Event Detection System Using Social Media and Knowledge Graph Ontology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for notifying first responders about significant events, such as natural catastrophes or protests, face delays and inefficiencies, as they rely on human reports and may not capture the underlying causes or details of events, making it difficult to assess the situation accurately.
Innovation Solution
A system that uses social media content and real-time data feeds to detect events through a neural network-based event detector, determines the event type and sentiment, and generates recommendations for response using a knowledge graph ontology, enabling timely and informed decision-making for first responders.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a dispatch service relies on human reports to notify first responders, then the system is simple to operate, but the response time is significantly delayed
Solution Approach 1:
The system performs preliminary actions by continuously monitoring social media platforms and real-time data feeds for event indicators before actual events occur. The event detector is pre-configured with patterns and thresholds to automatically identify potential events, enabling early warning and faster response times without waiting for human reports.
Solution Approach 2:
The patent introduces social media platforms and real-time data feeds as intermediary sources between event occurrence and first responder notification. These intermediaries automatically generate and transmit event information to the dispatch service, eliminating the delay caused by waiting for human observers to contact authorities.
2Loss of information
If surveillance systems are deployed to monitor events, then real-time detection capability is improved, but the ability to capture underlying causes and event details is insufficient
Solution Approach 1:
The system achieves multi-functionality by integrating multiple data sources (social media platforms, news outlets, weather services, traffic authorities) into a single event detection framework. This universal approach allows the system to capture diverse event details including underlying causes, participant sentiments, and contextual information that traditional surveillance systems cannot obtain.
Solution Approach 2:
The patent replaces mechanical surveillance systems with an information-based detection mechanism that uses natural language processing and data analysis. Instead of relying on physical cameras and human observers, the system processes text and data from digital sources to extract event information, achieving superior detail capture without the limitations of physical surveillance.
3Measurement precision
If traditional dispatch services are used, then the system is easy to operate, but it cannot assess the situation accurately or determine appropriate responses
Solution Approach 1:
The system implements feedback mechanisms by continuously analyzing event data, determining event types and sentiments, and generating recommended responses. The dispatch service receives structured feedback including event classification, sentiment analysis results, and actionable recommendations, enabling accurate situational assessment and informed decision-making.
Solution Approach 2:
The patent transforms raw event data into structured parameters including event type classification and sentiment scores. By changing the parameters from unstructured text to standardized categories and metrics, the system enables precise situational assessment and facilitates automated response recommendation generation.
Data Source
AI summary
A system for predicting the occurrence of an event includes an event detector and a reporting processor. The event detector is configured to: receive data that defines a plurality of social media items; receive a real-time data feed; and predict the occurrence of an event based on a correlation between information in the plurality of social media items and activity associated with the real-time data feed. The reporting processor is configured to determine an event type associated with the event; identify a sentiment of the predicted event based on historical data in the real-time data feed, and generate a recommendation for preventing the occurrence of the event based on at least one of the event type and the sentiment of the predicted event. The recommendation includes a plurality of actions. The reporting processor is coupled to a knowledge graph database that corresponds to an ontology that defines one or more relationships between event types, and response types. The reporting processor determines an order of the actions of the recommendation based on the knowledge graph ontology.