WO2020007153A1 - 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备 - Google Patents

识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备 Download PDF

Info

Publication number
WO2020007153A1
WO2020007153A1 PCT/CN2019/089939 CN2019089939W WO2020007153A1 WO 2020007153 A1 WO2020007153 A1 WO 2020007153A1 CN 2019089939 W CN2019089939 W CN 2019089939W WO 2020007153 A1 WO2020007153 A1 WO 2020007153A1
Authority
WO
WIPO (PCT)
Prior art keywords
account
transaction
related data
misappropriation
risk
Prior art date
Application number
PCT/CN2019/089939
Other languages
English (en)
French (fr)
Inventor
马蕊
赵华
朱通
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 WO2020007153A1 publication Critical patent/WO2020007153A1/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
    • G06Q20/386—Payment protocols; Details thereof using messaging services or messaging apps
    • 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
    • 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
    • G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
    • G06Q20/32—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
    • G06Q20/322—Aspects of commerce using mobile devices [M-devices]
    • 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
    • G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
    • G06Q20/32—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
    • G06Q20/325—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices using wireless networks
    • G06Q20/3255—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices using wireless networks using mobile network messaging services for payment, e.g. SMS
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • G06Q30/0185—Product, service or business identity fraud

Definitions

  • This specification relates to the technical field of computer software, and in particular, to a risk control model training, a risk control method, a device, and a device for identifying the misappropriation of a secondary account.
  • the mobile phone number resource belongs to the country, and users only have the right to use it. Due to the limited resources of the mobile phone number, when the user disables the mobile phone number, the mobile phone number will be recovered by the communication operator. After a period of freezing period, the mobile phone number will be re-entered into the market and re-entered the market, that is, the secondary number is placed. At present, the minimum freeze period for mobile phone numbers is 90 days.
  • the embodiments of the present specification provide a risk control method, device, and device for identifying the misappropriation of a secondary number account, which are used to solve the following technical problem: A more effective risk control scheme for identifying the misappropriation of a secondary number account is required.
  • obtaining a qualitative label of the account transaction For a historical account transaction included in the transaction-related data, obtaining a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a secondary account misappropriation event;
  • the following two types of risk characteristics of each of the account transactions are extracted from the transaction-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and other accounts of the same identity. Consistent mobile phone numbers
  • a supervised model is trained to identify the fraudulent use of secondary number account.
  • the following two types of risk characteristics of the account transaction are extracted from the transaction-related data: the consistency of user names between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the second number account misappropriation for the account transaction is determined.
  • the following two types of risk characteristics of the account operation are extracted from the operation-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the misappropriation of the secondary number account for the account operation is determined.
  • a first acquisition module which acquires transaction-related data of multiple accounts
  • a second obtaining module for a historical account transaction included in the transaction-related data, obtaining a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a second number account misappropriation event;
  • the extraction module extracts the following two types of risk characteristics of each account transaction from the transaction-related data: the correspondence between the user name system of the corresponding phone number and the account system, and the corresponding account and the same identity Consistency of mobile phone numbers between other accounts;
  • the training module uses the obtained qualitative labels and the extracted risk features as training data, and trains a supervised model to identify the fraudulent use of the secondary account number.
  • An acquisition module which acquires transaction-related data corresponding to an account transaction to be identified
  • the extraction module extracts the following two types of risk characteristics of the account transaction from the transaction-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, and the corresponding account and other users of the same identity Mobile phone numbers are consistent between accounts;
  • a processing module that inputs the extracted risk features into the trained supervised model for processing
  • the determination module determines the identification result of the second number account misappropriation for the account transaction according to the prediction result output after processing by the supervised model.
  • An acquisition module which acquires operation-related data corresponding to an account operation to be identified
  • the extraction module extracts the following two types of risk characteristics of the account operation from the operation-related data: the identity of the user between the address book system and the account system to which the corresponding mobile phone number belongs, and the corresponding account and other people with the same identity Mobile phone numbers are consistent between accounts;
  • the determination module determines the identification result of the misappropriation of the secondary account number operation for the account according to the extracted risk characteristics.
  • At least one processor At least one processor
  • a memory connected in communication with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
  • obtaining a qualitative label of the account transaction For a historical account transaction included in the transaction-related data, obtaining a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a secondary account misappropriation event;
  • the following two types of risk characteristics of each of the account transactions are extracted from the transaction-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and other accounts of the same identity. Consistent mobile phone numbers
  • a supervised model is trained to identify the fraudulent use of secondary number account.
  • At least one processor At least one processor
  • a memory connected in communication with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
  • the following two types of risk characteristics of the account transaction are extracted from the transaction-related data: the consistency of user names between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the second number account misappropriation for the account transaction is determined.
  • At least one processor At least one processor
  • a memory connected in communication with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
  • the following two types of risk characteristics of the account operation are extracted from the operation-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the misappropriation of the secondary number account for the account operation is determined.
  • the at least one of the above technical solutions adopted in the embodiments of the present specification can achieve the following beneficial effects: instead of relying on the mobile phone number access time and status data provided by the communication operator, it can use its own Internet platform data resources, especially using the mobile phone number
  • FIG. 1 is a schematic flowchart of a risk control model training method for identifying misappropriation of a secondary number account provided by an embodiment of the present specification
  • FIG. 2 is a schematic flowchart of a risk control method for identifying theft of a secondary number account provided by an embodiment of the present specification
  • FIG. 3 is a schematic flowchart of a specific implementation of the foregoing wind control model training method and a wind control method in an actual application scenario provided by an embodiment of the specification;
  • FIG. 4 is a schematic flow chart of another risk control method for identifying theft of a secondary number account provided by an embodiment of the present specification
  • FIG. 5 is a schematic structural diagram of a wind control model training device corresponding to FIG. 1 for identifying a fraudulent use of a secondary number account provided by an embodiment of the present specification
  • FIG. 6 is a schematic structural diagram of a risk control device corresponding to FIG. 2 and identifying a fraudulent use of a secondary number account provided by an embodiment of the present specification;
  • FIG. 7 is a schematic structural diagram of a risk control device corresponding to FIG. 4 and identifying a fraudulent use of a secondary number account according to an embodiment of the present disclosure.
  • the embodiments of the present specification provide a risk control model training, a risk control method, a device, and a device for identifying the misappropriation of a secondary number account.
  • FIG. 1 is a schematic flow chart of a risk control model training method for identifying the misappropriation of a secondary numbering account provided by an embodiment of the present specification.
  • the process may be automatically performed by a server, and some steps may also allow manual intervention.
  • the process in Figure 1 can include the following steps:
  • the account is, for example, an account of an application carried on the terminal, such as an account of a third-party payment application, an account of a bank application, an account of an instant messaging application, and the like. Transactions can be performed between different accounts of the same application. Through the transaction, the transfer of actual funds or virtual items between the accounts of both parties in the transaction is triggered.
  • the account itself can be a mobile phone number; or, although it is not a mobile phone number, it is bound with a mobile phone number, and you can log in using the bound mobile phone number (directly log in with the mobile phone number through SMS verification, or use the mobile phone number to retrieve the account Password login, etc.) account.
  • the identification of the misappropriation of the second number account can be for account transactions or for accounts.
  • an account transaction can be regarded as a sample. .
  • the corresponding account is at risk and the account can be directly controlled to avoid user losses.
  • S104 For historical account transactions included in the transaction-related data, obtain a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a second number account misappropriation event.
  • the qualitative label may be determined based on a manual analysis or a user's initiative to report a case, and the conclusion contained in the qualitative label may be considered credible.
  • Qualitative labels can be expressed in the form of binary values (such as 0-1, etc.) or probability values.
