Co-movement Categorization Using Life-Logging Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current life-logging technologies struggle to accurately analyze and categorize co-movement between individuals using bio-signals and behavior information, limiting the effectiveness of social networking services based on such data.
Innovation Solution
A co-movement-based automatic categorization system and method that processes image data to detect movement patterns, generates co-movement and non-co-movement clusters, and issues social identifications by calculating standard deviations and duration times to form accurate social networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If life-logging technologies use bio-signals and behavior information to analyze co-movement, then social networking service capability is improved, but measurement precision of co-movement is insufficient
Solution Approach 1:
The patent segments co-movement analysis into multiple dimensions: spatial co-movement (position, distance, orientation), temporal co-movement (synchronization, duration, frequency), and interaction intensity (contact frequency, interaction type). This segmentation allows precise measurement of each aspect separately while maintaining comprehensive social networking service capability.
Solution Approach 2:
The patent introduces multiple analytical dimensions beyond traditional bio-signal analysis, including spatial coordinates (x, y, z positions), temporal parameters (time stamps, duration, frequency), and interaction categories (physical contact, proximity, synchronized movement). This multi-dimensional approach significantly improves measurement precision while preserving service versatility.
2Measurement precision
If the system processes image data to detect movement patterns and generate co-movement clusters, then co-movement detection accuracy is improved, but device complexity increases
Solution Approach 1:
The system segments the complex image processing task into distinct modules: image data reception unit, movement pattern detection unit, co-movement determination unit, cluster generation unit, and duration calculation unit. Each module handles a specific aspect of analysis, improving detection accuracy while managing complexity through modular design.
Solution Approach 2:
The patent introduces intermediate data structures and processing layers between raw image data and final co-movement conclusions. Movement patterns are extracted as intermediate representations, then transformed into co-movement clusters, which are further processed into duration metrics. These intermediaries simplify the overall processing complexity while maintaining high detection accuracy.
3Measurement precision
If the system calculates standard deviation and duration time for each co-movement cluster, then categorization precision is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary calculations of standard deviation and duration time as clusters are being formed, rather than computing them after all data is processed. This allows categorization to proceed with pre-computed metrics, reducing overall processing time while maintaining precision.
Solution Approach 2:
The patent implements continuous processing where image data reception, movement detection, cluster generation, and statistical calculation occur in an ongoing pipeline rather than discrete batch operations. This continuous action eliminates idle time between processing stages, maintaining high categorization precision without excessive time loss.
Data Source
AI summary
Provided is a co-movement-based automatic categorization method, which includes: receiving image data created by photographing a plurality of subjects; detecting movement data including information on subjects' behaviors from the image data; determining whether or not co-movement between the subjects has been done during each predetermined time interval, and generating co-movement clusters in synchronized time sections, and non-co-movement clusters in desynchronized time sections depending on results of determination; if the duration time of a co-movement cluster is shorter than a standard co-movement duration time, converting the co-movement cluster to a non-co-movement cluster; categorizing the co-movement clusters by grouping a plurality of co-movement clusters existing in the same timeslot into one group; and forming a social network with a co-movement cluster group or a single co-movement cluster, and issuing a social identification to the social network.