Method, device and equipment for determining account type

Abstract

An embodiment of the present invention provides a method, apparatus and device for determining an account type. The method includes: obtaining historical behavior characteristics of a first account, obtaining the type of the first account based on the historical behavior characteristics, and when determining that the type of the first account is the first type, also determining the type of at least one second account associated with the first account as the first type. In this way, there is no need to re-identify the at least one second account according to the identification method of the first account, thereby improving identification efficiency and reducing computing costs.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of Internet technology, and in particular, to a method, device, and equipment for determining an account type. Background Art

[0002] With the development of Internet technology, more and more online platforms have emerged, such as e-commerce platforms, social platforms, knowledge platforms, etc.

[0003] Usually, the interaction between users and network platforms is in the form of accounts. In some application scenarios, network platforms need to classify and manage accounts. For example, taking e-commerce platforms as an example, different discounts are provided for different categories of accounts, or different levels of services are provided for different categories of accounts, etc. Therefore, the network platform needs to identify the category to which the account belongs. In the prior art, the network platform identifies the category to which the account belongs based on the historical operation characteristics corresponding to the account.

[0004] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art: when identifying the category to which an account belongs, the calculation cost is high and the identification efficiency is low. Summary of the invention

[0005] Embodiments of the present invention provide a method, apparatus and device for determining an account type, so as to reduce computing costs and improve the efficiency of identifying the account type.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining an account type, comprising:

[0007] Obtain the historical behavior characteristics of the first account;

[0008] According to the historical behavior characteristics, obtaining the type of the first account;

[0009] When the type of the first account is a first type, obtaining at least one second account associated with the first account;

[0010] Determine that the type of the at least one second account is the first type.

[0011] In a possible implementation, obtaining at least one second account associated with the first account includes:

[0012] querying an account relationship database according to the first account to obtain a first user identifier associated with the first account, wherein the account relationship database is used to store the association between the user identifier and the account;

[0013] Other accounts in the account relationship database that are associated with the first user identifier except the first account are used as the at least one second account.

[0014] In a possible implementation, the account relationship database is further used to store the accuracy coefficient corresponding to the association relationship between the user identifier and the account;

[0015] Using other accounts in the account relationship database that are associated with the first user identifier, except the first account, as the at least one second account includes:

[0016] Other accounts other than the first account in the account relationship database that have a first association relationship with the first user identifier are used as the at least one second account, and the accuracy coefficient corresponding to the first association relationship is greater than a preset threshold.

[0017] In a possible implementation, before querying an account relationship database according to the first account to obtain a first user identifier associated with the first account, the method further includes:

[0018] Acquire multiple sampling accounts, and respectively acquire key features and auxiliary features of the sampling accounts;

[0019] According to the key features and auxiliary features of the multiple sampling accounts, the multiple sampling accounts are associated with each other to determine the user identifiers associated with the multiple sampling accounts;

[0020] The account relationship database is generated according to the user identifiers associated with each of the plurality of sampling accounts.

[0021] In a possible implementation, obtaining the key features and auxiliary features of the sampled account includes:

[0022] Acquire multiple sampling features of the sampling account, each sampling feature corresponding to a priority;

[0023] Using the sampling feature with the highest corresponding priority among the multiple sampling features as the key feature of the sampling account;

[0024] The sampling features other than the key features among the multiple sampling features are used as auxiliary features of the sampling account.

[0025] In a possible implementation, the multiple sampling accounts are associated with each other according to the key features and auxiliary features of the multiple sampling accounts, and the user identifiers associated with each of the multiple sampling accounts are determined, including:

[0026] According to the priorities corresponding to the key features of the multiple sampling accounts, the multiple sampling accounts are divided into N groups, wherein the priority corresponding to the key features of the sampling accounts in the nth group is the nth priority, and n is a natural number less than or equal to N;

[0027] For each first sampling account in the first group, determine a user identifier associated with the first sampling account according to a key feature of the first sampling account;

[0028] For each first sampling account in the i-th group, the user identifier associated with the first sampling account is determined based on the matching results of the key features of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups, where i is 2, 3, ..., N in sequence.

[0029] In a possible implementation, determining the user identifier associated with the first sampling account according to the matching result of the key feature of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups includes:

[0030] In the order of k from 1 to i-1, the key features of the first sampled account are matched with the auxiliary features of the sampled accounts in the kth group in sequence until the match is successful, or until the match is completed;

[0031] If the match is successful, the user identifier associated with the successfully matched sampling account in the kth group is determined as the user identifier associated with the first sampling account;

[0032] If the matching is completed, the user identifier associated with the first sampling account is determined according to the key feature of the first sampling account.

[0033] In a possible implementation manner, after determining the user identifiers associated with each of the plurality of sampling accounts, the method further includes:

[0034] Determining, based on the key features of the sampled account, an accuracy coefficient of the association relationship between the sampled account and its associated user identifier;

[0035] Generating the account relationship database according to the user identifiers associated with each of the plurality of sampling accounts includes:

[0036] The account relationship database is generated according to the user identifiers associated with each of the plurality of sampling accounts and the accuracy coefficient.

[0037] In a second aspect, an embodiment of the present invention provides a device for determining an account type, including:

[0038] An acquisition module, used to acquire historical behavior characteristics of the first account;

[0039] A first determination module, configured to obtain the type of the first account according to the historical behavior characteristics;

[0040] The second determining module is configured to, when the type of the first account is the first type, obtain at least one second account associated with the first account, and determine that the type of the at least one second account is the first type.

