SBC Session Initiation Filtering via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Session Border Controllers (SBCs) face challenges in efficiently handling session initiation messages, particularly in determining the compatibility of devices to support TTY tones, which can lead to resource wastage and incorrect call handling.
Innovation Solution
The implementation of a method where an SBC receives an invitation to create a session, determines whether to forward it based on a datastore of prior invitations and their results, and uses statistical modeling and machine learning to assess the likelihood of successful session creation, thereby optimizing call handling and resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the SBC forwards all session initiation messages without filtering, then the call setup process is simple and fast, but incompatible calls are not detected early leading to resource wastage
Solution Approach 1:
The SBC performs preliminary compatibility assessment using statistical modeling and machine learning on session description parameters before forwarding the session initiation message. This preliminary action identifies incompatible calls early, preventing resource wastage while maintaining relatively simple call handling through automated decision-making.
Solution Approach 2:
The patent replaces manual or rule-based call compatibility checking with statistical modeling and machine learning algorithms. This substitution enables automated, intelligent decision-making that can detect incompatibilities (such as TTY tone compatibility) without requiring complex manual configuration or filtering rules.
2Reliability
If the SBC uses complex filtering rules to detect incompatible calls, then resource wastage is reduced, but the device complexity and processing overhead increase
Solution Approach 1:
The patent replaces complex mechanical filtering rules with statistical modeling and machine learning systems. These systems analyze session description parameters to predict call compatibility, achieving high detection accuracy without requiring manually configured filtering rules. The machine learning models are trained on historical call data to recognize patterns of incompatibility.
Solution Approach 2:
The SBC system uses machine learning models that continuously learn from call outcomes to improve their compatibility detection accuracy over time. The system serves itself by automatically updating its understanding of incompatible call patterns without requiring manual rule adjustments, maintaining high reliability while keeping the operational complexity low.
3Loss of energy
If the SBC rejects calls based on format specifiers like TTY tones, then resource wastage is reduced, but false rejections of compatible calls may occur
Solution Approach 1:
The patent replaces rigid rule-based rejection of calls with format specifiers (like TTY tones) with machine learning-based prediction. The system analyzes multiple session description parameters and call history to predict actual compatibility, reducing false rejections while still preventing resource wastage from truly incompatible calls. The statistical model provides probability-based decisions rather than absolute rule-based rejections.
Data Source
AI summary
A second device (e.g., a session border controller (SBC) receives, from a first device (e.g., a video teleconference server) of an IP communication network, an invitation (e.g., a session initiation protocol (SIP) message) to create a session between the first device and a third device (e.g., a computer of a person participating in the teleconference) of the network. The invitation includes a session description, e.g., in session description protocol (SDP) format. The second device determines whether to forward the invitation toward the third device based on a datastore comprising i) prior invitations received by the second device to create sessions between devices of the network, and ii) results of the prior invitations. Upon determining to forward the invitation, the second device forwards the invitation.