WO2020233070A1 - 支付风险校验方法、装置、计算机设备及存储介质 - Google Patents

支付风险校验方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2020233070A1
WO2020233070A1 PCT/CN2019/121829 CN2019121829W WO2020233070A1 WO 2020233070 A1 WO2020233070 A1 WO 2020233070A1 CN 2019121829 W CN2019121829 W CN 2019121829W WO 2020233070 A1 WO2020233070 A1 WO 2020233070A1
Authority
WO
WIPO (PCT)
Prior art keywords
payee
account
website
user
official account
Prior art date
Application number
PCT/CN2019/121829
Other languages
English (en)
French (fr)
Inventor
李静静
Original Assignee
深圳壹账通智能科技有限公司
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 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2020233070A1 publication Critical patent/WO2020233070A1/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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing

Definitions

  • This application relates to the technical field of payment security, and in particular to a method, device, computer equipment and storage medium for checking payment risk.
  • the payment scenario is for example transfer back entry, that is, the insurance company recovers some compensation that has been compensated but the amount of compensation is over, and the general user will pay without hesitation , Thus fell into the trap of fraudsters. Therefore, how to effectively identify the existing payment risk is a problem that needs to be solved urgently.
  • This application provides a payment risk verification method, device, computer equipment and storage medium, which are used to effectively identify a user's potential payment risk.
  • the embodiment of the application provides a payment risk verification method, including:
  • the website If the payee has a risk of suspicious fraud, the website, the account information of the payee, the user complaint and report record, the number of payments of the official account, and the number of visits to the official account are composed of
  • the feature vector is input to the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • the embodiment of the application provides a payment risk verification device, including:
  • the obtaining module is used to obtain the payment request initiated by the user through the website, the payment request including the account information of the payee;
  • the obtaining module is also used to obtain the official account of the payee and the complaint and report record of the user through the information of the receiving account;
  • the statistics module is used to count the number of payments and visits of the official account
  • the verification module is used to verify the corresponding payment request through the website, the payee account information, the user complaint report record, the number of payments of the official account, and/or the number of visits to the official account Whether there is a suspicious risk of fraud on the payee;
  • the confirmation module is configured to, if the payee has a suspicious fraud risk, log the website, the payee account information, the complaint and report record of the user, the number of payments of the official account, and the official account
  • the feature vector composed of the number of visits is input to the suspicious fraud risk prediction model to obtain the fraud result of the payee.
  • a computer device includes a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor, and the processor implements the following steps when the processor executes the computer-readable instructions:
  • the website If the payee has a risk of suspicious fraud, the website, the account information of the payee, the user complaint and report record, the number of payments of the official account, and the number of visits to the official account are composed of
  • the feature vector is input to the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • One or more readable storage media storing computer readable instructions, when the computer readable instructions are executed by one or more processors, the one or more processors execute the following steps:
  • the website If the payee has a risk of suspicious fraud, the website, the account information of the payee, the user complaint and report record, the number of payments of the official account, and the number of visits to the official account are composed of
  • the feature vector is input to the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • FIG. 1 is a schematic diagram of an application environment of a payment risk verification method in an embodiment of the present application
  • Figure 2 is a flowchart of a payment risk verification method in an embodiment of the present application
  • FIG. 3 is a flowchart of payment verification in an embodiment of the present application
  • Fig. 4 is a functional block diagram of a payment risk verification device in an embodiment of the present application.
  • Fig. 5 is a schematic diagram of a computer device in an embodiment of the present application.
  • the payment risk verification method provided in this application can be applied in the application environment as shown in Figure 1, where the computer equipment communicates with the server through the network.
  • the computer device initiates a payment request to the server.
  • the payment request includes the account information of the payee.
  • the server obtains the official account of the payee through the account information of the payee, and the user complaints and reports records; The number of correct payments and the number of visits to the official account; finally through the website, the payee account information, the user complaint and report record, the correct number of payments of the official account, and/or the normality of the official account
  • the number of user visits verifies whether the payee corresponding to the payment request has a suspicious fraud risk.
  • the website, the account information of the payee, and the user complaint are reported
  • the feature vector composed of the record, the number of payments of the official account and the number of visits of the official account is input into the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • the computer equipment can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.
  • the server can be implemented as an independent server or a server cluster composed of multiple servers.
  • a payment risk verification method is provided.
  • the method is applied to the server in FIG. 1 as an example for description, including the following steps:
  • S10 Obtain a payment request initiated by a user through a website, where the payment request includes account information of the payee.
  • the account information of the payee includes the name of the payee and the account of the payee.
  • the name of the payee may be the name of the company or the name of the individual user, which is not specifically limited in the embodiment of the application.
  • the embodiment of this application can be applied to payment platforms such as Alipay and WeChat. That is, when a user makes a payment through Alipay or WeChat, the embodiment of this application can monitor the payment risk corresponding to the user's initiation of a payment request. Prevent users from the risk of fraud.
  • the user makes online payment through a link sent by a fraudster in the name of an insurance company, and then obtains a payment request initiated by the user through the link URL.
  • the payment request includes the amount to be paid, the recipient Name, as well as the recipient’s account number and other information.
  • the payee’s official account and the payee’s complaint and report record by the user through the payee account information in the payment request may be a WeChat official account. Or Alipay official account.
  • the user's complaint and report record can be obtained through the connected Alipay or WeChat platform, and the user's complaint and report record can also be obtained through business administration and other channels, which is not specifically limited in this application embodiment.
  • the payee's official account can be obtained through the payee account information in the payment request.
  • the number of payments includes the total number of payments, the number of correct payments, and the number of incorrect payments
  • the number of visits includes the total number of visits, the number of normal user visits, and the number of abnormal user visits.
  • the total number of payments of the user and the total number of visits of the user are obtained through the official account, and the correct number of payments is confirmed according to the total number of payments ; From the total number of visits, confirm the number of normal user visits.
  • this embodiment of the application can preliminarily determine whether a user is a normal visitor based on the time length of the user’s access to the official account. For example, a time threshold can be set. If the visit time is higher than this time threshold, it can be determined that the user is Normal access user; if the access duration is lower than this time threshold, the user can be preliminarily determined to be an abnormal access user. For a user who is initially determined to have abnormal access, check whether there is a purchase record. If it exists and has purchased a certain product through the official account within a short period of time, it can be confirmed that the user is an abnormal access user. Then, by counting the number of normal users visiting the official account, the number of normal users visiting the official account is obtained.
  • the verification through the website whether the payee corresponding to the payment request has a suspicious fraud risk includes: obtaining the domain name of the payee through the website; The cloud service platform determines whether the domain name is the domain name of a regular website; if the domain name is not the domain name of a regular website, it is determined that the payee corresponding to the payment request has a suspicious fraud risk.
