CN115860749B

CN115860749B - Data processing method, device and equipment

Info

Publication number: CN115860749B
Application number: CN202310111090.0A
Authority: CN
Inventors: 李怀松; 宋博文; 张天翼; 成鹏; 秦思嘉
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2023-02-09
Filing date: 2023-02-09
Publication date: 2023-05-16
Anticipated expiration: 2043-02-09
Also published as: CN115860749A

Abstract

The embodiment of the specification discloses a data processing method, a device and equipment, wherein the method comprises the following steps: receiving an account opening request for a target account; obtaining the threshold limit data for threshold limit target accounts, determining whether the target accounts are in an account white list or in an account black list based on the threshold limit data, refusing to carry out threshold limit processing on the target accounts if the target accounts are determined to be in the account black list, and obtaining and executing a first threshold limit rule corresponding to the account white list if the target accounts are determined to be in the account white list so as to carry out threshold limit processing on the target accounts; if the target account cannot be determined to be in the account white list or the account black list based on the threshold-solving data, processing the different types of data contained in the threshold-solving data through preset data processing rules to obtain corresponding threshold-solving auxiliary information, so that threshold-solving processing is performed on the target account based on the threshold-solving auxiliary information, and the threshold-solving efficiency and accuracy of the account are improved.

Description

Data processing method, device and equipment

Technical Field

The present document relates to the field of computer technologies, and in particular, to a data processing method, apparatus, and device.

Background

In the field of risk prevention and control, the situation that misjudgment can occur inevitably so that certain one or more authorities of a certain account are limited to use and the like can cause great disturbance to user experience, so that when a user complains about the related misjudgment or requests to release the authority limit, the first time is required to process the requirements of the user, whether the account of the user is at risk is reviewed again, and whether the authority limit of the account of the user is to be released is further determined, but in the review, different levels of aesthetic requirements (such as high aesthetic speed and accurate review result are required, and compliance and interpretability are also required) are often present. Generally, a manual examination and approval mode can be adopted, however, the manual examination and approval mode has high cost and low efficiency, and cannot process a large number of tasks at the same time, although a certain efficiency can be improved through a preset rule, the accuracy is difficult to control, and serious misjudgment events are easy to occur.

Disclosure of Invention

The embodiment of the specification aims to provide an account limitation solving scheme which can well meet the above-mentioned different levels of aesthetic requirements so as to improve the limitation solving efficiency and well control the accuracy of the account limitation solving scheme.

In order to achieve the above technical solution, the embodiments of the present specification are implemented as follows:

the embodiment of the specification provides a data processing method, which comprises the following steps: an account de-limiting request for a target account is received. And obtaining the threshold limit data for threshold limit the target account, determining whether the target account is in an account white list or in an account black list based on the threshold limit data, refusing to carry out threshold limit processing on the target account if the target account is determined to be in the account black list, and obtaining and executing a first threshold limit rule corresponding to the account white list if the target account is determined to be in the account white list so as to carry out threshold limit processing on the target account. If the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

The embodiment of the specification provides a data processing system, which includes an atomic capability subsystem, an algorithm system subsystem and an application subsystem, wherein: the atomic capability subsystem is configured to provide corresponding algorithm support for the algorithmic hierarchy subsystem and the application subsystem. The application subsystem is configured to receive an account limitation-removing request for a target account, obtain limitation-removing data for limiting the target account, and call the algorithm system subsystem to carry out limitation-removing processing based on the limitation-removing data. The algorithm architecture subsystem is configured to invoke an algorithm in the atomic capability subsystem to perform the following: determining whether the target account is in an account white list or in an account black list based on the threshold data, if the target account is determined to be in the account black list, refusing to perform threshold processing on the target account, and if the target account is determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to perform threshold processing on the target account; if the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

The embodiment of the present specification provides a data processing apparatus, including: and the unlimited request module is used for receiving an account limited request aiming at the target account. The first limitation removing module is used for obtaining limitation removing data for removing the target account, determining whether the target account is in an account white list or in an account black list based on the limitation removing data, refusing to carry out limitation removing processing on the target account if the target account is determined to be in the account black list, and obtaining and executing a first limitation removing rule corresponding to the account white list if the target account is determined to be in the account white list so as to carry out limitation removing processing on the target account. And the second limitation removing module is used for respectively processing different types of data contained in the limitation removing data through a preset data processing rule to obtain corresponding limitation removing auxiliary information if the target account cannot be determined to be in an account white list or an account black list based on the limitation removing data, wherein the limitation removing auxiliary information is used for triggering a limitation removing management party to carry out limitation removing processing on the target account based on the limitation removing auxiliary information.

A data processing apparatus provided in an embodiment of the present specification includes: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: an account de-limiting request for a target account is received. And obtaining the threshold limit data for threshold limit the target account, determining whether the target account is in an account white list or in an account black list based on the threshold limit data, refusing to carry out threshold limit processing on the target account if the target account is determined to be in the account black list, and obtaining and executing a first threshold limit rule corresponding to the account white list if the target account is determined to be in the account white list so as to carry out threshold limit processing on the target account. If the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

The present description also provides a storage medium for storing computer-executable instructions that when executed by a processor implement the following: an account de-limiting request for a target account is received. And obtaining the threshold limit data for threshold limit the target account, determining whether the target account is in an account white list or in an account black list based on the threshold limit data, refusing to carry out threshold limit processing on the target account if the target account is determined to be in the account black list, and obtaining and executing a first threshold limit rule corresponding to the account white list if the target account is determined to be in the account white list so as to carry out threshold limit processing on the target account. If the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

Drawings

For a clearer description of embodiments of the present description or of the solutions of the prior art, the drawings that are required to be used in the description of the embodiments or of the prior art will be briefly described, it being obvious that the drawings in the description below are only some of the embodiments described in the description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art;

FIG. 1A is a diagram illustrating an embodiment of a data processing method according to the present disclosure;

FIG. 1B is a schematic diagram of a data processing process according to the present disclosure;

FIG. 2 is a schematic diagram of a data processing system according to the present disclosure;

FIG. 3 is a schematic diagram of another data processing procedure according to the present disclosure;

FIG. 4 is a schematic diagram of another data processing system according to the present disclosure;

FIG. 5 is a diagram of an embodiment of a data processing apparatus according to the present disclosure;

fig. 6 is a data processing apparatus embodiment of the present specification.

Detailed Description

The embodiment of the specification provides a data processing method, a device and equipment.

In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.

Example 1

As shown in fig. 1A and fig. 1B, the embodiment of the present disclosure provides a data processing method, where an execution subject of the method may be a terminal device or a server, where the terminal device may be a certain terminal device such as a mobile phone, a tablet computer, or a computer device such as a notebook computer or a desktop computer, or may also be an IoT device (specifically, a smart watch, an in-vehicle device, or the like). The server may be a single server, a server cluster including a plurality of servers, a background server such as a financial service or an online shopping service, or a background server of an application program. In this embodiment, a server is taken as an example for detailed description, and the following related contents may be referred to for the execution process of the terminal device, which is not described herein. The method specifically comprises the following steps:

in step S102, an account de-limit request for a target account is received.

The target account may be any account, and in this embodiment, the target account may be an account registered to execute a certain service or a plurality of different services, where the services may include a plurality of services, for example, any service for performing a transaction, such as online shopping, physical transaction, marketing event, transfer service, payment service, and the like, which may be specifically set according to actual situations, and embodiments of the present disclosure are not limited to this. The account opening request may be a request for opening the authority of an account, where the authority of an account may be defined by one or more different authorities of an account, for example, payment authority of an account or transfer authority of an account, which may be specifically set according to actual situations, and the embodiment of the present disclosure does not limit the authority.

