CN113760939B

CN113760939B - Method, device and equipment for determining account type

Info

Publication number: CN113760939B
Application number: CN202010618196.6A
Authority: CN
Inventors: 杨丽
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2020-07-01
Filing date: 2020-07-01
Publication date: 2025-01-14
Anticipated expiration: 2040-07-01
Also published as: CN113760939A

Abstract

The embodiment of the invention provides a method, a device and equipment for determining the type of an account, which comprise the steps of obtaining historical behavior characteristics of a first account, obtaining the type of the first account according to the historical behavior characteristics, and determining the type of at least one second account related to the first account as the first type under the condition that the type of the first account is determined as the first type, so that the at least one second account is not required to be re-identified according to the identification mode of the first account, the identification efficiency is improved, and the calculation cost is reduced.

Description

Account type determining method, device and equipment

Technical Field

The embodiment of the invention relates to the technical field of Internet, in particular to a method, a device and equipment for determining account types.

Background

With the development of internet technology, more and more network platforms, such as an e-commerce platform, a social platform, a knowledge platform and the like, are appeared.

Typically, interactions between users and network platforms take the form of accounts. In some application scenarios, the network platform needs to perform classification management on the account number. For example, taking an e-commerce platform as an example, offers with different strengths are provided for accounts of different categories, or services with different levels are provided for accounts of different categories, and the like. Therefore, the network platform needs to identify the category to which the account belongs. In the prior art, a network platform identifies the category to which an account belongs according to the historical operation characteristics corresponding to the account.

In the process of realizing the invention, the inventor finds that at least the following problems exist in the prior art, namely, when the category to which the account number belongs is identified, the calculation cost is higher, and the identification efficiency is lower.

Disclosure of Invention

The embodiment of the invention provides a method, a device and equipment for determining an account type, which are used for reducing the calculation cost and improving the recognition efficiency of the account type.

In a first aspect, an embodiment of the present invention provides a method for determining an account type, including:

Acquiring historical behavior characteristics of a first account;

Acquiring the type of the first account according to the historical behavior characteristics;

when the type of the first account is a first type, acquiring at least one second account associated with the first account;

And determining the type of the at least one second account to be the first type.

In a possible implementation manner, obtaining at least one second account associated with the first account includes:

Inquiring an account relation database according to the first account, and acquiring a first user identifier with an association relation with the first account, wherein the account relation database is used for storing the association relation between the user identifier and the account;

and taking other accounts except the first account, which have an association relation with the first user identification, in the account relation database as the at least one second account.

In a possible implementation manner, the account relation database is further used for storing an accuracy coefficient corresponding to the association relation between the user identifier and the account;

and taking other accounts except the first account, which have an association relation with the first user identifier, in the account relation database as the at least one second account, wherein the account comprises:

And taking other accounts except the first account, which have a first association relation with the first user identification in the account relation database, as the at least one second account, wherein the accuracy coefficient corresponding to the first association relation is larger than a preset threshold.

In a possible implementation manner, before the first user identifier having an association relationship with the first account is obtained by querying an account relationship database according to the first account, the method further includes:

acquiring a plurality of sampling account numbers, and respectively acquiring key features and auxiliary features of the sampling account numbers;

performing association processing on the plurality of sampling accounts according to key features and auxiliary features of the plurality of sampling accounts, and determining user identifications associated with the plurality of sampling accounts respectively;

and generating the account relation database according to the user identifications associated with the sampling accounts.

In a possible implementation manner, acquiring key features and auxiliary features of the sampling account includes:

acquiring a plurality of sampling features of the sampling account, wherein each sampling feature corresponds to a priority;

taking the sampling feature with the highest corresponding priority among the sampling features as the key feature of the sampling account;

and taking the sampling features except the key features in the plurality of sampling features as auxiliary features of the sampling account.

In a possible implementation manner, according to key features and auxiliary features of the plurality of sampling accounts, performing association processing on the plurality of sampling accounts to determine user identifiers associated with the plurality of sampling accounts, where the method includes:

Dividing the plurality of sampling accounts into N groups according to priorities corresponding to key features of the plurality of sampling accounts, wherein the priorities corresponding to the key features of the sampling accounts in the nth group are nth priorities, and N is a natural number smaller than or equal to N;

For each first sampling account in the 1 st group, determining a user identifier associated with the first sampling account according to key features of the first sampling account;

And aiming at each first sampling account in the i-th group, determining a user identifier associated with the first sampling account according to a matching result of key features of the first sampling account and auxiliary features of the sampling accounts in the previous i-1 group, wherein i sequentially takes 2,3, and N.