  • a user jumps to this platform through a certain website to make payment, he needs to obtain the domain name corresponding to the redirected website and determine whether the domain name is the domain name of the official website.
  • the cloud service domain name of a small platform can be connected with the cloud service platform to determine whether the domain name is the domain name of a regular website through the linked cloud service platform, and the process of verifying whether the domain name is regular, many companies use such as Ali’s
  • the platform of the embodiment of this application can interface with Facebook Cloud, and even for all cloud services, verify whether the payee corresponding to the user's payment request is a regular merchant.
  • the account information of the payee can be the company information of the applied merchant.
  • some illegal accounts can be screened through detailed verification of the company's application information. Specifically, in this embodiment of the application, you can check whether the payee account information is legal through the connected national enterprise credit information publicity system. If it is not, you can confirm whether the payee corresponding to the payment request has a suspicious fraud risk. Enter the risk warning information to remind the user that there is a suspicious risk of fraud in the payment behavior.
  • the user’s complaint report record, the number of payments of the official account, or the number of visits of the official account are used to verify whether the payee corresponding to the payment request has a suspicious fraud risk , Including: if the user complaint and report record exceeds the preset number of reports, or the percentage of the number of correct payments of the official account is less than the first preset value, or the percentage of the number of normal user visits of the official account is less than the second
  • the preset value determines that the payee corresponding to the payment request has a suspicious fraud risk.
  • the first preset value and the second preset value can be set according to actual needs.
  • the percentage of the correct payment times of the official account is less than 60%, it is considered that there is a suspicious fraud risk; If the percentage of normal user visits is less than 50%, it can be considered that there is a risk of suspicious fraud, which is not specifically limited in the embodiment of the application.
  • the percentage of the correct payment times of the official account is the percentage value of the number of successful payments to the total number of payments. If the total number of payments is larger and the percentage of correct payments is higher, then the payment request corresponds to the payment The payer is more likely to be a regular merchant; if the total number of payments is large, but the percentage of correct payments is lower, that is, less than the first preset value, it can be determined that the payee corresponding to the payment request has a suspicious risk of fraud .
  • the percentage of the number of visits by normal users of the official account is the percentage of the number of visits by normal users to the total number of visitors.
  • the embodiment of the application can collect the historical visit times of the official account by docking WeChat or Alipay, and draw the visit curve according to the historical visit times, and judge whether there is an abnormal visit by analyzing the visit curve over a period of time, such as when there is no activity. In the case of a sharp increase in the number of visits, it can be confirmed that the official account is suspected of swiping orders, that is, the user is at risk of payment.
  • the embodiment of this application verifies whether the payee corresponding to the payment request exists according to the website, payee account information, user complaint and report record, the number of official account payments and/or the number of official account visits.
  • step S50 The verification step directly jumps to step S50 to continue; if it is verified that the payee does not have a suspicious fraud risk, continue to pass the payee account information, the user complaint and report record, the number of official accounts paid and the number of official account visits Recipients are verified separately according to the information of other dimensions. If the result of verification of the recipient according to the information of one dimension is that there is no suspicious fraud risk, then according to the website, the recipient’s account information, the user’s complaint and report record, and the official account The combination of multiple dimensions in the number of payments and the number of visits to the official account verifies whether the payee has a suspicious fraud risk.
  • the credit rating information of the website and the payee account information before inputting the feature vector consisting of the website, the payee account information, the user complaint and report record, the number of official account payments, and the number of official account visits into the suspicious fraud risk prediction model, it also includes: Obtain the credit rating information of the website and the payee account information; obtain the credit rating information of the website, the credit rating information of the payee account information, the user complaint and report record, and the public The feature vector of the number of payments of the account and the number of visits of the official account.
  • the credit rating information of the website and the payee account information can be determined by collecting the information marked by the network user.
  • the embodiment of the application may also determine the credit rating of the website and the payee account information in the form of a black and white list, which is not specifically limited in the embodiment of the application.
  • the suspicious fraud risk prediction model in this embodiment of the application is trained on a large amount of sample data, which contains the credit rating information of the website and the payee account information, the user complaint and report record, and the official account information.
  • the number of payments and the number of visits to the official account are obtained through the analysis and training of sample data to obtain a suspicious fraud risk preset model.
  • the probability that the payee is an online fraud can be predicted, thereby passing the suspicious fraud risk in the embodiment of this application.
  • the prediction model can accurately predict the user's dangerous behavior of online payment, thereby improving the security of user payment.
  • the payment risk information can be output to the client where the user is located to remind the user of the dangerous behavior that the user is paying; or after the risk of fraud is determined , Directly report to the relevant department and prohibit the user’s payment behavior this time, which is not specifically limited in the embodiment of this application.
  • the embodiment of the application provides a payment risk verification method. First, obtain the payment request initiated by the user through the website, and then obtain the official account of the payee, the record of complaints and reports by the user through the account The number of payments and the number of visits of the official account are finally verified by the website, the account information of the payee, the record of complaints and reports by the user, the number of payments of the official account, and/or the number of visits of the official account Whether the payee corresponding to the payment request has a suspicious fraud risk, if the payee has a suspicious fraud risk, the website, the payee account information, the user complaint and report record, the number of payments of the official account, and the visits of the official account The feature vector composed of times is input into the suspicious fraud risk prediction model to obtain the fraud result of the payee. Therefore, through the embodiments of the application, it is possible to determine whether there is a fraud risk in the user's payment behavior through multiple channels, so as to ensure the user's payment security, avoid the user's online payment behavior without
  • step S40 the number of payments made through the website, the payee account information, the user complaint and report record, and the official account, The number of visits to the official account verifies whether the payee corresponding to the payment request has a suspicious fraud risk, including:
  • S401 Calculate scores corresponding to the website and the payee account information respectively.
  • the embodiment of the application first obtains the domain name corresponding to the website, and then determines whether the domain name belongs to a regular website, and if so, sets the score of the website to 1; otherwise, sets the score of the website to 0.
  • the account information of the payee can be checked through the connected national enterprise credit information publicity system to check whether the account information of the payee is legal. If it is legal, set the score of the payee account information to 1; otherwise, the payee The score of the account information is set to 0.
  • S402 Calculate the number of times that the user has not complained and reported, the percentage value of the number of correct payments of the official account, and the percentage value of the number of normal user visits of the official account.
  • the number of user complaint and report records can be obtained through the official account, and the user's complaint and report records can also be obtained through channels such as business administration.
