短距离值，其中，最短距离值通过用于直接或间接连接F与T的一条或多条有向边的相应权值计算得出。以下以图5所示实施例的账户关系图为例对F与T之间的最短距离值(即Distance(F，T))为例进行示例说明。
在该实施例中，采用广度优先的算法，在图5中寻找F到T的Distance (F，T)，例如，从F到T，可以遍历出3条路径，即F→3→T、F→2→T和F→2→4→T，分别计算它们的权值之和，分别为4/3、4/3、7/3，因此，Distance(F，T)＝4/3。
在又一实施例中，如果T被认定为不可信账户，其可信度被为0，也即其直接连接的有向边的权值都被置位0，此时则直接返回Distance(F,T)＝0，这样，不但计算省时，而且有助于控制转账风险。
在还一实施例中，在计算Distance(F,T)的过程中，如果Distance(F,T)大于预先设定的Distance(max)，则采用类似投票的策略，诸如询问通过有向边与该F直接连接的多个相邻金融账户，如果M个相邻金融账户(L1，L2，…，LM)分别与该T的最短距离值Distance(L1,T)，…，Distance(LM,T)都小于Distance(max)，则更新Distance(F,T)为该M个相邻金融账户的Distance(L1,T)，…，Distance(LM,T)的平均值，其中M为大于或等于2的整数。
在计算所述最短距离值的过程中，如果从F出发遍历的顶点的层数超过Layer(max)仍未到达T，则停止遍历过程，直接记录Distance(F,T)大于Distance(max)，此时，Distance(F,T)的计算也通过以上投票策略来确定。
在一实施例中，为进一步控制风险，至少有两条权值不为0的有向边直接指向每个相邻金融账户，此时该相邻金融账户的可信度小于1；越多条不为0的有向边直接指向相邻金融账户，该相邻金融账户的可信度越高。
需要理解的是，Distance(max)和Layer(max)可根据实际情况进行配置，例如，预先设置Distance(max)＝10，Layer(max)＝10。
在计算出最短距离值后Distance(F,T)，其被发生至交易响应模块，完成交易相应步骤130。交易响应模块可以对基于最短距离值判断该转账交易的风险等级，并且根据相应的风险等级来响应控制该转账交易过程。例如，根据不同的风险等级，进行不同的响应，比如直接拒绝、直接批准，弱验证因素批准和强验证因素批准等。
图6所示为基于最短距离值评定转账交易的风险等级的示意图。如图6所示，示例性地说明了如何根据最短距离值Distance(F,T)判断该转账交易的风险等级，也即风险程度。
如果Distance(F,T)＝0，则说明T发生过欺诈行为，可以直接拒绝转 账交易；
如果Distance(F,T)小于Distance(max)，则可以根据Distance(F,T)所处的区间划分风险等级；在0＜Distance(F,T)≤D1时，评定为较低风险区间；在D1＜Distance(F,T)≤D2时，评定为低风险区间；在D2＜Distance(F,T)≤Distance(max)时，评定为中风险区间；可以根据具体的风险等级，确定该笔转账交易是否需要收集金融账户用户更多信息，以提升用户体验，提升交易成功率；
如果Distance(F,T)＞Distance(max)时，评定为高风险区间；说明该笔交易风险较大(即转出金融账户及其金融账户的用户均认为该笔转账交易风险大)，属于高风险，用户被告知风险等级，对于该高风险区间的转账交易，需要完整收集用户验证要素、设置限额等方法来限制转账交易的自由度，以尽可能地减少风险发生。
需要理解的是，如何具体根据风险等级来采取金融交易的限制措施并不是限制性的，可以根据具体情况而设置。如果最短距离值大于0且小于或等于Distance(max)，根据所述最短距离值的大小来限制该转账交易的自由度，例如在小于或等于D1时，可以免收集或少收集用户信息，提高交易限额，因此，在此时转账交易的用户体验得到大大提升。
需要理解的是，在F与T之间成功进行转账交易后，该转账交易被记录为历史转账交易数据，并返回至账户关系图生成步骤110，以上述实施例的方式更新所述账户关系图。
因此，本发明实施例转账交易的风险控制是通过历史转账交易数据得到账户关系图、进而得到转出金融账户和转入金融账户之间的最短距离值来对该笔转账交易的风险等级进行评级，一方面能有效降低风险发生的概率，另一方面也能提升转账交易的用户体验。
正如本领域人员将认识到的，本发明可以作为方法来实施，而且作为系统和装置来实施，作为系统和装置来实施时，至少包括账户关系图生成模块、最短距离计算模块和交易相应模块。因此，本发明可以采用硬件和/或软件(包括固件、驻留软件、微代码等)的形式来实施。用于执行本发明的操作的计算机程序代码可以采用面向对象的编程语言(如
Figure PCTCN2015076511-appb-000001
Smalltalk或C++)、常规过程编程语言(例如“C”编程语言或低级代码(例如汇编语言和/或微代码)来编写。该程序代码可以完全在单个处理器上执行和/或在多个处理器上执行，作为单独运行的软件包或另 一个软件包的一部分来执行。该程序代码可以完全在多媒体装置上执行或仅部分在多媒体装置上执行以及部分在另一个装置上执行。在后一种情况中，另一个装置可以通过有线和/或无线局域网(LAN)和/或广域网(WAN)连接到多媒体装置，或该连接可以连到外部计算机(例如通过使用因特网服务提供商的因特网)。
以上例子主要说明了本发明的转账交易的风险控制方法及装置。尽管只对其中一些本发明的实施方式进行了描述，但是本领域普通技术人员应当了解，本发明可以在不偏离其主旨与范围内以许多其他的形式实施。因此，所展示的例子与实施方式被视为示意性的而非限制性的，在不脱离如所附各权利要求所定义的本发明精神及范围的情况下，本发明可能涵盖各种的修改与替换。

