WO2019095829A1 - 基于互联网信贷的风险监控方法、装置及设备 - Google Patents

基于互联网信贷的风险监控方法、装置及设备 Download PDF

Info

Publication number
WO2019095829A1
WO2019095829A1 PCT/CN2018/105766 CN2018105766W WO2019095829A1 WO 2019095829 A1 WO2019095829 A1 WO 2019095829A1 CN 2018105766 W CN2018105766 W CN 2018105766W WO 2019095829 A1 WO2019095829 A1 WO 2019095829A1
Authority
WO
WIPO (PCT)
Prior art keywords
account
loan
type
collection
payment
Prior art date
Application number
PCT/CN2018/105766
Other languages
English (en)
French (fr)
Inventor
甘利民
陈凯
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2019095829A1 publication Critical patent/WO2019095829A1/zh

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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof

Definitions

  • the present application relates to the field of computer technology, and in particular, to a method, device and device for monitoring risk based on internet credit.
  • financial institutions can provide credit services to users.
  • financial institutions can provide loans with specified credits to users with loan needs based on the user's application (ie, transfer the specified amount of loans to the user's loan). In the account).
  • financial institutions In order to prevent loan users from using the loan maliciously or illegally, financial institutions usually monitor the user's loan behavior and use of the money.
  • financial institutions usually implement the monitoring of loans in the form of entrusted payment. Specifically, the financial institution pays the specified amount of money to the transaction object of the borrower who meets the agreed purpose.
  • financial institutions also use manual methods for risk monitoring.
  • the embodiments of the present specification provide a method, device and device for monitoring risk based on internet credit, which are used to implement risk monitoring of funds in an internet credit scenario.
  • an estimated risk result for the item is generated.
  • Monitoring module to monitor the collection account transferred from the loan account
  • An identification module that identifies the type of the collection account and the relationship between the accounts
  • the risk estimation module generates an estimated risk result for the payment according to the loan data, the type of the collection account, and the relationship between the accounts.
  • an internet credit-based risk monitoring device including: a processor and a memory, wherein:
  • the memory stores a risk monitoring program based on internet credit
  • the processor calls an internet credit based risk monitoring program stored in the memory and executes:
  • An estimated risk result for the payment is generated based on the loan data, the type of the collection account, and the relationship between the accounts.
  • a credit flow monitoring system based on the Internet financial model is established. Based on the system, after the loan is loaned to the borrower, the server can monitor the transfer path of the money in the loan account, and identify the payment account in the transfer path of the payment. The type and relationship between the accounts can determine the purpose of the payment, and in turn, can estimate the risk of the borrower's use of the loan. In the process, by introducing social network data, the scope of credit reflow monitoring has been expanded and the monitoring accuracy has been improved.
  • FIG. 1 is an execution logic relationship diagram based on an Internet credit-based risk monitoring process provided by an embodiment of the present specification
  • 3a and 3b are schematic diagrams showing a transfer path of funds according to an embodiment of the present specification
  • FIG. 4 is a schematic diagram of a method for determining an account type according to an embodiment of the present disclosure
  • FIG. 5 is a schematic diagram of actual application of risk monitoring based on Internet credit provided by an embodiment of the present disclosure
  • FIG. 6 is a schematic structural diagram of an Internet credit-based risk monitoring apparatus according to an embodiment of the present disclosure.
  • an execution logic diagram as shown in FIG. 1 may be employed.
  • the loan server, the loan account, and the associated account associated with the loan account may be included. among them:
  • the lender is generally considered to be an institution that can provide loans to users, such as banks, financial platforms, and financial websites. In some embodiments, the lender may also be a website or platform that provides virtual currency and related loan business.
  • the lender server shown in FIG. 1 may adopt a distributed/cluster server architecture, which is not specifically limited herein. For convenience of description, in the following, it will be simply referred to as: server. In practical applications, the lender can lend money to the borrower based on the request of the borrower, that is, the lender transfers the amount of the corresponding amount to the borrower's loan account through its server.
  • the borrowing account can be considered as the account used by the borrowing user for the loan.
  • the loan account may be an account that the borrowing user registers in advance with the lender, or may be another bank account, and is not specifically limited herein.
  • the payment is usually used, such as: payment, transfer, repayment, stock purchase, etc.
  • the money in the loan account will be transferred.
  • the aforementioned related account associated with the loan account can be understood as the account that flows after the transfer of the money.
  • the transfer of funds between accounts can be reflected in the change in the value of the account balance. Specifically, if the amount (assumed to be 300 yuan) is transferred from account A to account B. Then, the balance of the balance of the account A is reduced by 300, and the balance of the account B is increased by 300.
  • the server can monitor and track the payment based on the change of the balance value of the loan account and the related account, combined with the data such as the transfer/transaction record.
  • the server can monitor and track the payment based on the change of the balance value of the loan account and the related account, combined with the data such as the transfer/transaction record.
  • the server can identify the aforementioned related accounts, it is possible to determine whether the relevant account is a risk account, an illegal account or a general account, thereby determining whether the borrowing user illegally or maliciously utilizes the money, and further providing the estimated risk result.
  • the method may include the following steps:
  • Step S201 Acquire the loan data generated after the loan is made for the loan account.
  • the borrowing user may borrow from the lender, and accordingly, the lender transfers the specified amount of money to the borrowing account of the borrowing user through its server.
  • the server usually generates loan data for the loan operation, and the loan data may include at least: the loan account information, the loan amount information (usually, the loan amount is equal to the loan amount), the loan time information, the loan account information, and the like. .
  • Step S203 Monitor the payment account transferred from the loan account.
  • This amount is usually used when the borrower has received the payment.
  • the borrower may transfer the money from the loan account to another user's account. In the process, the borrower may use the money for illegal purposes or for malicious exploitation. Therefore, in the embodiment of the present specification, the server will monitor the account to which the payment is transferred (i.e., the collection account).
  • the account B can be considered as the actual collection account.
  • the funds are transferred from the loan account A to the account C, transferred to the account D via the account C, and then transferred from the account D to the account E, then the accounts C, D and E can be regarded as the collection account.
  • the money may be transferred between different accounts.
  • the transfer of funds between different accounts can be regarded as a kind of Path, that is, the money transfer path.
  • the account experienced by the money transfer path can be considered as a collection account.
  • Step S205 Identify the type of the payment account and the relationship between the accounts.
  • the type of the payment account can be identified through various ways, such as: identifying the type of the payment account by using the account name combined with the transfer keyword; or identifying the payment account through a pre-established identification model.
  • the collection mode which in turn determines the type of the collection account. The identification of the type of collection account will be described in detail in the following content, so I will not go into details here.
  • the server may assign a corresponding type identifier to the identified type of the payment account, thereby generating identification data.
  • relationship between the accounts may include the relationship between the loan account and each of the collection accounts, and may also include the relationship between the various collection accounts.
  • the association relationship between the accounts in this step can represent the association relationship between the account holders, and the association relationship may include: a person (the same person), a relative, a colleague, a classmate, a friend, and the like. This is not specifically limited.
  • Step S207 Generate an estimated risk result for the payment according to the loan data, the type of the payment account, and the relationship between the accounts.
  • the use of the loan amount can be estimated by combining the loan data, the type of the payment account, and the relationship between the accounts.
  • the loan account A transfers money to the collection account B
  • the collection account B transfers money to the collection account C
  • the holder of the collection account B is identified as the borrowing user himself
  • the collection account C is a betting bookmaker account
  • data can be identified by the transfer time interval, the number of transfers, the amount of transfer, and the type of collection account.
  • the server can use this to generate an estimated risk result for the payment.
  • the server can monitor the transfer path of the money in the loan account, and by identifying the type of the transfer account to which the payment is transferred, and the relationship between the accounts, it can be determined.
  • the purpose of the payment in turn, can be used to estimate the risk based on the use of the money.
  • the lender can be a non-bank third-party financial platform.