In a possible implementation manner, determining the user identifier associated with the first sampling account according to a matching result of the key feature of the first sampling account and the auxiliary feature of the sampling account in the previous i-1 group includes:

According to the sequence from k to i-1, sequentially matching the key features of the first sampling account with the auxiliary features of the sampling accounts in the k group until the matching is successful or until the matching is finished;

If the matching is successful, determining the user identification associated with the sampling account number successfully matched in the kth group as the user identification associated with the first sampling account number;

and if the matching is finished, determining the user identification associated with the first sampling account according to the key characteristics of the first sampling account.

In a possible implementation manner, after determining the user identities associated with the plurality of sampling accounts, the method further includes:

determining an accurate coefficient of the association relationship between the sampling account and the associated user identifier according to the key characteristics of the sampling account;

Generating the account relation database according to the user identifications associated with the plurality of sampling accounts, wherein the generating comprises the following steps:

and generating the account relation database according to the user identifications respectively associated with the plurality of sampling accounts and the accuracy coefficient.

In a second aspect, an embodiment of the present invention provides an account type determining apparatus, including:

The acquisition module is used for acquiring historical behavior characteristics of the first account;

The first determining module is used for acquiring the type of the first account according to the historical behavior characteristics;

And the second determining module is used for acquiring at least one second account related to the first account when the type of the first account is a first type, and determining that the type of the at least one second account is the first type.

In a possible implementation manner, the second determining module is specifically configured to:

In a possible implementation manner, the account relation database is further configured to store an accuracy coefficient corresponding to an association relation between the user identifier and the account, and the second determining module is specifically configured to:

In a possible implementation manner, the device further comprises a generating module, wherein the generating module is used for:

In a possible implementation manner, the generating module is specifically configured to:

In a possible implementation manner, the generating module is further configured to:

The generation module is specifically configured to generate the account relationship database according to the user identifiers associated with the plurality of sampling accounts and the accuracy coefficients.

In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor;

The memory is for storing computer-executable instructions that are executed by the processor to implement the method of any of the first aspects.

In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having stored therein computer-executable instructions for performing the method according to any of the first aspects when executed by a processor.

The method, the device and the equipment for determining the account types, which are provided by the embodiment of the invention, comprise the steps of obtaining the historical behavior characteristics of the first account, obtaining the type of the first account according to the historical behavior characteristics, and determining the type of at least one second account associated with the first account as the first type under the condition that the type of the first account is determined as the first type, so that the at least one second account is not required to be re-identified according to the identification mode of the first account, the identification efficiency is improved, and the calculation cost is reduced.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 is a schematic diagram of one possible system architecture to which embodiments of the present invention may be applied;

Fig. 2 is a flowchart of a method for determining an account type according to an embodiment of the present invention;

Fig. 3 is a flowchart illustrating a method for generating an account relational database according to another embodiment of the present invention;

FIG. 4 is a schematic diagram of key features and auxiliary features provided in an embodiment of the present invention;

fig. 5 is a schematic diagram of a sample account association processing procedure provided in an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an account type determining device according to an embodiment of the present invention;

Fig. 7 is a schematic structural diagram of an account type determining device according to another embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Specific embodiments of the present invention have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.

The embodiment of the invention is suitable for the field of Internet. With the development of internet technology, more and more network platforms, such as an e-commerce platform, a social platform, a knowledge platform and the like, are appeared.

A possible system architecture of an embodiment of the present invention is described below with reference to fig. 1. Fig. 1 is a schematic diagram of one possible system architecture to which embodiments of the present invention are applicable. As shown in fig. 1, system architecture 1000 may include terminal devices 1001, 1002, 1003, a network 1004, and a server 1005. The network 1004 is a medium for providing a communication link between the terminal apparatuses 1001, 1002, 1003 and the server 1005. The network 1004 may include various connection types such as wired communication links, wireless communication links, or fiber optic cables, among others.

A user can interact with the server 1005 via the network 1004 using the terminal apparatuses 1001, 1002, 1003 to receive or transmit information or the like. The terminal apparatuses 1001, 1002, 1003 can have clients of various network platforms installed thereon. The terminal devices 1001, 1002, 1003 may be various electronic devices having a display screen and which can receive/transmit information, including but not limited to computers, smartphones, notebook computers, tablet computers, smart wearable devices, etc.

The server 1005 may be a service end corresponding to a network platform, and is configured to provide various services to a terminal device. For example, the server may receive service requests transmitted from the terminal devices 1001, 1002, 1003, process the service requests, and transmit the processing results to the terminal devices. The server 1005 may also actively push information to the terminal devices 1001, 1002, 1003. In some embodiments, the server 1005 may be a cloud server. The server 1005 may also be a distributed server, a clustered server, or the like.

