Adaptive Target Value Algorithm for Portable Activity Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing algorithms for determining target values for physical activity parameters, such as steps or distance traveled, fail to adapt to changes in user behavior and do not effectively consider past successes or failures in achieving goals, leading to unrealistic and unresponsive goal settings.
Innovation Solution
A computer-implemented method that calculates a target value for an upcoming time window by analyzing past data using a selected time scale, considering the user's past successes and failures, and incorporating a success factor and stability/regularity scores to adjust the goal settings dynamically, while also allowing for weighting of recent data for more accurate and realistic objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a linear moving weighted average algorithm is used to calculate target values, then the algorithm can adapt to changes in user's daily life through weighting coefficients, but it does not take into account the user's success or failure in achieving previous goals and does not detect changes in individual's daily behavior
Solution Approach 1:
The patent introduces a feedback mechanism by calculating a success factor that compares the actual parameter value with the target value from previous time windows. This success factor is then used to adjust the target value for the upcoming time window, creating a closed-loop system that learns from past performance. The feedback loop enables the algorithm to adapt to the user's actual achievement patterns rather than just relying on historical averages.
Solution Approach 2:
The algorithm performs self-adjustment by automatically modifying target values based on the calculated success factor without requiring external intervention. The system serves itself by using its own performance data to improve future target setting, making the goal-setting process autonomous and adaptive to the user's actual capabilities.
2Measurement precision
If a moving-window percentile rank algorithm is used to determine target values, then the application can suggest realistic goals based on measured physical activity, but it makes no distinction between measurement days and does not adapt to possible drastic changes in the user's daily life
Solution Approach 1:
The patent implements a dynamic target adjustment mechanism where the target value is not fixed based on historical percentiles but is continuously updated based on the success factor. The algorithm transitions from a static percentile-based approach to a dynamic adaptive approach that responds to recent performance trends, enabling it to adapt to drastic changes in the user's daily life while maintaining realistic goal setting.
Solution Approach 2:
The algorithm performs preliminary analysis by calculating the success factor based on previous time windows before determining the new target value. This preliminary assessment of past performance allows the system to proactively adjust targets in anticipation of the user's current capability level, rather than reactively adjusting after changes occur.
3Adaptability or versatility
If multiple time scales are used to retrieve data from preceding time windows, then the system can take advantage of periodic behavior in the variations of the parameter value, but it increases the complexity of data retrieval and processing
Solution Approach 1:
The patent segments the data retrieval process by dividing it into multiple time scales (e.g., short-term, medium-term, long-term windows). Each time scale retrieves data at a different granularity, allowing the system to capture periodic behaviors at various levels. This segmentation enables the algorithm to process complex periodic patterns efficiently by breaking them down into manageable temporal segments rather than analyzing all data uniformly.
Data Source
AI summary
A method for determining a target value for a parameter over an upcoming time window, the method including providing a set of data including, for each preceding time window, the value reached by the parameter and the associated target value, selecting an appropriate time scale among at least two time scales, retrieving data relating to preceding time windows based on the time scale, calculating a success factor based on the comparison between the value reached by the parameter over one or more preceding time windows and the associated target value, and determining the target value based on the success factor and the value reached by the parameter over each preceding time window of the retrieved data. The parameter can be a number of steps measured by a portable pedometer-type device worn by an individual.