Generative AI Recommendations for Program Metric Bottlenecks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Program managers face challenges in quickly grasping the overall status of their programs and identifying projects that require immediate attention, especially when dealing with complex financial metrics, leading to increased risks of errors and missed critical details.

Innovation Solution

A system utilizing a generative AI model generates actionable recommendations for program improvements based on key metrics, leveraging a machine learning model to identify influential metrics and generate prompts for the AI model to suggest specific actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If program managers manually analyze complex financial metrics to grasp program status, then they can understand detailed financial information, but the process becomes time-consuming and error-prone

Engineering Contradiction:

Improveprogram status understanding accuracyVSAvoidtime to grasp program status

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical analysis of financial metrics with an AI-based automated system. The system uses natural language processing to interpret financial data and generate program status summaries, eliminating the need for manual calculation and review while improving both speed and accuracy of program status understanding.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an AI intermediary layer between raw financial metrics and program status understanding. This intermediary processes complex financial data through machine learning models and generates human-readable summaries, making the information accessible and accurate without requiring manual analysis time.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If program managers manually review all projects to identify those requiring attention, then they can assess all project details, but the complexity increases and critical details may be missed

Engineering Contradiction:

Improveidentification of critical projectsVSAvoidcomplexity of project review process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces manual project review with an automated AI system that continuously monitors project metrics. The system uses machine learning to identify patterns and flag critical projects, eliminating the complex manual review process while improving reliability through consistent, data-driven assessment.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically monitoring, analyzing, and identifying critical projects without human intervention. The AI models continuously process project data and self-adjust to improve identification accuracy, freeing managers from manual review while maintaining high reliability.

Inventive Principle:

Principle #25Self-service

3Productivity

If program managers manually monitor program metrics, then they can track performance, but the risk of errors increases with complex financial data

Engineering Contradiction:

Improveprogram monitoring efficiencyVSAvoiderror rate in metric analysis

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent substitutes manual metric monitoring with an automated AI system that continuously tracks program performance. The system uses machine learning algorithms to process financial data and generate monitoring reports, dramatically improving productivity while eliminating human errors through consistent, algorithm-based analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system incorporates feedback mechanisms where AI models continuously learn from program data and adjust their analysis. This feedback loop improves monitoring accuracy over time, maintaining high reliability even as program complexity increases, while automated processing maintains high productivity.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260064554A1Actionable Recommendations by Generative Artificial Intelligence Based on Influential Project Metrics

Publication Date: 2026.03.05 ORACLE INT CORP

AI summary

Techniques for generating actionable recommendations to improve program performance using generative AI are disclosed. A system invokes an application programming interface (API) service to obtain a set of program attributes. The program is made up of multiple projects that share a strategic objective. The system determines an overall performance classification for the program and a set of key program metrics that influence the overall performance classification. The system generates a prompt using the key program metrics. The system provides the prompt to a generative AI model to generate a program summary and a set of actionable recommendations to improve program performance by improving one or more of the key program metrics.