In practical application, a user can access the network platform through the terminal equipment. The interaction between the user and the network platform takes the form of an account number. That is, the user registers an account number in the network platform, or the network platform assigns an account number to the user, and the user logs in to the network platform through the account number to interact with the network platform. And the network platform manages the user by using the account number. Generally, the management of the user by the network platform is actually the management of the account number.

In some application scenarios, the network platform needs to perform classification management on the account number. For example, taking an e-commerce platform as an example, the e-commerce platform can provide offers with different strengths for accounts of different categories, or provide different levels of services for accounts of different categories, and so on. Therefore, the network platform needs to identify the category to which the account belongs.

In the prior art, when the network platform identifies the category to which the account belongs, an identification method is generally adopted, wherein the category to which the account belongs is identified according to the historical operation characteristics corresponding to the account. However, in the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art, that in practical application, the same user may correspond to a plurality of accounts in a network platform. Because the multiple accounts correspond to the same user, the categories to which the multiple accounts belong are generally the same in some application scenarios. In the prior art, when the category to which the account belongs is identified, the account is taken as granularity, each account needs to be identified respectively, and the problems of high calculation cost and low identification efficiency exist.

The method for determining the account type provided by the embodiment of the invention aims to solve the technical problems in the prior art.

The following describes the technical scheme of the present invention and how the technical scheme of the present invention solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Fig. 2 is a flowchart of a method for determining an account type according to an embodiment of the present invention. As shown in fig. 2, the method of the present embodiment may include:

s201, acquiring historical behavior characteristics of the first account.

S202, acquiring the type of the first account according to the historical behavior characteristics.

It should be noted that, the execution body of the embodiment may be a server and/or a terminal device. In some embodiments, the method of the present embodiment may be performed by a server. In other embodiments, the method of this embodiment may also be performed by the terminal device when the terminal device has a certain data processing capability. In still other embodiments, the method of this embodiment may also be performed by the server and the terminal device in cooperation. Illustratively, a part of the steps, such as S201 and S202, are performed by the terminal device, and the remaining steps, such as S203 and S204, are performed by the server.

The first account is an account currently to be subjected to type identification. In some embodiments, the type identification of the first account is triggered when it is detected that the user performs certain operations (e.g., a billing operation, a coupon operation, a login operation, an after-market application operation, etc.) through the first account. In other embodiments, the type identification of the first account may be triggered by other triggering conditions. This embodiment is not limited thereto.

It should be understood that the present embodiment is not limited to the dividing manner of the account types. Different division modes can be adopted according to different application scenes. The type of the first account is illustrated below by taking two possible application scenarios in the e-commerce field as an example.

For example, in a promotional offer in the e-commerce domain, the e-commerce platform may wish to have the offer enjoyed by active users, but not inactive users. Thus, the account number may be divided into a valid account number and a invalid account number in this scenario.

As another example, in an after-market service scenario in the e-commerce domain, an e-commerce platform may provide a number of different levels of service, desirably different levels of service for different levels of users. Thus, the account numbers may be divided into different levels in the scene, each level corresponding to a type.

In this embodiment, the historical behavior feature of the first account may be obtained, and the type of the first account may be obtained by using the historical behavior feature of the first account. The historical behavior characteristics of the first account are characteristics obtained according to historical operations performed by the user on the network platform through the first account.

Specifically, the historical operation of the first account on the network platform can be collected, and the historical operation is subjected to feature extraction to obtain the historical behavior feature.

It can be appreciated that when different types of partitioning are employed, the required historical behavior characteristics may also be different, and accordingly, the historical operations that need to be collected may also be different. Therefore, the present embodiment is not limited to the specific content of the history behavior feature.

By way of example, taking an account type including a valid account and a invalid account as an example, the process of determining the type of the first account may include collecting a history operation of the first account on the network platform, where the history operation includes, but is not limited to, an order-making operation, a coupon-taking operation, an operation of participating in a preferential activity, and the like. And extracting the historical behavior characteristics of the first account according to the historical operation, such as whether the first account has frequent ordering behavior, whether the first account has ordering unpaid behavior, whether the first account has coupon non-use behavior, and the like. And further, according to the historical behavior characteristics, determining that the first account is a valid account or an invalid account.

In a possible implementation manner, S202 may specifically include inputting the historical behavior feature into a recognition model, and determining the type of the first account according to an output result of the recognition model. The recognition model can be a machine learning model based on deep learning which is trained in advance. The structure of the recognition model and the training process are not limited in this embodiment. It should be understood that when different account type divisions are employed, their corresponding identification models may also be different.

And S203, when the type of the first account is the first type, acquiring at least one second account associated with the first account.

S204, determining the type of the at least one second account as the first type.

In this embodiment, after the type of the first account is identified, the type of at least one second account associated with the first account is further identified. That is, when the type of the first account is the first type, at least one second account associated with the first account is acquired, and the type of the at least one second account is determined to be the first type.