  • S106 The following two types of risk characteristics of each account transaction are extracted from the transaction-related data: the identity of the user between the address book system and the account system to which the corresponding mobile phone number belongs, and the corresponding account and other accounts of the same identity Mobile phone numbers are consistent between accounts.
  • the risk characteristics based on the address book and the risk characteristics based on the static information of the account are considered as the basis for identification.
  • the reason is that the address book and the static information of the account directly or indirectly involve the mobile phone number, which has a high Reference value.
  • the account static information can include the mobile phone number bound to the account, and other accounts related to the account.
  • the risk characteristics based on the address book include the consistency of the above user names.
  • the mobile phone number corresponding to the account can be determined.
  • the address book system to which the mobile phone number belongs for example, includes the address book that comes with the mobile phone of the corresponding user and his friend, the current application and other applications belonging to the same company or a cooperative The address book of the three-party application, etc.
  • the account system to which the mobile phone number belongs for example, includes the account system of the current application. The higher the degree of user name inconsistency between the address book system and the account system, the more likely there is a case of account misappropriation.
  • the specific extraction methods of such risk characteristics can be various.
  • Address book-based risk characteristics can include more.
  • the mobile phone number of the same user has changed in the recent period of time, and the name of the user who has the same mobile phone number has changed.
  • the risk characteristics based on the static information of the account include the aforementioned mobile phone number consistency.
  • the specific extraction methods of such risk characteristics can be various. For example, you can determine whether the mobile phone number bound to other active accounts with the same identity (such as the ID card number, the same bank card number, etc.) is consistent with the mobile phone number bound to the current account. If not, the risk of misappropriation is high, and the corresponding risk characteristics are extracted accordingly.
  • Risk characteristics based on account static information can also include more content. For example, changes in mobile phone numbers associated with other accounts related to the account.
  • the risk characteristics of the two dimensions of the address book and the account static information have been described above, and the risk characteristics of more dimensions can also be used. More dimensions include, for example: account activity, account abnormal operation behavior, account equipment information and other dimensions.
  • the extracting the following two types of risk characteristics of each account transaction from the transaction-related data may also be performed: extracting at least one of the following types of each account transaction from the transaction-related data Risk characteristics: Multiple account logins on the device in use, corresponding SMS logins for the corresponding account, and active status of the corresponding account.
  • the risk of misappropriation is higher; if you used to log in to your account via SMS less frequently, you have recently tried to use SMS multiple times The risk of misappropriation is high when you log in to your account by using this method; if the account has performed sensitive operations such as transactions or cash withdrawals for a period of time, the risk of misappropriation is high.
  • S108 Use the obtained qualitative label and the extracted risk features as training data, and train a supervised model to identify the fraudulent use of the secondary number account.
  • a single account transaction can be used as a training sample.
  • the extracted risk features are used as input data for the supervised model.
  • the prediction results output by the supervised model are compared with qualitative labels. If they are not consistent, the supervised model is adjusted (for example, the model structure is adjusted, the weight parameters are adjusted) Wait). Iterate this way until the model meets the expectations, and then it can be put into use, for example, the model is released online to determine whether the online transaction is a second-number account misappropriation event.
  • the supervised model may be various, such as a supervised algorithm based on a gradient boosting decision tree or a random forest.
  • the trained supervised model described above can be put into risk control for identifying theft of secondary number account. Based on this, the embodiment of this specification also provides a schematic flowchart of a risk control method for identifying theft of secondary number account. Shown in Figure 2.
  • the process in Figure 2 may include the following steps:
  • the account transaction to be identified may be an online transaction in progress or an offline transaction that has been completed.
  • S204 Extract the following two types of risk characteristics of the account transaction from the transaction-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and other accounts of the same identity The phone numbers are consistent between the two.
  • S208 Determine, according to the prediction result output after processing by the supervised model, the identification result of the secondary number account misappropriation for the account transaction.
  • the corresponding account can be controlled, and the ongoing transactions of the account can be suspended, so as not to cause losses to the user.
  • step S204 the following two types of risk characteristics of the account transaction extracted from the transaction-related data may also be executed: the following of the account transaction are extracted from the transaction-related data. At least one type of risk characteristics: multiple account logins on the device used, corresponding SMS logins of the account, and active status of the corresponding account.
  • the prediction result output after processing by the supervised model can reflect: the possibility that the account transaction belongs to a second number account misappropriation event.
  • the prediction result may be, for example, a probability value, or a certain value in a specified value interval similar to the probability value.
  • risk control can be combined with the prediction results and other certification measures to improve the overall reliability of the solution and to avoid accidentally injuring accounts.
  • the step of determining the identification result of the second number account misappropriation for the account transaction according to the prediction result output after the supervised model processing may specifically include: if the probability is higher than a set If the threshold value is exceeded, the user of the account transaction is authenticated through an authentication method other than the biometric and / or bank card and / or credential verification. Based on the authentication result, it is determined whether the account transaction belongs to a secondary account A misappropriation event; or if the probability is higher than a set threshold, it is determined that the account transaction belongs to a second number account misappropriation event.
  • the embodiment of the present specification also provides a schematic flowchart of a specific implementation of the foregoing wind control model training method and wind control method in an actual application scenario, as shown in FIG. 3.
  • the process in FIG. 3 may include the following steps:
  • the above mainly uses account transactions as an example to explain the identification of the second number account theft.
  • the idea of the above solution is also applicable to other account operations other than account transactions, such as account login, account modification, and other sensitive operations.
  • the recognition is not limited to the use of supervised models.
  • the embodiment of the present specification also provides another schematic diagram of a risk control method for identifying theft of a secondary number account, as shown in FIG. 4, and a part of the process in FIG. 4 is consistent with FIG. 2, referring to the above. It is enough to understand the description of FIG. 2 and will not be repeated.
  • the process in FIG. 4 may include the following steps:
  • S404 The following two types of risk characteristics of the account operation are extracted from the operation-related data: the user name consistency between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and other accounts of the same identity The phone numbers are consistent between the two.
  • S406 Determine, according to the extracted risk characteristics, the identification result of the second number account misappropriation for the account operation.
  • a model may be used to determine the identification result of the secondary number account misappropriation; or, a relatively simple and straightforward rule such as a regular expression may be used to determine the secondary number
  • a relatively simple and straightforward rule such as a regular expression may be used to determine the secondary number
  • the misappropriation of the identification result of the account No. helps to reduce the cost of implementation. For example, if it is determined through regular expression matching that the above-mentioned user name consistency and mobile phone number consistency are inconsistent, it can be directly determined that the account operation to be identified is a second number account misappropriation event.
  • step S404 the following two types of risk characteristics of the account operation that are extracted from the operation-related data may also be performed: the following operations of the account operation are extracted from the operation-related data. At least one type of risk characteristics: multiple account logins on the device used, corresponding SMS logins of the account, and active status of the corresponding account.
  • the embodiments of the present specification also provide a device corresponding to the foregoing method, as shown in FIG. 5, FIG. 6, and FIG. 7.
  • FIG. 5 is a schematic structural diagram of a wind control model training device corresponding to FIG. 1 for identifying a fraudulent use of a secondary number account provided by an embodiment of the present specification, and the device includes:
  • a first acquiring module 501 acquiring transaction-related data of multiple accounts
  • a second obtaining module 502 for a historical account transaction included in the transaction-related data, obtaining a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a second number account misappropriation event;
  • An extraction module 503 extracts the following two types of risk characteristics of each of the account transactions from the transaction-related data: the identity of the user between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and the same identity Consistency of mobile phone numbers between other accounts;
  • the training module 504 uses the acquired qualitative labels and the extracted risk features as training data, and trains a supervised model to identify the misappropriation of the secondary number account.
  • the extraction module 503 extracts the following two types of risk characteristics of each of the account transactions from the transaction-related data, further including:
  • the extraction module 503 extracts, from the transaction-related data, at least one of the following types of risk characteristics of each of the account transactions: multiple account logins on the device used, corresponding SMS logins of the account, and active status of the corresponding account .