[0041] In a possible implementation manner, the second determining module is specifically configured to:

[0042] querying an account relationship database according to the first account to obtain a first user identifier associated with the first account, wherein the account relationship database is used to store the association between the user identifier and the account;

[0043] Other accounts in the account relationship database that are associated with the first user identifier except the first account are used as the at least one second account.

[0044] In a possible implementation, the account relationship database is further used to store an accuracy coefficient corresponding to an association relationship between a user identifier and an account, and the second determination module is specifically used to:

[0045] Other accounts other than the first account in the account relationship database that have a first association relationship with the first user identifier are used as the at least one second account, and the accuracy coefficient corresponding to the first association relationship is greater than a preset threshold.

[0046] In a possible implementation, the device further includes: a generating module, wherein the generating module is configured to:

[0047] Acquire multiple sampling accounts, and respectively acquire key features and auxiliary features of the sampling accounts;

[0048] According to the key features and auxiliary features of the multiple sampling accounts, the multiple sampling accounts are associated with each other to determine the user identifiers associated with the multiple sampling accounts;

[0049] The account relationship database is generated according to the user identifiers associated with each of the plurality of sampling accounts.

[0050] In a possible implementation, the generating module is specifically used for:

[0051] Acquire multiple sampling features of the sampling account, each sampling feature corresponding to a priority;

[0052] Using the sampling feature with the highest corresponding priority among the multiple sampling features as the key feature of the sampling account;

[0053] The sampling features other than the key features among the multiple sampling features are used as auxiliary features of the sampling account.

[0054] In a possible implementation, the generating module is specifically used for:

[0055] According to the priorities corresponding to the key features of the multiple sampling accounts, the multiple sampling accounts are divided into N groups, wherein the priority corresponding to the key features of the sampling accounts in the nth group is the nth priority, and n is a natural number less than or equal to N;

[0056] For each first sampling account in the first group, determine a user identifier associated with the first sampling account according to a key feature of the first sampling account;

[0057] For each first sampling account in the i-th group, the user identifier associated with the first sampling account is determined based on the matching results of the key features of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups, where i is 2, 3, ..., N in sequence.

[0058] In a possible implementation, the generating module is specifically used for:

[0059] In the order of k from 1 to i-1, the key features of the first sampled account are matched with the auxiliary features of the sampled accounts in the kth group in sequence until the match is successful, or until the match is completed;

[0060] If the match is successful, the user identifier associated with the successfully matched sampling account in the kth group is determined as the user identifier associated with the first sampling account;

[0061] If the matching is completed, the user identifier associated with the first sampling account is determined according to the key feature of the first sampling account.

[0062] In a possible implementation, the generating module is further used for:

[0063] Determining, based on the key features of the sampled account, an accuracy coefficient of the association relationship between the sampled account and its associated user identifier;

[0064] The generating module is specifically used to generate the account relationship database according to the user identifiers associated with each of the multiple sampling accounts and the accuracy coefficient.

[0065] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor;

[0066] The memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions to implement the method as described in any one of the first aspects.

[0067] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.

[0068] The embodiments of the present invention provide a method, apparatus and device for determining an account type. The method includes: obtaining historical behavior characteristics of a first account, obtaining the type of the first account based on the historical behavior characteristics, and when determining that the type of the first account is the first type, also determining the type of at least one second account associated with the first account as the first type. In this way, there is no need to re-identify the at least one second account according to the identification method of the first account, thereby improving identification efficiency and reducing computing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] 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.

[0070] Figure 1 A schematic diagram of a possible system architecture applicable to an embodiment of the present invention;

[0071] Figure 2 A schematic diagram of a flow chart of a method for determining an account type provided by an embodiment of the present invention;

[0072] Figure 3 A schematic diagram of a flow chart of a method for generating an account relationship database provided by another embodiment of the present invention;

[0073] Figure 4 A schematic diagram of key features and auxiliary features provided in an embodiment of the present invention;

[0074] Figure 5 A schematic diagram of a sampling account association processing process provided by an embodiment of the present invention;

[0075] Figure 6 A schematic diagram of the structure of an apparatus for determining an account type provided by an embodiment of the present invention;

[0076] Figure 7 A schematic diagram of the structure of an apparatus for determining an account type provided by another embodiment of the present invention;

[0077] Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0078] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0079] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0080] The embodiments of the present invention are applicable to the Internet field. With the development of Internet technology, more and more network platforms have emerged, such as e-commerce platforms, social platforms, knowledge platforms, etc.

[0081] Combine the following Figure 1 A possible system architecture of an embodiment of the present invention is introduced. Figure 1 FIG. 1 is a schematic diagram of a possible system architecture applicable to an embodiment of the present invention. Figure 1 As shown, the system architecture 1000 may include terminal devices 1001, 1002, 1003, a network 1004, and a server 1005. The network 1004 is used to provide a medium for communication links between the terminal devices 1001, 1002, 1003 and the server 1005. The network 1004 may include various connection types, such as: a wired communication link, a wireless communication link, or an optical fiber cable, etc.

[0082] The user can use the terminal devices 1001, 1002, 1003 to interact with the server 1005 through the network 1004 to receive or send information, etc. The terminal devices 1001, 1002, 1003 can be installed with clients of various network platforms. The terminal devices 1001, 1002, 1003 can be various electronic devices with display screens that can receive / send information, including but not limited to: computers, smart phones, laptops, tablet computers, smart wearable devices, etc.

