User classification

1. A computer-implemented user classification method, comprising:

obtaining, by a target terminal device, an initial user classification model from a server, wherein the initial user classification model is provided by the server to multiple terminal devices, the multiple terminal devices comprising the target terminal device;

obtaining first operation data of a registered user of the target terminal device during a first time period, the first operation data recording one or more operations performed by the registered user on the target terminal device;

delaying updating the initial user classification model for a predetermined amount of time after an occurrence time of the one or more operations during the first time period in order to prevent the initial user classification model from learning based on an operation of a user other than the registered user;

the predetermined amount of time after the occurrence time of the one or more operations, updating the initial user classification model based on the first operation data, to obtain an updated user classification model that is personalized for the registered user; and

classifying, based on the updated user classification model, an identity of a current user of the target terminal device.

2. The computer-implemented method of claim 1 , wherein classifying the identity of the current user comprises:

obtaining current operation data, wherein the current operation data records one or more operations performed by the current user on the target terminal device;

analyzing, based on the updated user classification model, the current operation data, to obtain a risk value;

determining that the risk value is greater than a predetermined threshold; and

based on determining that the risk value is greater than the predetermined threshold, determining that the current user and the registered user are different users.

3. The computer-implemented method of claim 2 , further comprising, subsequent to determining that the current user and the registered user are different users:

performing identity verification on the current user;

determining that the identity verification has succeeded; and

based on determining that the identity verification has succeeded, responding to an additional operation performed by the current user.

4. The computer-implemented method of claim 1 , wherein the first operation data records one or more operations performed by the registered user on the target terminal device in the first time period; and

wherein, subsequent to updating the initial user classification model, the computer-implemented method further comprises:

obtaining second operation data, wherein the second operation data records one or more additional operations performed by the registered user on the target terminal device in a second time period, wherein the second time period and the first time period are different time periods; and

updating the updated user classification model based on the second operation data.

5. The computer-implemented method of claim 1 , further comprising:

obtaining alarm information, wherein the alarm information indicates that the target terminal device is lost or embezzled; and

based on the alarm information, stopping the updating of the initial user classification model.

6. The computer-implemented method of claim 1 , wherein updating the initial user classification model comprises:

performing feature extraction on the first operation data to obtain a first operation data feature set, wherein the first operation data feature set comprises a character data feature set and a numerical data feature set.

7. The computer-implemented method of claim 1 , wherein the first operation data comprises at least one of login data, function setting data, communication data, browsing data, and transaction data.

8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

obtaining, by a target terminal device, an initial user classification model from a server, wherein the initial user classification model is provided by the server to multiple terminal devices, the multiple terminal devices comprising the target terminal device;

obtaining first operation data of a registered user of the target terminal device during a first time period, the first operation data recording one or more operations performed by the registered user on the target terminal device;

delaying updating the initial user classification model for a predetermined amount of time after an occurrence time of the one or more operations during the first time period in order to prevent the initial user classification model from learning based on an operation of a user other than the registered user;

the predetermined amount of time after the occurrence time of the one or more operations, updating the initial user classification model based on the first operation data, to obtain an updated user classification model that is personalized for the registered user; and

classifying, based on the updated user classification model, an identity of a current user of the target terminal device.

9. The computer-readable medium of claim 8 , wherein classifying the identity of the current user comprises:

obtaining current operation data, wherein the current operation data records one or more operations performed by the current user on the target terminal device;

analyzing, based on the updated user classification model, the current operation data, to obtain a risk value;

determining that the risk value is greater than a predetermined threshold; and

based on determining that the risk value is greater than the predetermined threshold, determining that the current user and the registered user are different users.

10. The computer-readable medium of claim 9 , wherein the operations further comprise, subsequent to determining that the current user and the registered user are different users:

performing identity verification on the current user;

determining that the identity verification has succeeded; and

based on determining that the identity verification has succeeded, responding to an additional operation performed by the current user.

11. The computer-readable medium of claim 8 , wherein the first operation data records one or more operations performed by the registered user on the target terminal device in the first time period; and

wherein, subsequent to updating the initial user classification model, the operations further comprise:

obtaining second operation data, wherein the second operation data records one or more additional operations performed by the registered user on the target terminal device in a second time period, wherein the second time period and the first time period are different time periods; and

updating the updated user classification model based on the second operation data.

12. The computer-readable medium of claim 8 , further comprising:

obtaining alarm information, wherein the alarm information indicates that the target terminal device is lost or embezzled; and

based on the alarm information, stopping the updating of the initial user classification model.

13. The computer-readable medium of claim 8 , wherein updating the initial user classification model comprises:

performing feature extraction on the first operation data to obtain a first operation data feature set, wherein the first operation data feature set comprises a character data feature set and a numerical data feature set.

14. The computer-readable medium of claim 8 , wherein the first operation data comprises at least one of login data, function setting data, communication data, browsing data, and transaction data.

15. A computer-implemented system, comprising:

one or more computers; and

one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:

obtaining, by a target terminal device, an initial user classification model from a server, wherein the initial user classification model is provided by the server to multiple terminal devices, the multiple terminal devices comprising the target terminal device;

obtaining first operation data of a registered user of the target terminal device during a first time period, the first operation data recording one or more operations performed by the registered user on the target terminal device;

delaying updating the initial user classification model for a predetermined amount of time after an occurrence time of the one or more operations during the first time period in order to prevent the initial user classification model from learning based on an operation of a user other than the registered user;

the predetermined amount of time after the occurrence time of the one or more operations, updating the initial user classification model based on the first operation data, to obtain an updated user classification model that is personalized for the registered user; and

classifying, based on the updated user classification model, an identity of a current user of the target terminal device.

16. The computer-implemented system of claim 15 , wherein classifying the identity of the current user comprises:

obtaining current operation data, wherein the current operation data records one or more operations performed by the current user on the target terminal device;

analyzing, based on the updated user classification model, the current operation data, to obtain a risk value;

determining that the risk value is greater than the predetermined threshold; and

based on determining that the risk value is greater than the predetermined threshold, determining that the current user and the registered user are different users.

17. The computer-implemented system of claim 16 , wherein the operations further comprise, subsequent to determining that the current user and the registered user are different users:

performing identity verification on the current user;

determining that the identity verification has succeeded; and

based on determining that the identity verification has succeeded, responding to an additional operation performed by the current user.

18. The computer-implemented system of claim 15 , wherein the first operation data records one or more operations performed by the registered user on the target terminal device in the first time period; and

wherein, subsequent to updating the initial user classification model, the operations further comprise:

obtaining second operation data, wherein the second operation data records one or more additional operations performed by the registered user on the target terminal device in a second time period, wherein the second time period and the first time period are different time periods; and

updating the updated user classification model based on the second operation data.

19. The computer-implemented system of claim 15 , further comprising:

obtaining alarm information, wherein the alarm information indicates that the target terminal device is lost or embezzled; and

based on the alarm information, stopping the updating of the initial user classification model.

20. The computer-implemented system of claim 15 , wherein updating the initial user classification model comprises:

performing feature extraction on the first operation data to obtain a first operation data feature set, wherein the first operation data feature set comprises a character data feature set and a numerical data feature set.