Machine-learned policies for pcrf
AssigneeVerizon Patent and Licensing Inc.
InventorJames Mathison
Life of this patent
Estimating the term…
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 input for PCRF policies; generates a policy list based on the input; receives signaling messages for user equipment; determines, based on the policy list, policy decisions that are responsive to each of the signaling messages; logs a decision flow associated with each of the signaling messages and a corresponding policy decision; and optimizes an order of the policy list based on the logging.
Claims20
A method, comprising:
- receiving, by a network device, input for Policy and Charging Rules Function (PCRF) policies;
- generating, by the network device, a policy list based on the input;
- receiving, by the network device, signaling n messages for user equipment;
- determining, by the network device and based on the policy list, policy decisions that are responsive to each of the signaling messages;
- logging, by the network device, a decision flow associated with each of the signaling messages and a corresponding policy decision;
- and
- optimizing, by the network device, an order of the policy list based on the logging.
A network device, comprising:
- an interface that communicates with a network;
- a memory configured to store instructions;
- and
- a processor, coupled to the interface and the memory, wherein the processor is configured to execute the instructions stored in the memory to:
- receive input for Policy and Charging Rules Function (PCRF) policies,
- generate a policy list based on the input,
- receive signaling messages for user equipment,
- determine, based on the policy list, policy decisions that are responsive to each of the signaling messages,
- log a decision flow associated with each of the signaling messages and a corresponding policy decision, and
- optimize an order of the policy list based on the logging.
A non-transitory computer-readable medium, storing instructions executable by one or more processors, the non-transitory computer-readable medium comprising one or more instructions to:
- receive input for Policy and Charging Rules Function (PCRF) policies;
- generate a policy list based on the input;
- receive signaling messages for user equipment;
- determine, based on the policy list, policy decisions that are responsive to each of the signaling messages;
- log a decision now associated with each, of the signaling messages and a corresponding policy decision;
- and
- optimize an order of the policy list based on the logging.
Dependencies are inferred from the claim text.