Action Set Ranking System for Event Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current smartphone and desktop applications lack effective techniques for optimizing action set selection for users based on their needs and previous activities while traveling to an event, as existing suggestions often rely on tagged locations or advertisements rather than user-specific preferences.
Innovation Solution
A computer program product and method that ranks action sets for events by calculating action values and event weights, using machine learning to adjust these weights and values based on user feedback, thereby optimizing action set selection and presentation to users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If action suggestions are based on tagged locations or advertisements, then the system is simple to implement, but the suggestions do not align with user-specific preferences and needs
Solution Approach 1:
The system performs preliminary actions by maintaining action event weights and values in advance, calculating ranks for action sets before the user needs them, and using machine learning to pre-adjust these weights and values based on historical user feedback. This allows the system to be complex in preparation but simple and personalized in execution.
Solution Approach 2:
The system introduces feedback mechanisms where user responses to presented action sets are recorded and used to adjust action event weights and values through machine learning. This feedback loop enables the system to continuously improve its understanding of user preferences, resolving the contradiction between simplicity and adaptability.
2Measurement precision
If multiple action sets are presented to the user, then user preference accuracy improves, but time for action set selection increases
Solution Approach 1:
The system presents only the top-ranked action sets (partial action) rather than all possible action sets, based on pre-calculated ranks that prioritize actions most likely to align with user preferences. This partial presentation maintains high preference accuracy while significantly reducing selection time compared to presenting all options.
Solution Approach 2:
The system performs preliminary ranking of action sets using maintained action event weights and values before presenting them to the user. This pre-sorting ensures that when the user views action sets, they are already ordered by relevance, minimizing the time needed for selection while maintaining accuracy.
3Reliability
If action event weights and values are continuously adjusted using machine learning, then action set relevance improves, but computational resources and processing time increase
Solution Approach 1:
The system performs machine learning adjustments of action event weights and values in advance, using historical user feedback to pre-train the ranking model. This preliminary training allows the system to make accurate relevance assessments without requiring intensive real-time computational resources during actual action set presentation.
Solution Approach 2:
The system adjusts weights and values selectively based on the specific action sets being evaluated rather than retraining the entire model for every evaluation. This partial adjustment approach maintains high relevance while minimizing computational resource consumption during operation.
Data Source
AI summary
Provided are a computer program product, system, and method for ranking action sets comprised of actions for an event to optimize action set selection. Information is maintained on actions for a plurality of events. Each action indicates an action value of the action to the user and event weights of the action with respect to a plurality of the events. A determination is made of actions sets having at least one action to perform for the event. For each determined action set, a rank of the action set is calculated as a function of the action value for each action in the action set and an event weight of the action with respect to the event. At least one action set is presented to the user for consideration. In response to receiving user feedback, an adjusted rank is set for at least one of the presented action sets.