Claims (17)

  1. 一种转账交易的风险控制方法，其特征在于，包括：
    账户关系图生成步骤：根据历史转账交易数据，将所有已经发生转账交易的多个金融账户、以金融账户为顶点建立账户关系图，在所述账户关系图中，在已发生转账交易的任意两个金融账户之间建立带权值的有向边，其中，越多有向边共同指向某一金融账户时，指向该金融账户的有向边的权值越小；
    最短距离值计算步骤：响应于转账交易的请求，基于所述账户关系图计算转出金融账户与转入金融账户之间的最短距离值，其中，所述最短距离值通过用于直接或间接连接所述转出金融账户与转入金融账户的一条或多条有向边的相应权值计算得出；以及
    交易响应步骤：基于所述最短距离值判断该转账交易的风险等级，并且根据相应的风险等级来响应控制该转账交易过程。
  2. 如权利要求1所述的风险控制方法，其特征在于，在所述交易响应步骤中，在所述转出金融账户与所述转入金融账户之间成功进行转账交易后，该转账交易被记录为历史转账交易数据，并返回至所述账户关系图生成步骤以更新所述账户关系图。
  3. 如权利要求1所述的风险控制方法，其特征在于，在某一历史转账交易数据被确定为欺诈交易的情况下，与该转账交易数据的转入金融账户相关的所有有向边的权值被设置为0以将其标识为不可信金融账户；并且，在所述最短距离值计算步骤中，如果该不可信金融账户被判断为转账交易的请求的转入金融账户时，则直接计算所述最短距离值为0。
  4. 如权利要求3所述的风险控制方法，其特征在于，所述不可信金融账户的下游的金融账户也被标识为不可信金融账户。
  5. 如权利要求3或4所述的风险控制方法，其特征在于，在所述最短距离值为0时，风险等级被判定为“严重风险”，并禁止所述转账交易。
  6. 如权利要求1所述的风险控制方法，其特征在于，在N个有向边共同指向某一金融账户时，该N个有向边的权值被设置为N分之一， 其中N为大于或等于2的整数。
  7. 如权利要求1或6所述的风险控制方法，其特征在于，在某一金融账户仅被一条有向边所指向时，该条有向边的权值被设置1。
  8. 如权利要求1所述的风险控制方法，其特征在于，采用广度优先的算法在所述账户关系图中计算转出金融账户与转入金融账户之间的最短距离值。
  9. 如权利要求1所述的风险控制方法，其特征在于，在所述最短距离值计算步骤中，如果转出金融账户与转入金融账户之间的所述最短距离值大于预定值时，询问通过有向边与该转出金融账户直接连接的多个相邻金融账户，如果M个所述相邻金融账户分别与该转入金融账户的最短距离值小于所述预定值，则更新所述转出金融账户与转入金融账户之间的所述最短距离值为M个所述相邻金融账户分别与该转入金融账户的最短距离值的平均值，其中M为大于或等于2的整数。
  10. 如权利要求9所述的风险控制方法，其特征在于，在计算所述最短距离值的过程中，如果从所述转出金融账户出发遍历的顶点的层数超过预定层数仍未到达转入金融账户，则停止所述遍历过程，直接记录转出金融账户与转入金融账户之间的所述最短距离值大于预定值。
  11. 如权利要求9或10所述的风险控制方法，其特征在于，至少有两条权值不为0的有向边直接指向每个所述相邻金融账户。
