Cognitive Report Prioritization via Predicted Completion Time

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing approaches to report generation in resource-constrained environments fail to effectively prioritize reports based on predicted completion time and user importance, leading to inefficient resource allocation and potential blocking of urgent reports.

Innovation Solution

A cognitive prioritization system that uses a multi-variable regression model for predicting completion time and a text mining model for predicting importance, combining these with user profile importance to determine a prioritization score for each report, which is then used to schedule report generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If reports are generated in first-come-first-served order without prioritization, then system resource allocation is simple, but urgent reports with high user profile importance may experience long delays

Engineering Contradiction:

Improvereport generation schedulingVSAvoidreport completion delay

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system changes the scheduling parameter from simple FIFO ordering to a composite prioritization score that incorporates predicted completion time and user profile importance. This allows urgent reports to be identified and scheduled appropriately without complex manual intervention.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces manual prioritization mechanisms with an automated cognitive system that uses machine learning models (multi-variable regression for completion time prediction, text mining for importance prediction) to automatically determine report priority based on historical data and user profiles.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of time

If reports are prioritized based solely on user profile importance, then urgent reports are processed quickly, but the system may not account for actual completion time requirements and resource constraints

Engineering Contradiction:

Improvereport completion delayVSAvoidsystem resource utilization

Core Design Contradiction:

Loss of timeVSProductivity

Solution Approach 1:

The system performs preliminary actions by predicting both the completion time and importance of reports before actual processing. This allows the scheduler to make informed decisions about resource allocation and prioritization in advance, balancing urgency with resource constraints.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses historical completion time data and user feedback to continuously refine its predictions. The multi-variable regression model learns from past report generation patterns, and the text mining model improves its importance predictions based on user interactions, creating a feedback loop that optimizes resource utilization over time.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If the system uses complex prediction models for report prioritization, then report scheduling accuracy improves, but system complexity and computational overhead increase

Engineering Contradiction:

Improveprioritization accuracyVSAvoidprediction model complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the prioritization problem into two separate prediction models: one for predicting completion time (multi-variable regression) and another for predicting importance (text mining). This segmentation allows each model to be optimized independently and keeps the overall system manageable despite the complexity of the prioritization task.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11295257B2Cognitive prioritization for report generation

Publication Date: 2022.04.05 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A system for cognitive prioritization for report generation may include a processor and a memory cooperating therewith. The processor may be configured to accept a request for a new report from a user, the request having a user profile importance associated therewith and generate a predicted completion time for the new report based upon a historical completion time prediction model based upon historical data for prior reports. The processor may be configured to generate a predicted importance of the new report based upon a historical importance prediction model based upon the historical data for prior reports and determine a combined predicted importance based upon the user profile importance and the predicted importance. The processor may also be configured to generate a prioritization of the new report among other reports based upon the predicted completion time and the combined predicted importance and generate the new report based upon the prioritization.