Semantic Ticket Hashing for Duplicate Incident Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems face challenges in efficiently and automatically detecting duplicate incident tickets, leading to unnecessary effort and resource consumption in identifying and resolving issues that have already been addressed.

Innovation Solution

Implementing a semantic hashing technique to create a hash function on incident ticket descriptive text, mapping it to clusters in a condensed hash database, and using machine learning to identify semantically similar tickets, thereby automating the detection of duplicates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual determination of duplicate tickets is performed, then detection accuracy may be maintained, but time consumption and resource usage increase significantly

Engineering Contradiction:

Improveduplicate detection accuracyVSAvoidtime to investigate tickets

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical review of tickets with an automated semantic hashing system. The system applies hash functions to ticket descriptions and compares semantic representations automatically, eliminating the need for human investigators to manually review each ticket for duplicates while maintaining detection accuracy through sophisticated semantic analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces semantic hashes as an intermediary representation between the original ticket text and the comparison process. By converting ticket descriptions into compact semantic hash values, the system enables efficient automated comparison without requiring direct human intervention, thus reducing time loss while preserving detection capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If semantic hashing is applied to all tickets, then duplicate detection efficiency improves, but computational resources and storage requirements increase

Engineering Contradiction:

Improveduplicate detection efficiencyVSAvoidstorage space for hash database

Core Design Contradiction:

ProductivityVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential semantic features of ticket descriptions into compact hash values, storing only these condensed representations in the database rather than full text. This extraction approach enables efficient duplicate detection while minimizing storage requirements by keeping only the most critical identifying characteristics of each ticket.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the original text data into a different parameter representation (semantic hashes) that occupies less space while retaining the essential information needed for duplicate detection. By changing the data representation from full text to compact hash values, the system achieves both improved efficiency and reduced storage requirements.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If traditional text matching is used, then system complexity remains low, but the ability to detect semantically similar tickets decreases

Engineering Contradiction:

Improvesystem implementation complexityVSAvoidsemantic similarity detection

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces simple string matching mechanics with semantic hashing that captures the meaning and intent of ticket descriptions. This substitution enables the system to detect semantically similar tickets even when the exact wording differs, significantly improving detection precision while the hashing mechanism keeps the implementation relatively straightforward.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20260044532A1Semantic hash machine learning for duplicate ticket identification and alerting

Publication Date: 2026.02.12 SAP SE

AI summary

A system associated with incident tickets includes an incident ticket data store with electronic records for incident tickets (each including a ticket identifier and descriptive text). An incident ticket framework performs a hash function on the descriptive text to create a semantic descriptive text hash based on a semantic hashing technique. The semantic descriptive text hash is mapped to a cluster of similar incident tickets and the incident ticket identifier and mapped cluster are stored in a condensed hash database. A new incident ticket, including new incident ticket descriptive text, is received from a reporter. A hash function is performed on the new incident ticket descriptive text to create a semantic descriptive text hash using the same semantic hashing technique. Semantically similar incident tickets can then be determined based on clusters in the condensed hash database.