  • the supervised model is based on a gradient boosted decision tree or a random forest.
  • FIG. 6 is a schematic structural diagram of a risk control device corresponding to FIG. 2 for identifying theft of a secondary numbering account provided by an embodiment of the specification, and the device includes:
  • the obtaining module 601 obtains transaction-related data corresponding to an account transaction to be identified
  • the extraction module 602 extracts the following two types of risk characteristics of the account transaction from the transaction-related data: the correspondence between the user name system of the corresponding phone number and the account system, and the corresponding account and the same identity Consistency of mobile phone numbers between other accounts;
  • the processing module 603 inputs the extracted risk features into the trained supervised model for processing
  • the determination module 604 determines the identification result of the secondary account number misappropriation for the account transaction according to the prediction result output after processing by the supervised model.
  • the extraction module 602 extracts the following two types of risk characteristics of the account transaction from the transaction-related data, further including:
  • the extraction module 602 extracts at least one of the following risk characteristics of the account transaction from the transaction-related data: multiple account logins on the device used, corresponding SMS logins of the account, and active status of the corresponding account.
  • the prediction result output after processing by the supervised model reflects: the possibility that the account transaction belongs to a second number account misappropriation event;
  • the determining module 604 determines, according to a prediction result output after processing by the supervised model, the identification result of the secondary number account misappropriation for the account transaction, which specifically includes:
  • the operation user of the account transaction is authenticated through biometrics and / or bank cards and / or certificates, and the account transaction is determined according to the authentication result. Whether it is a case of misappropriation of secondary account; or,
  • the probability is higher than a set threshold, it is determined that the account transaction belongs to a second number account misappropriation event.
  • FIG. 7 is a schematic structural diagram of a risk control device corresponding to FIG. 4 and identifying a fraudulent use of a secondary number account according to an embodiment of the present specification.
  • the device includes:
  • the obtaining module 701 obtains operation-related data corresponding to an account operation to be identified
  • the extraction module 702 extracts the following two types of risk characteristics of the account operation from the operation-related data: the identity of the user between the address book system and the account system to which the corresponding mobile phone number belongs, and the corresponding account and the same identity Consistency of mobile phone numbers between other accounts;
  • the determining module 703 determines, according to the extracted risk characteristics, the identification result of the second number account misappropriation for the account operation.
  • the extraction module 702 extracts the following two types of risk characteristics of the account operation from the operation-related data, and further includes:
  • the extraction module 702 extracts at least one of the following types of risk characteristics of the account operation from the operation-related data: the multi-account login situation on the used device, the SMS account login situation of the corresponding account, and the corresponding account Active situation.
  • the embodiment of the present specification also provides a wind control model training device corresponding to FIG. 1 for identifying the misappropriation of a secondary number account, including:
  • At least one processor At least one processor
  • a memory connected in communication with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
  • obtaining a qualitative label of the account transaction For a historical account transaction included in the transaction-related data, obtaining a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a secondary account misappropriation event;
  • the following two types of risk characteristics of each of the account transactions are extracted from the transaction-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and other accounts of the same identity. Consistent mobile phone numbers
  • a supervised model is trained to identify the fraudulent use of secondary number account.
  • the embodiment of the present specification also provides a risk control device corresponding to FIG. 2 for identifying theft of a secondary number account, including:
  • At least one processor At least one processor
  • a memory connected in communication with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
  • the following two types of risk characteristics of the account transaction are extracted from the transaction-related data: the consistency of user names between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the second number account misappropriation for the account transaction is determined.
  • the embodiment of the present specification also provides a risk control device corresponding to FIG. 4 to identify theft of a secondary number account, including:
  • At least one processor At least one processor
  • a memory connected in communication with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
  • the following two types of risk characteristics of the account operation are extracted from the operation-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the misappropriation of the secondary number account for the account operation is determined.
  • the embodiment of the present specification also provides a non-volatile computer storage medium corresponding to FIG. 1, which stores computer-executable instructions, and the computer-executable instructions are set to:
  • obtaining a qualitative label of the account transaction For a historical account transaction included in the transaction-related data, obtaining a qualitative label of the account transaction, where the qualitative label indicates whether the corresponding account transaction belongs to a secondary account misappropriation event;
  • the following two types of risk characteristics of each of the account transactions are extracted from the transaction-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, the corresponding account and other accounts of the same identity. Consistent mobile phone numbers
  • a supervised model is trained to identify the fraudulent use of secondary number account.
  • the embodiment of the present specification also provides a non-volatile computer storage medium corresponding to FIG. 2, which stores computer-executable instructions, and the computer-executable instructions are set to:
  • the following two types of risk characteristics of the account transaction are extracted from the transaction-related data: the consistency of user names between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the second number account misappropriation for the account transaction is determined.
  • the embodiment of the present specification also provides a non-volatile computer storage medium corresponding to FIG. 4, which stores computer-executable instructions, and the computer-executable instructions are set to:
  • the following two types of risk characteristics of the account operation are extracted from the operation-related data: the consistency of the user name between the address book system and the account system to which the corresponding mobile phone number belongs, and between the corresponding account and other accounts of the same identity Consistent mobile phone number;
  • the identification result of the misappropriation of the secondary number account for the account operation is determined.
  • the apparatus, device, and non-volatile computer storage medium provided in the embodiments of the present specification correspond to the method. Therefore, the apparatus, device, and non-volatile computer storage medium also have beneficial technical effects similar to the corresponding method.
  • the beneficial technical effects of the method are described in detail, and therefore, the beneficial technical effects of the corresponding device, device, and non-volatile computer storage medium are not repeated here.
  • a programmable logic device Programmable Logic Device (PLD)
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • the controller may be implemented in any suitable way, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, With the Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
  • the controller may take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited
  • controller logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded controllers by logically programming the method steps.
  • Microcontrollers and the like to achieve the same function. Therefore, such a controller can be regarded as a hardware component, and a device included in the controller for implementing various functions can also be regarded as a structure within the hardware component. Or even, the means for implementing various functions may be regarded as a structure that can be both a software module implementing the method and a hardware component.
  • the system, device, module, or unit described in the foregoing embodiments may be specifically implemented by a computer chip or entity, or a product with a certain function.
  • a typical implementation device is a computer.
  • the computer may 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.
  • the embodiments of the present specification may be provided as a method, a system, or a computer program product. Therefore, the embodiments of the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a specific manner such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, the instructions
  • the device implements the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of steps can be performed on the computer or other programmable device to produce a computer-implemented process, which can be executed on the computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.
  • a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.
  • processors CPUs
  • input / output interfaces output interfaces
  • network interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include non-persistent memory, random access memory (RAM), and / or non-volatile memory in computer-readable media, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media includes permanent and non-persistent, removable and non-removable media.
  • Information storage can be accomplished by any method or technology.
  • Information may be computer-readable instructions, data structures, modules of a program, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), and read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transmitting medium may be used to store information that can be accessed by a computing device.
  • computer-readable media does not include temporary computer-readable media, such as modulated data signals and carrier waves.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • This specification can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected through a communication network.
  • program modules may be located in local and remote computer storage media, including storage devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Telephonic Communication Services (AREA)
  • Lock And Its Accessories (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