[0083] The server 1005 may be a server corresponding to the network platform, and is used to provide various services to the terminal devices. For example, the server may receive a service request sent by the terminal devices 1001, 1002, and 1003, process the service request, and send the processing result to the terminal device. The server 1005 may also actively push information to the terminal devices 1001, 1002, and 1003. In some embodiments, the server 1005 may be a cloud server. The server 1005 may also be a distributed server, a cluster server, etc.

[0084] In actual applications, users can access the network platform through terminal devices. The interaction between users and the network platform takes the form of accounts. That is, the user registers an account on the network platform, or the network platform assigns an account to the user, and the user logs in to the network platform through the account to interact with the network platform. The network platform uses the account to manage users. Generally speaking, the network platform's management of users is actually the management of accounts.

[0085] In some application scenarios, the network platform needs to classify and manage accounts. For example, taking an e-commerce platform as an example, the e-commerce platform can provide different discounts for different categories of accounts, or provide different levels of services for different categories of accounts, etc. Therefore, the network platform needs to identify the category to which the account belongs.

[0086] In the prior art, when a network platform identifies the category to which an account belongs, the identification method usually adopted is to identify the category to which the account belongs based on the historical operation characteristics corresponding to the account. However, in the process of implementing the present invention, the inventors found that the prior art has at least the following problems: In actual applications, the same user may have multiple accounts corresponding to the network platform. Since multiple accounts correspond to the same user, the categories to which multiple accounts belong are usually the same in some application scenarios. However, when the above-mentioned prior art identifies the category to which an account belongs, it uses the account as the granularity, and each account needs to be identified separately, which has the problems of high computational cost and low identification efficiency.

[0087] The method for determining the account type provided in the embodiment of the present invention is intended to solve the above technical problems in the prior art.

[0088] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0089] Figure 2A flowchart of a method for determining an account type provided by an embodiment of the present invention. Figure 2 As shown, the method of this embodiment may include:

[0090] S201: Obtain historical behavior characteristics of the first account.

[0091] S202: Obtain the type of the first account according to the historical behavior characteristics.

[0092] First of all, it should be noted that the execution subject of this embodiment can be a server and / or a terminal device. In some embodiments, the method of this embodiment can be executed by a server. In other implementations, when the terminal device has a certain data processing capability, the method of this embodiment can also be executed by the terminal device. In some other implementations, the method of this embodiment can also be executed by a server and a terminal device in cooperation. Exemplarily, a part of the steps, such as S201 and S202, is executed by the terminal device, and the remaining steps, such as S203 and S204, are executed by the server.

[0093] The first account is the account currently to be identified by type. In some implementations, when it is detected that the user performs certain operations (e.g., order placement, coupon collection, login, after-sales application, etc.) through the first account, the type identification of the first account is triggered. In other implementations, the type identification of the first account may also be triggered by other trigger conditions. This embodiment is not limited to this.

[0094] It should be understood that this embodiment does not limit the division method of account types. Different division methods can be adopted according to different application scenarios. The following uses two possible application scenarios in the e-commerce field as examples to illustrate the type of the first account.

[0095] For example, in the promotional activities in the e-commerce field, the e-commerce platform hopes that the promotional activities are enjoyed by valid users, but not by invalid users. Therefore, in this scenario, accounts can be divided into valid accounts and invalid accounts.

[0096] For another example, in the after-sales service scenario in the e-commerce field, the e-commerce platform may provide multiple different levels of services, hoping to provide different levels of services to users of different levels. Therefore, in this scenario, accounts can be divided into different levels, and each level corresponds to a type.

[0097] In this embodiment, the historical behavior characteristics of the first account can be obtained, and the type of the first account can be obtained by using the historical behavior characteristics of the first account. The historical behavior characteristics of the first account refer to the characteristics obtained based on the historical operations performed by the user through the first account on the network platform.

[0098] Specifically, historical operations of the first account on the network platform may be collected, and features of the historical operations may be extracted to obtain historical behavior features.

[0099] It is understandable that when different types of classification are used, the required historical behavior characteristics may also be different, and accordingly, the historical operations that need to be collected may also be different. Therefore, this embodiment does not limit the specific content of the historical behavior characteristics.

[0100] Exemplarily, taking the account types including valid accounts and invalid accounts as an example, the process of determining the type of the first account may include: collecting historical operations of the first account on the network platform, wherein the historical operations include but are not limited to: ordering operations, coupon collection operations, operations of participating in promotional activities, etc. According to the above historical operations, extract the historical behavior characteristics of the first account, for example: whether the first account has frequent ordering behaviors, whether there is ordering without payment behaviors, whether there is no use after receiving coupons, etc. Then, according to the historical behavior characteristics, determine whether the first account is a valid account or an invalid account.

[0101] In a possible implementation, S202 may specifically include: inputting the historical behavior features into a recognition model, and determining the type of the first account according to the output result of the recognition model. The recognition model may be a pre-trained machine learning model based on deep learning. This embodiment does not limit the structure of the recognition model and the training process. It should be understood that when different account type classification methods are used, the corresponding recognition models may also be different.

[0102] S203: When the type of the first account is the first type, obtain at least one second account associated with the first account.

[0103] S204: Determine that the type of the at least one second account is the first type.

[0104] 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 obtained, and it is determined that the type of the at least one second account is also the first type.