  • the financial platform can provide various financial services to a large number of users, such as : deposit, transfer, payment and other services.
  • the process of transferring the funds in the borrowing account to other accounts by the borrowing user may use the transfer service provided by the third-party financial platform, and the receiving account also belongs to the account of the third-party financial platform, then The server can monitor the transfer of funds.
  • the monitoring account transferred from the borrowing account to the receiving account may specifically: monitor the direct receiving account transferred to the borrowing account by the borrowing account, and the receiving account.
  • the direct receiving account and the receiving account are determined as the receiving account.
  • the loan account A transfers money to the collection account B
  • the payment account B is a direct receipt account
  • the collection account B transfers money to the collection account C
  • the collection account C is Receiving account.
  • the financial platform released a loan of 200,000 yuan to the borrowing user Wu X's loan account on October 20, 2017.
  • Wu X transferred the amount of 200,000 yuan in his loan account to Wang X's account.
  • Wang X transferred the RMB 190,000 in his account to Li X, and finally transferred RMB 190,000 from Li X to a bookmaker's account.
  • the server may determine the inter-accounting account by the following means, that is, monitoring the inter-accounting account, which may specifically include: determining the transfer of the money generated by the transfer to the direct receiving account The information, the account for monitoring the transfer amount and the time that meets the transfer information of the money, and the accounts are determined as the receiving account.
  • the transfer ratio (the ratio of the transfer amount to the loan amount), the transfer limit (only monitor the flow of the transfer amount), and the transfer interval (only how much after the loan is monitored)
  • the flow of funds within the day), the flow of funds to the monitoring level (tracking the flow of multiple credits) is monitored and determined. This is not specifically limited.
  • the social relationship network data is introduced, and the association between the users corresponding to the respective collection accounts is identified by the social relationship network data.
  • the server can identify between the users to which the payment account belongs in the money transfer path according to historical transfer records, network and device information, address book, and location based service (LBS) data. Relationship.
  • the server may obtain social relationship network data based on the corresponding algorithm or model and based on the above data, and the description is not excessive herein.
  • the network and device information may include: wireless fidelity network wifi information, a media access control (MAC) address of the terminal device used by the user, and an international mobile device identity code (International Mobile Equipment Identity, IMEI), Internet Protocol Address (IP) and other information.
  • MAC media access control
  • IMEI International Mobile Equipment Identity
  • IP Internet Protocol Address
  • social network data can be generated. Then, for the money transfer path in the foregoing example, for the money transfer performed by the account in which the financial platform is not used, the social relationship network data can be used to determine the relationship between the users to which the accounts belong, and further improve The transfer path.
  • the server may, according to Wang X's historical transfer record, count that Wang X has repeatedly transferred money to a user named "Li X", in the remarks of the multiple transfers, indicating Li X's mobile phone number.
  • Li X the transfer information of Li X to the betting bookmaker account, it is determined that Li X notes the same mobile phone number, so it can be determined that Li X in Wang X’s historical transfer record, and Li X in Figure 3a same person.
  • the server may obtain information such as the MAC address and IP address of the terminal device used by Wang X and Li X in the historical use of the corresponding financial service, and determine that the IP addresses used by the two persons are the same, then, There is a certain relationship between the two characters. Further, if in the transfer process shown in FIG. 3a, the server monitors that the MAC address of the terminal device that transfers the money to the bookmaker account is the same as the MAC address of the terminal device that is historically acquired by Li ⁇ , the server can be determined to go to the bookmaker. The transferee of the account is Li X.
  • the server can estimate that Wang X uses the money to Li X at a certain moment. The transfer is made, so the server can determine the payment transfer path as shown in Figure 3b.
  • the financial platform has a high probability of being illegally used for the loan of Wu X, so the corresponding risk result can be generated to suggest that the money may be at risk.
  • the type of collection account is determined by monitoring the collection/transfer behavior of the collection account.
  • the server may monitor the collection behavior of the amount, amount, and the like of a payment account within a set period of time.
  • the server may also monitor the number of times, the amount of money transferred, etc. of the payment account during the set time period.
  • an account receives the transfer of one or more accounts in a short period of time, then the possibility of the account is a small loan company account, a gaming account, a securities company account or a lottery, fund sales account. Large, the risk level is also higher.
  • the server can also determine other accounts having a high association with the account as the type based on the type of the predetermined account. For example, if an account is a betting book bank account, the probability that the account with which it has a high correlation relationship is a betting book bank account is higher.
  • the type of the payment account can be determined by the account name keyword and the keyword in the transfer information. Specifically, for the account name keyword, the account type is confirmed by matching the account name with keywords such as a small loan company, a securities company, and a real estate development company. For the transfer information keywords, the keywords appearing in the transfer notes such as repayment, interest, down payment, and house payment are confirmed to be types of online lending institutions and housing markets.
  • web crawling technology can be used to climb high-risk websites such as gambling, financial mutual assistance, P2P, etc., to associate the company names of these websites, and then associate the corresponding collection accounts according to the company name.
  • the risk monitoring method in the embodiment of the present specification can also be applied to a scenario in which a salesperson collects a user fee.
  • a salesperson collects a user fee.
  • the obtaining module 601 is configured to obtain the loan data generated after the loan is made for the loan account;
  • the monitoring module 602 monitors the collection account to which the payment is transferred from the borrowing account
  • the identification module 603 identifies the type of the payment account and the relationship between the accounts
  • the risk estimation module 604 generates an estimated risk result for the payment according to the loan data, the type of the payment account, and the relationship between the accounts.
  • the monitoring module 602 monitors the direct receiving account transferred by the borrowing account to the direct receiving account, and the receiving account, and determines the direct receiving account and the receiving account to be collected. Account.
  • the monitoring module 602 determines the money transfer information generated by the transfer of the money to the direct receiving account, monitors each account whose transfer amount and time meet the transfer information, and determines each account as the indirect Accounts receivable.
  • the identification module 603 identifies the type of the collection account by an account behavior of the collection account
  • the account behavior includes at least: the number of times, the amount of money received during the set time period, or the number and amount of money transferred during the set time period.
  • the identification module 603 identifies the type of the payment account by an association relationship with an account whose type has been determined.
  • the identification module 603 identifies the type of the payment account through the account name keyword of the payment account and the transfer remark keyword.
  • the identification module 603 identifies the type of the payment account based on the website information acquired in advance for the designated website.
  • the identification module 603 identifies an association relationship between the borrowing account, the direct receiving account, and the inter-accounting account according to the pre-generated social network data.
  • the risk estimation module 604 determines the use of the payment according to the loan data, the type of the payment account, and the relationship between the accounts, and generates an estimated risk result for the payment according to the use.
  • an internet credit-based risk monitoring device including: a processor and a memory, wherein:
  • the memory stores a risk monitoring program based on internet credit
  • the processor calls an internet credit based risk monitoring program stored in the memory and executes:
  • An estimated risk result for the payment is generated based on the loan data, the type of the collection account, and the relationship between the accounts.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • the controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor.
  • computer readable program code eg, software or firmware
  • examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component.
  • a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.
  • the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, 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 disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the application can be described in the general context of computer-executable instructions executed by a computer, such as a program module.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular transactions or implement particular abstract data types.
  • the present application can also be practiced in distributed computing environments where transactions are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (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