本说明书实施例公开了识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备。方案包括：获取多个账户的交易相关数据；针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用；用训练过的有监督模型识别二次放号账户盗用。

Description

识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备 技术领域
本说明书涉及计算机软件技术领域，尤其涉及识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备。
背景技术
手机号资源属于国家所有，用户仅享有使用权。由于手机号资源的有限性，当用户停用手机号，则该手机号会被通信运营商回收，经过一段时间的冻结期后，再入网重新投入市场，即二次放号。目前国家规定手机号最短冻结期限为90天。
伴随着移动互联网的发展，越来越多的互联网平台都以手机号直接作为用户的账户，或者与用户的账户绑定的身份标识，对于这两种情况，都可以利用账户对应的手机号，登录该账户。
若手机号的原有用户在停用手机号后，却未及时在这些互联网平台进行手机号变更操作，则存在个人隐私和财产被他人侵犯的风险。手机号的新用户或者部分不法分子会利用此风险漏洞，通过短信校验的方式，冒充原有用户的身份在这些互联网平台登录进而操作账户，导致原有用户资金损失和信息泄露。
在现有技术中，通过分别向各省通信运营商购买手机号入网时间和状态数据，若某手机号入网时间晚于对应账户注册时间，则该手机号有较大可能属于二次放号，进而可以据此识别二次放号账户盗用。
基于此，需要能够更为高效地识别二次放号账户盗用的风控方案。
发明内容
本说明书实施例提供识别二次放号账户盗用的风控方法、装置以及设备，用以解决如下技术问题：需要更为有效的识别二次放号账户盗用的风控方案。
为解决上述技术问题，本说明书实施例是这样实现的：
本说明书实施例提供的一种识别二次放号账户盗用的风控模型训练方法，包括：
获取多个账户的交易相关数据；
针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
本说明书实施例提供的一种识别二次放号账户盗用的风控方法，包括：
获取待识别的账户交易对应的交易相关数据；
从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
将提取的风险特征输入上述训练过的有监督模型进行处理；
根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
本说明书实施例提供的另一种识别二次放号账户盗用的风控方法，包括：
获取待识别的账户操作对应的操作相关数据；
从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
本说明书实施例提供的一种识别二次放号账户盗用的风控模型训练装置，包括：
第一获取模块，获取多个账户的交易相关数据；
第二获取模块，针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
提取模块，从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份 的其他账户之间的手机号一致情况；
训练模块，以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
本说明书实施例提供的一种识别二次放号账户盗用的风控装置，包括：
获取模块，获取待识别的账户交易对应的交易相关数据；
提取模块，从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
处理模块，将提取的风险特征输入上述训练过的有监督模型进行处理；
确定模块，根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
本说明书实施例提供的另一种识别二次放号账户盗用的风控装置，包括：
获取模块，获取待识别的账户操作对应的操作相关数据；
提取模块，从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
确定模块，根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
本说明书实施例提供的一种识别二次放号账户盗用的风控模型训练设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取多个账户的交易相关数据；
针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所 属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
本说明书实施例提供的一种识别二次放号账户盗用的风控设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取待识别的账户交易对应的交易相关数据；
从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
将提取的风险特征输入上述训练过的有监督模型进行处理；
根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
本说明书实施例提供的另一种识别二次放号账户盗用的风控设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取待识别的账户操作对应的操作相关数据；
从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
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：无需依赖于 通信运营商提供的手机号入网时间和状态数据，而是可以利用自有的互联网平台数据资源，尤其利用了手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、账户与同身份的其他账户之间的手机号一致情况，这两类与二次放号账户盗用密切相关的特征，从而有利于更为高效地识别二次放号账户盗用。
附图说明
为了更清楚地说明本说明书实施例或现有技术中的技术方案，下面将对实施例或现有技术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说明书中记载的一些实施例，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为本说明书实施例提供的一种识别二次放号账户盗用的风控模型训练方法的流程示意图；
图2为本说明书实施例提供的一种识别二次放号账户盗用的风控方法的流程示意图；
图3为本说明书实施例提供的一种实际应用场景下，上述风控模型训练方法和风控方法的一种具体实施方案的流程示意图；
图4为本说明书实施例提供的另一种识别二次放号账户盗用的风控方法的流程示意图；
图5为本说明书实施例提供的对应于图1的一种识别二次放号账户盗用的风控模型训练装置的结构示意图；
图6为本说明书实施例提供的对应于图2的一种识别二次放号账户盗用的风控装置的结构示意图；
图7为本说明书实施例提供的对应于图4的一种识别二次放号账户盗用的风控装置的结构示意图。
具体实施方式
本说明书实施例提供识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备。
为了使本技术领域的人员更好地理解本说明书中的技术方案，下面将结合本说明书 实施例中的附图，对本说明书实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本说明书实施例，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，都应当属于本申请保护的范围。
图1为本说明书实施例提供的一种识别二次放号账户盗用的风控模型训练方法的流程示意图，该流程可以由服务器自动执行，某些步骤也可以允许人工干预。
图1中的流程可以包括以下步骤：
S102：获取多个账户的交易相关数据。
在本说明书实施例中，账户比如是搭载于终端上的某个应用的账户，比如，第三方支付应用的账户、银行应用的账户、即时通讯应用的账户等。同一应用的不同账户之间能够进行交易，通过交易，引发实际资金或者虚拟物品在交易双方账户之间的转移。账户本身可以是手机号；或者，虽然不是手机号，但是绑定有手机号，利用所绑定的手机号，能够登录(直接用手机号通过短信验证的方式登录，或者用手机号找回账户密码登录等)账户。
在本说明书实施例中，识别二次放号账户盗用可以是针对账户交易的，也可以是针对账户的，本说明书主要以前一种情况为例进行说明，则一笔账户交易可以视为一个样本。一般地，若针对某笔账户交易，识别出其属于二次放号账户盗用事件，则相应的账户具有风险，可以直接对该账户进行管控，以免造成用户损失。
S104：针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件。
在本说明书实施例中，定性标签可以基于人工分析或者用户主动报案等方式确定，可以认为定性标签包含的结论是可信的。定性标签可以以二值(比如0-1等)或者概率值等形式表示。
S106：从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况。
在本说明书实施例中，考虑基于通讯录的风险特征，以及基于账户静态信息的风险特征，作为识别依据，原因在于，通讯录和账户静态信息会直接或者间接地涉及手机号，具有较高的参考价值。其中，账户静态信息可以包括账户绑定的手机号，以及与账户相 关的其他账户等。
基于通讯录的风险特征包括上述的用户姓名情况一致情况。针对某账户交易，可以确定账户对应的手机号，该手机号所属的通讯录体系比如包括相应用户及其好友的手机自带的通讯录、当前应用以及属于同一公司的其他应用或者有合作的第三方应用的通讯录等，该手机号所属的账号体系比如包括当前应用的账号体系等。通讯录体系与账户体系之间的用户姓名不一致的程度越高，越可能存在二次放号账户盗用情况。这类风险特征具体的提取方式可以是多样的，比如，可以比较通信录数据里最近3个月添加手机号码对应姓名与账户的用户姓名相似的次数，绝对值越低，则盗用风险越高，据此提取出相应的风险特征。
基于通讯录的风险特征还可以包括更多内容。比如，在通讯录中，近一段时间内相同用户的手机号码的变更情况，相同手机号码的用户姓名变更情况等。
基于账户静态信息的风险特征包括上述的手机号一致情况。这类风险特征具体的提取方式可以是多样的，比如，可以判断同身份(比如同身份证号、同银行卡号等)的其他活跃账户绑定的手机号与当前账户绑定的手机号是否一致，不一致则盗用风险高，据此提取出相应的风险特征。
基于账户静态信息的风险特征还可以包括更多内容。比如，账户相关的其他账户所绑定的手机号的变更情况等。
前面对通讯录、账户静态信息这两个维度的风险特征进行了说明，还可以利用更多维度的风险特征。更多维度比如包括：账户活跃度、账户异常操作行为、账户设备信息等维度。
例如，对于步骤S106，所述从所述交易相关数据中提取各所述账户交易的以下两类风险特征，还可以执行：从所述交易相关数据中提取各所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。比如，若所用设备(通常是某用户的手机)在一天内尝试登录的账户数量越多，则盗用风险越高；若以往较少通过短信方式登录账户，但最近一段时间却多次尝试通过短信方式登录账户，则盗用风险较高；若账户最近一段时间反常地进行交易或者提现等敏感操作，则盗用风险较高。