In the implementation, in the field of risk prevention and control, the situation that misjudgment inevitably occurs and one or more authorities of an account are limited to use and the like can cause great disturbance to user experience, so when a user complains about the related misjudgment or requests to release the authority limit, the first time is required to process the complaint of the user, whether the user account is at risk is rechecked, and whether the authority limit of the user account is to be released is determined, but in the recheck, different levels of aesthetic requirements (such as high aesthetic speed and accurate review result, compliance and interpretability) are often required. In general, a manual review mode may be adopted, for example, information of a key transaction related to the account is extracted through a first manual or preset rule, whether a limit-solving credential submitted by a user is qualified or not is judged through a second manual or preset rule, whether the account is at risk or not is comprehensively judged through a third manual or preset rule, and further whether limit-solving processing is performed on the account is determined. The embodiment of the specification provides a technical scheme which can be realized, and specifically comprises the following contents:

As shown in fig. 2, for some services (such as a transfer service, etc.), when a user performs the service, relevant information of the user performing the service may be obtained, the recorded information may include information related to the service (such as information of a transaction class), identity class information, time of performing the service, information generated by each operation of the user during the performance of the service, location information, etc., and based on the above information, if it is determined that there is a risk in the user or an account of the user (i.e., a target account), the authority of the target account to perform the service may be limited, so that the target account cannot perform the service, if the user considers that there is no risk in the target account, an account restriction request may be generated for the target account through a terminal device, and the account restriction request may be sent to a corresponding server, which may receive the account restriction request for the target account.

Or, as shown in fig. 2, the server may record information about a plurality of different users executing a service through respective accounts, may acquire information about a plurality of different users executing a service through respective accounts within a preset period (7 days or 1 month, etc.) each time the period arrives, may determine whether there is a risk in the different users or the user's accounts (i.e., target accounts) through the acquired information, may limit the authority of the target account to execute the service if it is determined that there is a risk in the user (or users) or the user's account (i.e., target account), so that the target account cannot execute the service, may generate an account restriction request for the target account through the terminal device if the corresponding user considers that there is no risk in the target account, may send the account restriction request to the corresponding server, and may receive the account restriction request for the target account.

It should be noted that the above-mentioned two alternative processing manners may be implemented in a plurality of different processing manners in practical application, and may be specifically set according to practical situations, which is not limited in the embodiment of the present disclosure.

In step S104, the solution limit data for the target account is obtained, whether the target account is in the account white list or in the account black list is determined based on the solution limit data, if the target account is determined to be in the account black list, the solution limit processing is refused to be performed on the target account, if the target account is determined to be in the account white list, a first solution limit rule corresponding to the account white list is obtained and executed, and the solution limit processing is performed on the target account by using the first solution limit rule.

The solution limit data may include various types, for example, may include one or more of structured data, an image, text, audio, etc., specifically, one or more of identification of a target account, user operation behavior data corresponding to the target account, a solution limit credential image of the target account, etc., which may be specifically set according to an actual situation, and embodiments of the present disclosure do not limit this. The account white list can be a preset list constructed by information of accounts without specified risks, and the accounts recorded in the account white list are free of the specified risks. The account blacklist can be a preset list constructed by information of accounts with specified risks, and the accounts recorded in the account blacklist have the specified risks. The first threshold rule may include various types, in practical application, the first threshold rule may be a relatively simple rule for releasing a certain authority of a certain account, for example, a user requesting a target account provides threshold credentials, specifically, an image requesting the user of the target account to provide credentials of the user capable of proving identity of the user, or an image requesting the user of the target account to provide business license of the user, or an image requesting the user of the target account to provide transaction flow data of the user, and if information of the requested image matches corresponding reference information of a prestored target account, threshold processing is performed on the target account, otherwise threshold processing is refused to be performed on the target account, and the like, which may be specifically set according to practical situations, and embodiments of the present disclosure do not limit.

In an implementation, after the account limitation-removing request is obtained in the above manner, the identifier of the target account may be extracted from the account limitation-removing request, and in addition, the account limitation-removing request may further include one or more of an image, a text and structured data uploaded by the user, so as to enable rapid limitation-removing processing on the target account. In the above way, the data contained in the account limitation removing request can be obtained, in addition, other relevant information of the target account can be obtained through the identification of the target account, for example, relevant data (including user operation behavior data, specific transaction data in executing the service and the like) generated in the process of executing certain services by the target account can be obtained, and the obtained data can be used as limitation removing data for the limitation removing target account. Then, a plurality of different algorithms or models can be preset, corresponding algorithms or models can be selected for different types of data, for example, for an image contained in the threshold data, a preset image recognition algorithm can be used for recognizing the image, content contained in the image is determined (such as determining image information contained in the image, characters contained in the image and the like), whether a target account is in an account white list or in an account black list can be obtained based on the determined content, in addition, the obtained result can be verified through other data, if the obtained result is different from the obtained result based on other data, different numbers and the same number can be counted, so that whether the target account is in the account white list or in the account black list can be judged, for example, if the different numbers are larger than the same number, the target account is in the account black list can be judged, and if the different numbers are smaller than the same number, the target account is in the account white list can be judged.

If the target account is determined to be in the account blacklist, the target account can be directly refused to be subjected to the unlimited processing, at this time, a notification message for refusing the unlimited processing can be sent to a user of the target account, and relevant data of the account unlimited request of the current target account can be provided for a manager so that the manager can further process the target account. If the target account is determined to be in the account white list, a relatively simple threshold-removing mode can be set to perform threshold-removing processing on the target account, based on the threshold-removing mode, a first threshold-removing rule corresponding to the account white list can be preset, for example, the first threshold-removing rule can provide an image of a certificate of the user, which can prove the identity of the user, for the user requesting the target account, if the information of the image obtained by the request is matched with corresponding certificate reference information of the target account, threshold-removing processing is performed on the target account, otherwise threshold-removing processing is refused to be performed on the target account, and the like. Then, a first threshold rule corresponding to the account white list can be obtained, and threshold processing can be performed on the target account by using the first threshold rule. If the account is successfully de-limited, a notification message of the successful de-limiting may be sent to the user of the target account.

In step S106, if the target account cannot be determined to be in the account white list or the account black list based on the above-mentioned solution limit data, the solution limit auxiliary information is obtained by processing different types of data included in the solution limit data through preset data processing rules, where the solution limit auxiliary information is used to trigger the solution limit manager to perform solution limit processing on the target account based on the solution limit auxiliary information.

The data processing rules may include various types of extraction rules of information in the image, retrieval rules of similar data, and transaction intention restoration rules, and may be specifically set according to actual situations, which are not limited in the embodiment of the present specification.

In implementation, for the situation that it is difficult to determine whether the target account is in the account white list or in the processing account black list, one or more different data processing rules may be preset, analysis processing may be performed on the solution limit data through the set data processing rules to obtain corresponding relevant information that is easy to determine whether the target account is in the account white list or in the processing account black list, or whether the target account has a specified risk or not may be easily determined, the obtained information may be used as solution limit auxiliary information, and subsequently, the solution limit manager may perform solution limit processing on the target account based on the solution limit auxiliary information, and specifically, if it is unable to determine that the target account is in the account white list or the account black list based on the solution limit data, processing may be performed on different types of data contained in the solution limit data through preset data processing rules, so as to obtain corresponding solution limit auxiliary information, for example, for an image contained in the solution limit data, the extraction rules of information in the image may be used to extract user, date, transaction time, birth name, transaction time, and other information and the like, and the extracted information may be used as the auxiliary information, thereby saving human resources by manually processing the upper limit. In addition, for the text data included in the solution limit data, a preset semantic analysis model or a classification algorithm may be used to analyze the text data to obtain the semantics corresponding to the text data and the category to which the text data belongs (such as frequent interaction with an account in the account blacklist, etc.), and the obtained information may be used as solution limit auxiliary information. For other data (such as audio data or transaction data) contained in the solution limit data, a preset corresponding data model or data processing algorithm can be used for analyzing the data to obtain a corresponding analysis result, and the obtained analysis result can be used as solution limit auxiliary information and the like.

