Authorization policy optimization method and apparatus, and storage medium

An authorization policy optimization apparatus comprising:

• at least one memory configured to store computer program code;
• and
• at least one processor configured to access the at least one memory and operate according to the computer program code, the computer program code comprising:
• policy receiving code configured to cause the at least one processor to:
• receive an authorization policy to be used to perform an authentication on a data access right of a user;
• obtain authorization log information of a first preset authorization policy, from the received authorization policy;
• and
• extract a log information feature, from the obtained authorization log information;
• model generation code configured to cause the at least one processor to:
• perform a feature optimization processing on the extracted log information feature;
• select, based on a preset rule, a training sample for the log information feature on which the feature optimization processing is performed;
• input, into a preset model, the selected training sample, to generate an authorization policy optimization model for outputting an output value corresponding to an input authorization policy;
• policy prediction code configured to cause the at least one processor to input the received authorization policy into the generated authorization policy optimization model, to obtain a predicted value corresponding to the received authorization policy;
• and
• optimization processing code configured to cause the at least one processor to:
• determine whether the obtained predicted value is less than or equal to a specified value;
• based on the predicted value being determined to be less than or equal to the specified value, prompt the user to perform an optimization processing on the authorization policy;
• and
• based on the predicted value being determined to be greater than the specified value, prompt the user that the authorization policy is a reasonable policy.

A non-transitory computer-readable storage medium storing instructions that cause at least one processor of to:

• receive an authorization policy to be used to perform an authentication on a data access right of a user;
• obtain authorization log information of a first preset authorization policy, from the received authorization policy;
• extract a log information feature, from the obtained authorization log information;
• perform a feature optimization processing on the extracted log information feature;
• select, based on a preset rule, a training sample for the log information feature on which the feature optimization processing is performed;
• input, into a preset model, the selected training sample, to generate an authorization policy optimization model for outputting an output value corresponding to an input authorization policy;
• input the received authorization policy into the generated authorization policy optimization model, to obtain a predicted value corresponding to the received authorization policy;
• determine whether the obtained predicted value is less than or equal to a specified value;
• based on the predicted value being determined to be less than or equal to the specified value, prompt the user to perform the optimization processing on the authorization policy;
• and
• based on the predicted value being determined to be greater than the specified value, prompt the user that the authorization policy is a reasonable policy.