本说明书实施例公开了基于互联网信贷的风险监控方法、装置及设备，当贷款方向借款用户放款后，服务器可针对借款账户中款项的所转移到的不同收款账户进行监测，通过识别出不同收款账户的类型、各账户之间的关联关系，可以进一步确定出款项的用途，进而，可以针对所借贷的款项的使用进行风险预估。

Description

基于互联网信贷的风险监控方法、装置及设备 技术领域
本申请涉及计算机技术领域，尤其涉及基于互联网信贷的风险监控方法、装置及设备。
背景技术
在传统金融的应用场景下，金融机构可以向用户提供信贷业务，换言之，金融机构可以基于用户的申请，向有贷款需求的用户提供指定额度的贷款(即，将指定额度的贷款转入用户的账户中)。为了防止贷款用户恶意或非法利用贷款，金融机构通常会针对用户的贷款行为及对款项的使用进行监控。作为一种惯常手段，金融机构通常会以受托支付的方式实现对贷款的监控，具体而言，金融机构将指定额度的款项支付给符合约定用途的借款人的交易对象。除此之外，金融机构还采用人工的方式进行风险监控。
但目前随着互联网技术的发展，传统金融机构与互联网技术的结合越来越紧密，互联网贷款自身所具有的在线、小额、高频、分散等特点，使得传统的监控方式难以有效监控。
基于此，我们需要一种有效地针对基于互联网信贷的风险监控方式。
发明内容
本说明书实施例提供基于互联网信贷的风险监控方法、装置及设备，用以在互联网信贷场景下实现对款项的风险监控。
本说明书实施例提供的一种基于互联网信贷的风险监控方法，包括：
获取针对借款账户进行放款后生成的放款数据；
监测款项从借款账户所转移到的收款账户；
识别所述收款账户的类型及账户之间的关联关系；
根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款 项的预估风险结果。
本说明书实施例提供的一种基于互联网信贷的风险监控装置，包括：
获取模块，获取针对借款账户进行放款后生成的放款数据；
监测模块，监测款项从借款账户所转移到的收款账户；
识别模块，识别所述收款账户的类型及账户之间的关联关系；
风险预估模块，根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
对应地，本说明书实施例中还提供一种基于互联网信贷的风险监控设备，包括：处理器、存储器，其中：
所述存储器，存储基于互联网信贷的风险监控程序；
所述处理器，调用存储器中存储的基于互联网信贷的风险监控程序，并执行：
获取针对借款账户进行放款后生成的放款数据；
监测款项从借款账户所转移到的收款账户；
识别所述收款账户的类型及账户之间的关联关系；
根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
本说明书实施例采用的上述至少一个技术方案能够达到以下有益效果：
搭建了基于互联网金融模式下的信贷流向监控体系，基于该体系，当贷款方向借款用户放款后，服务器可针对借款账户中款项的转移路径进行监测，通过识别出款项的转移路径中的收款账户的类型以及各账户之间的关联关系，可以确定出款项的用途，进而，可以针对借款用户对借款款项的使用进行风险预估。在该过程中，通过引入社交关系网络数据，扩大了信贷款项回流监测范围、提高了监测准确度。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1为本说明书实施例提供的基于互联网信贷的风险监控过程所基于的执行逻辑关系图；
图2为本说明书实施例提供的在数据提供方侧的基于互联网信贷的风险监控过程；
图3a和3b为本说明书实施例提供的对款项的转移路径示意图；
图4为本说明书实施例提供的确定账户类型的方式示意图；
图5为本说明书实施例提供的基于互联网信贷的风险监控的实际应用示意图；
图6为本说明书实施例提供的基于互联网信贷的风险监控装置结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请具体实施例及相应的附图对本申请技术方案进行清楚、完整地描述。显然，所描述的实施例仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
在本说明书的一个或多个实施例中，可以采用如图1所示的执行逻辑关系图。图1中至少可包括：贷款方服务器、借款账户、与借款账户具有关联的相关账户。其中：
贷款方，通常可认为是银行、金融平台、金融网站等能够向用户提供贷款业务的机构。在某些实施例中，所述的贷款方还可以是提供虚拟货币及相关贷款业务的网站或平台。图1中所示的贷款方服务器，具体可采用分布/集群式的 服务器架构，这里并不作具体限定。为便于描述，在以下内容中，将简称为：服务器。在实际应用中，贷款方可以基于借款用户的请求，向借款用户放款，也即，贷款方通过其服务器向借款用户的借款账户中转入相应额度的款项。
借款账户，可认为是借款用户为借款所使用的账户。具体地，该借款账户可以是借款用户预先在贷款方注册的账户，也可以是其他银行账户，这里并不进行具体限定。
在实际应用中，当借款用户从贷款方借贷了相应额度的款项后，通常会使用该款项，如：购物支付、转账、还款、买入股票等等，换言之，借款账户中的款项会转移至其他账户中。那么，前述与借款账户具有关联的相关账户，也就可理解为款项发生转移后所流入的账户。
这里需要说明的是，对于上述的任一账户而言，款项在账户间的转移，可体现在账户余额数值的变化，具体而言，如果款项(假设为300元)从账户A转移到账户B，那么，账户A的余额所减少的数值为300，而账户B的余额所增加的数值为300。
因此，在本说明书实施例中，服务器可基于借款账户及相关账户的余额数值的变化，结合转账/交易记录等数据，实现对款项的监控和追踪。此外，可以通过识别前述相关账户的方式，确定出相关账户是否为风险账户、非法账户或普通账户，进而确定出借款用户是否非法或恶意利用了款项，进一步提供预估的风险结果。
在上述如图1所示的架构基础上，下面将具体阐述本说明书实施例中的基于互联网信贷的风险监控方法。
如图2所示，所述方法可包括如下步骤：
步骤S201：获取针对借款账户进行放款后生成的放款数据。
在本说明书实施例中，借款用户可向贷款方借款，相应地，贷款方通过其服务器将指定额度的款项转入至借款用户的借款账户中。在此过程中，服务器通常会针对该放款操作，生成放款数据，该放款数据中至少可包括：放款账户 信息、放款额度信息(通常，放款额度等于借款额度)、放款时间信息、借款账户信息等。
