LLM Intent Translation for Communication Service Orchestration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current intent-based network management and orchestration solutions rely on manually defined translation policies, which are prone to errors and insufficient for comprehensive handling of various scenarios.
Innovation Solution
Utilize a large language model (LLM) to process intents describing required communication services, translating them into technical features and orchestrating the corresponding services in a network, leveraging generative AI techniques like Chain of Thought, Tree of Thought, and Retrieval-Augmented Generation to ensure accurate and efficient service orchestration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manually defined translation policies are used to translate intents to communication services, then the system can be implemented with current technology, but the translation is prone to errors and not comprehensive enough
Solution Approach 1:
The patent replaces the manual mechanical translation process with an automated LLM-based system. The LLM processes natural language intent descriptions and automatically generates communication service orchestration configurations, eliminating human errors in translation while reducing the complexity of manual policy definition and maintenance.
Solution Approach 2:
The LLM acts as an intermediary between the high-level business intent and the low-level technical service configuration. It translates intent descriptions into actionable service orchestration instructions, bridging the gap between business requirements and technical implementation without requiring manual translation policies.
2Adaptability or versatility
If manually defined translation policies are used, then the system structure is simpler, but the handling of various scenarios is insufficient
Solution Approach 1:
The LLM-based system provides universal translation capability that can handle diverse intent scenarios without requiring separate manual policies for each case. The model learns from training data and can adapt to various communication service requirements, making the system versatile while maintaining ease of use through a single unified interface.
3Productivity
If LLM-based translation is used to improve translation accuracy and speed, then fulfillment of intents is faster and more accurate, but the system complexity increases
Solution Approach 1:
The LLM is pre-trained on extensive communication service data and orchestration patterns before deployment. This preliminary training enables the system to quickly and accurately translate intents without requiring complex real-time processing, improving productivity while managing system complexity through pre-computed knowledge.
Data Source
AI summary
As described herein, a system, method, and computer program are provided for intent-based communication service orchestration with generative AI assistance. An intent describing properties of a required service is processed, using a large language model (LLM), to translate the intent into a communication service capable of being orchestrated in a network. The communication service is orchestrated in the network.