Invention Grant
- Patent Title: Machine-learned policies for PCRF
-
Application No.: US14938140Application Date: 2015-11-11
-
Publication No.: US09729728B2Publication Date: 2017-08-08
- Inventor: James Mathison
- Applicant: Verizon Patent and Licensing Inc.
- Applicant Address: US NJ Basking Ridge
- Assignee: Verizon Patent and Licensing Inc.
- Current Assignee: Verizon Patent and Licensing Inc.
- Current Assignee Address: US NJ Basking Ridge
- Main IPC: H04M11/00
- IPC: H04M11/00 ; H04M15/00 ; G06N99/00

Abstract:
A network device receives business logic for Policy and Charging Rules Function (PCRF) policies and automatically generates a policy list based on the business logic. The network device receives signaling messages for user equipment and determines, based on the policy list, policy decisions that are responsive to each of the signaling messages. The network device further logs a decision flow associated with each of the signaling messages and corresponding policy decisions; determines, based on the logging, if the policy list can be structured more efficiently; and automatically updates the policy list when the policy list can be structured more efficiently.
Public/Granted literature
- US20170134590A1 MACHINE-LEARNED POLICIES FOR PCRF Public/Granted day:2017-05-11
Information query