步骤S203：监测款项从借款账户所转移到的收款账户。
当借款用户获得了款项后，通常会使用该款项，如前所述，借款用户可能将借款账户中的款项转移到其他用户的账户内。在该过程中，借款用户可能会将款项用于非法目的或进行恶意利用。故在本说明书实施例中，服务器将监测款项所转移到的账户(即，收款账户)。
例如：款项从借款账户A转移至某账户B，则该账户B可认为是实际收款账户。又例如：款项从借款账户A转移至账户C，经账户C转移至账户D，再由账户D转移至账户E，那么，该账户C、D和E可认为是收款账户。
需要说明的是，借款用户将借款账户中的款项转移出该借款账户后，该款项可能会在不同账户之间发生转移，在此过程中，可将款项在不同账户间的转移看作为一种路径，即，款项转移路径。款项转移路径所经历过的账户均可认为是收款账户。
步骤S205：识别所述收款账户的类型及账户之间的关联关系。
在本说明书实施例中，可以通过多种途径识别出收款账户的类型，如：通过账户名结合转账关键词，识别收款账户的类型；或者，通过预先建立的识别模型，识别收款账户的收款模式，进而确定该收款账户的类型。对收款账户类型的识别将在后续内容中详细说明，这里先不过多赘述。
在一种可能的实施方式中，服务器可针对识别出的收款账户的类型，可以赋予相应的类型标识，从而生成标识数据。
应理解，账户之间的关联关系，可以包括借款账户和各个收款账户之间的关系，也可包括各个收款账户之间的关系。
本步骤中账户之间的关联关系，能够表征账户持有者之间的关联关系，该关联关系可包括：同人(同一人)、亲属、同事、同学、朋友等。这里不作具体限定。
步骤S207：根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
在本说明书实施例中，结合放款数据、收款账户的其类型及账户之间的关联关系，可以预估借款款项的用途。在一个简单示例中：假设，借款账户A向收款账户B转账，收款账户B又向收款账户C转账，如果识别出收款账户B的持有者是借款用户本人，而收款账户C是博彩庄家账户，那么，该款项便可能被用于赌博。
在另一个简单示例中：可以通过转账时间间隔、转账次数、转账额度等数据，结合收款账户的类型，识别款项的异常回流。
显然，服务器可以以此生成针对款项的预估风险结果。
基于前述内容，当贷款方向借款用户放款后，服务器可针对借款账户中款项的转移路径进行监测，通过识别出款项所转移到的收款账户的类型，以及账户之间的关联关系，便可以确定出款项的用途，进而，能够据此针对款项的使用进行风险预估。
以上是本说明书实施例中风险监控方法的主要过程，其中的贷款方可以是非银行的第三方金融平台，该金融平台除了能够提供贷款业务之外，其可面向大量用户提供各类金融服务，如：存款、转账、支付等服务。在此前提下，借款用户将借款账户中的款项转移至其他账户的过程，可能会使用该第三方金融平台所提供的转账服务，且，收款账户也属于该第三方金融平台的账户，那么，服务器便可对款项的转移进行监测。
基于此，在本说明书实施例中，监测款项从借款账户所转移到的收款账户，具体可为：监测由所述借款账户将所述款项转移到的直接收款账户，以及间接收款账户，将所述直接收款账户及间接收款账户，确定为收款账户。正如前例，借款账户A向收款账户B转账，那么，该收款账户B则为直接收款账户，而如果收款账户B又向收款账户C转账，那么，该收款账户C则为间接收款账户。
但应注意的是，在实际的应用场景中，款项转移路径中可能涉及多个收款账户，且，款项转移路径中某些账户之间所进行的款项转移并未使用上述第三方金融平台的转账服务，那么，这将导致服务器难以准确识别出款项转移路径。
例如，假设一条完整的款项转移路径为：
金融平台→吴×→王×→李×→博彩庄家账户
具体而言，金融平台作为贷款方，于2017年10月20日向借款用户吴×的借款账户放款20万元，同日，吴×将其借款账户中的款项20万元转入王×的账户，2017年10月21日王×将其账户中的19万元转给李×，最终由李×向某博彩庄家账户转账19万元。
并假设，在上述款项转移路径中，王×向李×转账的过程，并未使用上述金融平台所提供的转账服务。那么，在此情况下，对于服务器而言，其根据基础放款数据中的放款额度、放款时间等参数结合其他预警方式。
换言之，在此情况下，服务器可通过以下方式确定出间接收款账户，即，监测所述间接收款账户，具体可包括：确定所述款项转移到所述直接收款账户所生成的款项转移信息，监测转账额度及时间符合所述款项转移信息的各账户，将所述各账户确定为所述间接收款账户。
当然，对于间接收款账户而言，还可以通过配置转账比例(转账金额占放款金额的比例)、转账额度下限(只监测转账额度多少以上的款项流向)、转账时间间隔(只监测放款后多少天内的款项流向情况)、款项流向监控层数(追踪多次层信贷款项流向)等方式进行监测及确定。这里并不作具体限定。
然而，基于上述过程所监测到的结果可能如图3a所示，也仍不能有效识别出款项的款项转移路径。
为此，在本说明书实施例中，引入社交关系网络数据，通过该社交关系网络数据识别出各收款账户所对应的用户之间的关联。
具体而言，服务器可根据历史转账记录、网络及设备信息、通讯录、基于位置服务(Location Based Service，LBS)等数据，识别出款项转移路径中所 涉及到的收款账户所属的用户之间的关联关系。
当然，可以理解的是，在本说明书实施例中，服务器可以基于相应的算法或模型，并基于上述数据，得到社交关系网络数据，这里便不再过多进行说明。
其中，所述的网络及设备信息，可包括：无线保真网络wifi信息、用户所使用的终端设备的媒体访问控制(Media Access Control，MAC)地址、国际移动设备身份码(International Mobile Equipment Identity，IMEI)、互联网协议地址(Internet Protocol Address，IP)等信息。
基于上述方式，便可以生成社交关系网络数据。那么，对于前述示例中的款项转移路径而言，对于其中未使用金融平台的账户所进行的款项转移，可通过该社交关系网络数据，确定出这些账户所属用户之间的关联关系，并进一步完善款项转移路径。
结合上述示例，在一种示例中，服务器可根据王×的历史转账记录，统计出王×多次向名为“李×”的用户进行转账，在其多次转账的备注信息中，注明了李×的手机号码。在图3a中，根据李×向博彩庄家账户的转账信息，确定出李×备注了相同的手机号码，故可以确定出王×的历史转账记录中的李×，与图3a中的李×为同一人。