  • the percentage value of the correct number of payments of the official account is the percentage value of the number of successful payments and the total number of payments
  • the percentage of the number of normal user visits of the official account is the percentage value of the number of normal user visits to the total number of visits.
  • S403 Calculate the score of the website, the score of the payee account information, the percentage value of the record of no user complaint and report, the percentage value of the correct number of payments of the official account, and the percentage of the official account’s The weighted sum of the percentage values of the number of normal user visits to obtain the suspicious fraud risk coefficient.
  • the weight value corresponding to each evaluation parameter is set according to actual needs. If the percentage value of the correct payment times of the official account plays a larger role in the fraud judgment, the weight value can be set larger. The percentage value of the number of normal user visits of the official account plays a small role in the fraud judgment, and its weight value can be set relatively small. It should be noted that the weight value of each evaluation parameter adds up to 1.
  • the preset risk coefficient is set according to actual needs, for example, it can be determined according to the average value of the risk coefficient determined by the user's normal payment behavior, that is, according to the score of the normal payment behavior website and the payee account information
  • the weighted sum of the score, the percentage value of the record not reported by users, the percentage value of the correct payment times of the official account, and the percentage value of the normal user visits of the official account, and the weighted sum is averaged to get the preset Risk factor.
  • This embodiment of the application provides another payment risk verification method.
  • First calculate the scores corresponding to the website and the payee account information, and the number of complaints and reports recorded by the user. The percentage value of the number of correct payments and the percentage value of the number of normal user visits of the official account, and then calculate the score of the website, the score of the payee account information, and the number of complaints that have not been reported by the user.
  • the method further includes: obtaining the payee’s personal credit information through the personal account information; The weighted sum of the personal credit information and the percentage value of the record that has not been reported by the user to obtain the suspicious fraud risk coefficient; if the suspicious fraud risk coefficient is less than the preset risk coefficient, it is determined that the payee corresponding to the payment request has suspicious fraud risk.
  • a payment risk verification device is provided, and the payment risk verification device corresponds to the payment risk verification method in the above-mentioned embodiment one-to-one.
  • the payment risk verification device includes an acquisition module 10, a statistics module 20, a verification module 30, and a confirmation module 40.
  • acquisition module 10 the payment risk verification device includes an acquisition module 10, a statistics module 20, a verification module 30, and a confirmation module 40.
  • the obtaining module 10 is configured to obtain a payment request initiated by a user through a website, the payment request including account information of the payee;
  • the obtaining module 10 is also used to obtain the official account of the payee and the complaint and report record of the user through the information of the receiving account;
  • the statistics module 20 is used to count the number of payments and the number of visits of the official account
  • the verification module 30 is configured to verify the payment request through the website, the payee account information, the user complaint report record, the number of payments of the official account, and/or the number of visits to the official account Whether the corresponding payee has a suspicious fraud risk;
  • the confirmation module 40 is configured to, if the payee has a suspicious fraud risk, log the website, the payee account information, the user complaint and report record, the payment times of the official account, and the public
  • the feature vector composed of the number of visits of the account number is input to the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • the obtaining module 10 is also used to obtain credit rating information of the website and the account information of the payee;
  • the obtaining module 10 is also used to obtain the credit rating information of the website, the credit rating information of the payee account information, the complaint and report record of the user, the number of payments of the official account, and the account information of the official account. Feature vector of the number of visits.
  • the verification module 30 includes:
  • the obtaining unit 31 is configured to obtain the domain name of the payee through the website;
  • the verification unit 32 is configured to determine whether the domain name is the domain name of a regular website through the connected cloud service platform;
  • the determining unit 33 is configured to determine that the payee corresponding to the payment request has a suspicious fraud risk if it is determined that the domain name is not the domain name of a regular website.
  • the verification module 30 includes:
  • the calculation unit 34 is configured to calculate scores corresponding to the website and the payee account information respectively, and the corresponding score is 1 when the website is the domain name of a regular website or the payee account information is a regular account. , Otherwise 0;
  • the calculating unit 34 is configured to calculate the number of complaints and reports recorded by the user, the percentage value of the number of correct payments of the official account, and the percentage value of the number of normal user visits of the official account;
  • the calculation unit 34 is configured to calculate the score of the website, the score of the payee account information, the percentage value of the record of no complaints from users, the percentage value of the correct number of payments of the official account, and State the weighted sum of the percentage values of the number of normal user visits of the official account to obtain the suspicious fraud risk coefficient;
  • the determining unit 33 is further configured to determine that the payee corresponding to the payment request has a suspicious fraud risk if the suspicious fraud risk coefficient is less than a preset risk coefficient.
  • the device further includes:
  • the obtaining module 10 is further configured to obtain the personal credit information of the payee through the personal account information;
  • the calculation module 50 is configured to calculate the weighted sum of the personal credit information of the payee and the percentage value of the non-user complaint report record to obtain the suspicious fraud risk coefficient;
  • the verification module 30 is further configured to determine that the payee corresponding to the payment request has a suspicious fraud risk if the suspicious fraud risk coefficient is less than a preset risk coefficient.
  • Each module in the above payment risk verification device can be implemented in whole or in part by software, hardware and a combination thereof.
  • the foregoing modules may be embedded in the form of hardware or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the foregoing modules.
  • a computer device is provided.
  • the computer device may be a server, and its internal structure diagram may be as shown in FIG. 5.
  • the computer equipment includes a processor, a memory, a network interface and a database connected through a system bus.
  • the processor of the computer device is used to provide calculation and control capabilities.
  • the memory of the computer device includes a readable storage medium and an internal memory.
  • the readable storage medium stores an operating system, computer readable instructions, and a database.
  • the internal memory provides an environment for the operation of the operating system and computer readable instructions in the readable storage medium.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer-readable instruction is executed by the processor to realize a payment risk verification method.
  • the readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.
  • one or more readable storage media storing computer readable instructions are provided.
  • the readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage Medium; the readable storage medium stores computer readable instructions, and when the computer readable instructions are executed by one or more processors, the one or more processors implement the following steps:
  • the website If the payee has a risk of suspicious fraud, the website, the account information of the payee, the user complaint and report record, the number of payments of the official account, and the number of visits to the official account are composed of
  • the feature vector is input to the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • a computer-readable storage medium is provided, and computer-readable instructions are stored thereon, and the computer-readable instructions implement the following steps when executed by a processor:
  • the website, the payee account information, the user complaint and report record, the number of payments of the official account, and the number of visits to the official account are composed of
  • the feature vector is input to the suspicious fraud risk prediction model, and the fraud result of the payee is obtained.
  • Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Abstract

