Machine-Learning Detection of Unnecessary Resource Re-Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing resource management techniques struggle to accurately identify entities at high risk of avoidable resource re-utilization, often relying on insufficiently tailored education and follow-up measures, and are hindered by communication barriers.
Innovation Solution
A computer-implemented method using machine-learning models to analyze entity data, generate prediction indicators for resource re-utilization, and display results on a GUI, incorporating intervention flags for optimized resource management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional entity education and follow-up measures are used, then resource re-utilization reduction is attempted, but identification accuracy of high-risk entities remains insufficient
Solution Approach 1:
The patent replaces traditional manual assessment methods with machine learning models that automatically analyze entity data. The system uses trained ML models to process entity data objects and generate prediction indicators, substituting human judgment with algorithmic analysis to improve identification accuracy while maintaining manageable system complexity through automated processing.
Solution Approach 2:
The patent introduces an intermediary machine learning system that acts as a mediator between raw entity data and prediction outcomes. The ML model serves as an intermediary layer that transforms complex entity data into actionable prediction indicators, enabling accurate high-risk entity identification without requiring direct human analysis of all data points.
2Measurement precision
If comprehensive data analysis is performed to improve prediction accuracy, then identification precision increases, but processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models on historical entity data before deployment. The models are trained in advance to recognize patterns and relationships in entity data, so that during actual prediction, the system can quickly process new entities using pre-learned knowledge, reducing real-time processing time while maintaining high accuracy.
Solution Approach 2:
The patent utilizes parameter changes by optimizing ML model parameters through training to balance accuracy and processing speed. The system adjusts model parameters such as feature weights, threshold values, and processing depth to achieve optimal prediction accuracy within acceptable time frames, dynamically balancing the trade-off between precision and speed.
3Reliability
If machine-learning models are applied to improve prediction capability, then identification accuracy improves, but system complexity increases
Solution Approach 1:
The patent implements self-service by enabling the machine learning system to automatically train, evaluate, and optimize itself using historical data. The ML models perform self-adjustment through continuous learning from entity data, reducing the need for manual system configuration and maintenance, thereby managing complexity through automated self-optimization while improving prediction reliability.
Solution Approach 2:
The patent incorporates feedback mechanisms where prediction outcomes are fed back into the system to continuously improve model performance. The system uses feedback from actual entity outcomes to retrain and refine ML models, creating a closed-loop system that automatically improves prediction capability while managing complexity through iterative self-improvement rather than manual intervention.
Data Source
AI summary
Systems and methods are disclosed for detecting unnecessary resource re-utilization. A method includes receiving a first data object, the first data object including an entity data set containing a plurality of entities; a first data set including request data associated with the plurality of entities; an event data set; and a plurality of data sets associated with one or more performance metrics. The method further includes generating an entity data object for each of the plurality of entities and applying a machine-learning model to the entity data objects generated for the plurality of entities. The method further includes determining a prediction indicator for each entity of the plurality of entities, generating a re-utilization offset data object for each of the plurality of entities, and causing the re-utilization offset data object for each entity to be displayed on a Graphical User Interface (GUI).