在另一种示例中，服务器可获取王×、李×在历史上使用相应金融服务时所使用的终端设备的MAC地址、IP地址等信息，并确定二人所使用的IP地址相同，那么，表征二人存在一定的关联关系。进一步地，如果在图3a所示的转账过程中，服务器监测到向博彩庄家账户转账的终端设备的MAC地址与历史上获取到李×使用的终端设备的MAC地址相同，则可确定出向博彩庄家账户的转账人为李×。
结合上述两个示例中的监测识别结果，且吴×转给王×的款项的额度与李×转给博彩庄家账户的额度相近，那么，服务器可预估王×在某时刻向李×使用款项进行了转账，故服务器而言，便可确定出如图3b所示的款项转移路径。
当然，在实际应用中，还可以通过其他社交关系网络数据确定出款项所转 移到的不同收款账户，这里便不再过多赘述。
结合图3b所示的款项转移路径，金融平台向吴×的放款有较大概率被非法利用，故可生成相应的风险结果，以提示该笔款项可能存在风险。
需要说明的是，对于本说明书实施例中的上述方法而言，对于收款账户类型的确定，可以采用不同的方式。下面结合图4进行具体说明。
1、基于收款账户的行为
在该方式下，通过监测收款账户的收款/转账行为来确定收款账户的类型。在一种实施例中，服务器可以监测某一收款账户在设定时间段内所收取的款项的次数、额度等收款行为。当然，在其他实施例中，服务器也可以监测该收款账户在设定时间段内所转出的款项次数、额度等转出行为。
显然，如果某个账户，在短时间内集中接收到一个/多个账户的款项转入，那么，该账户是小型贷款公司账户、博彩账户、证券公司账户或彩票、基金销售账户的可能性比较大，其风险等级也较高。
2、基于收款账户的关联关系
在该方式下，服务器可以基于预先确定出的账户所属的类型，将与该账户具有高关联关系的其他账户也确定为该类型。例如：某账户是博彩庄家账户，则与其有高关联关系的账户是博彩庄家账户的概率较高。
3、基于关键词
在该方式下，可通过账户名关键词以及转账信息中的关键词，确定收款账户的类型。具体地，对于账户名称关键词而言，通过诸如小贷公司、证券公司、房地产开发公司等关键词匹配账号名称，从而确认账户类型。对于转账信息关键词而言，通过诸如还款、利息、首付、房款等转账备注中出现的关键词，确认收款账户类型为网贷机构、房市等类型。
4、基于爬取的网站信息
在该方式下，可通过网络爬虫技术，爬取诸如赌博、金融互助、P2P等高风险网站，关联出这些网站的公司名称，再根据公司名称关联出相应的收款账 户。
可以理解的是，上述所列出的方式仅是确定收款账户类型的可能方式，在实际应用中，还可能利用其它方式，诸如人工核查等，这里并不应构成对本申请的限定。
在上述内容的基础上，本说明书实施例中的风险监控方法，还可以应用于监测销售人员收取用户手续费的场景。具体而言：
如图5所示，假设销售人员孙**向银行推荐用户王**进行贷款，假设银行于2017年5月21日向用户王**发放50万元个人贷款，通过社交关系网络数据，服务器确定出王**的亲友账户在2017年5月22日，即贷款发放后不到1天时间，转账5万元到孙**的亲友账户胡**账户上，从而生成相应的风险结果，银行基于该风险结果可以采取相应措施，如：进行人工排查。
以上为本申请提供的基于互联网信贷的风险监控方法的几种实施例，基于同样的思路，本申请还提供了基于互联网信贷的风险监控装置的实施例，如图6所示，在数据提供方侧，基于互联网信贷的风险监控装置包括：
获取模块601，获取针对借款账户进行放款后生成的放款数据；
监测模块602，监测款项从借款账户所转移到的收款账户；
识别模块603，识别所述收款账户的类型及账户之间的关联关系；
风险预估模块604，根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
进一步地，所述监测模块602，监测由所述借款账户将所述款项转移到的直接收款账户，以及间接收款账户，将所述直接收款账户及间接收款账户，确定为收款账户。
所述监测模块602，确定所述款项转移到所述直接收款账户所生成的款项转移信息，监测转账额度及时间符合所述款项转移信息的各账户，将所述各账户确定为所述间接收款账户。
所述识别模块603，通过所述收款账户的账户行为识别所述收款账户的类 型；
其中，所述账户行为至少包括：在设定时间段内所收取的款项的次数、额度，或，在设定时间段内所转出的款项的次数、额度。
所述识别模块603，通过与类型已确定的账户之间的关联关系，识别所述收款账户的类型。
所述识别模块603，通过所述收款账户的账户名关键词及转账备注关键词，识别所述收款账户的类型。
所述识别模块603，基于预先针对指定网站获取的网站信息，识别所述收款账户的类型。
所述识别模块603，根据预先生成的社交关系网络数据，识别所述借款账户、直接收款账户以及间接收款账户之间的关联关系。
所述风险预估模块604，根据所述放款数据、收款账户类型以及账户之间的关联关系，确定所述款项的用途，根据所述用途生成针对所述款项的预估风险结果。
相应地，本说明书实施例中，还提供一种基于互联网信贷的风险监控设备，包括：处理器、存储器，其中：
所述存储器，存储基于互联网信贷的风险监控程序；
所述处理器，调用存储器中存储的基于互联网信贷的风险监控程序，并执行：
获取针对借款账户进行放款后生成的放款数据；
监测款项从借款账户所转移到的收款账户；
识别所述收款账户的类型及账户之间的关联关系；
根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对 于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存 储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本申请时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、 方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定事务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行事务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (19)