一种支付风险校验方法、装置、计算机设备及存储介质，涉及支付安全技术领域，用于有效的识别潜在的支付风险。所述支付风险校验方法包括：获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息（S10）；通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录（S20）；统计公众号的支付次数、访问次数（S30）；通过网站、收款方账号信息、被用户投诉举报记录、公众号的支付次数、和/或公众号的访问次数验证支付请求对应的收款方是否存在可疑诈骗风险（S40）；若收款方存在可疑诈骗风险，则将网站、收款方账号信息、被用户投诉举报记录、公众号的支付次数和公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到收款方的诈骗结果（S50）。

Description

支付风险校验方法、装置、计算机设备及存储介质
本申请以2019年5月22日提交的申请号为201910431052.7，名称为“支付风险校验方法、装置、计算机设备及存储介质”的中国申请专利申请为基础，并要求其优先权。
技术领域
本申请涉及支付安全技术领域，尤其涉及一种支付风险校验方法、装置、计算机设备及存储介质。
背景技术
随着在线电子商务的繁荣发展，遭受支付欺诈的风险也越来越多。一些欺诈犯非常精通电脑网络，制造出高级的令人信服的欺诈手段骗取他人进行网上支付。这些欺诈手段在他们的巧妙伪装下花样百出，从最简单的到最复杂的骗术让人难以分辨真假，最终上当受骗。
例如，如果有人以保险公司的名义发链接让用户填信息，或者做支付，支付的场景是比如转回录入，即保险公司追回一些已经赔偿但是多赔偿的金额，一般用户会不假思索的支付了，从而就落入了诈骗分子的圈套。因此如何有效的识别存在的支付风险，是目前亟待解决的问题。
申请内容
本申请提供一种支付风险校验方法、装置、计算机设备及存储介质，用于有效的识别用户的潜在支付风险。
本申请实施例提供一种支付风险校验方法，包括：
获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计所述公众号的支付次数、访问次数；
通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号 的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
本申请实施例提供一种支付风险校验装置，包括：
获取模块，用于获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
所述获取模块，还用于通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计模块，用于统计所述公众号的支付次数、访问次数；
验证模块，用于通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
确认模块，用于若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，所述处理器执行所述计算机可读指令时实现如下步骤：
获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计所述公众号的支付次数、访问次数；
通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述 被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
一个或多个存储有计算机可读指令的可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计所述公众号的支付次数、访问次数；
通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
本申请的一个或多个实施例的细节在下面的附图和描述中提出，本申请的其他特征和优点将从说明书、附图以及权利要求变得明显。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例的描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一实施例中支付风险校验方法的一应用环境示意图；
图2是本申请一实施例中支付风险校验方法的一流程图；
图3是本申请一实施例中支付验证的流程图
图4是本申请一实施例中支付风险校验装置的一原理框图；
图5是本申请一实施例中计算机设备的一示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例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作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。
本申请提供的支付风险校验方法，可应用在如图1的应用环境中，其中，计算机设备通过网络与服务器进行通信。计算机设备向服务器发起支付请求，该支付请求包括收款方账号信息，服务器在收到该支付请求后，通过收款账号信息获取收款方的公众号、被用户投诉举报记录；然后统计所述公众号的正确支付次数、访问次数；最后通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的正确支付次数、和/或所述公众号的正常用户访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。其中，计算机设备可以但不限于各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备。服务器可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一实施例中，如图2所示，提供一种支付风险校验方法，以该方法应用在图1中的服务器为例进行说明，包括如下步骤：
S10，获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息。
其中，收款方账号信息包含收款方名头，以及收款方账号。收款方的名头可以是公司名头，也可以是个人用户的姓名，本申请实施例不做具体限定。需要说明的是，本申请实施例可以应用于支付宝、微信等支付平台，即在用户通过支付宝或是微信进行支付时，通过本申请实施例即可以监控用户发起支付请求对应的支付风险，以此防止用户受到诈骗的风险。
例如，本申请实施例中的用户通过诈骗分子以保险公司的名义发来的链接进行网上支付，则获取用户通过该链接网址发起的支付请求，该支付请求中包含需要支付的金额、收款方名头、以及收款方账号等信息。
S20，通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录。
对于本申请实施例，在获取用户发起的支付请求之后，通过支付请求中的收款账号信息获取收款方的公众号以及收款方被用户投诉举报记录，该公众号具体可以为微信公众号或支付宝公众号。其中，被用户投诉举报记录具体可以通过连接的支付宝或是微信平台获取，还可以通过工商管理等途径获取用户的投诉举报记录，本申请实施例不做具体限定。
需要说明的是，由于用户在开通企业公众号时，需要上传运营者身份证信息以及运营者本人手持身份证正面照片，或者用绑定过银行卡的微信扫描后进行身份验证，企业公众号同时需要上传企业营业执照副本、组织结构代码以及企业授权运营者管理运营公众账号的授权书。因此，本申请实施例在接收到用户发送的支付请求后，通过支付请求中的收款方账号信息便可以获取到收款方的公众号。
S30，统计所述公众号的支付次数、访问次数。
其中，支付次数包括支付总次数、正确支付次数及错误支付次数；访问次数包括总访问次数、正常用户访问的次数及异常用户访问的次数。在本申请实施例中，在成功的获取到收款方的公众号之后，通过该公众号获取用户的支付总次数，以及用户的访问总次数，并根据从支付总次数中确认出正确支付次数；从访问总次数中确认出正常用户访问的次数。然后，计算正确支付次数与支付总次数的百分比值，以及正常用户访问次数与总访问次数的百分比值，以便于在后续步骤中根据上述两个百分比值验证用户的支付行为是否存在风险，从而保证用户支付的安全性。
需要说明的是，本申请实施例可以根据统计用户访问公众号的时长来初步确定是否为正常访问的用户，如可以设置一个时间阈值，如果访问时长高于这个时间阈值，则可确定该用户为正常访问的用户；如果访问时长低于这个时间阈值，则可初步确定该用户为异常访问的用户。对于初步确定出异常访问的用户，查看其是否存在购买记录，若存在且短时间内就通过公众号购买了某样商品，则可确认该用户为异常访问的用户。然后通过统计公众号正常访问用户的个数，得到该公众号正常用户访问的次数。
S40，通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险。