S108：以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
在本说明书实施例中，可以将单笔账户交易作为一个训练用的样本。在训练过程中，提取的风险特征作为有监督模型的输入数据，有监督模型输出的预测结果与定性标签进行比较，若不一致，则对有监督模型进行调整(比如，调整模型结构、调整权重参数等)。如此迭代，直至模型符合预期，进而可以投入使用，比如，将模型发布上线，用于判定线上交易是否属于二次放号账户盗用事件等。
在本说明书实施例中，有监督模型可以是多样的，其比如基于梯度提升决策树或者随机森林等有监督算法。
通过图1的方法，无需依赖于通信运营商提供的手机号入网时间和状态数据，而是可以利用自有的互联网平台数据资源，尤其利用了手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、账户与同身份的其他账户之间的手机号一致情况，这两类与二次放号账户盗用密切相关的特征，从而有利于更为高效地识别二次放号账户盗用。
上述训练过的有监督模型可以投入风控，用于识别二次放号账户盗用，基于此，本说明书实施例还提供了一种识别二次放号账户盗用的风控方法的流程示意图，如图2所示。
图2中的流程可以包括以下步骤：
S202：获取待识别的账户交易对应的交易相关数据。
在本说明书实施例中，待识别的账户交易可以是线上正在进行中的交易，也可以是离线的已经进行完毕的交易。
S204：从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况。
S206：将提取的风险特征输入上述训练过的有监督模型进行处理。
S208：根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
在本说明书实施例中，根据识别结果，若判定属于二次放号账户盗用事件，则可以对相应的账户进行控制，以及中止该账户进行中的交易，以免给用户带来损失。
通过图2的方法，无需依赖于通信运营商提供的手机号入网时间和状态数据，而是可以利用自有的互联网平台数据资源，尤其利用了手机号所属的通讯录体系与账户体系 之间的用户姓名一致情况、账户与同身份的其他账户之间的手机号一致情况，这两类与二次放号账户盗用密切相关的特征，从而有利于更为高效地识别二次放号账户盗用。
在本说明书实施例中，对于步骤S204，所述从所述交易相关数据中提取所述账户交易的以下两类风险特征，还可以执行：从所述交易相关数据中提取所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
在本说明书实施例中，有监督模型处理后输出的预测结果能够反映：所述账户交易属于二次放号账户盗用事件的可能性。预测结果比如可以是一个概率值，或者类似概率值的指定取值区间中的一个确定值等。
在实际应用中，可以结合预测结果和其他一些认证措施，来进行风控，以提高方案整体的可靠性，尽量避免误伤账户。
例如，对于步骤S208，所述根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果，具体可以包括：若所述可能性高于设定阈值，则通过生物特征和/或银行卡和/或证件等短信验证以外的认证方式，对所述账户交易的操作用户进行认证，根据认证结果，判定所述账户交易是否属于二次放号账户盗用事件；或者，若所述可能性高于设定阈值，则判定所述账户交易属于二次放号账户盗用事件。
根据前面的说明，本说明书实施例还提供了一种实际应用场景下，上述风控模型训练方法和风控方法的一种具体实施方案的流程示意图，如图3所示。
图3中的流程可以包括以下步骤：
获取账户的交易相关数据，将其包含的账户交易作为样本进行黑白样本打标签处理；从五个不同维度提取风险特征，包括：基于账户活跃度的风险特征，(比如账户过去90天的交易数量)，基于账户异常操作行为的风险特征(比如过去30天内有无短信方式尝试登录账户)，基于通讯录的风险特征(比如通讯录内最近三个月内添加手机号的用户姓名与账户的用户姓名相似的次数)，基于账户静态信息的风险特征(比如同证件其他活跃账户与当前账户绑定的手机号是否一致)，基于账户静态信息的风险特征(比如同证件其他活跃账户与当前账户绑定的手机号是否一致)；得到模型输入数据X，X是特征向量，包含各个风险特征；使用诸如梯度提升决策树或者随机森林等算法生成有监督模型；利用训练集打标样本训练，并评估模型性能，直至模型符合预期；部署模 型上线，对线上交易进行打分，判断线上的当前交易的分值是否是高分；若不是高分，则交易通过，不认为是盗用事件；若是高分，则利用非短信方式校验产品，比如人脸、银行卡号校验，判断该当前交易的操作用户是否通过校验，若校验通过，则交易通过，不认为是盗用事件，若校验不通过，则交易不通过，认为是盗用事件。
上面主要是以针对账户交易为例，对识别二次放号账户盗用进行说明的，上述方案的思路也适用于针对账户交易以外的其他账户操作，比如账户登录、账户修改密码等敏感操作，而且在识别时也并不限于利用有监督模型。基于此，本说明书实施例还提供了另一种识别二次放号账户盗用的风控方法的流程示意图，如图4所示，图4中的流程的一部分内容与图2一致，参照上面对图2的说明理解即可，不再赘述。
图4中的流程可以包括以下步骤：
S402：获取待识别的账户操作对应的操作相关数据。
S404：从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况。
S406：根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
在本说明书实施例中，以提取的风险特征作为输入数据，可以采用模型，确定二次放号账户盗用识别结果；或者，也可以利用诸如正则表达式等相对简单直接的规则，确定二次放号账户盗用识别结果，有利于降低方案实施成本。比如，若通过正则表达式匹配，确定上述用户姓名一致情况、手机号一致情况不一致均为不一致，则可以直接判定待识别的账户操作属于二次放号账户盗用事件。
通过图4的方法，有利于更为高效地识别二次放号账户盗用。
在本说明书实施例中，对于步骤S404，所述从所述操作相关数据中提取所述账户操作的以下两类风险特征，还可以执行：从所述操作相关数据中提取所述账户操作的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
基于同样的思路，本说明书实施例还提供了上述方法对应的装置，如图5、图6、图7所示。
图5为本说明书实施例提供的对应于图1的一种识别二次放号账户盗用的风控模型训练装置的结构示意图，所述装置包括：
第一获取模块501，获取多个账户的交易相关数据；
第二获取模块502，针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
提取模块503，从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
训练模块504，以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
可选地，所述提取模块503从所述交易相关数据中提取各所述账户交易的以下两类风险特征，还包括：
所述提取模块503从所述交易相关数据中提取各所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
可选地，所述有监督模型基于梯度提升决策树或者随机森林。
图6为本说明书实施例提供的对应于图2的一种识别二次放号账户盗用的风控装置的结构示意图，所述装置包括：
获取模块601，获取待识别的账户交易对应的交易相关数据；
提取模块602，从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
处理模块603，将提取的风险特征输入上述训练过的有监督模型进行处理；
确定模块604，根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
可选地，所述提取模块602从所述交易相关数据中提取所述账户交易的以下两类风险特征，还包括：
所述提取模块602从所述交易相关数据中提取所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
可选地，所述有监督模型处理后输出的预测结果反映：所述账户交易属于二次放号账户盗用事件的可能性；
所述确定模块604根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果，具体包括：
所述确定模块604若所述可能性高于设定阈值，则通过生物特征和/或银行卡和/或证件，对所述账户交易的操作用户进行认证，根据认证结果，判定所述账户交易是否属于二次放号账户盗用事件；或者，
若所述可能性高于设定阈值，则判定所述账户交易属于二次放号账户盗用事件。
图7为本说明书实施例提供的对应于图4的一种识别二次放号账户盗用的风控装置的结构示意图，所述装置包括：
获取模块701，获取待识别的账户操作对应的操作相关数据；
提取模块702，从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
确定模块703，根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
所述提取模块702从所述操作相关数据中提取所述账户操作的以下两类风险特征，还包括：
可选地，所述提取模块702从所述操作相关数据中提取所述账户操作的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
基于同样的思路，本说明书实施例还提供了对应于图1的一种识别二次放号账户盗用的风控模型训练设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取多个账户的交易相关数据；
针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
基于同样的思路，本说明书实施例还提供了对应于图2的一种识别二次放号账户盗用的风控设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取待识别的账户交易对应的交易相关数据；
从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
将提取的风险特征输入上述训练过的有监督模型进行处理；
根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
基于同样的思路，本说明书实施例还提供了对应于图4的一种识别二次放号账户盗用的风控设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取待识别的账户操作对应的操作相关数据；
从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
基于同样的思路，本说明书实施例还提供了对应于图1的一种非易失性计算机存储介质，存储有计算机可执行指令，所述计算机可执行指令设置为：
获取多个账户的交易相关数据；
针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
基于同样的思路，本说明书实施例还提供了对应于图2的一种非易失性计算机存储介质，存储有计算机可执行指令，所述计算机可执行指令设置为：
获取待识别的账户交易对应的交易相关数据；