[0105] The first type may be any one of the account types. It should be understood that since the account type classification method is usually related to the application scenario, the first type is also related to the application scenario. This embodiment does not limit the first type.

[0106] For example, when a certain type classification method is adopted, the accounts are divided into valid accounts and invalid accounts, and the first type can be a valid account or an invalid account. For another example, when a certain type classification method is adopted, the accounts are divided into high-level accounts, intermediate accounts and low-level accounts, and the first type can be a high-level account, an intermediate account or a low-level account.

[0107] In this embodiment, the second account refers to an account associated with the first account. The second account and the first account may be associated in a variety of ways. For example, the second account may be an account with the same attribute information as the first account (such as the second account and the first account are bound to the same mobile phone number). For another example, the second account may be an account bound to the first account. For another example, the second account and the first account may be accounts of the same user.

[0108] The method for determining an account type provided in this embodiment includes: obtaining historical behavior characteristics of a first account, obtaining the type of the first account based on the historical behavior characteristics, and when determining that the type of the first account is the first type, also determining the type of at least one second account associated with the first account as the first type, thereby eliminating the need to re-identify the at least one second account according to steps S201 and S202, thereby improving identification efficiency and reducing computing costs.

[0109] exist Figure 2 Based on the illustrated embodiment, in a possible implementation, the user identifier associated with the at least one second account is the same as the user identifier associated with the first account. The user identifier refers to a natural person identifier. In other words, the first account and the second account are accounts of the same natural person user. In other words, the first account and the second account are associated with the same natural person user identifier.

[0110] Specifically, the account relationship database can be queried according to the first account to obtain at least one second account associated with the first account. The account relationship database is used to store the association relationship between the user identifier and the account. In the account relationship database, the first account has an association relationship with the first user identifier, and the at least one second account is another account in the account relationship database that has an association relationship with the first user identifier.

[0111] It should be understood that the account relationship database in this embodiment can be obtained by counting the account relationships in advance. It should be noted that this embodiment does not limit the generation method of the account relationship database. A possible implementation method can refer to the detailed description of the subsequent embodiments.

[0112] Exemplarily, a possible account 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 with user identifier A, that is, accounts 1-3 are all accounts of user A. Account 4 and account 5 are associated with user identifier B, that is, accounts 4-5 are all accounts of user B. Account 6, account 7, account 8, and account 9 are associated with user identifier C, that is, accounts 6-9 are all accounts of user C.

[0113] Based on the account relationship database shown in Table 1, at least one second account associated with the first account can be obtained in the following feasible manner: query the account relationship database according to the first account, obtain a first user identifier associated with the first account, and use other accounts in the account relationship database that are associated with the first user identifier except the first account as the at least one second account.

[0114] Table 1

[0115] User ID The account associated with the user ID User ID A Account 1, Account 2, Account 3 User ID B Account 4, Account 5 User ID C Account 6, Account 7, Account 8, Account 9 … …

[0116] Taking Table 1 as an example, assuming that the first account is account 1, the determined second accounts include: account 2 and account 3. Assuming that the first account is account 5, the determined second accounts include account 4. Assuming that the first account is account 8, the determined second accounts include: account 6, account 7, and account 9.

[0117] In this embodiment, since at least one second account pulled out from the account relationship database is an account associated with the same natural person identifier as the first account, when the type of the first account is determined to be the first type, the types of other accounts associated with the same natural person identifier can also be determined to be the first type, thereby improving recognition efficiency and reducing computing costs.

[0118] Exemplarily, another possible account relationship database is shown in Table 2. Based on the account relationship database shown in Table 1, the account relationship database is also used to store the accuracy coefficient corresponding to the association relationship between the user identifier and the account. The accuracy coefficient indicates the accuracy of the association relationship between the user identifier and the account.

[0119] Table 2

[0120]

[0121] Referring to Table 2, in the account relationship database, the accuracy coefficient corresponding to the association relationship between account 1 and user identification A is 100%, the accuracy coefficient corresponding to the association relationship between account 2 and user identification A is 90%, the accuracy coefficient corresponding to the association relationship between account 3 and user identification A is 80%, the accuracy coefficient corresponding to the association relationship between account 4 and user identification B is 95%, the accuracy coefficient corresponding to the association relationship between account 5 and user identification B is 70%, and so on.

[0122] Based on the account relationship database shown in Table 2, at least one second account associated with the first account can be obtained in the following feasible manner: query the account relationship database according to the first account, obtain a first user identifier associated with the first account, and use other accounts in the account relationship database that have a first association relationship with the first user identifier except the first account as the at least one second account, and the accuracy coefficient corresponding to the first association relationship is greater than a preset threshold.

[0123] That is, when obtaining at least one second account associated with the first account, the accuracy coefficient in Table 2 is also considered to ensure that the accuracy coefficient corresponding to the association relationship between the determined second account and the user identifier associated with it is greater than the preset threshold. It should be understood that this embodiment does not limit the value of the preset threshold. The preset threshold can be determined according to the actual application scenario.

[0124] Taking Table 2 as an example, assuming that the threshold is preset to 81%, if the first account is account 1, the second account determined includes: account 2. If the first account is account 5, the second account determined includes account 4. If the first account is account 8, the second account determined includes: account 6 and account 7.

[0125] In this embodiment, by recording the accuracy coefficient in the account relationship database, different second accounts can be pulled out from the account relationship database according to different application scenarios, thereby meeting the business needs of different application scenarios and making the application more flexible.