在本申请提供的一个实施例中，所述通过所述网站验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：通过所述网站获取所述收款方的域名；通过连接的云服务平台确定所述域名是否为正规网站的域名；若所述域名不是正规网站的域名，则确定所述支付请求对应的收款方存在可疑诈骗风险。在本申请实施例中，在用户通过某个网站跳转进入本平台进行付款时，需要获取跳转网站对应的域名，并判断该域名是否正式网站的域名。例如，小平台的云服务域名，那么可以通过与云服务平台进行一个连接，通过链接的云服务平台确定域名是否为正规网站的域名，校验域名是否正规的过程，有很多公司使用比如阿里的云服务，那么他的域名是阿里分配给他的，那么本申请实施例平台可以与阿里云进行对接，甚至所有的云服务，校验用户的支付请求对应的收款方是否是正规商家。
需要说明的是，收款方账号信息可以为申请的商户公司信息，一般来说，通过对公司的申请信息详细核实校验，是可以筛选部分不法账户。具体的，本申请实施例可以通过连接的国家企业信用信息公示系统查看收款方账号信息是否合法，若不合法，则可确认出支付请求对应的收款方是否存在可疑诈骗风险，此时可输入风险提示信息，以提示用户正在支付的行为存在可疑诈骗风险。
在本申请提供的一个实施例中，通过所述被用户投诉举报记录、所述公众号的支付次数，或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：若所述被用户投诉举报记录超过预置举报次数，或所述公众号的正确支付次数的百分比小于第一预置数值，或所述公众号的正常用户访问次数的百分比小于第二预置数值，则确定所述支付请求对应的收款方存在可疑诈骗风险。其中，第一预置数值和第二预置数值可以根据实际需求进行设置，例如对于支付行为中，公众号的正确支付次数的百分比小于60％的即可认为存在可疑诈骗风险；公众号中的正常用户访问次数的百分比小于50％的即可以认为存在可疑诈骗风险，本申请实施例不做具体限定。
需要说明的是，所述公众号的正确支付次数的百分比为支付成功数与支付总次数的百分比值，如果支付总次数较多，并且正确支付次数的百分比较高，那么该支付请求对应的收款方为正规商户的可能性较大；如果支付总次数较多，但是正确支付次数的百分比较低，即小于第一预置数值，此时可确定支付请求对应的收款方存在可疑诈骗风险。所述公众号的正常用户访问次数的百分比为正常用户访问次数与访问总人数的百分比值，若公众号的正常用户访问次数的百分比小于第二预置数值，说明该公众号存在刷单的嫌疑，即用户存在支付风险，此时需要输出提示信息以提示用户存在的潜在支付风险；若公众号的正常用户访问次数的百分比大于等于第二预置数值，说明该公众号大部分的支付行为属于正常用户的支付行为，用户可以正常进行支付行为。具体的，本申请实施例可以通过对接微信或者支付宝，采集公众号的历史访问次数，并根据历史访问次数绘制访问曲线，通过分析一段时间内的访问曲线判断是否出现访问异常，如在没有任何活动的情况下访问次数激增，则可确认公众号存在刷单的嫌疑，即用户存在支付风险。
需要说明的是，本申请实施例在根据网站、收款方账号信息、被用户投诉举报记录、公众号的支付次数和/或公众号的访问次数组数验证支付请求对应的收款方是否存在可疑诈骗风险时，可以首先按一个维度的信息对收款方是否存在可疑诈骗进行验证，如首先通过网站对收款方进行验证，若验证出该收款方存在可疑诈骗风险，则停止后续的验证步骤直接跳转至步骤S50继续执行；若验证出该收款方不存在可疑诈骗风险，则继续通过收款方账号信息、被用户投诉举报记录、公众号的支付次数和公众号的访问次数等维度信息对收款方分别进行验证，若按照一个维度信息对收款方验证的结果均为不存在可疑诈骗风险，则按照网站、收款方账号信息、被用户投诉举报记录、公众号的支付次数和公众号的访问次数中多个维度组合的方式对收款方是否存在可疑诈骗风险进行验证。
S50，若收款方存在可疑诈骗风险，则将网站、收款方账号信息、被用户投诉举报记录、公众号的支付次数和公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到收款方的诈骗结果。
在本申请实施例中，在将网站、收款方账号信息、被用户投诉举报记录、公众 号的支付次数和公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型之前，还包括：获取所述网站和所述收款方账号信息的信用等级信息；分别获取所述网站的信用等级信息、所述收款方账号信息的信用等级信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数的特征向量。其中，网站和收款方账号信息的信用等级信息可以通过收集网络用户对其进行标注的信息来进行确定，例如用户A对访问了网站B后确定该网站为潜在风险网站，则可以通过其对该网站的打分得到网站B的信用等级；收款方账号信息的信用等级信息同样也可以通过用户成功支付之后，用户对该收款方账号信息的评价信息进行确定。另外，本申请实施例还可通过黑白名单的形式确定网站和收款方账号信息的信用等级，本申请实施例不做具体限定。
需要说明的是，本申请实施例中的可疑诈骗风险预测模型是大量的样本数据训练得到，该样本数据中包含网站和收款方账号信息的信用等级信息、被用户投诉举报记录、公众号的支付次数和公众号的访问次数，通过对样本数据的分析训练得到可疑诈骗风险预置模型，通过该模型可以预测出收款方是网络诈骗的概率，从而通过本申请实施例中的可疑诈骗风险预测模型可以准确的预测出用户进行网络支付的危险行为，从而提高用户支付的安全性。
对于本申请实施例，在确认出支付请求对应的收款方存在诈骗风险之后，可向用户所在的客户端输出支付风险信息，以提示用户正在支付的危险行为；或是在确定存在诈骗风险之后，直接向有关部门报警，并禁止用户此次的支付行为，本申请实施例不做具体限定。
本申请实施例提供了一种支付风险校验方法，首先获取用户通过网站发起的支付请求，然后通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录，并统计所述公众号的支付次数、访问次数，最后通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，若收款方存在可疑诈骗风险，则将网站、收款方账号信息、被用户投诉举报记录、公众号的支付次数和公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到收款方的诈骗结果。从而通过本申请实施例可实现通过多种途径 判断用户的支付行为是否存在诈骗风险，以此保证用户的支付安全，避免了用户在没有经过核实的情况下就在网上进行支付的行为，大大降低用户受骗率。
如图3所示，在本申请提供的一个实施例中，步骤S40：所述通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数，和所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
S401，计算所述网站、所述收款方账号信息分别对应的分值。
其中，所述网站为正规网站的域名或所述收款方账号信息为正规账号时对应的分值为1，否者为0。具体的，本申请实施例首先获取网站对应的域名，然后判断该域名是否属于正规网站，若是，则将该网站的分值设置为1；否则将该网站的分值设置为0。所述收款方账号信息可以通过连接的国家企业信用信息公示系统查看收款方账号信息是否合法，若合法，则将该收款方账信息的分值设置为1；否则将该收款方账号信息的分值设置为0。
S402，计算未被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值。
在本申请实施例中，可通过公众号获取用户投诉举报记录的次数，还可以通过工商管理等途径获取用户的投诉举报记录。公众号的正确支付次数的百分比值为支付成功数与支付总次数的百分比值，所述公众号的正常用户访问次数的百分值为正常用户访问次数与访问总人数的百分比值。
S403，通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和，得到可疑诈骗风险系数。
其中，各评估参数对应的权重值是根据实际需求进行设定的，若公众号的正确支付次数的百分比值在诈骗判断中起到的作用较大，则可将其权重值设置大一些，若公众号的正常用户访问次数的百分值在诈骗判断中起到的作用较小，则可以将其权重值设置的相对小些。需要说明的是，各个评估参数的权重值相加为1。
S404，若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应 的收款方存在可疑诈骗风险。
其中，预置风险系数是根据实际需求进行设定的，例如可根据用户正常支付行为所确定出的风险系数的平均值确定，即根据正常支付行为的网站的分值、收款方账号信息的分值、未被用户投诉举报记录的百分比值、公众号的正确支付次数的百分比值，以及公众号的正常用户访问次数的百分值的加权和，并对加权和求平均值，得到预置风险系数。
本申请实施例提供了另一种支付风险校验方法，首先计算所述网站、所述收款方账号信息分别对应的分值，以及所述被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值，然后通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和，得到可疑诈骗风险系数，若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。由于申请实施例是综合多种参数进行加权求和得到可疑诈骗风险系数，因此通过该可疑诈骗风险系数可提高在支付过重中的诈骗行为，从而减少用户受骗的概率。