By the method, one or more different limitation-solving auxiliary information can be obtained, the obtained limitation-solving auxiliary information can be provided for a limitation-solving management party (such as a service operator and the like), the limitation-solving management party can judge whether to carry out limitation-solving processing on the target account or not based on the limitation-solving auxiliary information, if the limitation-solving processing on the target account is determined to be carried out, the limitation-solving processing on the target account can be directly carried out, and when the limitation-solving of the account is successful, a notification message of successful limitation-solving can be sent to a user of the target account, and if the limitation-solving processing on the target account cannot be carried out, the limitation-solving processing on the target account is directly refused, and at the moment, the notification message of refusing the limitation-solving processing can be sent to the user of the target account.

The embodiment of the specification provides a data processing method, which is used for acquiring the threshold data for threshold target accounts by receiving account threshold request aiming at the target accounts, determining whether the target accounts are in an account white list or in an account black list based on the threshold data, if the target accounts are determined to be in the account black list, refusing to carry out threshold processing on the target accounts, if the target accounts are determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to carry out threshold processing on the target accounts, if the target accounts are determined to be in the account white list or the account black list based on the threshold data, carrying out processing on different types of data contained in the threshold data respectively through preset data processing rules so as to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering threshold auxiliary information to carry out threshold processing on the target accounts, so that based on the atomic algorithm capability, the threshold auxiliary threshold of interpretation through automatic examination and interpretation correspondingly provides different algorithm capabilities, the threshold auxiliary threshold of threshold auxiliary information is not only greatly improved, but also the threshold auxiliary information is not only examined and the threshold auxiliary threshold information is greatly improved, and the threshold information is required to be applied to a plurality of false threshold information, and a plurality of false threshold information is not to be simultaneously read and read by a plurality of false threshold information.

Example two

As shown in fig. 3, the embodiment of the present disclosure provides a data processing method, where an execution subject of the method may be a terminal device or a server, where the terminal device may be a certain terminal device such as a mobile phone, a tablet computer, or a computer device such as a notebook computer or a desktop computer, or may also be an IoT device (specifically, such as a smart watch, an in-vehicle device, or the like). The server may be a single server, a server cluster including a plurality of servers, a background server such as a financial service or an online shopping service, or a background server of an application program. In this embodiment, a server is taken as an example for detailed description, and the following related contents may be referred to for the execution process of the terminal device, which is not described herein. The method specifically comprises the following steps:

in step S302, an account de-limit request for a target account is received.

The account unlimited request may be a request received after determining that the target account is an account with a preset risk after performing risk detection on transaction data of different users in a preset risk detection period when the preset risk detection period is reached and performing rights limiting processing on the target account, or the account unlimited request may be a request received after performing designated transaction on the target account and performing rights limiting processing on the target account when the designated transaction is detected to have the preset risk. The risk detection period can be set according to practical situations, such as 24 hours or 7 days.

In step S304, the solution limit data for the solution limit target account is acquired.

The above-mentioned threshold-removing data includes structured data and/or unstructured data, the structured data can be called row data, and the structured data is logically expressed and implemented by two-dimensional table structure, and strictly follows data format and length specification, and mainly uses relational database to make storage and management. Unstructured data may be data that is not suitable for presentation by a two-dimensional table of a database, including office documents in all formats, XML, HTML, various types of reports, image and audio, video information, and the like. The database supporting unstructured data adopts a multi-value field, a sub-field and a variable length field mechanism to create and manage data items.

In step S306, the above-mentioned solution limit data is input into a pre-trained first multi-mode solution limit model, to obtain an output result of whether the target account is in the account white list or in the account black list, where the first multi-mode solution limit model is obtained by performing model training based on the first historical data as structured data and the second historical data as unstructured data.

The first multi-mode solution limit model may be a model for processing multiple different data, where the multiple different data may be structured data, may also include unstructured data, and the like, and the first multi-mode solution limit model may be constructed by multiple different algorithms, for example, may be constructed by a classification algorithm, may be constructed by a neural network model, and the like, and may specifically be set according to practical situations, which is not limited in this embodiment of the present disclosure.

In implementation, a corresponding algorithm may be obtained, a first multi-mode solution limit model may be constructed based on the algorithm, input data of the first multi-mode solution limit model may be structured data and/or unstructured data, output data may be an output result of whether a target account is in an account white list or in an account black list, then a training sample (i.e., first historical data as structured data and second historical data as unstructured data) for training the first multi-mode solution limit model may be obtained, the training sample may be used to perform model training on the first multi-mode solution limit model, in a process of performing model training, in consideration of simple encoding processing on the training sample in an actual service scene, to obtain corresponding vector features, an objective function may be preset, model parameters in the first multi-mode solution limit model may be optimized based on the objective function, and the first multi-mode solution limit model may be adjusted according to the objective function. And then, training the first multi-mode solution limit model by using a training sample, and simultaneously optimizing the model parameters through the objective function to finally obtain the trained first multi-mode solution limit model. And then, inputting the threshold data into a pre-trained first multi-mode threshold model to obtain an output result of whether the target account is in the account white list or in the account black list.

In practical applications, the above-mentioned threshold data may include voiceprint data input by the user, and then it may be determined whether the target account is in the account white list based on the voiceprint data input by the user, and the following processing of step S308 and step S310 may be referred to specifically.

In step S308, the voiceprint data input by the user is matched with the reference voiceprint data of the account in the account white list, and whether the target account is in the account white list is determined based on the obtained matching result.

In step S310, if the target account is not in the account whitelist, the voiceprint data input by the user is matched with the reference voiceprint data of the account in the account blacklist, and whether the target account is in the account blacklist is determined based on the obtained matching result.

In step S312, if it is determined that the target account is in the account blacklist, the target account is refused to be subjected to the unlimited processing.

In step S314, if it is determined that the target account is in the account white list, the unlimited credential information is acquired from the user of the target account.

In step S316, the above-mentioned unlimited certificate information is input into a pre-trained certificate identification model, and it is determined whether the limited certificate information is valid, and if the limited certificate information is valid, the limited account is subjected to limited processing.

The credential recognition model may be a model for processing solution limit credential information, and the credential recognition model may be constructed by a plurality of different algorithms, for example, may be constructed by a classification algorithm, may be constructed by a neural network model, and the like, and may specifically be set according to actual situations, which is not limited in the embodiments of the present disclosure.

In implementation, a corresponding algorithm can be obtained, a credential recognition model can be constructed based on the algorithm, input data of the credential recognition model can be solution limit credential information provided by a user, output data can be whether the solution limit credential information is valid or not, then a training sample (namely, historical solution limit credential information provided by the user) for training the credential recognition model can be obtained, the training sample can be used for model training of the credential recognition model, in the process of model training, in consideration of the fact that in an actual service scene, the training sample is simply subjected to coding processing to obtain corresponding vector features, an objective function can be preset, model parameters in the credential recognition model can be optimized based on the objective function, and the credential recognition model can be adjusted according to the objective function. And then, training the model of the voucher identification model by using a training sample, and simultaneously optimizing the model parameters by the objective function to finally obtain the trained voucher identification model. The solution credential information may then be input into a pre-trained credential recognition model to determine if the solution credential information is valid.