The first type may be any one of account types. It should be appreciated that since account type partitioning is generally application scenario dependent, the first type is also application scenario dependent. The present embodiment is not limited to the first type either.

For example, when some type of division is used, the account is divided into a valid account and a invalid account, and the first type may be a valid account or a invalid account. For another example, when a certain type of division is used, the accounts are divided into a high-level account, a medium-level account and a low-level account, and the first type may be a high-level account, a medium-level account or a low-level account.

In this embodiment, the second account refers to an account having an association relationship with the first account. The second account and the first account can have an association relationship in various ways. For example, the second account may be an account having the same attribute information as the first account (e.g., the second account and the mobile phone number to which the first account is bound are the same). For another example, the second account may be an account having a binding relationship with the first account. For another example, the second account number and the first account number may be the same user account number.

The method for determining the account types comprises the steps of obtaining historical behavior characteristics of a first account, obtaining the type of the first account according to the historical behavior characteristics, and determining the type of at least one second account associated with the first account as the first type under the condition that the type of the first account is determined to be the first type, so that the at least one second account is not required to be re-identified according to the steps of S201 and S202, identification efficiency is improved, and calculation cost is reduced.

Based on the embodiment shown in fig. 2, in a possible implementation manner, the user identifier associated with the at least one second account is the same as the user identifier associated with the first account. Wherein, the user identification refers to natural person identification. That is, the first account and the second account are accounts of the same natural person user. Alternatively, the first account number and the second account number are associated with the same natural person user identification.

Specifically, the account relation database may be queried according to the first account, and at least one second account associated with the first account is obtained. The account relation database is used for storing the association relation between the user identification and the account. The first account and the first user identification have an association relationship in an account relationship database, and the at least one second account is other accounts which have association relationship with the first user identification in the account relationship database.

It should be understood that the account relation database in this embodiment may be obtained by counting account relations in advance. It should be noted that, the generation manner of the account number relation database is not limited in this embodiment, and one possible implementation may be referred to the detailed description of the following embodiments.

By way of example, one possible account number relationship database is shown in table 1. Referring to table 1, in the account relationship database, account 1, account 2 and account 3 are associated to user identification a, i.e. accounts 1-3 are all accounts of user a. Account number 4 and account number 5 are associated to user identification B, i.e. account numbers 4-5 are both account numbers of user B. The account numbers 6, 7, 8, 9 are associated to the user identification C, i.e. the account numbers 6-9 are all account numbers of the user C.

On the basis of the account relation database shown in table 1, at least one second account related to a first account can be obtained in a feasible manner that a first user identification with an association relation with the first account is obtained according to the first account inquiry account relation database, and other accounts except the first account with the association relation with the first user identification in the account relation database are used as the at least one second account.

TABLE 1

User identification	Account number associated with user identification
		User identification A	Account number 1, account number 2, account number 3
User identification B	Account number 4, account number 5
		User identification C	Account number 6, account number 7, account number 8, account number 9
...	...

By way of example with reference to table 1, assuming that the first account is account 1, the determined second account includes account 2 and account 3. Assuming that the first account number is account number 5, the determined second account number includes account number 4. And assuming that the first account number is an account number 8, the determined second account number comprises an account number 6, an account number 7 and an account number 9.

In this embodiment, since at least one second account pulled from the account relationship database is an account related to the same natural person identifier with the first account, when the type of the first account is determined to be the first type, the types of other accounts related to the same natural person identifier can be determined to be the first type, thereby improving the recognition efficiency and reducing the calculation cost.

By way of example, another possible account number relationship database is shown in table 2. The account relation database is also used for storing accurate coefficients corresponding to the association relation between the user identification and the account on the basis of the account relation database shown in the table 1. The accuracy coefficient indicates the accuracy degree of the association relationship between the user identifier and the account.

TABLE 2

Referring to table 2, in the account relation database, the accuracy coefficient corresponding to the association relation between the account 1 and the user identifier a is 100%, the accuracy coefficient corresponding to the association relation between the account 2 and the user identifier a is 90%, the accuracy coefficient corresponding to the association relation between the account 3 and the user identifier a is 80%, the accuracy coefficient corresponding to the association relation between the account 4 and the user identifier B is 95%, the accuracy coefficient corresponding to the association relation between the account 5 and the user identifier B is 70%, and so on.

Based on the account relation database shown in table 2, at least one second account related to the first account can be obtained in a feasible manner that a first user identifier with an association relation with the first account is obtained according to the first account query account relation database, other accounts except the first account with the first association relation with the first user identifier in the account relation database are used as the at least one second account, and the accuracy coefficient corresponding to the first association relation is larger than a preset threshold.

