Incident Similarity Scoring With Two-Stage Candidate Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying similar incidents in large datasets of event data is challenging due to the large number of incidents and associated event data, making manual identification time-consuming and resource-intensive, and it's difficult to determine the relevance of incidents from common entities.
Innovation Solution
A processor filters a set of candidate incidents based on first similarity scores calculated from predefined types of properties and probability values, forming a candidate incidents pool, and assigns second similarity scores to identify a subset of incidents that are most similar to a subject incident.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of similar incidents is performed, then accuracy in identifying relevant incidents is improved, but time consumption and resource usage increase significantly
Solution Approach 1:
The patent replaces manual mechanical identification processes with an automated computer-based system that calculates similarity scores using predefined properties and probability values, eliminating the need for human analysts to manually review and compare incidents while maintaining accurate identification through computational methods
Solution Approach 2:
The system performs self-service by automatically comparing incidents against each other using calculated similarity scores, where the computer system independently identifies similar incidents without requiring human intervention, thereby reducing time consumption while maintaining accuracy through algorithmic comparison
2Measurement precision
If all candidate incidents are reviewed to ensure completeness, then identification accuracy is improved, but computational load and processing time increase
Solution Approach 1:
The patent segments the incident review process into two stages: first filtering incidents based on predefined properties to create a candidate pool, then calculating similarity scores only for incidents in this reduced pool. This segmentation reduces the computational burden while maintaining accuracy by ensuring thorough review of filtered candidates rather than all possible incidents
Solution Approach 2:
The system performs preliminary filtering action by pre-establishing predefined properties and probability values before incident comparison, and by preliminarily filtering incidents into a candidate pool before full similarity analysis. This preliminary action reduces the scope of detailed analysis while maintaining comprehensive coverage of relevant incidents
3Measurement precision
If similarity comparison is performed on all incident properties, then identification accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent applies local quality by focusing similarity comparison on specific predefined properties that are most relevant to incident identification, rather than uniformly analyzing all incident properties. The system calculates probability values for each predefined property and weights them accordingly, concentrating computational resources on the most discriminative properties while maintaining accurate identification
Data Source
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.