在本申请提供的一个实施例中，若收款方账号信息为个人账号信息，所述方法还包括：通过所述个人账号信息获取所述收款方的个人信用信息；所述收款方的个人信用信息、未被用户投诉举报记录的百分比值的加权和，得到可疑诈骗风险系数；若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在一实施例中，提供一种支付风险校验装置，该支付风险校验装置与上述实施例中支付风险校验方法一一对应。如图4所示，该支付风险校验装置包括获取模块10、统计模块20、验证模块30、确认模块40。各功能模块详细说明如下：
获取模块10，用于获取用户通过网站发起的支付请求，所述支付请求包括收款 方账号信息；
所述获取模块10，还用于通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计模块20，用于统计所述公众号的支付次数、访问次数；
验证模块30，用于通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
确认模块40，用于若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
所述获取模块10，还用于获取所述网站和所述收款方账号信息的信用等级信息；
获取模块10，还用于分别获取所述网站的信用等级信息、所述收款方账号信息的信用等级信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数的特征向量。
对于本申请实施例，所述验证模块30包括：
获取单元31，用于通过所述网站获取所述收款方的域名；
验证单元32，用于通过连接的云服务平台确定所述域名是否为正规网站的域名；
确定单元33，用于若确定所述域名不是正规网站的域名，则确定所述支付请求对应的收款方存在可疑诈骗风险。
在本申请提供的实施例中，所述验证模块30，包括：
计算单元34，用于计算所述网站、所述收款方账号信息分别对应的分值，所述网站为正规网站的域名或所述收款方账号信息为正规账号时对应的分值为1，否者为0；
计算单元34，用于计算所述被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值；
计算单元34，用于通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和，得到可疑诈骗风险系数；
确定单元33，还用于若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
在本申请提供的实施例中，若收款方账号信息为个人账号信息，所述装置还包括：
所述获取模块10，还用于通过所述个人账号信息获取所述收款方的个人信用信息；
计算模块50，用于通过计算所述收款方的个人信用信息、未被用户投诉举报记录的百分比值的加权和，得到可疑诈骗风险系数；
所述验证模块30，还用于若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
关于支付风险校验装置的具体限定可以参见上文中对于支付风险校验方法的限定，在此不再赘述。上述支付风险校验装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图5所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括可读存储介质、内存储器。该可读存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为可读存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种支付风险校验方法。本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质。
在一个实施例中，提供了一个或多个存储有计算机可读指令的可读存储介质，本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质；该可读存储介质上存储有计算机可读指令，该计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器实现以下步骤：
获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计所述公众号的支付次数、访问次数；
通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机可读指令，计算机可读指令被处理器执行时实现以下步骤：
获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
统计所述公众号的支付次数、访问次数；
通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读取存储介质或易失性可读存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供 的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。
以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种支付风险校验方法，其特征在于，所述方法包括：
    获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
    通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
    统计所述公众号的支付次数、访问次数；
    通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
    若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
  2. 根据权利要求1所述的支付风险校验方法，其特征在于，所述将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型之前，所述方法还包括：
    获取所述网站和所述收款方账号信息的信用等级信息；
    分别获取所述网站的信用等级信息、所述收款方账号信息的信用等级信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数的特征向量。
  3. 根据权利要求1所述的支付风险校验方法，其特征在于，所述通过所述网站验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    通过所述网站获取所述收款方的域名；
    通过连接的云服务平台确定所述域名是否为正规网站的域名；
    若确定所述域名不是正规网站的域名，则确定所述支付请求对应 的收款方存在可疑诈骗风险。
  4. 根据权利要求1所述的支付风险校验方法，其特征在于，通过所述被用户投诉举报记录、所述公众号的支付次数，或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    若所述被用户投诉举报记录超过预置举报次数，或所述公众号的正确支付次数的百分比小于第一预置数值，或所述公众号的正常用户访问次数的百分比小于第二预置数值，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  5. 根据权利要求2-4任一项所述的支付风险校验方法，其特征在于，所述通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数，和所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    计算所述网站、所述收款方账号信息分别对应的分值，所述网站为正规网站的域名或所述收款方账号信息为正规账号时对应的分值为1，否者为0；
    计算所述被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值；
    通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和，得到可疑诈骗风险系数；
    若所述诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  6. 根据权利要求5所述的支付风险校验方法，其特征在于，若收款方账号信息为个人账号信息，所述方法还包括：
    通过所述个人账号信息获取所述收款方的个人信用信息；
    通过计算所述收款方的个人信用信息、未被用户投诉举报记录的 百分比值的加权和，得到可疑诈骗风险系数；
    若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  7. 一种支付风险校验装置，其特征在于，所述装置包括：
    获取模块，用于获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
    所述获取模块，还用于通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
    统计模块，用于统计所述公众号的支付次数、访问次数；