That is, when at least one second account associated with the first account is acquired, the accuracy coefficient in table 2 is also considered, so that the accuracy coefficient corresponding to the association relationship between the determined second account and the user identifier associated with the second account is ensured to be greater than a preset threshold. It should be understood that the value of the preset threshold is not limited in this embodiment. The preset threshold may be determined according to an actual application scenario.

For example, in combination with table 2, assuming that the threshold is preset to be 81%, if the first account is account 1, the determined second account includes account 2. Assuming that the first account number is account number 5, the determined second account number includes account number 4. Assuming that the first account number is an account number 8, the determined second account number comprises an account number 6 and an account number 7.

In this embodiment, by recording the accuracy coefficients in the account relationship database, different second accounts can be pulled out from the account relationship database according to different application scenarios, so as to meet the service requirements of different application scenarios, and make the application more flexible.

The above embodiment describes a process of acquiring at least one second account associated with a first account using an account relationship database, and the generation process of the account relationship database is described below in connection with the embodiment shown in fig. 3.

Fig. 3 is a flowchart illustrating a method for generating an account relational database according to another embodiment of the present invention. As shown in fig. 3, the method of the present embodiment may include:

s301, acquiring a plurality of sampling account numbers, and respectively acquiring key features and auxiliary features of the sampling account numbers.

The sampling account may be any account registered in the network platform, for example. And extracting the characteristics of each sampling account, so that the key characteristics and auxiliary characteristics of the sampling account can be obtained. Specifically, feature extraction can be performed on each sampling account to obtain a plurality of sampling features, and then key features and auxiliary features of the sampling account are determined from the plurality of sampling features.

It will be appreciated that the sampling characteristics of its acquisition may be different for different application scenarios. Taking an e-commerce platform as an example, the sampling feature of each account number can include, but is not limited to, registration mobile phone number information, identity card number information, binding mobile phone number information, historical mobile phone number information, receiving mobile phone number information, ordering address information, login IP information, login equipment information, common equipment information, real-name authentication mobile phone number information, fingerprint information, voiceprint information, facial feature information and the like.

Optionally, after the sampling feature is collected, the sampling feature may be further screened to obtain a screened sampling feature. For example, the sampling features may be filtered according to factors such as current application scenario, coverage user range, technology maturity, etc. The key features and the assist features may be subsequently determined from the screened sampled features.

The key feature refers to a sampling feature with highest credibility among a plurality of sampling features. In other words, the key feature is the sampling feature that is most capable of characterizing the user identity information. The auxiliary feature refers to other sampling features than the key feature in the plurality of sampling features of the sampling account. The reliability of the auxiliary features is lower than that of the key features, or the identification degree of the auxiliary features to the user identity information is lower.

It should be understood that the key features and the auxiliary features are relative concepts. Since the sampling features that can be acquired for different sampling accounts may be different, the key features corresponding to the two different sampling accounts may be different, and the auxiliary features corresponding to the two different sampling accounts may be different. For example, for the sampling account number 1, the corresponding key feature may be identification card number information, and the auxiliary feature may include registration mobile phone number information and binding mobile phone number information. For the sampling account number 2, the corresponding key feature may be binding mobile phone number information, and the auxiliary feature may include registering mobile phone number information.

In one possible implementation, the key features and auxiliary features of the sampling account may be acquired in a feasible manner by acquiring a plurality of sampling features of the sampling account, where each sampling feature corresponds to a priority. Taking the sampling feature with the highest corresponding priority among the sampling features as the key feature of the sampling account; and taking the sampling features except the key features in the plurality of sampling features as auxiliary features of the sampling account.

Wherein the priority may be used to indicate a degree of confidence of the sampled feature, the higher the degree of confidence, the higher the priority, and the lower the degree of confidence, the lower the priority. Alternatively, the priority may be used to indicate the identity of the sampled feature to the user identity information, with higher priority and lower priority for higher identity. It should be appreciated that the priority to which the sampling feature corresponds may be determined in advance based on a large amount of statistical information.

For example, three sampling features, namely, identification card information, binding mobile phone number information and registration mobile phone number information are taken as examples, and the identification card information has the highest reliability degree or the identification card information has the highest identification degree on the user identification information, so that the priority of the identification card information is the highest. Similarly, the credibility of the binding mobile phone number information is higher than that of the registration mobile phone number information, or the identification degree of the binding mobile phone number information to the user identity information is higher than that of the registration mobile phone number information, so that the priority of the binding mobile phone number information is higher than that of the registration mobile phone number information. The priority order of the three sampling features is that the priority is 1, the priority is 2, the priority is binding the mobile phone number information, and the priority is 3, the mobile phone number information is registered.

