Identity verification method and apparatus

One or more non-transitory computer-readable storage media storing instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

• obtaining historical feature information comprising historical device environment information of a historical device;
• determining a training set comprising first historical feature information of the historical feature information and a verification set comprising second historical feature information of the historical feature information;
• training the device verification model by using the first historical feature information;
• verifying the device verification model by using the second historical feature information;
• in response to determining that accuracy of the device verification model does not meet one or more application requirements, retraining the device verification model using updated historical feature information to meet the one or more application requirements;
• obtaining evaluation data of the device verification model during a usage phase after training by using a binary classification method according to a real time output of the device verification model;
• adjusting a model parameter of the device verification model according to the evaluation data until the evaluation data of the retrained device verification model satisfies a preset condition;
• determining a feature vector corresponding to a current computing device according to current device environment information of the current computing device;
• and
• determining, by the retrained device verification model based on the feature vector corresponding to the current computing device, a credibility of the current computing device.

A system, comprising one or more processors and one or more non-transitory computer-readable memories coupled to the one or more processors and configured with instructions executable by the one or more processors to cause the system to perform operations comprising:

• obtaining historical feature information comprising historical device environment information of a historical device;
• determining a training set comprising first historical feature information of the historical feature information and a verification set comprising second historical feature information of the historical feature information;
• training the device verification model by using the first historical feature information;
• verifying the device verification model by using the second historical feature information;
• in response to determining that accuracy of the device verification model does not meet one or more application requirements, retraining the device verification model using updated historical feature information to meet the one or more application requirements;
• obtaining evaluation data of the device verification model during a usage phase after training by using a binary classification method according to a real time output of the device verification model;
• adjusting a model parameter of the device verification model according to the evaluation data until the evaluation data of the retrained device verification model satisfies a preset condition;
• determining a feature vector corresponding to a current computing device according to current device environment information of the current computing device;
• and
• determining, by the retrained device verification model based on the feature vector corresponding to the current computing device, a credibility of the current computing device.