    验证模块，用于通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
    确认模块，用于若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
  8. 根据权利要求7所述的支付风险校验装置，其特征在于，所述获取模块，还用于获取所述网站和所述收款方账号信息的信用等级信息；
    获取模块，还用于分别获取所述网站的信用等级信息、所述收款方账号信息的信用等级信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数的特征向量。
  9. 根据权利要求7所述的支付风险校验装置，其特征在于，所述验证模块还用于：若所述被用户投诉举报记录超过预置举报次数，或所述公众号的正确支付次数的百分比小于第一预置数值，或所述公众号的正常用户访问次数的百分比小于第二预置数值，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  10. 根据权利要求8所述的支付风险校验装置，其特征在于，所述验证 模块包括：
    计算单元，用于计算所述网站、所述收款方账号信息分别对应的分值，所述网站为正规网站的域名或所述收款方账号信息为正规账号时对应的分值为1，否者为0；用于计算所述被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值；用于通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和，得到可疑诈骗风险系数；
    确定单元，还用于若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  11. 根据权利要求10所述的支付风险校验方法，其特征在于，若收款方账号信息为个人账号信息，所述获取模块还用于通过所述个人账号信息获取所述收款方的个人信用信息；
    所述装置还包括计算模块，所述计算模块用于通过计算所述收款方的个人信用信息、未被用户投诉举报记录的百分比值的加权和，得到可疑诈骗风险系数；
    所述验证模块还用于若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  12. 一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，其特征在于，所述处理器执行所述计算机可读指令时实现如下步骤：
    获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
    通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
    统计所述公众号的支付次数、访问次数；
    通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
    若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
  13. 如权利要求12所述的计算机设备，其特征在于，所述将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型之前，所述处理器执行所述计算机可读指令时还实现如下步骤：
    获取所述网站和所述收款方账号信息的信用等级信息；
    分别获取所述网站的信用等级信息、所述收款方账号信息的信用等级信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数的特征向量。
  14. 如权利要求12所述的计算机设备，其特征在于，通过所述被用户投诉举报记录、所述公众号的支付次数，或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    若所述被用户投诉举报记录超过预置举报次数，或所述公众号的正确支付次数的百分比小于第一预置数值，或所述公众号的正常用户访问次数的百分比小于第二预置数值，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  15. 如权利要求14所述的计算机设备，其特征在于，所述通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数，和所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    计算所述网站、所述收款方账号信息分别对应的分值，所述网站为正规网站的域名或所述收款方账号信息为正规账号时对应的分值为1，否者为0；
    计算所述被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值；
    通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和，得到可疑诈骗风险系数；
    若所述诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  16. 一个或多个存储有计算机可读指令的可读存储介质，其特征在于，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
    获取用户通过网站发起的支付请求，所述支付请求包括收款方账号信息；
    通过所述收款账号信息获取收款方的公众号、被用户投诉举报记录；
    统计所述公众号的支付次数、访问次数；
    通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数、和/或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险；
    若所述收款方存在可疑诈骗风险，则将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型，得到所述收款方的诈骗结果。
  17. 如权利要求16所述的可读存储介质，其特征在于，所述将所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众 号的支付次数和所述公众号的访问次数组成的特征向量输入到可疑诈骗风险预测模型之前，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器还执行如下步骤：
    获取所述网站和所述收款方账号信息的信用等级信息；
    分别获取所述网站的信用等级信息、所述收款方账号信息的信用等级信息、所述被用户投诉举报记录、所述公众号的支付次数和所述公众号的访问次数的特征向量。
  18. 如权利要求16所述的可读存储介质，其特征在于，通过所述被用户投诉举报记录、所述公众号的支付次数，或所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    若所述被用户投诉举报记录超过预置举报次数，或所述公众号的正确支付次数的百分比小于第一预置数值，或所述公众号的正常用户访问次数的百分比小于第二预置数值，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  19. 如权利要求17所述的可读存储介质，其特征在于，所述通过所述网站、所述收款方账号信息、所述被用户投诉举报记录、所述公众号的支付次数，和所述公众号的访问次数验证所述支付请求对应的收款方是否存在可疑诈骗风险，包括：
    计算所述网站、所述收款方账号信息分别对应的分值，所述网站为正规网站的域名或所述收款方账号信息为正规账号时对应的分值为1，否者为0；
    计算所述被用户投诉举报记录的次数，所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值；
    通过计算所述网站的分值、所述收款方账号信息的分值、未被用户投诉举报记录的百分比值、所述公众号的正确支付次数的百分比值，以及所述公众号的正常用户访问次数的百分值的加权和， 得到可疑诈骗风险系数；
    若所述诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
  20. 如权利要求19所述的可读存储介质，其特征在于，若收款方账号信息为个人账号信息，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器还执行如下步骤：
    通过所述个人账号信息获取所述收款方的个人信用信息；
    通过计算所述收款方的个人信用信息、未被用户投诉举报记录的百分比值的加权和，得到可疑诈骗风险系数；
    若所述可疑诈骗风险系数小于预置风险系数，则确定所述支付请求对应的收款方存在可疑诈骗风险。
PCT/CN2019/121829 2019-05-22 2019-11-29 支付风险校验方法、装置、计算机设备及存储介质 WO2020233070A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910431052.7A CN110335044A (zh) 2019-05-22 2019-05-22 支付风险校验方法、装置、计算机设备及存储介质
CN201910431052.7 2019-05-22