In connection with the above priority example, fig. 4 is a schematic diagram of key features and auxiliary features provided in an embodiment of the present invention. As shown in fig. 4, assuming that the sampling account number 1 includes 3 sampling features, namely, identification card information (priority 1), binding mobile phone number information (priority 2) and registration mobile phone number information (priority 3), the key features corresponding to the sampling account number 1 are identification card information, and the auxiliary features include binding mobile phone number information and registration mobile phone number information. With continued reference to fig. 4, assuming that the sampling account 2 includes 2 sampling features, namely binding mobile phone number information (priority 2) and registering mobile phone number information (priority 3), the key features corresponding to the sampling account 2 are binding mobile phone number information, and the auxiliary features include registering mobile phone number information.

S302, carrying out association processing on the plurality of sampling accounts according to key features and auxiliary features of the plurality of sampling accounts, and determining user identifications associated with the plurality of sampling accounts respectively.

In this embodiment, performing association processing on multiple sampling accounts refers to performing feature association/matching on different sampling accounts, so as to achieve association of different sampling accounts to the same user identifier. The user identifier may also be referred to as a natural person identifier, that is, through the association process, it may be identified which sampling account numbers belong to the same natural person user.

In one possible implementation, the association processing may be performed on a plurality of sampling accounts in the following possible manners:

(1) Dividing the plurality of sampling accounts into N groups according to priorities corresponding to key features of the plurality of sampling accounts, wherein the priorities corresponding to the key features of the sampling accounts in the nth group are nth priorities, and N is a natural number smaller than or equal to N. Priority 1 is the highest priority.

For example, it is assumed that in a certain application scenario, only three sampling features of identification card number information (priority 1), binding mobile phone number information (priority 2), and registration mobile phone number information (priority 3) are considered. When a plurality of sampling accounts are grouped, the sampling accounts can be divided into 3 groups, the key characteristics of the sampling accounts in the 1 st group are identification card number information, the key characteristics of the sampling accounts in the 2 nd group are binding mobile phone number information, and the key characteristics of the sampling accounts in the 3 rd group are registration mobile phone number information.

(2) And aiming at each first sampling account in the 1 st group, determining the user identification associated with the first sampling account according to the key characteristics of the first sampling account.

In combination with the above example, since the key feature of the sample account number in the 1 st group is identification card number information, and the priority of the identification card number information is highest, for each first sample account number in the 1 st group, the identification card number information of the first sample account number may be directly used as the user identifier associated with the first sample account number, or the result obtained by encoding the identification card number information of the first sample account number may be used as the user identifier associated with the first sample account number.

(3) And aiming at each first sampling account in the i-th group, determining a user identifier associated with the first sampling account according to a matching result of key features of the first sampling account and auxiliary features of the sampling accounts in the previous i-1 group, wherein i sequentially takes 2,3, and N.

That is, for the sampling account numbers in the 2-N groups, the user identification associated with the sampling account numbers can be determined by performing association matching on the key features of the sampling account numbers and the auxiliary features of the sampling account numbers with higher priority than the key features of the sampling account numbers. Alternatively, the following possible ways may be adopted:

and sequentially matching the key features of the first sampling account with the auxiliary features of the sampling accounts in the k group according to the sequence from 1 to i-1 until the matching is successful or until the matching is finished, determining the user identification associated with the sampling account in the k group as the user identification associated with the first sampling account if the matching is successful, and determining the user identification associated with the first sampling account according to the key features of the first sampling account if the matching is finished.

Taking the matching process of the first sampling account in the 3 rd group as an example, firstly matching the key features of the first sampling account with the auxiliary features of the sampling accounts in the 1 st group, if the matching is successful, using the user identifier associated with the sampling account successfully matched in the 1 st group as the user identifier associated with the first sampling account, if the matching is unsuccessful with the sampling accounts in the 1 st group, continuing to match the key features of the first sampling account with the auxiliary features of the sampling accounts in the 2 nd group, and if the matching is successful, using the user identifier associated with the sampling account successfully matched in the 2 nd group as the user identifier associated with the first sampling account. If the matching process is unsuccessful, determining the user identification associated with the first sampling account according to the key characteristics of the first sampling account. For example, the key features of the first sampling account are directly used as the associated user identifications, or the result of encoding the key features of the first sampling account is used as the associated user identifications.

The feature association matching process is illustrated below in conjunction with fig. 5. Fig. 5 is a schematic diagram of a sample account association processing procedure according to an embodiment of the present invention. Only two sampling account numbers are exemplified in fig. 5.

As shown in fig. 5, for the sampling account number 1, the key features are identification card number information, and the auxiliary features include binding mobile phone number information, registering mobile phone number information and the like. Since the priority of the key feature (id card number information) of the sampling account 1 is 1, that is, the highest priority, the user identifier (user identifier a) associated with the sampling account 1 is generated according to the key feature (id card number information) of the sampling account 1.