In practical applications, the processing in the step S316 may be various, and an optional processing manner is provided below, which may specifically include the following processing in step A2 and step A4.

In step A2, the solution limit credential information is input into a pre-trained credential recognition model, and whether the image matches with pre-stored reference credential information is determined by the credential recognition model.

Wherein the credential recognition model may be a model for analyzing the recognition image.

In step A4, if the images are matched, extracting image information from the images, judging whether the images have preset risks or not based on the extracted image information, and if the images do not have the preset risks, determining that the solution limit credential information is valid.

The preset risk may include various types, for example, the preset risk may include fraud risk, illegal financial activity, etc., and may be specifically set according to actual situations, which is not limited in the embodiment of the present specification.

In practical applications, the above-mentioned solution limit data may include historical transaction data for the target account, and then the processing may be performed in step S318 described below.

In step S318, if it cannot be determined that the target account is in the account whitelist or the account blacklist based on the solution limit data, the historical transaction data is restored based on the pre-trained meta learning model, so as to obtain scene information and transaction intention information corresponding to the historical transaction data, and text information serving as the solution limit auxiliary information is determined based on the obtained scene information and transaction intention information, so that the meta learning model is used for restoring the scene and the transaction intention corresponding to the transaction data.

The meta-learning model can be a model which can enable the meta-learning model to acquire the capacity of adjusting the super-parameters, so that the meta-learning model can quickly learn new tasks on the basis of acquiring the existing knowledge. The meta learning model may be constructed by a plurality of different algorithms, for example, a convolutional neural network model may be constructed, or a classification algorithm (for example, a binary classification algorithm) may be constructed, which may be specifically set according to the actual situation, which is not limited in the embodiment of the present specification.

In the implementation, a corresponding algorithm can be obtained, a meta learning model can be constructed based on the algorithm, input data of the meta learning model can be historical transaction data of a user, output data can be a scene and transaction intention corresponding to the restored historical transaction data, then a training sample (namely historical transaction data of the user) for training the meta learning model can be obtained, the training sample can be used for model training of the meta learning model, in the process of model training, in consideration of simple coding processing of the training sample under an actual service scene, corresponding vector characteristics can be obtained, an objective function can be preset, model parameters in the meta learning model can be optimized based on the objective function, and the meta learning model can be adjusted. And then, training the meta learning model by using a training sample, and simultaneously optimizing the model parameters through the objective function to finally obtain the trained meta learning model.

According to the method, the fact that the target account cannot be determined to be in the account white list or the account black list based on the threshold value data is determined, the historical transaction data can be restored based on the pre-trained meta learning model, scene information and transaction intention information corresponding to the historical transaction data are obtained, and text information serving as threshold value auxiliary information is determined based on the obtained scene information and the transaction intention information.

In step S320, if it cannot be determined that the target account is in the account white list or the account black list based on the above-mentioned solution limit data, historical solution limit data with a similarity greater than a first preset similarity threshold value with the solution limit data is obtained from the solution limit database, and the obtained historical solution limit data is used as solution limit auxiliary information.

The first preset similarity threshold may be set according to practical situations, for example, 80% or 90% or the like.

In practical applications, the above-mentioned threshold data may include voiceprint data input by the user, and the following process of step S322 may be performed.

In step S322, if it cannot be determined that the target account is in the account white list or the account black list based on the above-mentioned threshold data, historical voiceprint data with a similarity greater than a second preset similarity threshold value with voiceprint data input by a user is obtained from the historical voiceprint data input by different users.

The second preset similarity threshold may be set according to practical situations, for example, 80% or 90% or the like.

In step S324, the acquired history voiceprint data and the user information corresponding to the acquired history voiceprint data are used as the solution limit auxiliary information.

In step S326, behavior data generated by the user corresponding to the target account within a preset time period after the account opening request is provided is obtained.

The preset time period can be set according to practical situations, such as 1 month or 1 year. The behavior data may be the number of times of making a call by the user, the operation behavior track on the application program, the unlimited certificate information submitted by the user, and the like, which are acquired after the permission of the target account is limited, specifically may be set according to the actual situation, and the embodiment of the present specification does not limit the present specification.

In step S328, the behavior data and the solution limit data are input into a pre-trained second multi-mode solution limit model, so as to obtain an output result of whether the target account has a preset risk, where the second multi-mode solution limit model is obtained by performing model training based on the third historical data as structured data and the fourth historical data as unstructured data, and the historical behavior data of the user.

The second multi-mode solution limit model may be a model for processing multiple different data, where the multiple different data may be structured data, may also include unstructured data, and the like, and the second multi-mode solution limit model may be constructed by multiple different algorithms, for example, may be constructed by a classification algorithm, may be constructed by a neural network model, and the like, and may specifically be set according to practical situations, and the embodiment of the present disclosure does not limit this.

In implementation, a corresponding algorithm may be obtained, a second multi-mode solution model may be constructed based on the algorithm, input data of the second multi-mode solution model may be structured data and/or unstructured data, output data may be an output result of whether a target account has a preset risk, then a training sample (i.e., third historical data serving as structured data and fourth historical data serving as unstructured data, and historical behavior data of a user) for training the second multi-mode solution model may be obtained, the training sample may be used to perform model training on the second multi-mode solution model, in a process of performing model training, in consideration of simple encoding processing on the training sample in an actual service scene, to obtain corresponding vector features, an objective function may be preset, model parameters in the second multi-mode solution model may be optimized based on the objective function, and the second multi-mode solution model may be adjusted for the objective function. And then, training the second multi-mode solution limit model by using a training sample, and simultaneously optimizing the model parameters through the objective function to finally obtain the trained second multi-mode solution limit model. And then, the behavior data and the threshold data can be input into a second multi-mode threshold model to obtain an output result of whether the target account has preset risk.

In addition, a multi-mode solution limit algorithm is used for replacing manual or rule comprehensive judgment of whether the user needs to be subjected to solution limit, the accuracy is high, the coverage is wide, and besides the algorithm, information such as voiceprint, interpretable characteristics and the like can be provided, so that the method is helpful for more accurately and quickly determining whether the account is subjected to solution limit.