Publications (1)

Publication Number Publication Date
WO2020233070A1 true WO2020233070A1 (zh) 2020-11-26

Family

ID=68139808

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/121829 WO2020233070A1 (zh) 2019-05-22 2019-11-29 支付风险校验方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN110335044A (zh)
WO (1) WO2020233070A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114506756A (zh) * 2022-01-20 2022-05-17 中国计量大学 一种目标系统功能安全定级方法、装置、设备、存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110335044A (zh) * 2019-05-22 2019-10-15 深圳壹账通智能科技有限公司 支付风险校验方法、装置、计算机设备及存储介质
CN111353784A (zh) * 2020-02-25 2020-06-30 支付宝(杭州)信息技术有限公司 一种转账处理方法、系统、装置和设备
CN111401897B (zh) * 2020-03-13 2023-09-08 Oppo广东移动通信有限公司 信息处理方法、装置、电子设备及计算机可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150186880A1 (en) * 2013-12-26 2015-07-02 Tencent Technology (Shenzhen) Company Limited Systems and Methods for Safe Payments
CN106878309A (zh) * 2017-02-21 2017-06-20 腾讯科技（深圳）有限公司 应用于网络支付的安全预警方法及装置
CN108734380A (zh) * 2018-04-08 2018-11-02 阿里巴巴集团控股有限公司 风险账户判定方法、装置及计算设备
CN109410036A (zh) * 2018-10-09 2019-03-01 北京芯盾时代科技有限公司 一种欺诈检测模型训练方法和装置及欺诈检测方法和装置
CN110335044A (zh) * 2019-05-22 2019-10-15 深圳壹账通智能科技有限公司 支付风险校验方法、装置、计算机设备及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106557925B (zh) * 2016-11-29 2020-07-24 流量海科技成都有限公司 一种反欺诈支付的校验方法及系统
CN108805583B (zh) * 2018-05-18 2020-01-31 连连银通电子支付有限公司 基于地址映射的电商欺诈检测方法、装置、设备及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150186880A1 (en) * 2013-12-26 2015-07-02 Tencent Technology (Shenzhen) Company Limited Systems and Methods for Safe Payments
CN106878309A (zh) * 2017-02-21 2017-06-20 腾讯科技（深圳）有限公司 应用于网络支付的安全预警方法及装置
CN108734380A (zh) * 2018-04-08 2018-11-02 阿里巴巴集团控股有限公司 风险账户判定方法、装置及计算设备
CN109410036A (zh) * 2018-10-09 2019-03-01 北京芯盾时代科技有限公司 一种欺诈检测模型训练方法和装置及欺诈检测方法和装置
CN110335044A (zh) * 2019-05-22 2019-10-15 深圳壹账通智能科技有限公司 支付风险校验方法、装置、计算机设备及存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114506756A (zh) * 2022-01-20 2022-05-17 中国计量大学 一种目标系统功能安全定级方法、装置、设备、存储介质

Also Published As

Publication number Publication date
CN110335044A (zh) 2019-10-15

Similar Documents

Publication Publication Date Title
CN110827032B (zh) 智能风控决策方法及系统、业务处理方法及系统
US10460382B2 (en) Fraud reduction system for transactions
US11941635B1 (en) System and architecture for electronic fraud detection
WO2020233070A1 (zh) 支付风险校验方法、装置、计算机设备及存储介质
JP4778899B2 (ja) リスクベース認証のためのシステムおよび方法
US8666861B2 (en) Software and methods for risk and fraud mitigation
US8463702B2 (en) Global compliance processing system for a money transfer system
US20190295085A1 (en) Identifying fraudulent transactions
US10872389B2 (en) Taxpayer identity determination through external verfication
US20140046786A1 (en) Mobile Merchant POS Processing System, Point-of-Sale App, Analytical Methods, and Systems and Methods for Implementing the Same
US20110071946A1 (en) Credit applicant and user authentication solution
US20110320355A1 (en) Value transfer with identity database
WO2021098274A1 (zh) 针对隐私数据泄漏的风险评估方法及装置
CN106789436A (zh) 一种征信报告生成方法及系统
US11575670B2 (en) Adaptive user authentication
CA3165099A1 (en) System and method for assessing a digital interaction with a digital third party account service
CN107918911A (zh) 用于执行安全网上银行交易的系统和方法
CN108428135A (zh) 身份验证方法
US20150310545A1 (en) System and method for progress account opening by means of risk-based context analysis
EP3547243A1 (en) Methods and apparatuses for fraud handling
CN111489175B (zh) 在线身份认证方法、装置、系统及存储介质
US20230012460A1 (en) Fraud Detection and Prevention System
TWI518620B (zh) 結合行動通訊系統之貸款管理方法
US20210185036A1 (en) Secure authentication system
CN111047341B (zh) 信息处理方法、装置、服务器及终端设备

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: 19929526

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: 19929526

Country of ref document: EP

Kind code of ref document: A1