Indoor Location Analytics Track Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current indoor analytics systems fail to accurately identify and segment location data streams into meaningful tracks, leading to poor estimates of statistics and indicators, and overlook concerns about anonymity preservation in operational environments.
Innovation Solution
A system that tracks entities in indoor environments using a hybrid localization system combining client-side and server-side technologies, with data cleaning and analytics computing modules to reconstruct tracks and compute relevant metrics without personally identifiable information, ensuring robust identification and segmentation of tracks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If location data streams are segmented into tracks using conventional methods, then track identification can be performed, but the accuracy of track identification deteriorates in noisy data environments leading to poor statistics estimates
Solution Approach 1:
The patent segments the indoor location data stream into distinct tracks by identifying unique entities and their movement patterns. The system divides the continuous data stream into discrete track segments, each representing a unique entity's journey through the indoor environment, enabling accurate tracking and analysis even in noisy conditions
Solution Approach 2:
The patent performs preliminary cleaning and processing of location data before track segmentation. By pre-processing the data to remove noise and anomalies, the system prepares the data stream in advance, making subsequent track identification more accurate and reliable
2Loss of information
If detailed location data is collected for accurate analytics, then behavior understanding improves, but anonymity preservation deteriorates
Solution Approach 1:
The patent extracts and removes personally identifiable information from the location data while retaining the behavioral patterns and movement characteristics. By separating the identifying information from the analytical information, the system preserves anonymity while maintaining the ability to perform detailed behavior analysis
Solution Approach 2:
The patent creates anonymized copies of location data that preserve movement patterns and behavioral characteristics without containing personally identifiable information. These copies are used for analytics while the original identifying data is excluded, enabling analysis without compromising anonymity
Data Source
AI summary
A system comprising: an indoor localisation system to localise a tracked entity in an indoor environment and to output an indoor location data stream comprising indoor location data representing locations assumed by the tracked entity in the indoor environment; an analytics computing system designed to receive and process the indoor location data stream from the indoor localisation system to compute entity-related analytics; wherein the analytics computing system is designed to: identify in the indoor location data stream one or more sessions, each representing a corresponding period during which a tracked entity carries out an associated activity in the indoor environment, based on an indoor environment model specifying one or more session open/close rules, and compute, for one or more identified sessions, associated track data representing a track travelled by the tracked entity in the indoor environment during an identified session, based on the indoor location data stream (208).