从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
将提取的风险特征输入上述训练过的有监督模型进行处理；
根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
基于同样的思路，本说明书实施例还提供了对应于图4的一种非易失性计算机 存储介质，存储有计算机可执行指令，所述计算机可执行指令设置为：
获取待识别的账户操作对应的操作相关数据；
从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
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，对于装置、设备、非易失性计算机存储介质实施例而言，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。
本说明书实施例提供的装置、设备、非易失性计算机存储介质与方法是对应的，因此，装置、设备、非易失性计算机存储介质也具有与对应方法类似的有益技术效果，由于上面已经对方法的有益技术效果进行了详细说明，因此，这里不再赘述对应装置、设备、非易失性计算机存储介质的有益技术效果。
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，在实施本说明书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，本说明书实施例可提供为方法、系统、或计算机程序产品。因此，本说明书实施例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，本说明书实施例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。
本说明书是参照根据本说明书实施例的方法、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，本说明书实施例可提供为方法、系统或计算机程序产品。因此，本说明书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，本说明书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。
本说明书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任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说明书，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任务。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。
以上所述仅为本说明书实施例而已，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. 一种识别二次放号账户盗用的风控模型训练方法，包括：
    获取多个账户的交易相关数据；
    针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
    从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
  2. 如权利要求1所述的方法，所述从所述交易相关数据中提取各所述账户交易的以下两类风险特征，还包括：
    从所述交易相关数据中提取各所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
  3. 如权利要求1所述的方法，所述有监督模型基于梯度提升决策树或者随机森林。
  4. 一种识别二次放号账户盗用的风控方法，包括：
    获取待识别的账户交易对应的交易相关数据；
    从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    将提取的风险特征输入按照如权利要求1～3任一项所述的方法训练过的有监督模型进行处理；
    根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
  5. 如权利要求4所述的方法，所述从所述交易相关数据中提取所述账户交易的以下两类风险特征，还包括：
    从所述交易相关数据中提取所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
  6. 如权利要求4所述的方法，所述有监督模型处理后输出的预测结果反映：所述账户交易属于二次放号账户盗用事件的可能性；
    所述根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放 号账户盗用识别结果，具体包括：
    若所述可能性高于设定阈值，则通过生物特征和/或银行卡和/或证件，对所述账户交易的操作用户进行认证，根据认证结果，判定所述账户交易是否属于二次放号账户盗用事件；或者，
    若所述可能性高于设定阈值，则判定所述账户交易属于二次放号账户盗用事件。
  7. 一种识别二次放号账户盗用的风控方法，包括：
    获取待识别的账户操作对应的操作相关数据；
    从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
  8. 如权利要求7所述的方法，所述从所述操作相关数据中提取所述账户操作的以下两类风险特征，还包括：
    从所述操作相关数据中提取所述账户操作的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
  9. 一种识别二次放号账户盗用的风控模型训练装置，包括：
    第一获取模块，获取多个账户的交易相关数据；
    第二获取模块，针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
    提取模块，从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    训练模块，以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
  10. 如权利要求9所述的装置，所述提取模块从所述交易相关数据中提取各所述账户交易的以下两类风险特征，还包括：
    所述提取模块从所述交易相关数据中提取各所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
  11. 如权利要求9所述的装置，所述有监督模型基于梯度提升决策树或者随机森林。
  12. 一种识别二次放号账户盗用的风控装置，包括：
    获取模块，获取待识别的账户交易对应的交易相关数据；
    提取模块，从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    处理模块，将提取的风险特征输入按照如权利要求1～3任一项所述的方法训练过的有监督模型进行处理；
    确定模块，根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
  13. 如权利要求12所述的装置，所述提取模块从所述交易相关数据中提取所述账户交易的以下两类风险特征，还包括：
    所述提取模块从所述交易相关数据中提取所述账户交易的以下至少一类风险特征：所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
  14. 如权利要求12所述的装置，所述有监督模型处理后输出的预测结果反映：所述账户交易属于二次放号账户盗用事件的可能性；
    所述确定模块根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果，具体包括：
    所述确定模块若所述可能性高于设定阈值，则通过生物特征和/或银行卡和/或证件，对所述账户交易的操作用户进行认证，根据认证结果，判定所述账户交易是否属于二次放号账户盗用事件；或者，
    若所述可能性高于设定阈值，则判定所述账户交易属于二次放号账户盗用事件。
  15. 一种识别二次放号账户盗用的风控装置，包括：
    获取模块，获取待识别的账户操作对应的操作相关数据；
    提取模块，从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    确定模块，根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
  16. 如权利要求15所述的装置，所述提取模块从所述操作相关数据中提取所述账户操作的以下两类风险特征，还包括：
    所述提取模块从所述操作相关数据中提取所述账户操作的以下至少一类风险特征： 所用设备上的多账户登录情况、对应的账户的短信方式登录情况、对应的账户的活跃情况。
  17. 一种识别二次放号账户盗用的风控模型训练设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
    获取多个账户的交易相关数据；
    针对所述交易相关数据包含的历史的账户交易，获取所述账户交易的定性标签，所述定性标签表明其对应的账户交易是否属于二次放号账户盗用事件；
    从所述交易相关数据中提取各所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    以获取的定性标签和提取的风险特征作为训练数据，训练有监督模型，用以识别二次放号账户盗用。
  18. 一种识别二次放号账户盗用的风控设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
    获取待识别的账户交易对应的交易相关数据；
    从所述交易相关数据中提取所述账户交易的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    将提取的风险特征输入按照如权利要求1～3任一项所述的方法训练过的有监督模型进行处理；
    根据所述有监督模型处理后输出的预测结果，确定针对所述账户交易的二次放号账户盗用识别结果。
  19. 一种识别二次放号账户盗用的风控设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
    获取待识别的账户操作对应的操作相关数据；
    从所述操作相关数据中提取所述账户操作的以下两类风险特征：对应的手机号所属的通讯录体系与账户体系之间的用户姓名一致情况、对应的账户与同身份的其他账户之间的手机号一致情况；
    根据提取的风险特征，确定针对所述账户操作的二次放号账户盗用识别结果。
PCT/CN2019/089939 2018-07-03 2019-06-04 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备 WO2020007153A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810716529.1 2018-07-03
CN201810716529.1A CN109087106B (zh) 2018-07-03 2018-07-03 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备