Example III

The data processing method provided for the embodiments of the present disclosure, based on the same concept, may further provide a data processing system, where the execution body in the above embodiments may be provided with a data processing system, as shown in fig. 4, where the data processing system includes an atomic capability subsystem 410, an algorithm system subsystem 420, and an application subsystem 430, where:

the atomic capability subsystem 410 is configured to provide corresponding algorithm support for the algorithmic hierarchy subsystem 430 and the application subsystem 420;

the application subsystem 420 is configured to receive an account limitation-removing request for a target account, obtain limitation-removing data for limiting the target account, and call the algorithm system subsystem 430 to perform limitation-removing processing based on the limitation-removing data;

The algorithmic hierarchy subsystem 430 is configured to invoke algorithms in the atomic capability subsystem to: determining whether the target account is in an account white list or in an account black list based on the threshold data, if the target account is determined to be in the account black list, refusing to perform threshold processing on the target account, and if the target account is determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to perform threshold processing on the target account; if the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

In this embodiment of the present disclosure, the algorithm system subsystem 430 includes a first deblocking layer 431, a second deblocking layer 432, and a third deblocking layer 433, where:

The first solution-approval-layer 431 is configured to determine, based on the solution-approval-data, whether the target account is in an account white list or in an account black list, if it is determined that the target account is in the account black list, reject to perform a solution-approval process on the target account, and if it is determined that the target account is in the account white list, acquire and execute a first solution-approval rule corresponding to the account white list, so as to perform a solution-approval process on the target account;

the second solution-limit-checking layer 432 is configured to, if the target account cannot be determined to be in the account white list or the account black list based on the solution-limit data, process, respectively, different types of data included in the solution-limit data through a preset data processing rule, so as to obtain corresponding solution-limit auxiliary information;

the third solution-approval-layer 433 is configured to perform solution-approval processing on the target account by:

performing a de-limiting process on the target account based on the de-limiting auxiliary information;

acquiring historical threshold value data with similarity larger than a first preset similarity threshold value from a threshold database, and performing threshold value processing on the target account based on the acquired historical threshold value data;

And restoring historical transaction data in the threshold data based on a pre-trained meta-learning model, so as to obtain scene information and transaction intention information corresponding to the historical transaction data, respectively converting the scene information and the transaction intention information into text information, and carrying out threshold processing on the target account based on the converted text information, wherein the meta-learning model is used for restoring the scene and the transaction intention corresponding to the transaction data.

In this embodiment of the present disclosure, the atomic capability subsystem 410 is provided with one or more of a first multi-mode solution limit model, a second multi-mode solution limit model, a credential identification model, a first solution limit rule corresponding to an account white list, a meta learning model, a transaction restoration algorithm, a data-to-text conversion algorithm, a retrieval algorithm for an image, a voiceprint identification algorithm, and a voiceprint clustering algorithm, where the first multi-mode solution limit model is obtained by performing model training based on first historical data as structured data and second historical data as unstructured data, and the second multi-mode solution limit model is obtained by performing model training based on third historical data as structured data and fourth historical data as unstructured data, and historical behavior data of a user.

The first multi-modal threshold model may identify whether the user is at risk using a plurality of data formats (e.g., structured data, pictures, text, etc.), and may be used directly in the data processing system to perform the automated processing in the first threshold aesthetic layer 431. When the meta learning model restores the transaction data, the restoring type of the transaction data of a plurality of small samples needs to be judged, and the meta learning model has better application in learning of the small samples. The transaction restoration algorithm may restore each transaction to identify which intent the transaction belongs to (multiple classification processes may be performed), and may use a meta-learning model to classify the transaction in addition to classifying the transaction using a specified strategy. The input data of the data-to-text conversion algorithm may be a characteristic of the user and the output data may be a piece of interpretable text information describing the behavior of the user, which, if the user or the user's account is at risk, may describe which the risk behavior of the user or the user's account contains. If the user or the account of the user is not at risk, the normal behavior of the user, such as normal life consumption, enterprise operation, etc., will be described in conjunction with the transaction restoration algorithm. The searching algorithm for the image can search a plurality of solution limit cases similar to the current solution limit data from the solution limit database to serve as solution limit auxiliary information. And the voiceprint recognition algorithm determines whether the target account is in the account blacklist or not by matching the voiceprint data of the user with the user voiceprint data of the account in the account blacklist. The voiceprint clustering algorithm can be used for searching whether the voiceprint data of other users requesting the solution limit are similar to the voiceprint data of the current user based on the voiceprint data of the current user so as to obtain whether the user is the same person, and if the user is the same person, the voiceprint data are clustered into a category so as to judge whether the user requests the solution limit for a plurality of users in batches.

In addition, the atomic capability subsystem 410 may further include a plurality of different algorithms, such as an image algorithm and a credential recognition algorithm, where the image algorithm is a process in which a user submits the threshold-release credential information, which is typically an image, during the threshold-release processing, so that the image algorithm is required to perform the automated processing in the first threshold-release processing layer 431. For the credential recognition algorithm, if the threshold credential information submitted by the user is an image (in particular, a credential capable of proving the identity of the user, an image of a business license, an image of a bank running water), the recognition process mainly includes a plurality of functions, such as anti-counterfeiting, anti-modification, anti-repetition, whether or not it is clear, and the like. In addition, the device can also have an important function: the information in the unlimited certificate information, such as the mark, date and sex in the certificate which can prove the identity of the user, the time, amount of money and number of strokes in the bank running water, etc., is extracted, if the information is processed manually, a great deal of effort is required, and if the algorithm is used, a great amount of manpower resources can be saved.

The first threshold clearing layer 431 can use the account in the account blacklist or the account in the account whitelist identified by the first multi-mode threshold clearing model to automatically process, without manual intervention, thereby greatly saving time and improving the clearing efficiency and throughput, wherein: and rejecting the threshold clearing process for the accounts in the determined account blacklist, or actively clearing the threshold for the accounts in the determined account whitelist. In addition, the account in the account white list is only needed to be subjected to simple unlimited processing.

The second solution-limited-approval-layer 432, that is, the algorithm of this layer, provides a plurality of interpretable results and forms them into a certain structural form, so as to prove that the target account belongs to the account whitelist, or prove that the target account belongs to the account whitelist, and an approval person can quickly approve according to the auxiliary information, thereby improving the approval efficiency, wherein:

white users (i.e., users corresponding to accounts in the account whitelist): the user with the accuracy rate of 80% can carry out the threshold clearing processing preferentially, and only simple threshold clearing certificate information is needed to be provided, so that the user experience can be effectively improved. Transaction reduction & Data2Text: for each transaction, firstly judging whether risk exists, and secondly, restoring scene information and transaction intention information of the transaction, for example, a plurality of recent transactions of a user mainly purchase things at a merchant of a certain e-commerce, and further, the transaction has detailed logistics information and receiving time, so that the transaction can be considered to be normal shopping consumption, and an unlimited manager can rapidly unlimited the account based on the information. A second multi-modal solution model (i.e., a post-hoc multi-modal solution model): after the authority of the user is limited, behavior data such as the number of times of calling the user, the operation behavior track on the application program, the unlimited certificate information submitted by the user and the like can be obtained, whether the account is at risk can be accurately identified by combining the post information (namely the behavior data), and the unlimited manager can rapidly unlimited the account based on the behavior data.

The third constraint solving layer 433 may be some constraint solving cases with very little available information, and needs to be examined in combination with the interpretable information provided by the algorithm: the features can explain the & Data2Text algorithm: providing a main judging feature for judging whether risk exists or not, and summarizing the risk behaviors or normal transaction behaviors of the user by using texts so as to assist in judgment; search algorithm: for the cases which are difficult to be subjected to the limitation clearing before, the case which is closest to the cases can be found from the limitation clearing database, so that the limitation clearing management side is helped to carry out limitation clearing processing.

The application subsystem 420 is configured to, when the target account performs a specified transaction and detects that the specified transaction has a preset risk, reject the specified transaction and perform a weight limiting process on the target account, and receive an account unlimited request for the target account, where the process may be a process performed in a process of a real-time transaction; or when a preset risk detection period is reached, performing risk detection on transaction data of different users in the risk detection period, if the target account is determined to be the account with the preset risk, performing weight limiting processing on the target account, and receiving an account unlimited request aiming at the target account, wherein the processing can be performed in offline transaction.

In this embodiment of the present disclosure, the solution limit data includes structured data and/or unstructured data, and the first solution limit layer 431 is configured to input the solution limit data into a pre-trained first multi-mode solution limit model, to obtain an output result of whether the target account is in an account whitelist or in an account blacklist, where the first multi-mode solution limit model is obtained by performing model training based on first historical data serving as structured data and second historical data serving as unstructured data.

