Policy enforcement using natural language processing

摘要

A term of use policy document defines permissible actions that may be implemented by a user using a computing device. A natural language processing (NLP)-based question and answer (Q&A) system is trained to understand the policy document. The device includes a management application that interacts with the Q&A system to identify a policy violation. When the user performs an action on the device, the application converts that action into an NLP query directed to the Q&A system to determine whether the action constitutes a violation. The query may be accompanied by metadata associated with the user, the device or its state. Upon receipt of the query and any associated metadata, the Q&A system determines if the user action is compliant with the policy and returns a response. Based on the response, the user's computing device may take an enforcement action, e.g., restricting or disabling functionality, or issuing a warning.