[0126] The above embodiment describes the process of using the account relationship database to obtain at least one second account associated with the first account. Figure 3 The illustrated embodiment describes the process of generating an account relationship database.

[0127] Figure 3 A flow chart of a method for generating an account relationship database according to another embodiment of the present invention is shown below. Figure 3 As shown, the method of this embodiment may include:

[0128] S301: Acquire multiple sampling accounts, and respectively acquire key features and auxiliary features of the sampling accounts.

[0129] Exemplarily, the sampling account may be any account registered in the network platform. By performing feature extraction on each sampling account, key features and auxiliary features of the sampling account may be obtained. Specifically, feature extraction may be performed on each sampling account to obtain multiple sampling features, and then the key features and auxiliary features of the sampling account may be determined from the multiple sampling features.

[0130] It should be understood that for different application scenarios, the sampled features collected may be different. Taking the e-commerce platform as an example, the sampled features of each account may include but are not limited to: registered mobile phone number information, ID card number information, bound mobile phone number information, historical mobile phone number information, delivery mobile phone number information, order address information, login IP information, login device information, commonly used device information, real-name authentication mobile phone number information, fingerprint information, voiceprint information, facial feature information, etc.

[0131] Optionally, after the sampling features are collected, the sampling features may be further screened to obtain screened sampling features. For example, the sampling features may be screened based on factors such as the current application scenario, the scope of covered users, and the maturity of the technology. When determining the key features and auxiliary features later, they may be determined from the screened sampling features.

[0132] Among them, the key feature refers to the sampling feature with the highest credibility among multiple sampling features. In other words, the key feature is the sampling feature that can best represent the user identity information. The auxiliary feature refers to the other sampling features other than the key feature among the multiple sampling features of the sampled account. The credibility of the auxiliary feature is lower than that of the key feature, or in other words, the auxiliary feature has a lower degree of recognition of the user identity information.

[0133] It should be understood that key features and auxiliary features are relative concepts. Since the sampling features that can be collected for different sampling accounts may be different, for two different sampling accounts, the key features corresponding to the two may be different, and the auxiliary features corresponding to the two may also be different. For example, for sampling account 1, its corresponding key feature may be the ID card number information, and the auxiliary features may include: registered mobile phone number information, bound mobile phone number information. For sampling account 2, its corresponding key feature may be the bound mobile phone number information, and the auxiliary features may include the registered mobile phone number information.

[0134] In a possible implementation, the key features and auxiliary features of the sampling account may be obtained in the following feasible manner: multiple sampling features of the sampling account are obtained, each sampling feature has a corresponding priority. The sampling feature with the highest priority among the multiple sampling features is used as the key feature of the sampling account; and the sampling features other than the key feature among the multiple sampling features are used as the auxiliary features of the sampling account.

[0135] Among them, the priority can be used to indicate the credibility of the sampling feature. The higher the credibility, the higher the priority, and the lower the credibility, the lower the priority. In other words, the priority can be used to indicate the recognition of the sampling feature to the user identity information. The higher the recognition, the higher the priority, and the lower the recognition, the lower the priority. It should be understood that the priority corresponding to the sampling feature can be determined in advance based on a large amount of statistical information.

[0136] For example, taking the three sampling features: ID card information, bound mobile phone number information, and registered mobile phone number information as examples, since the ID card information has the highest credibility, or in other words, the ID card information has the highest recognition of the user's identity information, the ID card information has the highest priority. Similarly, the bound mobile phone number information has a higher credibility than the registered mobile phone number information, or in other words, the bound mobile phone number information has a higher recognition of the user's identity information than the registered mobile phone number information, so the bound mobile phone number information has a higher priority than the registered mobile phone number information. That is, the priority order of the above three sampling features is: priority 1: ID card information, priority 2: bound mobile phone number information, priority 3: registered mobile phone number information.

[0137] Combining the above priority examples, Figure 4 Schematic diagram of key features and auxiliary features provided in the embodiments of the present invention. Figure 4 As shown in the figure, assuming that the sampled account 1 includes three sampling features, namely: ID card information (priority 1), bound mobile phone number information (priority 2), and registered mobile phone number information (priority 3), then the key feature corresponding to the sampled account 1 is: ID card information, and the auxiliary features include: bound mobile phone number information and registered mobile phone number information. Figure 4 Assuming that the sampling account 2 includes two sampling features, namely: bound mobile phone number information (priority 2) and registered mobile phone number information (priority 3), the key feature corresponding to the sampling account 2 is: bound mobile phone number information, and the auxiliary features include: registered mobile phone number information.

[0138] S302: performing association processing on the multiple sampling accounts according to the key features and auxiliary features of the multiple sampling accounts, and determining user identifiers associated with each of the multiple sampling accounts.

[0139] In this embodiment, associating multiple sampling accounts means associating / matching different sampling accounts with features, so as to associate different sampling accounts with the same user ID. The user ID can also be called a natural person ID, that is, through the association process, it is possible to identify which sampling accounts belong to the same natural person user.

[0140] In a possible implementation, multiple sampling accounts may be associated in the following feasible manner:

[0141] (1) According to the priorities corresponding to the key features of the multiple sampling accounts, the multiple sampling accounts are divided into N groups, wherein the priority corresponding to the key features of the sampling accounts in the nth group is the nth priority, where n is a natural number less than or equal to N. The first priority is the highest priority.