For the sampling account number 2, the key characteristic is binding mobile phone number information, and the auxiliary characteristic comprises registration mobile phone number information and the like. Because the priority of the key feature (the information of binding mobile phone number) of the sampling account 2 is 2, namely, the priority is not the highest priority, the key information (the information of binding mobile phone number) of the sampling account 2 is matched with the auxiliary information (the information of binding mobile phone number) of the sampling account 1.

If the matching is successful, the sampling account number 2 is also associated with the user identifier associated with the sampling account number 1, namely, the sampling account number 2 is associated with the user identifier A. In this case, it is considered that the sampling account number 1 and the sampling account number 2 are associated with the same user (user identification a). If the matching is unsuccessful, generating a user identifier (user identifier B) associated with the sampling account 2 according to the key characteristics (identity card number information) of the sampling account 2. In this case, it is considered that the sampling account number 1 and the sampling account number 2 are associated with different users.

S303, generating the account relation database according to the user identifications associated with the sampling accounts.

It can be appreciated that after determining the user identifier associated with each of the sample accounts, an account relationship database as shown in table 1 may be generated.

In a possible implementation manner, after determining the user identifier associated with each sampling account, an accurate coefficient of the association relationship between the sampling account and the user identifier associated with the sampling account may also be determined according to the key features of the sampling account. Furthermore, an account relation database can be generated according to the user identifications and the accuracy coefficients respectively associated with the sampling accounts. The account number relationship database generated in this embodiment is shown in table 2.

Optionally, when determining the accuracy coefficient, the accuracy coefficient may be determined according to a priority corresponding to the key feature of the sampling account. If the priority corresponding to the key features is higher, the accuracy coefficient is also higher. If the priority corresponding to the key feature is lower, the accuracy coefficient is lower.

For example, taking fig. 5 as an example, since the priority of the key features of the sampling account 1 is 1, that is, the priority is highest, the accuracy of the association relationship between the sampling account 1 and the user identifier a is also highest, and therefore, the accuracy coefficient of the association relationship between the sampling account 1 and the user identifier a may be set to 100%.

Again by way of example, still taking fig. 5 as an example, assume that sampling account number 2 is also associated with user identification a. Because the priority of the key features of the sampling account 2 is 2 and is lower than that of the key features of the sampling account 1, the accuracy coefficient of the association relationship between the sampling account 2 and the user identifier A is also lower than that between the sampling account 1 and the user identifier A. For example, the accuracy coefficient of the association relationship between the sampling account number 2 and the user flag a may be 90%.

By the method, an account relation database can be generated, and the association relation between the natural person user identification and the account is indicated in the account relation database. In the process of generating the account number relation database, the feature matching relation among different sampling accounts is considered, so that the accuracy of the account number relation database is ensured.

Further, under the condition that the type of the first account is determined to be the first type, the account relation database can be utilized to draw out a second account which is related to the same natural person user identifier with the first account, and the type of the second account is determined to be the first type, so that the identification efficiency can be improved, and the calculation cost can be reduced. In addition, by recording the accuracy coefficients in the account relation database, different second accounts can be pulled out of the account relation database according to different application scenes, so that the service requirements of different application scenes are met, and the application is more flexible.

Fig. 6 is a schematic structural diagram of an account type determining device according to an embodiment of the present invention. The apparatus of this embodiment may be in the form of software and/or hardware. As shown in fig. 6, the account type determining device 10 provided in this embodiment may include an obtaining module 11, a first determining module 12, and a second determining module 13. Wherein,

An obtaining module 11, configured to obtain a historical behavior feature of the first account;

A first determining module 12, configured to obtain a type of the first account according to the historical behavior feature;

the second determining module 13 is configured to obtain at least one second account associated with the first account when the type of the first account is a first type, and determine that the type of the at least one second account is the first type.

In a possible implementation manner, the second determining module 13 is specifically configured to:

In a possible implementation manner, the account relation database is further configured to store an accuracy coefficient corresponding to an association relation between the user identifier and the account, and the second determining module 13 is specifically configured to:

Fig. 7 is a schematic structural diagram of an account type determining device according to another embodiment of the present invention. As shown in fig. 7, the apparatus of this embodiment may further include a generating module 14 based on the embodiment shown in fig. 6. The generating module 14 is configured to:

In a possible implementation manner, the generating module 14 is specifically configured to:

In a possible implementation manner, the generating module 14 is further configured to:

The generating module 14 is specifically configured to generate the account relationship database according to the user identifiers associated with the plurality of sampling accounts and the accuracy coefficients.