In this embodiment of the present disclosure, the threshold-clearing data includes voiceprint data input by a user, and the first threshold-clearing layer 431 is configured to match the voiceprint data input by the user with reference voiceprint data of an account in the account whitelist, and determine whether the target account is in the account whitelist based on the obtained matching result; and if the target account is not in the account white list, matching the voiceprint data input by the user with the reference voiceprint data of the account in the account black list, and determining whether the target account is in the account black list or not based on the obtained matching result.

In this embodiment of the present disclosure, the solution limit data includes historical transaction data for the target account, the second solution limit approval layer 432 is configured to perform reduction processing on the historical transaction data based on a pre-trained meta learning model, obtain scene information and transaction intention information corresponding to the historical transaction data, and determine text information serving as solution limit auxiliary information based on the obtained scene information and transaction intention information, where the meta learning model is used for performing reduction processing on the scene and the transaction intention corresponding to the transaction data.

In the embodiment of the present disclosure, the first solution-limit-checking layer 431 is configured to obtain solution-limit credential information from the user of the target account if it is determined that the target account is in the account white list; inputting the unlimited certificate information into a pre-trained certificate identification model, determining whether the limited certificate information is valid, and if the limited certificate information is valid, performing limited processing on the target account.

In this embodiment of the present disclosure, the solution-limited credential information is an image, and the first solution-limited approval layer 431 is configured to input the solution-limited credential information into a pre-trained credential identification model, and determine, through the credential identification model, whether the image is matched with pre-stored reference credential information; if so, extracting image information from the image, judging whether the image has preset risk or not based on the extracted image information, and if not, determining that the solution limit credential information is valid.

In this embodiment of the present disclosure, the second solution limit examining layer 432 is configured to obtain, from a solution limit database, historical solution limit data with a similarity with the solution limit data greater than a first preset similarity threshold, and use the obtained historical solution limit data as the solution limit auxiliary information.

In this embodiment of the present disclosure, the solution limit data includes voiceprint data input by a user, and the second solution limit approval layer 432 is configured to obtain, from historical voiceprint data input by a different user, historical voiceprint data having a similarity with the voiceprint data input by the user greater than a second preset similarity threshold; and taking the acquired historical voiceprint data and user information corresponding to the acquired historical voiceprint data as solution limit auxiliary information.

In this embodiment of the present disclosure, the second solution-limit-checking layer 432 is configured to obtain behavior data generated by the user corresponding to the target account within a preset period of time after the account-limit-checking request is provided; and inputting the behavior data and the threshold data into a pre-trained second multi-mode threshold model to obtain an output result of whether the target account has preset risk, wherein the second multi-mode threshold model is obtained by model training based on third historical data serving as structured data and fourth historical data serving as unstructured data and historical behavior data of a user.

The specific processing procedures of the above parts can be referred to the relevant content in the first embodiment and the second embodiment, and will not be described herein.

The embodiment of the specification provides a data processing system, which is used for acquiring the threshold data for threshold target accounts by receiving an account threshold request for the target accounts, determining whether the target accounts are in an account white list or in an account black list based on the threshold data, if the target accounts are determined to be in the account black list, refusing to perform threshold processing on the target accounts, if the target accounts are determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to perform threshold processing on the target accounts, if the target accounts are determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data respectively through preset data processing rules so as to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering threshold auxiliary information to perform threshold processing on the target accounts, so that based on the atomic algorithm capability, the threshold auxiliary threshold of automatic examination and interpretation correspondingly provides different algorithm capabilities, the threshold auxiliary examination and verification capabilities only do not only greatly improve the threshold examination and approval efficiency, but also greatly improve the user experience, and the threshold security, and the threshold information are required to be applied to a plurality of false scenes, and the threshold information is not to be subjected to the threshold information.

Example IV

The data processing system provided in the embodiment of the present disclosure further provides a data processing device based on the same concept, as shown in fig. 5.

The data processing apparatus includes: a solution limit request module 501, a first solution limit module 502, and a second solution limit module 503, wherein:

the unlimited request module 501 receives an account limited request for a target account;

the first limitation removing module 502 is configured to obtain limitation removing data for removing the limitation from the target account, determine whether the target account is in an account white list or in an account black list based on the limitation removing data, reject the limitation removing process on the target account if the target account is determined to be in the account black list, and obtain and execute a first limitation removing rule corresponding to the account white list if the target account is determined to be in the account white list, so as to perform the limitation removing process on the target account;

And the second solution limit module 503 is configured to, if the target account cannot be determined to be in the account white list or the account black list based on the solution limit data, process, according to different types of data included in the solution limit data, through preset data processing rules, respectively, to obtain corresponding solution limit auxiliary information, where the solution limit auxiliary information is used to trigger a solution limit manager to perform solution limit processing on the target account based on the solution limit auxiliary information.

In this embodiment of the present disclosure, the solution limit data includes structured data and/or unstructured data, and the first solution limit module 502 inputs the solution limit data into a first multi-mode solution limit model trained in advance, to obtain an output result of whether the target account is in an account white list or in an account black list, where the first multi-mode solution limit model is obtained by performing model training based on first historical data as structured data and second historical data as unstructured data.

In this embodiment of the present disclosure, the solution limitation data includes voiceprint data input by a user, and the first solution limitation module 502 includes:

the first matching unit is used for matching voiceprint data input by a user with reference voiceprint data of an account in the account white list and determining whether the target account is in the account white list or not based on an obtained matching result;

And the second matching unit is used for matching the voiceprint data input by the user with the reference voiceprint data of the account in the account blacklist if the target account is not in the account blacklist, and determining whether the target account is in the account blacklist or not based on the obtained matching result.

In this embodiment of the present disclosure, the solution limit data includes historical transaction data for the target account, the second solution limit module 503 performs reduction processing on the historical transaction data based on a pre-trained meta-learning model, so as to obtain scene information and transaction intention information corresponding to the historical transaction data, and determines text information serving as solution limit auxiliary information based on the obtained scene information and transaction intention information, where the meta-learning model is used for performing reduction processing on the scene and transaction intention corresponding to the transaction data.

In the embodiment of the present disclosure, the first solution limiting module 502 includes:

the information acquisition unit is used for acquiring the threshold-clearing credential information from a user of the target account if the target account is determined to be in the account white list;

the first unlimited certificate information is input into a pre-trained certificate identification model, whether the limited certificate information is valid or not is determined, and if the limited certificate information is valid, limited processing is performed on the target account.

In this embodiment of the present disclosure, the solution limit credential information is an image, and the first solution limit unit inputs the solution limit credential information into a pre-trained credential identification model, and determines, through the credential identification model, whether the image is matched with pre-stored reference credential information; if so, extracting image information from the image, judging whether the image has preset risk or not based on the extracted image information, and if not, determining that the solution limit credential information is valid.

In this embodiment of the present disclosure, the second solution limit module 502 obtains, from a solution limit database, historical solution limit data with a similarity greater than a first preset similarity threshold, and uses the obtained historical solution limit data as the solution limit auxiliary information.

In this embodiment of the present disclosure, the solution limitation data includes voiceprint data input by a user, and the second solution limitation module 502 includes:

the data acquisition unit acquires historical voiceprint data with similarity between the historical voiceprint data and voiceprint data input by different users being greater than a second preset similarity threshold value;

and the auxiliary information determining unit takes the acquired historical voiceprint data and user information corresponding to the acquired historical voiceprint data as solution limit auxiliary information.