[0142] For example, assume that in a certain application scenario, only the following three sampling features are considered: ID number information (priority 1), bound mobile phone number information (priority 2), and registered mobile phone number information (priority 3). When grouping multiple sampled accounts, they can be divided into 3 groups. The key feature of the sampled accounts in group 1 is the ID number information, the key feature of the sampled accounts in group 2 is the bound mobile phone number information, and the key feature of the sampled accounts in group 3 is the registered mobile phone number information.

[0143] (2) For each first sampling account in the first group, determine the user identifier associated with the first sampling account according to the key feature of the first sampling account.

[0144] Combined with the above example, since the key feature of the sampling account in Group 1 is the ID number information, and the ID number information has the highest priority, for each first sampling account in Group 1, its ID number information can be directly used as the user identifier associated with the first sampling account, or the result of encoding its ID number information can be used as the user identifier associated with the first sampling account.

[0145] (3) For each first sampling account in the i-th group, determine the user identifier associated with the first sampling account based on the matching results of the key features of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups, where i is 2, 3, ..., N in sequence.

[0146] That is, for the sampled accounts in the 2nd to Nth groups, the key features can be associated and matched with the auxiliary features of the sampled accounts with a higher priority than the key features to determine the user identifier associated with the sampled accounts. Optionally, the following feasible methods can be adopted:

[0147] In the order of k from 1 to i-1, the key features of the first sampling account are matched with the auxiliary features of the sampling accounts in the kth group in sequence until the match is successful, or until the matching is completed; if the match is successful, the user identifier associated with the successfully matched sampling account in the kth group is determined as the user identifier associated with the first sampling account; if the matching is completed, the user identifier associated with the first sampling account is determined based on the key features of the first sampling account.

[0148] Taking the matching process of the first sampling account in the third group as an example, firstly, the key feature of the first sampling account is matched with the auxiliary features of each sampling account in the first group. If the match is successful, the user identifier associated with the successfully matched sampling account in the first group is used as the user identifier associated with the first sampling account; if the match with each sampling account in the first group is not successful, the key feature of the first sampling account is continued to be matched with the auxiliary features of each sampling account in the second group. If the match is successful, the user identifier associated with the successfully matched sampling account in the second group is used as the user identifier associated with the first sampling account. If the above matching process fails to match successfully, the user identifier associated with the first sampling account is determined according to the key feature of the first sampling account. For example, the key feature of the first sampling account is directly used as its associated user identifier, or the result of encoding the key feature of the first sampling account is used as its associated user identifier.

[0149] Combine the following Figure 5 The feature association matching process is illustrated with an example. Figure 5 A schematic diagram of a sampling account association processing process provided by an embodiment of the present invention. Figure 5 Only two sample accounts are used as examples.

[0150] like Figure 5 As shown, for sample account 1, its key feature is the ID number information, and the auxiliary features include: bound mobile phone number information, registered mobile phone number information, etc. Since the priority of the key feature (ID number information) of sample account 1 is 1, that is, the highest priority, the user ID (user ID A) associated with the sample account 1 is generated based on the key feature (ID number information) of the sample account 1.

[0151] For sample account 2, its key feature is the bound mobile phone number information, and its auxiliary features include: registered mobile phone number information, etc. Since the priority of the key feature of sample account 2 (bound mobile phone number information) is 2, which is not the highest priority, the key information of sample account 2 (bound mobile phone number information) is matched with the auxiliary information of sample account 1 (bound mobile phone number information).

[0152] If the match is successful, the sampling account 2 is also associated with the user ID associated with the sampling account 1, that is, the sampling account 2 is associated with the user ID A. In this case, it is considered that the sampling account 1 and the sampling account 2 are associated with the same user (user ID A). If the match is unsuccessful, the user ID (user ID B) associated with the sampling account 2 is generated based on the key features of the sampling account 2 (ID number information). In this case, it is considered that the sampling account 1 and the sampling account 2 are associated with different users.

[0153] S303: Generate the account relationship database according to the user identifiers associated with each of the plurality of sample accounts.

[0154] It can be understood that after determining the user identifiers associated with each sampled account, an account relationship database as shown in Table 1 can be generated.

[0155] In a possible implementation, after determining the user ID associated with each sampled account, the accuracy coefficient of the association relationship between the sampled account and the user ID associated with it can also be determined based on the key features of the sampled account. Furthermore, an account relationship database can be generated based on the user IDs associated with each sampled account and the accuracy coefficients. The account relationship database generated by this implementation is shown in Table 2.

[0156] Optionally, when determining the accuracy coefficient, it can be determined according to the priority corresponding to the key feature of the sampled account. If the priority corresponding to the key feature is higher, the accuracy coefficient is higher. If the priority corresponding to the key feature is lower, the accuracy coefficient is lower.

[0157] For example, Figure 5 For example, since the priority of the key feature of the sampling account 1 is 1, that is, the highest priority, the accuracy of the association relationship between the sampling account 1 and the user identification A is also the highest. Therefore, the accuracy coefficient of the association relationship between the sampling account 1 and the user identification A can be set to 100%.

[0158] For example, Figure 5 For example, assume that the sampling account 2 is also associated with the user identifier A. Since the priority of the key feature of the sampling account 2 is 2, which is lower than the priority of the key feature 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 the accuracy coefficient of the association relationship between the sampling account 1 and the user identifier A. For example, the accuracy coefficient of the association relationship between the sampling account 2 and the user identifier A can be 90%.

