Reasoning Engine Activity Timeline Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In complex sensor networks, such as those used in security systems, automatically detecting and analyzing activities from sensor data is challenging due to the intricate relationships between different activities, making it difficult for users to piece together a coherent timeline of events.
Innovation Solution
A deep fusion reasoning engine (DFRE) is employed to detect activities from sensor data, identify relevant preceding activities, and make inferences about their relationships, providing an activity timeline that displays the detected activities, relevant precedents, and inferred connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine learning is used to automatically detect activities from sensor data, then detection automation is improved, but the ability to understand relationships between activities and construct coherent timelines deteriorates
Solution Approach 1:
A reasoning engine is introduced as an intermediary component between the machine learning activity detector and the user interface. This reasoning engine consumes detected activities as input and generates activity timelines with inferred relationships as output, thereby preserving and reconstructing the relationship information that was lost in the automated detection process.
2Loss of information
If traditional manual monitoring of sensor data is used, then activity relationship understanding is improved, but monitoring efficiency and productivity deteriorate
Solution Approach 1:
The system segments the monitoring task into two distinct components: (1) a machine learning component that automatically detects individual activities from sensor data, and (2) a reasoning engine component that constructs activity timelines and infers relationships. This segmentation allows each component to specialize, maintaining high productivity while recovering relationship information.
3Adaptability or versatility
If complex sensor networks with multiple sensors are deployed, then detection coverage is improved, but system complexity and difficulty of analysis increase
Solution Approach 1:
The reasoning engine serves as an intermediary that simplifies the complex output from multiple sensors by organizing detected activities into coherent timelines with inferred relationships. This intermediary layer presents a simplified, structured view to users, reducing the perceived complexity despite comprehensive multi-sensor coverage.
Data Source
AI summary
In one embodiment, a device detects a particular activity from sensor data generated by one or more sensors in a sensor network. The device identifies, using a semantic reasoning engine, relevant preceding activities to the particular activity that are relevant to the particular activity. The device makes, using the semantic reasoning engine, an inference about the relevant preceding activities and the particular activity. The device provides an activity timeline for display that indicates the particular activity, the relevant preceding activities, and the inference about the relevant preceding activities and the particular activity.