  1. 一种基于互联网信贷的风险监控方法，所述方法包括：
    获取针对借款账户进行放款后生成的放款数据；
    监测款项从借款账户所转移到的收款账户；
    识别所述收款账户的类型及账户之间的关联关系；
    根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
  2. 如权利要求1所述的方法，监测款项从借款账户所转移到的收款账户，具体包括：
    监测由所述借款账户将所述款项转移到的直接收款账户，以及间接收款账户；
    将所述直接收款账户及间接收款账户，确定为收款账户。
  3. 如权利要求2所述的方法，监测所述间接收款账户，具体包括：
    确定所述款项转移到所述直接收款账户所生成的款项转移信息；
    监测转账额度及时间符合所述款项转移信息的各账户；
    将所述各账户确定为所述间接收款账户。
  4. 如权利要求2所述的方法，识别所述收款账户的类型，具体包括：
    通过所述收款账户的账户行为识别所述收款账户的类型；
    其中，所述账户行为至少包括：在设定时间段内所收取的款项的次数、额度，或，在设定时间段内所转出的款项的次数、额度。
  5. 如权利要求2所述的方法，识别所述收款账户的类型，具体包括：
    通过与类型已确定的账户之间的关联关系，识别所述收款账户的类型。
  6. 如权利要求2所述的方法，识别所述收款账户的类型，具体包括：
    通过所述收款账户的账户名关键词及转账备注关键词，识别所述收款账户的类型。
  7. 如权利要求2所述的方法，识别所述收款账户的类型，具体包括：
    基于预先针对指定网站获取的网站信息，识别所述收款账户的类型。
  8. 如权利要求2所述的方法，识别账户之间的关联关系，具体包括：
    根据预先生成的社交关系网络数据，识别所述借款账户、直接收款账户以及间接收款账户之间的关联关系。
  9. 如权利要求1所述的方法，根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果，具体包括：
    根据所述放款数据、收款账户类型以及账户之间的关联关系，确定所述款项的用途；
    根据所述用途生成针对所述款项的预估风险结果。
  10. 一种基于互联网信贷的风险监控装置，包括：
    获取模块，获取针对借款账户进行放款后生成的放款数据；
    监测模块，监测款项从借款账户所转移到的收款账户；
    识别模块，识别所述收款账户的类型及账户之间的关联关系；
    风险预估模块，根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
  11. 如权利要求10所述的装置，所述监测模块，监测由所述借款账户将所述款项转移到的直接收款账户，以及间接收款账户，将所述直接收款账户及间接收款账户，确定为收款账户。
  12. 如权利要求11所述的装置，所述监测模块，确定所述款项转移到所述直接收款账户所生成的款项转移信息，监测转账额度及时间符合所述款项转移信息的各账户，将所述各账户确定为所述间接收款账户。
  13. 如权利要求11所述的装置，所述识别模块，通过所述收款账户的账户行为识别所述收款账户的类型；
    其中，所述账户行为至少包括：在设定时间段内所收取的款项的次数、额度，或，在设定时间段内所转出的款项的次数、额度。
  14. 如权利要求11所述的装置，所述识别模块，通过与类型已确定的账户之间的关联关系，识别所述收款账户的类型。
  15. 如权利要求11所述的装置，所述识别模块，通过所述收款账户的账户名关键词及转账备注关键词，识别所述收款账户的类型。
  16. 如权利要求11所述的装置，所述识别模块，基于预先针对指定网站获取的网站信息，识别所述收款账户的类型。
  17. 如权利要求11所述的装置，所述识别模块，根据预先生成的社交关系网络数据，识别所述借款账户、直接收款账户以及间接收款账户之间的关联关系。
  18. 如权利要求10所述的装置，所述风险预估模块，根据所述放款数据、收款账户类型以及账户之间的关联关系，确定所述款项的用途，根据所述用途生成针对所述款项的预估风险结果。
  19. 一种基于互联网信贷的风险监控设备，包括：处理器、存储器，其中：
    所述存储器，存储基于互联网信贷的风险监控程序；
    所述处理器，调用存储器中存储的基于互联网信贷的风险监控程序，并执行：
    获取针对借款账户进行放款后生成的放款数据；
    监测款项从借款账户所转移到的收款账户；
    识别所述收款账户的类型及账户之间的关联关系；
    根据所述放款数据、收款账户的类型及账户之间的关联关系，生成针对款项的预估风险结果。
PCT/CN2018/105766 2017-11-14 2018-09-14 基于互联网信贷的风险监控方法、装置及设备 WO2019095829A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711118989.6A CN108122163A (zh) 2017-11-14 2017-11-14 基于互联网信贷的风险监控方法、装置及设备
CN201711118989.6 2017-11-14