[0159] By using the method of this embodiment, an account relationship database can be generated, and the association relationship between the natural person user identifier and the account can be indicated in the account relationship database. Since the feature matching relationship between different sampled accounts is considered in the process of generating the account relationship database, the accuracy of the account relationship database is guaranteed.

[0160] Furthermore, when it is determined that the type of the first account is the first type, the account relationship database can be used to pull out the second account associated with the first account to the same natural person user identifier, and determine that the type of the second account is also the first type, thereby improving recognition efficiency and reducing computing costs. In addition, by recording the accuracy coefficient in the account relationship database, different second accounts can be pulled out from the account relationship database according to different application scenarios, thereby meeting the business needs of different application scenarios and making the application more flexible.

[0161] Figure 6 This is a schematic diagram of the structure of an account type determination device provided by an embodiment of the present invention. The device of this embodiment may be in the form of software and / or hardware. Figure 6 As shown, the device 10 for determining the account type provided in this embodiment may include: an acquisition module 11, a first determination module 12, and a second determination module 13.

[0162] An acquisition module 11 is used to acquire historical behavior characteristics of the first account;

[0163] A first determination module 12, configured to obtain the type of the first account according to the historical behavior characteristics;

[0164] The second determining module 13 is configured to, when the type of the first account is the first type, obtain at least one second account associated with the first account, and determine that the type of the at least one second account is the first type.

[0165] In a possible implementation, the second determining module 13 is specifically configured to:

[0166] querying an account relationship database according to the first account to obtain a first user identifier associated with the first account, wherein the account relationship database is used to store the association between the user identifier and the account;

[0167] Other accounts in the account relationship database that are associated with the first user identifier except the first account are used as the at least one second account.

[0168] In a possible implementation, the account relationship database is further used to store the accuracy coefficient corresponding to the association relationship between the user identifier and the account, and the second determination module 13 is specifically used to:

[0169] Other accounts other than the first account in the account relationship database that have a first association relationship with the first user identifier are used as the at least one second account, and the accuracy coefficient corresponding to the first association relationship is greater than a preset threshold.

[0170] Figure 7 A schematic diagram of the structure of an account type determination device provided by another embodiment of the present invention. Figure 7 As shown, in Figure 6 On the basis of the embodiment shown, the device of this embodiment may further include a generating module 14. The generating module 14 is used to:

[0171] Acquire multiple sampling accounts, and respectively acquire key features and auxiliary features of the sampling accounts;

[0172] According to the key features and auxiliary features of the multiple sampling accounts, the multiple sampling accounts are associated with each other to determine the user identifiers associated with the multiple sampling accounts;

[0173] The account relationship database is generated according to the user identifiers associated with each of the plurality of sampling accounts.

[0174] In a possible implementation, the generating module 14 is specifically used for:

[0175] Acquire multiple sampling features of the sampling account, each sampling feature corresponding to a priority;

[0176] Using the sampling feature with the highest corresponding priority among the multiple sampling features as the key feature of the sampling account;

[0177] The sampling features other than the key features among the multiple sampling features are used as auxiliary features of the sampling account.

[0178] In a possible implementation, the generating module 14 is specifically used for:

[0179] According to the priorities corresponding to the key features of the multiple sampling accounts, the multiple sampling accounts are divided into N groups, wherein the priority corresponding to the key features of the sampling accounts in the nth group is the nth priority, and n is a natural number less than or equal to N;

[0180] For each first sampling account in the first group, determine a user identifier associated with the first sampling account according to a key feature of the first sampling account;

[0181] For each first sampling account in the i-th group, the user identifier associated with the first sampling account is determined based on the matching results of the key features of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups, where i is 2, 3, ..., N in sequence.

[0182] In a possible implementation, the generating module 14 is specifically used for:

[0183] In the order of k from 1 to i-1, the key features of the first sampled account are matched with the auxiliary features of the sampled accounts in the kth group in sequence until the match is successful, or until the match is completed;

[0184] If the match is successful, the user identifier associated with the successfully matched sampling account in the kth group is determined as the user identifier associated with the first sampling account;

[0185] If the matching is completed, the user identifier associated with the first sampling account is determined according to the key feature of the first sampling account.

[0186] In a possible implementation, the generating module 14 is further configured to:

[0187] Determining, based on the key features of the sampled account, an accuracy coefficient of the association relationship between the sampled account and its associated user identifier;

[0188] The generating module 14 is specifically used to generate the account relationship database according to the user identifiers associated with each of the plurality of sampled accounts and the accuracy coefficient.

[0189] The device for determining the account type provided in this embodiment can be used to execute the technical solution in any of the above method embodiments. Its implementation principle and technical effects are similar and will not be described in detail here.

[0190] Figure 8 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 8 As shown, the electronic device 20 provided in this embodiment includes: a processor 21 and a memory 22; wherein the memory 22 is used to store a computer program; the processor 21 is used to execute the computer program stored in the memory to implement the method for determining the account type in the above embodiment. For details, please refer to the relevant description in the above method embodiment.

[0191] Optionally, the memory 22 may be independent or integrated with the processor 21 .

[0192] When the memory 22 is a device independent of the processor 21 , the electronic device 20 may further include: a bus 23 for connecting the memory 22 and the processor 21 .

[0193] Optionally, the electronic device 20 may further include a communication component 24 for communicating with other devices.