In an embodiment of the present disclosure, the apparatus further includes:

the behavior data acquisition module is used for acquiring behavior data generated by a user corresponding to the target account within a preset time period after the account unlimited request is provided;

the risk determination module is used for inputting the behavior data and the threshold data into a pre-trained second multi-mode threshold model to obtain an output result of whether the target account has preset risk or not, and the second multi-mode threshold model is obtained by model training based on third historical data serving as structured data and fourth historical data serving as unstructured data and historical behavior data of a user.

In this embodiment of the present disclosure, the account unlimited request is a request received after determining that the target account is an account with a preset risk after performing risk detection on transaction data of different users in a risk detection period when the account unlimited request reaches the preset risk detection period, and performing rights limiting processing on the target account, or the account unlimited request is a request received after performing a designated transaction on the target account, and when detecting that the designated transaction has the preset risk, the designated transaction is refused and the rights limiting processing is performed on the target account.

The embodiment of the specification provides a data processing device, which is used for acquiring the threshold data for threshold target accounts by receiving an account threshold request for the target accounts, determining whether the target accounts are in an account white list or in an account black list based on the threshold data, if the target accounts are determined to be in the account black list, refusing to perform threshold processing on the target accounts, if the target accounts are determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to perform threshold processing on the target accounts, if the target accounts are determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data respectively through preset data processing rules so as to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering threshold auxiliary information to perform threshold processing on the target accounts, so that based on the atomic algorithm capability, the threshold auxiliary threshold of automatic examination and interpretation correspondingly provides different algorithm capabilities, the threshold auxiliary examination and verification capabilities only do not only greatly improve the threshold examination and approval efficiency, but also greatly improve the user experience, and the threshold security, and the threshold information are required to be applied to a plurality of security protection scenes by using the threshold information, and the threshold information.

Example five

The data processing system provided in the embodiment of the present disclosure further provides a data processing device based on the same concept, as shown in fig. 6.

The data processing device may provide a terminal device or a server or the like for the above-described embodiments.

The data processing apparatus may vary considerably in configuration or performance and may include one or more processors 601 and memory 602, where the memory 602 may store one or more stored applications or data. Wherein the memory 602 may be transient storage or persistent storage. The application programs stored in the memory 602 may include one or more modules (not shown) each of which may include a series of computer executable instructions for use in a data processing apparatus. Still further, the processor 601 may be arranged to communicate with the memory 602 and execute a series of computer executable instructions in the memory 602 on a data processing apparatus. The data processing device may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input/output interfaces 605, and one or more keyboards 606.

In particular, in this embodiment, the data processing apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the data processing apparatus, and the one or more programs configured to be executed by the one or more processors comprise instructions for:

receiving an account opening request for a target account;

obtaining limitation-solving data for limiting the target account, determining whether the target account is in an account white list or in an account black list based on the limitation-solving data, refusing to carry out limitation-solving processing on the target account if the target account is determined to be in the account black list, and obtaining and executing a first limitation-solving rule corresponding to the account white list if the target account is determined to be in the account white list so as to carry out limitation-solving processing on the target account;

if the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

In this embodiment of the present disclosure, the determining, based on the threshold data, whether the target account is in an account white list or in an account black list includes:

and inputting the threshold data into a pre-trained first multi-mode threshold model to obtain an output result of whether the target account is in an account white list or in an account black list, wherein the first multi-mode threshold model is obtained by model training based on first historical data serving as structured data and second historical data serving as unstructured data.

matching voiceprint data input by a user with reference voiceprint data of an account in the account white list, and determining whether the target account is in the account white list or not based on the obtained matching result;

and if the target account is not in the account white list, matching the voiceprint data input by the user with the reference voiceprint data of the account in the account black list, and determining whether the target account is in the account black list or not based on the obtained matching result.

In this embodiment of the present disclosure, the solution limit data includes historical transaction data for the target account, and the data for different types included in the solution limit data are respectively processed by a preset data processing rule to obtain corresponding solution limit auxiliary information, where the solution limit auxiliary information includes:

and restoring the historical transaction data based on a pre-trained meta-learning model to obtain scene information and transaction intention information corresponding to the historical transaction data, and determining text information serving as solution limit auxiliary information based on the obtained scene information and transaction intention information, wherein the meta-learning model is used for restoring the scene and the transaction intention corresponding to the transaction data.

In this embodiment of the present disclosure, if it is determined that the target account is in the account white list, acquiring and executing a first threshold rule corresponding to the account white list to perform threshold processing on the target account includes:

if the target account is determined to be in the account white list, obtaining the unlimited credential information from a user of the target account;

inputting the unlimited certificate information into a pre-trained certificate identification model, determining whether the limited certificate information is valid, and if the limited certificate information is valid, performing limited processing on the target account.

In this embodiment of the present disclosure, the solution limit credential information is an image, and the inputting the solution limit credential information into a pre-trained credential identification model, determining whether the solution limit credential information is valid, includes:

inputting the unlimited voucher information into a pre-trained voucher identification model, and judging whether the image is matched with pre-stored reference voucher information or not through the voucher identification model;

if so, extracting image information from the image, judging whether the image has preset risk or not based on the extracted image information, and if not, determining that the solution limit credential information is valid.

In this embodiment of the present disclosure, the processing, for different types of data included in the solution limit data, by using preset data processing rules, to obtain corresponding solution limit auxiliary information includes:

and acquiring historical threshold limit data with the similarity between the threshold limit data and the threshold limit data being larger than a first preset similarity threshold value from a threshold limit database, and taking the acquired historical threshold limit data as the threshold limit auxiliary information.

In this embodiment of the present disclosure, the solution limit data includes voiceprint data input by a user, and the processing, for different types of data included in the solution limit data, is performed by using preset data processing rules, to obtain corresponding solution limit auxiliary information, where the processing includes:

Acquiring historical voiceprint data with similarity between the historical voiceprint data and voiceprint data input by a user being greater than a second preset similarity threshold value from the historical voiceprint data input by the user;

and taking the acquired historical voiceprint data and user information corresponding to the acquired historical voiceprint data as solution limit auxiliary information.

In this embodiment of the present specification, further includes:

acquiring behavior data generated by a user corresponding to the target account within a preset time period after the account unlimited request is provided;

and inputting the behavior data and the threshold data into a pre-trained second multi-mode threshold model to obtain an output result of whether the target account has preset risk, wherein the second multi-mode threshold model is obtained by model training based on third historical data serving as structured data and fourth historical data serving as unstructured data and historical behavior data of a user.

The embodiment of the specification provides data processing equipment, which is used for acquiring the threshold data for threshold target accounts by receiving an account threshold request for the target accounts, determining whether the target accounts are in an account white list or in an account black list based on the threshold data, if the target accounts are determined to be in the account black list, refusing to carry out threshold processing on the target accounts, if the target accounts are determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to carry out threshold processing on the target accounts, if the target accounts are determined to be in the account white list or the account black list based on the threshold data, respectively carrying out processing on different types of data contained in the threshold data through preset data processing rules so as to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering threshold auxiliary information to carry out threshold processing on the target accounts, so that based on the atomic algorithm capability, the threshold auxiliary threshold of the threshold auxiliary information can be correspondingly provided, the threshold auxiliary threshold of the threshold data can be automatically examined and audited, the threshold auxiliary threshold of the threshold auxiliary information can not only be greatly improved, and the threshold of threshold auxiliary threshold information can be clearly examined and clearly, and the threshold auxiliary threshold information can be clearly used for carrying out threshold data, and the threshold auxiliary threshold information can be clearly and clearly read and clearly.

