Similar Incident Identification Through Two-Stage Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Identifying similar incidents in large datasets of event data is challenging due to the time-consuming and resource-intensive manual process, making it difficult to determine the relevance of incidents from common entities, especially when a large number of similar incidents exist.

Innovation Solution

A processor filters a set of candidate incidents based on similarity scores, calculating first and second similarity scores to identify a predefined number of candidate incidents, forming a candidate incidents pool, and outputting a subset of incidents that are most similar to a subject incident, thereby reducing computational load and improving accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual identification of similar incidents is used, then accuracy of incident relevance determination is improved, but time consumption and resource consumption increase

Engineering Contradiction:

Improveaccuracy of incident relevance determinationVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical identification processes with an automated computer-based similarity scoring system. The system calculates similarity scores between subject incidents and candidate incidents using defined properties and thresholds, eliminating the need for manual review while maintaining accurate relevance determination through structured comparison criteria.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms the manual evaluation process into a parameter-driven automated system by defining specific properties (such as entity type, event type, location) and assigning weights to them. By changing the evaluation approach from subjective manual assessment to objective parameter-based scoring, the system achieves both speed and accuracy in incident identification.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If manual identification of similar incidents is used, then accuracy of incident relevance determination is improved, but resource consumption increases

Engineering Contradiction:

Improveaccuracy of incident relevance determinationVSAvoidresource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent replaces manual resource-intensive identification with an automated computational system that uses processing power to calculate similarity scores. This substitution eliminates the need for human resources to manually review incidents, thereby reducing overall resource consumption while maintaining high accuracy through systematic comparison algorithms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically comparing incidents against each other using predefined similarity criteria without requiring human intervention. The automated similarity scoring mechanism independently evaluates and ranks candidate incidents, eliminating the need for manual resource input while achieving accurate relevance determination.

Inventive Principle:

Principle #25Self-service

3Quantity of substance

If all candidate incidents are reviewed manually, then completeness of incident analysis is improved, but processing time increases

Engineering Contradiction:

Improvecompleteness of incident analysisVSAvoidprocessing speed

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The patent segments the incident review process into two stages: first, automated filtering using similarity scores to identify promising candidates; second, selective manual review only of the top-ranked incidents that meet the threshold criteria. This segmentation maintains analysis completeness by ensuring thorough review of the most relevant incidents while dramatically reducing processing time by excluding obviously irrelevant cases from manual review.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by manually reviewing only a subset of candidate incidents (those with highest similarity scores) rather than all incidents. This selective approach maintains sufficient completeness for effective incident analysis while significantly improving processing speed, as the system doesn't need to manually examine every single candidate incident.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12450141B2Identification of similar incidents based on similarity scores

Publication Date: 2025.10.21 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

According to examples, an apparatus may include a processor and a memory on which are stored machine-readable instructions that, when executed by the processor, may cause the processor to receive event data for a subject incident. The processor may filter a set of candidate incidents to identify a first predefined number of candidate incidents. The first predefined number of candidate incidents may be filtered based on a respective first similarity score assigned to each of the candidate incidents. The processor may assign a respective second similarity score to each of the identified first predefined number of candidate incidents. The second similarity score may be based on common property values between the subject incident and respective candidate incidents. The processor may identify and output a second predefined number of candidate incidents among the first predefined number of candidate incidents based on the assigned second similarity score.