  12. 如权利要求1所述的风险控制方法，其特征在于，在所述交易响应步骤中，如果所述最短距离值大于预定值，风险等级被判定为“高风险”并显示给转出金融账户的用户，同时限制该转账交易的自由度。
  13. 如权利要求1所述的风险控制方法，其特征在于，在所述交易响应步骤中，如果所述最短距离值大于0且小于或等于预定值，根据所述最短距离值的大小来限制该转账交易的自由度。
  14. 一种转账交易的风险控制装置，其特征在于，包括：
    账户关系图生成模块，其被配置为根据历史转账交易数据，将所有已经发生转账交易的多个金融账户、以金融账户为顶点建立账户关系图，在所述账户关系图中，在已发生转账交易的任意两个金融账户之间建立带权值的有向边，其中，越多有向边共同指向某一金融账户时，指向该金融账户的有向边的权值越小；
    最短距离值计算模块，其被配置为响应于转账交易的请求，基于所述账户关系图计算转出金融账户与转入金融账户之间的最短距离值，其中，所述最短距离值通过用于直接或间接连接所述转出金融账户与转入金融账户的一条或多条有向边的相应权值计算得出；以及
    交易响应模块，其被配置为基于所述最短距离值判断该转账交易的风险等级，并且根据相应的风险等级来响应控制该转账交易过程。
  15. 如权利要求14所述的转账交易的风险控制装置，其特征在于，在交易响应模块中，在所述转出金融账户与所述转入金融账户之间成功进行转账交易后，该转账交易被记录为历史转账交易数据，并返回至所述账户关系图生成模块以更新所述账户关系图。
  16. 如权利要求14所述的转账交易的风险控制装置，其特征在于，在所述最短距离值计算模块中，如果转出金融账户与转入金融账户之间的所述最短距离值大于预定值时，询问通过有向边与该转出金融账户直接连接的多个相邻金融账户，如果M个所述相邻金融账户分别与该转入金融账户的最短距离值小于所述预定值，则更新所述转出金融账户与转入金融账户之间的所述最短距离值为M个所述相邻金融账户分别与该转入金融账户的最短距离值的平均值，其中M为大于或等于2的整数。
  17. 一种包括计算机程序代码装置的计算机程序产品，用于当所述计算机程序代码装置被具有计算机能力的电子设备运行时执行根据权利要求1-13中任一项所述的方法。
PCT/CN2015/076511 2014-04-24 2015-04-14 转账交易的风险控制方法及装置 Ceased WO2015161746A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410166883.3A CN105005931A (zh) 2014-04-24 2014-04-24 转账交易的风险控制方法及装置
CN201410166883.3 2014-04-24

Publications (1)

Publication Number Publication Date
WO2015161746A1 true WO2015161746A1 (zh) 2015-10-29

Family

ID=54331733

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/076511 Ceased WO2015161746A1 (zh) 2014-04-24 2015-04-14 转账交易的风险控制方法及装置

Country Status (2)

