Runtime Process Reconfiguration Using LLM Urgency Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data processing systems lack the ability to dynamically reconfigure process models based on urgency levels, leading to inefficiencies in handling time-sensitive transactions.
Innovation Solution
A computer-implemented method that utilizes a large language model (LLM) to analyze transaction inputs and determine urgency levels, allowing for real-time reconfiguration of process models to align with these urgency levels by extracting dependencies, generating dependency graphs, and initializing protocols for execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed process model is used for transaction processing, then system stability is maintained, but responsiveness to time-sensitive transactions deteriorates
Solution Approach 1:
The process model transitions from a static, pre-defined structure to a dynamic configuration that can be modified at runtime. The system now allows process steps, dependencies, and execution paths to be adjusted based on real-time urgency assessments, enabling time-sensitive transactions to bypass non-critical steps while maintaining stability for standard transactions.
Solution Approach 2:
The system introduces urgency level as a dynamic parameter that modifies process execution characteristics. By analyzing transaction inputs with LLMs to determine urgency levels, the system adjusts processing parameters such as execution speed, resource allocation, and step prioritization, allowing critical transactions to be processed faster without affecting overall system stability.
2Loss of time
If process reconfiguration capability is added to handle urgent transactions, then transaction responsiveness improves, but system complexity increases
Solution Approach 1:
The process model is segmented into modular components with defined dependencies. This segmentation allows the system to selectively reconfigure only the necessary portions of the process for urgent transactions rather than redesigning the entire process model, thereby managing complexity while enabling rapid adaptation.
Solution Approach 2:
The system implements a feedback mechanism where LLMs continuously analyze transaction inputs to determine urgency levels, which then feed back into the process configuration system. This closed-loop feedback enables automatic, data-driven process reconfiguration without requiring complex manual intervention, simplifying the overall system architecture despite the added reconfiguration capability.
3Measurement precision
If LLM-based cognitive analysis is implemented to determine urgency levels, then transaction prioritization accuracy improves, but computational resource consumption increases
Solution Approach 1:
The system applies LLM-based cognitive analysis selectively only to transactions that require urgency assessment, rather than processing every transaction through the full LLM pipeline. For standard transactions, conventional processing methods are used, reserving the computationally intensive LLM analysis for cases where accurate urgency determination provides meaningful value.
Solution Approach 2:
The system performs preliminary filtering and preprocessing of transaction inputs before submitting them to the LLM for urgency analysis. This preliminary action reduces the complexity and size of inputs requiring LLM processing, thereby reducing computational resource consumption while maintaining the accuracy of urgency level detection for transactions that do require LLM analysis.
Data Source
AI summary
Computer implemented methods, systems, and computer program products include program code executing on a processor(s) initializes a process model for runtime reconfiguration. The program code extracts dependencies for components comprising the process model. The program code generates or updates a dependency graph representing the dependencies, based on the extracting. The program code initializes a protocol across a stack for executing the process based on the dependencies. The program code, after initializing initiates the transaction. During runtime, the program code receives an input related to the transaction performed by the process model. The program code cognitively analyzes the input utilizing a large language model (LLM) to determine an urgency level for the transaction. The program code determines that the urgency level is above a pre-determined threshold. The program code reconfigures the process model to comport with the urgency level.