Life Log Similarity Calculation Using Activity State Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in accurately comparing and analyzing their lifestyle habits due to the reliance on memory for recording information from various smart devices, leading to unreliable data and difficulty in recognizing lifestyle patterns associated with diseases like cancer, heart diseases, and hypertension.
Innovation Solution
A method and apparatus for calculating similarity among life log data by producing life log data with estimated activity states, converting it into modified life log data, and calculating similarity using activity state vectors, with options for weighted similarity based on time differences and additional information like weather and heart rate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users manually record information from smart devices by writing, then users can obtain various types of information such as position and motion state, but the reliability of recorded information deteriorates because users depend on their memory
Solution Approach 1:
The system automatically records life log data by having smart devices themselves generate and store data without requiring user intervention. Position information, motion state information, and other data are captured automatically by the devices' sensors and processors, eliminating the need for manual recording and thus ensuring high reliability while maintaining ease of operation.
2Ease of operation
If users electronically record daily life using life log, then users can easily record their daily life, but users need to directly compare multiple life logs to ascertain lifestyle habits, which is complex and time-consuming
Solution Approach 1:
The system pre-calculates and stores similarity values between life logs in advance. When users want to analyze lifestyle habits, the system retrieves pre-computed similarity data rather than requiring real-time comparison of multiple life logs. This preliminary computation significantly reduces the time needed for analysis while maintaining ease of operation.
Solution Approach 2:
The patent replaces the manual mechanical process of comparing life logs with an automated computational system. The similarity calculation unit automatically computes similarity values using algorithms that compare activity state vectors, positions, and timestamps, substituting human effort with automated processing that is both faster and more accurate.
3Measurement precision
If users directly compare multiple life logs to recognize lifestyle patterns, then users can identify habits related to diseases, but the complexity of comparison increases significantly
Solution Approach 1:
The system segments the complex comparison task into distinct components: position similarity calculation, time similarity calculation, and activity state similarity calculation. Each component is handled by a specialized unit that computes its specific metric independently. This segmentation reduces overall complexity while maintaining precise measurement of lifestyle patterns through multi-dimensional analysis.
Data Source
AI summary
Disclosed are a method and an apparatus for calculating similarity of life log data, the method including: producing, by a life log data producing unit, a plurality of life log data on a daily basis, in which at least one estimated activity state is indicated for each predetermined time section, by matching a user's position information per time period and a user's motion state information per time period with an estimated activity table in which the user's estimated activity states are defined in advance; converting, by a modified life log data producing unit, the plurality of life logs data into a plurality of modified life log data which is indicated for each merged time section made by merging a preset number of continuous time sections; and calculating, by a similarity calculating unit, life log similarity among the plurality of modified life log data by comparing the plurality of modified life log data for each merged time section.