The account type determining device provided in this embodiment may be used to execute the technical scheme in any of the above method embodiments, and its implementation principle and technical effect are similar, and will not be described herein.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 8, the electronic device 20 provided in this embodiment includes a processor 21 and a memory 22, where the memory 22 is configured to store a computer program, and the processor 21 is configured to execute the computer program stored in the memory, so as to implement the method for determining an account type in the foregoing embodiment. Reference may be made in particular to the relevant description of the embodiments of the method described above.

Alternatively, the memory 22 may be separate or integrated with the processor 21.

When the memory 22 is a device separate from the processor 21, the electronic device 20 may further comprise a bus 23 for connecting the memory 22 and the processor 21.

Optionally, the electronic device 20 may also include a communication component 24 for communicating with other devices.

The electronic device provided in this embodiment may be used to execute the technical solution in any of the above method embodiments, and its implementation principle and technical effects are similar, and this embodiment is not repeated here.

The embodiment of the invention also provides a computer readable storage medium, which comprises a computer program for realizing the technical scheme in any method embodiment.

The embodiment of the invention also provides a chip which comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the technical scheme in any method embodiment.

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each module may exist alone physically, or two or more modules may be integrated in one unit. The units formed by the modules can be realized in a form of hardware or a form of hardware and software functional units.

The integrated modules, which are implemented in the form of software functional modules, may be stored in a computer readable storage medium. The software functional module is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (english: processor) to perform some of the steps of the methods according to the embodiments of the invention.

It should be understood that the above Processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, a digital signal Processor (english: DIGITAL SIGNAL Processor, abbreviated as DSP), an Application-specific integrated Circuit (english: application SPECIFIC INTEGRATED Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.

The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile memory NVM, such as at least one magnetic disk memory, and may also be a U-disk, a removable hard disk, a read-only memory, a magnetic disk or optical disk, etc.

The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (PERIPHERAL COMPONENT, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present invention are not limited to only one bus or to one type of bus.

The storage medium may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an Application SPECIFIC INTEGRATED Circuits (ASIC). It is also possible that the processor and the storage medium reside as discrete components in an electronic device or a master device.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of implementing the various method embodiments described above may be implemented by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs the steps comprising the method embodiments described above, and the storage medium described above includes various media capable of storing program code, such as ROM, RAM, magnetic or optical disk.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

Claims

1. The method for determining the account type is characterized by comprising the following steps of:

Acquiring historical behavior characteristics of a first account;

Determining the type of the at least one second account as the first type;

obtaining at least one second account associated with the first account, including:

Taking other accounts except the first account, which have an association relation with the first user identification, in the account relation database as the at least one second account;

The account relation database is also used for storing an accurate coefficient corresponding to the association relation between the user identifier and the account;

Taking other accounts except the first account, which have a first association relationship with the first user identification in the account relationship database, as the at least one second account, wherein the accuracy coefficient corresponding to the first association relationship is larger than a preset threshold;

according to the first account, inquiring an account relation database, and before obtaining a first user identifier with an association relation with the first account, further comprising:

2. The method of claim 1, wherein obtaining key features and auxiliary features of the sampling account comprises:

3. The method of claim 2, wherein the performing association processing on the plurality of sampling accounts according to the key features and the auxiliary features of the plurality of sampling accounts, and determining the user identifications associated with the plurality of sampling accounts respectively, includes:

4. A method according to claim 3, wherein determining the user identification associated with the first sampling account according to the matching result of the key feature of the first sampling account and the auxiliary feature of the sampling account in the previous i-1 group comprises:

5. The method of claim 1, wherein after determining the user identities associated with each of the plurality of sampling account numbers, further comprising:

6. An account type determining apparatus, comprising:

the second determining module is used for acquiring at least one second account related to the first account when the type of the first account is a first type, and determining that the type of the at least one second account is the first type;

The second determining module is specifically configured to query an account relationship database according to the first account, obtain a first user identifier having an association relationship with the first account, and store an association relationship between the user identifier and the account, where the account relationship database is obtained by counting account relationships in advance;

the second determining module is specifically configured to use, as the at least one second account, other accounts in the account relationship database, except for the first account, that have a first association relationship with the first user identifier, where an accuracy coefficient corresponding to the first association relationship is greater than a preset threshold;

the system comprises a generation module, a correlation processing module and an account relation database, wherein the generation module is used for acquiring a plurality of sampling accounts, respectively acquiring key features and auxiliary features of the sampling accounts, performing correlation processing on the plurality of sampling accounts according to the key features and the auxiliary features of the plurality of sampling accounts to determine user identifications respectively correlated with the plurality of sampling accounts, and generating the account relation database according to the user identifications respectively correlated with the plurality of sampling accounts.

7. An electronic device is characterized by comprising a memory and a processor;

The memory is for storing computer-executable instructions that are executed by the processor to implement the method of any one of claims 1 to 5.

8. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 5.