Example six

Further, based on the method shown in fig. 1A to 3, one or more embodiments of the present disclosure further provide a storage medium, which is used to store computer executable instruction information, and in a specific embodiment, the storage medium may be a U disc, an optical disc, a hard disk, etc., where the computer executable instruction information stored in the storage medium can implement the following flow when executed by a processor:

receiving an account opening request for a target account;

In this embodiment of the present specification, further includes:

The embodiment of the specification provides a storage medium, which is used for acquiring the threshold data for threshold target accounts by receiving an account threshold request for the target accounts, determining whether the target accounts are in an account white list or in an account black list based on the threshold data, if the target accounts are determined to be in the account black list, refusing to perform threshold processing on the target accounts, if the target accounts are determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to perform threshold processing on the target accounts, if the target accounts are determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data respectively through preset data processing rules so as to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering threshold auxiliary information to perform threshold processing on the target accounts, so that different algorithm capacities are correspondingly provided based on the atomic algorithm capacities, the threshold auxiliary threshold of automatic examination and interpretation, the threshold auxiliary examination and the threshold are not only greatly improved, but also the threshold data are not required to be subjected to the threshold information, and the threshold information are also subjected to the threshold information of threshold de-multiplexing, and the threshold information is not required to be repeatedly read in a plurality of the context.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (FieldProgrammable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (AdvancedBoolean 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 HardwareDescription Language), etc., VHDL (Very-High-SpeedIntegrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, 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 (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmelAT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, 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.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing one or more embodiments of the present description.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present description are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable fraud case serial-to-parallel device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable fraud case serial-to-parallel device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash memory (flashRAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

One or more embodiments of the present specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the present description may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present description.

Claims

1. A method of data processing, the method comprising:

receiving an account opening request for a target account;

if the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information;

the processing is performed on different types of data contained in the solution limit data through preset data processing rules to obtain corresponding solution limit auxiliary information, including:

2. The method of claim 1, the threshold data comprising structured data and/or unstructured data, the determining whether the target account is in an account whitelist or in an account blacklist based on the threshold data comprising:

3. The method of claim 1, the threshold data comprising user-entered voiceprint data, the determining whether the target account is in an account whitelist or in an account blacklist based on the threshold data comprising:

4. The method of claim 1, wherein the solution limit data includes historical transaction data for the target account, and the processing is performed on different types of data included in the solution limit data through preset data processing rules to obtain corresponding solution limit auxiliary information, including:

5. The method of claim 1, wherein if the target account is determined to be in the account whitelist, acquiring and executing a first threshold rule corresponding to the account whitelist to threshold the target account, comprising:

6. The method of claim 5, the solution credential information being an image, the inputting the solution credential information into a pre-trained credential recognition model, determining whether the solution credential information is valid, comprising:

7. The method of claim 1, wherein the solution limit data includes voiceprint data input by a user, and the processing is performed on different types of data included in the solution limit data by a preset data processing rule to obtain corresponding solution limit auxiliary information, including:

8. The method of claim 1, the method further comprising:

9. The method according to any one of claims 1-8, wherein the account unlimited request is a request received after determining that the target account is an account with a preset risk after risk detection of transaction data of different users in a preset risk detection period when the preset risk detection period is reached and performing a limited process on the target account, or the account unlimited request is a request received after performing a specified transaction on the target account and performing a limited process on the target account when the specified transaction is detected to have the preset risk.

10. A data processing system, the system comprising an atomic capability subsystem, an algorithm architecture subsystem, and an application subsystem, wherein:

the atomic capability subsystem is configured to provide corresponding algorithm support for the algorithm architecture subsystem and the application subsystem;

the application subsystem is configured to receive an account limitation-removing request for a target account, obtain limitation-removing data for limiting the target account, and call the algorithm subsystem to perform limitation-removing processing based on the limitation-removing data;

the algorithm architecture subsystem is configured to invoke an algorithm in the atomic capability subsystem to perform the following: determining whether the target account is in an account white list or in an account black list based on the threshold data, if the target account is determined to be in the account black list, refusing to perform threshold processing on the target account, and if the target account is determined to be in the account white list, acquiring and executing a first threshold rule corresponding to the account white list so as to perform threshold processing on the target account; if the target account cannot be determined to be in the account white list or the account black list based on the threshold data, processing different types of data contained in the threshold data through preset data processing rules respectively to obtain corresponding threshold auxiliary information, wherein the threshold auxiliary information is used for triggering a threshold manager to perform threshold processing on the target account based on the threshold auxiliary information.

11. The system of claim 10, wherein the atomic capability subsystem is provided with one or more of a first multi-modal solution limit model, a second multi-modal solution limit model, a credential identification model, a first solution limit rule corresponding to an account white list, a meta learning model, a transaction restoration algorithm, a data-to-text conversion algorithm, a retrieval algorithm for an image, a voiceprint identification algorithm, and a voiceprint clustering algorithm, wherein the first multi-modal solution limit model is obtained by model training based on first historical data serving as structured data and second historical data serving as unstructured data, and the second multi-modal solution limit model is obtained by model training based on third historical data serving as structured data and fourth historical data serving as unstructured data, and historical behavior data of a user.

12. The system of claim 10, the algorithmic hierarchy subsystem comprising a first, second, and third solution layers, wherein:

the first unlimited-examination layer is configured to determine whether the target account is in an account white list or in an account black list based on the unlimited-examination data, if the target account is determined to be in the account black list, the unlimited-examination processing is refused to be carried out on the target account, and if the target account is determined to be in the account white list, a first unlimited-examination rule corresponding to the account white list is acquired and executed, so that the unlimited-examination processing is carried out on the target account;

The second solution limit examination layer is configured to process different types of data contained in the solution limit data respectively through a preset data processing rule to obtain corresponding solution limit auxiliary information if the target account cannot be determined to be in an account white list or an account black list based on the solution limit data;

the third unlimited aesthetic layer is configured to perform unlimited processing on the target account by the following ways:

13. The system of claim 10, the application subsystem configured to receive an account de-limiting request for the target account when the target account performs a specified transaction and detects that the specified transaction has a preset risk, the specified transaction is rejected and the target account is subject to a limiting process; or when a preset risk detection period is reached, performing risk detection on transaction data of different users in the risk detection period, if the target account is determined to be the account with the preset risk, performing weight limiting processing on the target account, and receiving an account limitation releasing request aiming at the target account.

14. A data processing apparatus, the apparatus comprising:

the account opening request module receives an account opening request for a target account;

the first limitation removing module is used for obtaining limitation removing data for removing the limitation of the target account, determining whether the target account is in an account white list or in an account black list based on the limitation removing data, refusing to carry out limitation removing processing on the target account if the target account is determined to be in the account black list, and obtaining and executing a first limitation removing rule corresponding to the account white list if the target account is determined to be in the account white list so as to carry out limitation removing processing on the target account;

And the second limitation removing module is used for respectively processing different types of data contained in the limitation removing data through a preset data processing rule to obtain corresponding limitation removing auxiliary information if the target account cannot be determined to be in an account white list or an account black list based on the limitation removing data, wherein the limitation removing auxiliary information is used for triggering a limitation removing management party to carry out limitation removing processing on the target account based on the limitation removing auxiliary information.

15. A data processing apparatus, the data processing apparatus comprising:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

receiving an account opening request for a target account;

16. A storage medium for storing computer executable instructions that when executed by a processor implement the following:

receiving an account opening request for a target account;