Publications (1)

Publication Number Publication Date
WO2020007153A1 true WO2020007153A1 (zh) 2020-01-09

Family

ID=64837163

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/089939 WO2020007153A1 (zh) 2018-07-03 2019-06-04 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备

Country Status (3)

Country Link
CN (1) CN109087106B (zh)
TW (1) TWI782205B (zh)
WO (1) WO2020007153A1 (zh)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582868A (zh) * 2020-05-26 2020-08-25 支付宝(杭州)信息技术有限公司 一种交易请求的处理方法、装置及设备
CN112101810A (zh) * 2020-09-23 2020-12-18 中国建设银行股份有限公司 风险事件控制方法、装置及系统
CN112529429A (zh) * 2020-12-16 2021-03-19 平安科技（深圳）有限公司 客户信息校验方法、装置、计算机设备及存储介质
CN112529624A (zh) * 2020-12-15 2021-03-19 北京百度网讯科技有限公司 生成业务预测模型的方法、装置、设备以及存储介质
CN112581259A (zh) * 2020-12-16 2021-03-30 同盾控股有限公司 账户风险识别方法及装置、存储介质、电子设备
CN112822676A (zh) * 2021-01-15 2021-05-18 中国银联股份有限公司 一种访问应用的方法及装置
CN113763057A (zh) * 2020-05-28 2021-12-07 北京金山云网络技术有限公司 用户身份画像的数据处理方法和装置
CN114092097A (zh) * 2021-11-23 2022-02-25 支付宝(杭州)信息技术有限公司 风险识别模型的训练方法、交易风险确定方法及装置
CN115730233A (zh) * 2022-10-28 2023-03-03 支付宝(杭州)信息技术有限公司 一种数据处理方法、装置、可读存储介质以及电子设备