Publications (1)

Publication Number Publication Date
WO2019095829A1 true WO2019095829A1 (zh) 2019-05-23

Family

ID=62228378

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/105766 WO2019095829A1 (zh) 2017-11-14 2018-09-14 基于互联网信贷的风险监控方法、装置及设备

Country Status (3)

Country Link
CN (1) CN108122163A (zh)
TW (1) TW201923681A (zh)
WO (1) WO2019095829A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738396A (zh) * 2019-09-18 2020-01-31 阿里巴巴集团控股有限公司 一种针对设备的特征提取方法、装置及设备
CN111105307A (zh) * 2019-12-27 2020-05-05 中国工商银行股份有限公司 一种贷后管理方法、系统、设备及可读介质
CN111784509A (zh) * 2020-07-02 2020-10-16 深圳鼎盛电脑科技有限公司 一种动态校验方法、装置、电子设备及存储介质
CN112150294A (zh) * 2020-10-12 2020-12-29 中国农业银行股份有限公司 针对非法集资的识别方法、装置及电子设备
CN113689148A (zh) * 2021-09-26 2021-11-23 支付宝(杭州)信息技术有限公司 一种文本风险识别方法、装置及设备
CN114691865A (zh) * 2022-03-03 2022-07-01 支付宝(杭州)信息技术有限公司 一种基金产品的审核方法、装置以及设备