Country Link
CN (1) CN105005931A (zh)
WO (1) WO2015161746A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111754342A (zh) * 2019-03-26 2020-10-09 众安信息技术服务有限公司 一种获得区块链加密货币流通速度的方法、系统及装置
US11074350B2 (en) 2016-07-01 2021-07-27 Advanced New Technologies Co., Ltd. Method and device for controlling data risk
CN115147115A (zh) * 2021-03-29 2022-10-04 腾讯科技（深圳）有限公司 资源转移数据的分析方法、装置、设备及介质
WO2022226910A1 (en) * 2021-04-29 2022-11-03 Paypal, Inc. Systems and methods for presenting and analyzing transaction flows using tube map format

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106682900B (zh) * 2015-11-10 2020-07-31 阿里巴巴集团控股有限公司 一种判断交易是否安全的方法和设备
CN106708839B (zh) * 2015-11-12 2021-04-23 创新先进技术有限公司 一种关系网络架构显示方法及装置
CN106803178B (zh) * 2015-11-26 2020-09-18 阿里巴巴集团控股有限公司 一种处理实体的方法和设备
CN105677801B (zh) * 2015-12-31 2021-06-08 中国银联股份有限公司 一种基于图的数据处理方法和系统
CN107292746A (zh) * 2016-04-13 2017-10-24 平安科技（深圳）有限公司 退保业务的信息处理方法和装置
CN106127463B (zh) * 2016-06-30 2020-03-17 宇龙计算机通信科技(深圳)有限公司 一种转账控制方法及终端设备
CN106548376A (zh) * 2016-10-27 2017-03-29 北京锐安科技有限公司 一种数据分析方法和装置
CN109934697A (zh) 2017-12-15 2019-06-25 阿里巴巴集团控股有限公司 一种基于图结构模型的信用风险控制方法、装置以及设备
CN109934706B (zh) 2017-12-15 2021-10-29 创新先进技术有限公司 一种基于图结构模型的交易风险控制方法、装置以及设备
CN108154368A (zh) * 2017-12-26 2018-06-12 阿里巴巴集团控股有限公司 一种资源风险的检测方法、装置及设备
CN109003089B (zh) * 2018-06-28 2022-06-10 中国工商银行股份有限公司 风险识别方法及装置
CN109118053B (zh) * 2018-07-17 2022-04-05 创新先进技术有限公司 一种盗卡风险交易的识别方法和装置
CN109146664A (zh) * 2018-07-20 2019-01-04 上海新储集成电路有限公司 一种针对金融账户的分类存储方法
CN109272323B (zh) * 2018-09-14 2022-03-04 创新先进技术有限公司 一种风险交易识别方法、装置、设备及介质
CN109461078B (zh) * 2018-10-22 2020-09-11 中信网络科技股份有限公司 一种基于资金交易网络的异常交易识别方法及系统
CN111612616A (zh) * 2020-02-27 2020-09-01 湖南天河国云科技有限公司 区块链账户评估方法、装置、终端设备及计算机可读介质
CN111432227B (zh) * 2020-03-27 2021-12-03 广州酷狗计算机科技有限公司 虚拟资源转移的风险确定方法、装置、服务器及存储介质
CN111539811B (zh) * 2020-05-27 2022-06-14 支付宝(杭州)信息技术有限公司 风险账户的识别方法及装置
CN114971921A (zh) * 2022-05-16 2022-08-30 中国银行股份有限公司 基于固定关系的交易风险控制方法及装置
CN114926160B (zh) * 2022-05-19 2025-08-15 中国银行股份有限公司 基于区块链的多账户支付方法及装置

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080133391A1 (en) * 2006-09-05 2008-06-05 Kerry Ivan Kurian User interface for sociofinancial systems and methods
CN101706937A (zh) * 2009-12-01 2010-05-12 中国建设银行股份有限公司 电子银行风险监控方法及系统
CN102110258A (zh) * 2009-12-28 2011-06-29 朱建明 基于信任模型的移动电子商务微支付方案

