Conversational LLM Intent Processing for Codeless Enterprise Apps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing enterprise applications, particularly those developed by codeless platforms, face challenges in processing complex data for procurement and supply chain tasks due to lack of context awareness, adaptability, and conversational fluency, leading to inefficiencies, errors, and increased costs.
Innovation Solution
A large language model-based data processing system with a layered architecture and conversational assistant that identifies user intent, processes inputs through LLM agents, and generates actionable data points, utilizing machine learning and AI to streamline tasks like procurement, supply chain management, application integration, and development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional enterprise applications are used to support multiple specialized parties, then collaboration coverage is improved, but process complexity and manual intervention increase
Solution Approach 1:
The patent introduces an AI assistant as an intermediary layer between multiple specialized parties in enterprise applications. This assistant mediates interactions, automatically processes requests, and coordinates workflows between different stakeholders, thereby maintaining comprehensive collaboration coverage while significantly reducing process complexity and manual intervention requirements.
Solution Approach 2:
The system enables self-service capabilities where the AI assistant autonomously handles task execution, data processing, and workflow management without requiring manual intervention from specialized parties. The assistant independently navigates complex processes, makes decisions based on learned patterns, and executes tasks across multiple systems, reducing the burden on human users while maintaining adaptability to various collaboration scenarios.
2Adaptability or versatility
If existing enterprise applications handle multiple parties with intricate workflows, then collaboration capability is improved, but time consumption and efficiency deteriorate
Solution Approach 1:
The patent replaces manual mechanical processes with an AI-driven automated system. The AI assistant substitutes human operators in navigating intricate workflows, automatically executing tasks across multiple systems, and processing information between specialized parties. This substitution maintains comprehensive collaboration capability while dramatically improving processing efficiency by eliminating manual intervention bottlenecks.
Solution Approach 2:
The system performs preliminary actions by pre-processing and understanding user intents before actual task execution. The AI assistant anticipates required actions, prepares necessary data, and pre-coordinates workflows between multiple parties, thereby streamlining the overall process and improving efficiency while maintaining adaptability to complex collaboration scenarios.
3Adaptability or versatility
If manual intervention is used in complex enterprise workflows, then flexibility and adaptability are improved, but errors and delays increase
Solution Approach 1:
The patent implements feedback mechanisms where the AI assistant continuously monitors workflow execution, learns from outcomes, and adjusts its behavior to improve accuracy. The system provides feedback loops that capture errors, analyze patterns, and refine processing logic, thereby maintaining workflow flexibility while systematically reducing error rates through continuous learning and adaptation.
Solution Approach 2:
The AI assistant performs self-correction and validation of its actions, automatically detecting and correcting errors without requiring manual intervention. The system independently validates data, verifies workflow compliance, and adjusts its processing to eliminate errors, thereby maintaining adaptability to flexible workflows while significantly improving reliability through autonomous error prevention and correction.
Data Source
AI summary
The present invention provides a large language model-based system and method for data processing in application developed by codeless platform. The invention includes identification of intent of a user to process procurement, supply chain, application integration, application restructuring or development scenarios.