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108122163A (zh) * 2017-11-14 2018-06-05 阿里巴巴集团控股有限公司 基于互联网信贷的风险监控方法、装置及设备
CN108961023A (zh) * 2018-06-19 2018-12-07 阿里巴巴集团控股有限公司 一种信用退税方法、装置、系统及电子设备
CN109409876A (zh) * 2018-09-27 2019-03-01 深圳壹账通智能科技有限公司 基于区块链的电子合同签署方法、装置、设备及存储介质
CN110033151B (zh) * 2018-11-09 2024-01-19 创新先进技术有限公司 关系风险评价方法、装置、电子设备及计算机存储介质
CN109360088A (zh) * 2018-11-13 2019-02-19 平安科技（深圳）有限公司 贷款业务的处理方法、装置和计算机设备
CN110033362B (zh) * 2018-11-14 2023-07-18 创新先进技术有限公司 一种打款方法、装置及设备
CN110046194A (zh) * 2019-03-19 2019-07-23 阿里巴巴集团控股有限公司 一种扩展节点关系图的方法、装置和电子设备
CN110148053B (zh) * 2019-04-25 2021-05-18 北京淇瑀信息科技有限公司 用户信贷额度评估方法、装置、电子设备和可读介质
CN110533531B (zh) * 2019-09-05 2022-03-29 中国工商银行股份有限公司 识别异常账户的方法和装置、介质和电子设备
CN112541765A (zh) * 2019-09-20 2021-03-23 京东数字科技控股有限公司 用于检测可疑交易的方法和装置
CN110827038A (zh) * 2019-10-11 2020-02-21 支付宝(杭州)信息技术有限公司 账户权限的管理方法和设备
CN110895757B (zh) * 2019-11-29 2022-09-30 中国银行股份有限公司 一种作弊数据识别方法、装置、设备及系统
CN111429258A (zh) * 2020-03-19 2020-07-17 中国建设银行股份有限公司 一种监测贷款资金流向的方法和装置
CN111429257B (zh) * 2020-03-19 2024-04-12 中国建设银行股份有限公司 一种交易监控方法和装置
CN112785476B (zh) * 2021-02-01 2024-05-14 浙江大华系统工程有限公司 一种用户行为识别方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101930585A (zh) * 2010-09-01 2010-12-29 中国建设银行股份有限公司 一种授信业务风险监测系统及其方法
US20150379517A1 (en) * 2014-06-27 2015-12-31 GraphSQL, Inc. System and method for enhanced detection of fraudulent electronic transactions
CN105809535A (zh) * 2016-03-07 2016-07-27 浙江爱贷金融服务外包股份有限公司 一种借贷风险控制方法及系统
CN106033575A (zh) * 2015-03-11 2016-10-19 阿里巴巴集团控股有限公司 风险账户识别方法及装置
CN107316238A (zh) * 2017-06-30 2017-11-03 李亚平 一种基于信用的互联网借贷系统
CN108122163A (zh) * 2017-11-14 2018-06-05 阿里巴巴集团控股有限公司 基于互联网信贷的风险监控方法、装置及设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107180030B (zh) * 2016-03-09 2020-11-17 创新先进技术有限公司 一种网络上的关系数据生成方法及装置
CN106780012A (zh) * 2016-12-29 2017-05-31 深圳微众税银信息服务有限公司 一种互联网信贷方法及系统
CN106855989A (zh) * 2016-12-29 2017-06-16 深圳微众税银信息服务有限公司 一种贷后风险监控方法与系统
CN107169860A (zh) * 2016-12-30 2017-09-15 中国建设银行股份有限公司 一种风险预警方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101930585A (zh) * 2010-09-01 2010-12-29 中国建设银行股份有限公司 一种授信业务风险监测系统及其方法
US20150379517A1 (en) * 2014-06-27 2015-12-31 GraphSQL, Inc. System and method for enhanced detection of fraudulent electronic transactions
CN106033575A (zh) * 2015-03-11 2016-10-19 阿里巴巴集团控股有限公司 风险账户识别方法及装置
CN105809535A (zh) * 2016-03-07 2016-07-27 浙江爱贷金融服务外包股份有限公司 一种借贷风险控制方法及系统
CN107316238A (zh) * 2017-06-30 2017-11-03 李亚平 一种基于信用的互联网借贷系统
CN108122163A (zh) * 2017-11-14 2018-06-05 阿里巴巴集团控股有限公司 基于互联网信贷的风险监控方法、装置及设备

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738396A (zh) * 2019-09-18 2020-01-31 阿里巴巴集团控股有限公司 一种针对设备的特征提取方法、装置及设备
CN111105307A (zh) * 2019-12-27 2020-05-05 中国工商银行股份有限公司 一种贷后管理方法、系统、设备及可读介质
CN111784509A (zh) * 2020-07-02 2020-10-16 深圳鼎盛电脑科技有限公司 一种动态校验方法、装置、电子设备及存储介质
CN112150294A (zh) * 2020-10-12 2020-12-29 中国农业银行股份有限公司 针对非法集资的识别方法、装置及电子设备
CN112150294B (zh) * 2020-10-12 2023-10-13 中国农业银行股份有限公司 针对非法集资的识别方法、装置及电子设备
CN113689148A (zh) * 2021-09-26 2021-11-23 支付宝(杭州)信息技术有限公司 一种文本风险识别方法、装置及设备
CN114691865A (zh) * 2022-03-03 2022-07-01 支付宝(杭州)信息技术有限公司 一种基金产品的审核方法、装置以及设备

Also Published As

Publication number Publication date
CN108122163A (zh) 2018-06-05
TW201923681A (zh) 2019-06-16

Similar Documents

Publication Publication Date Title
WO2019095829A1 (zh) 基于互联网信贷的风险监控方法、装置及设备
JP7030983B2 (ja) ブロックチェーン残高調整方法およびデバイス、ならびに電子デバイス
JP7026793B2 (ja) 資金フロー方法および装置、ならびに電子デバイス
KR102394303B1 (ko) 자금 흐름 방법과 장치, 및 전자 디바이스
EP3780541B1 (en) Identity information identification method and device
US20170024813A1 (en) System and Method for Provisioning Financial Transaction Between a Lender and a Borrower
KR20190137069A (ko) 자산 이체 방법 및 장치, 그리고 전자 디바이스
WO2020119293A1 (zh) 内容推送方法及装置、电子设备
KR101722017B1 (ko) 빅데이터 분석을 이용한 ｐ２ｐ 뱅킹 방법 및 이를 수행하는 장치
US11403641B2 (en) Transactional probability analysis on radial time representation
TW201633236A (zh) 一種用於處理電子錢的方法與設備
CN109274639A (zh) 开放平台异常数据访问的识别方法和装置
CN111566683A (zh) 强健和自适应的人工智能建模
AU2019209580A1 (en) Method, apparatus, and electronic device for regulatory inspection
WO2020108152A1 (zh) 身份数据的防误用方法及装置、电子设备
US20230274275A1 (en) Authorization preprocessing systems and methods
CN111582872A (zh) 异常账号检测模型训练、异常账号检测方法、装置及设备
US20220261814A1 (en) Systems and methods for expedited resource issue notification and response
US20230262059A1 (en) System and methods for secure validation of unrestricted resource distribution
US20230384967A1 (en) Distributed network providing certificate rights for intelligent modeling outputs
US20240161090A1 (en) Fiat-crypto onramp
US20230394467A1 (en) System and method for providing restricted token usage during an onboarding phase
CA3161368A1 (en) System and method for providing restricted token usage during an onboarding phase
TWM617748U (zh) 協助電子支付系統使用者取得貸款的電子支付系統伺服器
TW202244819A (zh) 協助電子支付系統使用者取得貸款的電子支付系統伺服器及方法

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: 18877957

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18877957

Country of ref document: EP

Kind code of ref document: A1