Abnormal Event Prediction Using Semantic Sequencing and Knowledge Graphs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional platforms for predicting and diagnosing abnormal signals or events operate in context-free domains, leading to inefficient resource utilization in resolving occurrences.

Innovation Solution

A computer-implemented platform for real-time prediction and explanation of abnormal events using semantic sequencing to provide context, which involves receiving data from domain-specific sources, determining similarity scores, and providing actions based on historical cases and knowledge graphs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional context-free prediction platforms are used, then the system structure is simple, but resource utilization efficiency deteriorates

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

A knowledge graph is introduced as an intermediary component that connects event data with domain context. The knowledge graph stores semantic relationships between entities (e.g., aircraft, airports, weather conditions) and enables the system to retrieve relevant contextual information when analyzing abnormal events, thereby improving resource utilization efficiency without creating an overly complex system architecture

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments the prediction and diagnosis process into distinct modules: event detection, context retrieval from knowledge graph, similarity calculation with historical cases, and resolution action generation. This segmentation allows each component to focus on specific tasks, improving overall efficiency while maintaining manageable system complexity

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If context-free diagnosis is used, then the processing speed is fast, but the accuracy of abnormal event diagnosis deteriorates

Engineering Contradiction:

Improvediagnosis accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The knowledge graph is pre-populated with domain-specific contextual information and relationships before actual diagnosis occurs. When an abnormal event is detected, the system can immediately query relevant context from the pre-built knowledge graph without time-consuming real-time analysis, thereby maintaining fast processing speeds while achieving accurate context-aware diagnosis

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a simplified representation of historical cases with their contextual information and stores them in a searchable format. When diagnosing current events, the system copies relevant historical patterns and compares them with current event features, enabling accurate diagnosis by leveraging past experiences without reprocessing entire historical datasets

Inventive Principle:

Principle #26Copying

3Loss of information

If semantic sequencing with context is applied, then the explanation quality improves, but the computational resources required increase

Engineering Contradiction:

Improvecontext information retentionVSAvoidcomputational resource consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

The system applies semantic sequencing and context analysis locally only to the specific portion of the knowledge graph relevant to the current event. By querying the knowledge graph for context information related to specific entities involved in the abnormal event, the system retains important contextual information while avoiding the computational expense of processing the entire knowledge graph

Inventive Principle:

Principle #3Local quality

4Reliability

If historical cases are analyzed in detail, then the resolution action accuracy improves, but the time required for analysis increases

Engineering Contradiction:

Improveresolution action reliabilityVSAvoidanalysis time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system analyzes only the necessary portions of historical cases that are most relevant to the current event. By calculating similarity scores between event features and historical case features, the system identifies and analyzes only the top-k most similar historical cases rather than processing all historical data, thereby maintaining reliable resolution actions while significantly reducing analysis time

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10824647B2Real-time prediction and explanation of sequences of abnormal events

Publication Date: 2020.11.03 ACCENTURE GLOBAL SOLUTIONS LTD

AI summary

Implementations are directed to providing a semantic sequence based on a sequence associated with the event, and context data provided from a knowledge graph, receiving a set of cases associated with at least one entity included in the event, the set of cases including previous instances of events, and actions performed to resolve the previous instances of events, defining a sub-set of cases from the set of cases based on the context data, for each case of the sub-set of cases, determining a similarity score, each similarity score representing a degree of similarity between the event, and a case of the sub-set of cases, determining an explanation based on features of cases in the sub-set of cases based on the context data, and providing one or more actions based on actions of cases in the sub-set of cases.