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101170409B1 (ko) * 2005-04-21 2012-08-02 주식회사 비즈모델라인 모바일 통합 금융계정 운용방법 및 시스템과 이를 위한서버, 기록매체
CN1987925A (zh) * 2006-12-29 2007-06-27 中国建设银行股份有限公司 一种金融系统综合前置平台及交易数据的转发方法
KR20130023307A (ko) * 2013-01-25 2013-03-07 인포뱅크 주식회사 휴대폰 번호를 이용한 실시간 계좌이체 서비스를 제공하는 중계 방법

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080133391A1 (en) * 2006-09-05 2008-06-05 Kerry Ivan Kurian User interface for sociofinancial systems and methods
CN101706937A (zh) * 2009-12-01 2010-05-12 中国建设银行股份有限公司 电子银行风险监控方法及系统
CN102110258A (zh) * 2009-12-28 2011-06-29 朱建明 基于信任模型的移动电子商务微支付方案

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
GUO, YANLI, RESEARCH ON DISTINGUISHING THE CLUSTERS OF CAPITAL ABNORMAL FLOW IN FINANCIAL NETWORK, 1 April 2007 (2007-04-01) *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11074350B2 (en) 2016-07-01 2021-07-27 Advanced New Technologies Co., Ltd. Method and device for controlling data risk
CN111754342A (zh) * 2019-03-26 2020-10-09 众安信息技术服务有限公司 一种获得区块链加密货币流通速度的方法、系统及装置
CN111754342B (zh) * 2019-03-26 2024-05-24 众安信息技术服务有限公司 一种获得区块链加密货币流通速度的方法、系统及装置
CN115147115A (zh) * 2021-03-29 2022-10-04 腾讯科技（深圳）有限公司 资源转移数据的分析方法、装置、设备及介质
WO2022226910A1 (en) * 2021-04-29 2022-11-03 Paypal, Inc. Systems and methods for presenting and analyzing transaction flows using tube map format

Also Published As

Publication number Publication date
CN105005931A (zh) 2015-10-28

Similar Documents

Publication Publication Date Title
WO2015161746A1 (zh) 转账交易的风险控制方法及装置
US9807105B2 (en) Adaptive behavior profiling and anomaly scoring through continuous learning
US11037229B2 (en) Fraud detection system for the faster payments system
WO2020051154A1 (en) Authenticated access and aggregation database platform
WO2019127834A1 (zh) 交易事件的处理方法、装置、终端设备及介质
US11935047B2 (en) Enhanced feedback exposure for merchants based on transaction metadata
US12536529B2 (en) Direct data share
WO2021137879A1 (en) Method and system for blockchain accreditation mechanism based on cybersecurity risk
CN110633988B (zh) 认证在线用户的系统和方法
US12131388B2 (en) System for data integrity monitoring and securitization
US20260120098A1 (en) Enhanced Feedback Exposure for Users Based on Transaction Metadata
US20210056620A1 (en) Multi-lender credit history record blockchain
US20230237467A1 (en) Risk Analysis System for Cold Restore Requests for Digital Wallets
US12373834B2 (en) Parallel transaction pre-authorization platform
CN112702410A (zh) 一种基于区块链网络的评估系统、方法及相关设备
CA3208415A1 (en) Direct data share
US10986198B2 (en) Multicomputer processing of user data with centralized event control
US20260127616A1 (en) Neuro-Symbolic Intelligence Configured for Transaction Dispute Resolution
US20260127605A1 (en) Intelligence Model for Analyzing and Determining Transaction Dispute Propensity
US11669838B2 (en) Dynamic transmission metadata validation adjustment based on network conditions
CN114187097B (zh) 数据分析方法、装置、设备、介质及产品
CN119963128A (zh) 一种基于智能合约的贷款审批方法、装置、设备及介质
CN116308378A (zh) 交易处理方法和装置
CN120807130A (zh) 基于区块链的额度确定方法、装置、设备、介质和程序产品
CN116342248A (zh) 基于ai的业务风险控制方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15783582

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09.03.2017)

122 Ep: pct application non-entry in european phase

Ref document number: 15783582

Country of ref document: EP

Kind code of ref document: A1