[0194] The electronic device provided in this embodiment can be used to execute the technical solution in any of the above method embodiments. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0195] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a computer program, and the computer program is used to implement the technical solution in any of the above method embodiments.

[0196] An embodiment of the present invention further provides a chip, comprising: 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 solution in any of the above method embodiments.

[0197] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0198] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on 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.

[0199] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned module-composed unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0200] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention.

[0201] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0202] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0203] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present invention is not limited to only one bus or one type of bus.

[0204] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, 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 disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0205] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0206] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0207] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the following claims.

Claims

1. A method for determining an account type, characterized in that: include: Obtain historical behavior characteristics of the first account; According to the historical behavior characteristics, obtaining the type of the first account; When the type of the first account is a first type, obtaining at least one second account associated with the first account; Determining that the type of the at least one second account is the first type; Acquiring at least one second account associated with the first account includes: According to the first account, query the account relationship database to obtain the first user identifier associated with the first account, wherein the account relationship database is used to store the association between the user identifier and the account; the account relationship database is obtained by pre-statisticing the account relationship; Using other accounts in the account relationship database that are associated with the first user identifier, except the first account, as the at least one second account; The account relationship database is also used to store the accuracy coefficient corresponding to the association relationship between the user identifier and the account; Using other accounts in the account relationship database that are associated with the first user identifier, except the first account, as the at least one second account includes: Using other accounts other than the first account in the account relationship database that have a first association relationship with the first user identifier as the at least one second account, wherein the accuracy coefficient corresponding to the first association relationship is greater than a preset threshold; Before querying the account relationship database according to the first account to obtain the first user identifier associated with the first account, the method further includes: Acquire multiple sampling accounts, and respectively acquire key features and auxiliary features of the sampling accounts; According to the key features and auxiliary features of the multiple sampling accounts, the multiple sampling accounts are associated with each other to determine the user identifiers associated with the multiple sampling accounts; The account relationship database is generated according to the user identifiers associated with each of the plurality of sampling accounts.

2. The method according to claim 1, characterized in that: The key features and auxiliary features of the sampled account are obtained, including: Acquire multiple sampling features of the sampling account, each sampling feature corresponding to a priority; Using the sampling feature with the highest corresponding priority among the multiple sampling features as the key feature of the sampling account; The sampling features other than the key features among the multiple sampling features are used as auxiliary features of the sampling account.

3. The method according to claim 2, characterized in that According to the key features and auxiliary features of the multiple sampling accounts, the multiple sampling accounts are associated with each other to determine the user identifiers associated with the multiple sampling accounts, including: According to the priorities corresponding to the key features of the multiple sampling accounts, the multiple sampling accounts are divided into N groups, wherein the priority corresponding to the key features of the sampling accounts in the nth group is the nth priority, and n is a natural number less than or equal to N; For each first sampling account in the first group, determine a user identifier associated with the first sampling account according to a key feature of the first sampling account; For each first sampling account in the i-th group, the user identifier associated with the first sampling account is determined based on the matching results of the key features of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups, where i is 2, 3, ..., N in sequence.

4. The method according to claim 3, characterized in that Determining the user identifier associated with the first sampling account according to the matching result of the key feature of the first sampling account and the auxiliary features of the sampling accounts in the first i-1 groups includes: In the order of k from 1 to i-1, the key features of the first sampled account are matched with the auxiliary features of the sampled accounts in the kth group in sequence until the match is successful, or until the match is completed; If the match is successful, the user identifier associated with the successfully matched sampling account in the kth group is determined as the user identifier associated with the first sampling account; If the matching is completed, the user identifier associated with the first sampling account is determined according to the key feature of the first sampling account.

5. The method according to claim 1, characterized in that After determining the user identifiers associated with each of the plurality of sampling accounts, the method further includes: Determining, based on the key features of the sampled account, an accuracy coefficient of the association relationship between the sampled account and its associated user identifier; Generating the account relationship database according to the user identifiers associated with each of the plurality of sampling accounts includes: The account relationship database is generated according to the user identifiers associated with each of the plurality of sampling accounts and the accuracy coefficient.

6. A device for determining an account type, characterized in that: include: An acquisition module, used to acquire historical behavior characteristics of the first account; A first determination module, configured to obtain the type of the first account according to the historical behavior characteristics; A second determining module, configured to, when the type of the first account is the first type, obtain at least one second account associated with the first account, and determine that the type of the at least one second account is the first type; The second determination module is specifically configured to query an account relationship database according to the first account to obtain a first user identifier associated with the first account, wherein the account relationship database is configured to store the association between the user identifier and the account; The account relationship database is obtained by pre-stating account relationships; other accounts in the account relationship database that are associated with the first user identifier, except the first account, are used as the at least one second account; The account relationship database is also used to store the accuracy coefficient corresponding to the association relationship between the user identifier and the account; The second determination module is specifically configured to use other accounts other than the first account in the account relationship database that have a first association relationship with the first user identifier as the at least one second account, and the accuracy coefficient corresponding to the first association relationship is greater than a preset threshold; A generation module, used to obtain multiple sampled accounts, and respectively obtain key features and auxiliary features of the sampled accounts; According to the key features and auxiliary features of the multiple sampling accounts, the multiple sampling accounts are associated with each other to determine the user identifiers associated with each of the multiple sampling accounts; and according to the user identifiers associated with each of the multiple sampling accounts, the account relationship database is generated.

7. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

Images