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109087106B (zh) * 2018-07-03 2020-12-08 创新先进技术有限公司 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备
CN110167007B (zh) * 2019-05-22 2021-09-17 中国联合网络通信集团有限公司 一种业务处理方法和系统
CN110263817B (zh) * 2019-05-28 2023-04-07 创新先进技术有限公司 一种基于用户账号的风险等级划分方法及装置
CN110363534B (zh) * 2019-06-28 2023-11-17 创新先进技术有限公司 用于识别异常交易的方法及装置
CN111263351B (zh) * 2020-01-09 2022-07-22 支付宝(杭州)信息技术有限公司 业务处理方法、业务处理装置、电子设备及存储介质
CN111581613B (zh) * 2020-04-29 2023-11-14 支付宝(杭州)信息技术有限公司 一种账户登录验证方法及系统
CN111784352A (zh) * 2020-06-30 2020-10-16 支付宝(杭州)信息技术有限公司 认证风险识别方法、装置和电子设备
CN112232809B (zh) * 2020-09-24 2022-09-16 支付宝(杭州)信息技术有限公司 冻结账户的数据管理方法、装置、设备及存储介质
CN112215613B (zh) * 2020-10-09 2022-06-24 支付宝(杭州)信息技术有限公司 一种密码验证方法、装置、设备及介质
CN112819175A (zh) * 2021-01-14 2021-05-18 中博信征信有限公司 非法所得合法化账户识别方法、装置、设备及存储介质
CN115426265B (zh) * 2022-11-02 2023-04-18 之江实验室 一种多模态网络下交换资源分配优化方法及装置、介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106600073A (zh) * 2016-12-28 2017-04-26 携程旅游网络技术（上海）有限公司 互联网支付风控系统的优化方法及装置
CN107480483A (zh) * 2016-06-07 2017-12-15 阿里巴巴集团控股有限公司 一种账号检测的方法及装置
CN108171519A (zh) * 2016-12-07 2018-06-15 阿里巴巴集团控股有限公司 业务数据的处理、账户识别方法及装置、计算机终端
CN109087106A (zh) * 2018-07-03 2018-12-25 阿里巴巴集团控股有限公司 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9652772B1 (en) * 2011-08-10 2017-05-16 Jpmorgan Chase Bank, N.A. Systems and methods for fraud detection
CN107169499B (zh) * 2016-03-07 2021-01-05 创新先进技术有限公司 一种风险识别方法及装置
CN107798390B (zh) * 2017-11-22 2023-03-21 创新先进技术有限公司 一种机器学习模型的训练方法、装置以及电子设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107480483A (zh) * 2016-06-07 2017-12-15 阿里巴巴集团控股有限公司 一种账号检测的方法及装置
CN108171519A (zh) * 2016-12-07 2018-06-15 阿里巴巴集团控股有限公司 业务数据的处理、账户识别方法及装置、计算机终端
CN106600073A (zh) * 2016-12-28 2017-04-26 携程旅游网络技术（上海）有限公司 互联网支付风控系统的优化方法及装置
CN109087106A (zh) * 2018-07-03 2018-12-25 阿里巴巴集团控股有限公司 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582868B (zh) * 2020-05-26 2023-08-04 支付宝(杭州)信息技术有限公司 一种交易请求的处理方法、装置及设备
CN111582868A (zh) * 2020-05-26 2020-08-25 支付宝(杭州)信息技术有限公司 一种交易请求的处理方法、装置及设备
CN113763057B (zh) * 2020-05-28 2024-05-14 北京金山云网络技术有限公司 用户身份画像的数据处理方法和装置
CN113763057A (zh) * 2020-05-28 2021-12-07 北京金山云网络技术有限公司 用户身份画像的数据处理方法和装置
CN112101810A (zh) * 2020-09-23 2020-12-18 中国建设银行股份有限公司 风险事件控制方法、装置及系统
CN112529624A (zh) * 2020-12-15 2021-03-19 北京百度网讯科技有限公司 生成业务预测模型的方法、装置、设备以及存储介质
CN112529624B (zh) * 2020-12-15 2024-01-09 北京百度网讯科技有限公司 生成业务预测模型的方法、装置、设备以及存储介质
CN112581259B (zh) * 2020-12-16 2023-09-19 同盾控股有限公司 账户风险识别方法及装置、存储介质、电子设备
CN112581259A (zh) * 2020-12-16 2021-03-30 同盾控股有限公司 账户风险识别方法及装置、存储介质、电子设备
CN112529429A (zh) * 2020-12-16 2021-03-19 平安科技（深圳）有限公司 客户信息校验方法、装置、计算机设备及存储介质
CN112529429B (zh) * 2020-12-16 2024-05-14 平安科技（深圳）有限公司 客户信息校验方法、装置、计算机设备及存储介质
CN112822676B (zh) * 2021-01-15 2023-06-30 中国银联股份有限公司 一种访问应用的方法及装置
CN112822676A (zh) * 2021-01-15 2021-05-18 中国银联股份有限公司 一种访问应用的方法及装置
CN114092097A (zh) * 2021-11-23 2022-02-25 支付宝(杭州)信息技术有限公司 风险识别模型的训练方法、交易风险确定方法及装置
CN114092097B (zh) * 2021-11-23 2024-05-24 支付宝(杭州)信息技术有限公司 风险识别模型的训练方法、交易风险确定方法及装置
CN115730233A (zh) * 2022-10-28 2023-03-03 支付宝(杭州)信息技术有限公司 一种数据处理方法、装置、可读存储介质以及电子设备
CN115730233B (zh) * 2022-10-28 2023-07-11 支付宝(杭州)信息技术有限公司 一种数据处理方法、装置、可读存储介质以及电子设备

Also Published As

Publication number Publication date
CN109087106A (zh) 2018-12-25
TW202006620A (zh) 2020-02-01
CN109087106B (zh) 2020-12-08
TWI782205B (zh) 2022-11-01

Similar Documents

Publication Publication Date Title
WO2020007153A1 (zh) 识别二次放号账户盗用的风控模型训练、风控方法、装置以及设备
US11526889B2 (en) Resource transferring monitoring method and device
CN105337928B (zh) 用户身份识别方法、安全保护问题生成方法及装置
TWI724326B (zh) 業務授權的方法、裝置及設備
WO2017162113A1 (zh) 一种风险信息输出、风险信息构建方法及装置
CN112184239B (zh) 一种安全支付方法、装置、设备和可读介质
CN108171486B (zh) 一种具有电子印章功能的终端
TW202109323A (zh) 操作用戶識別方法、裝置及設備
CN113837638B (zh) 话术确定方法、装置及设备
WO2021174969A1 (zh) 一种校验方法、装置以及设备
CN105790948B (zh) 一种身份认证方法及装置
CN107731234A (zh) 一种身份验证的方法及装置
CN108074024A (zh) 风险识别方法、装置及系统
WO2020220212A1 (zh) 生物特征识别方法以及电子设备
JP6875521B2 (ja) バイオメトリック特徴に基づくセキュリティ検証のための方法および装置
CN111582868B (zh) 一种交易请求的处理方法、装置及设备
CN113826135B (zh) 使用话音识别进行非接触式认证的系统、方法和计算机系统
US20240073203A1 (en) Computer-based systems involving enhanced one-time passcode (otp) messaging and methods of use thereof
US11151548B2 (en) Location based wallets
CN111882425B (zh) 业务数据处理方法、装置和服务器
CN109067767A (zh) 一种人脸识别认证方法及系统
US11004080B2 (en) Fraud deterrence and/or identification using multi-faceted authorization procedures
Boragule et al. On-device Face Authentication System for ATMs and Privacy Preservation
US20110264900A1 (en) Method and arrangement for configuring electronic devices
EP3217593A1 (en) Two-factor authentication method for increasing the security of transactions between a user and a transaction point or system

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: 19829974

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: 19829974

Country of ref document: EP

Kind code of ref document: A1