Suggestion Engine for Mobile App and Recipient Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern mobile devices with numerous communication applications face challenges in efficiently allowing users to select the appropriate application and recipient for sharing content, as users often need to perform multiple actions to find the desired option among many contacts and applications.
Innovation Solution
A suggestion engine uses historical user interactions and contextual data to generate pattern models, which are filtered and input into a machine learning model to provide ranked suggestions for applications and recipients on the user interface, reducing the need for additional user actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple communication applications and contacts are stored on the mobile device, then the device becomes more useful and versatile, but it becomes difficult and time consuming for the user to find and select a desired recipient
Solution Approach 1:
The system performs preliminary action by pre-processing historical interaction data to create a pattern model that predicts user preferences before the user needs to make a selection. The machine learning model continuously learns from past behaviors and prepares ranked lists of suggested recipients and applications, so when the user needs to communicate, the most likely options are already organized and ready for quick selection.
Solution Approach 2:
The system implements self-service by automatically analyzing user interaction patterns and generating personalized suggestions without requiring manual input. The machine learning model autonomously processes historical data, identifies patterns, and creates tailored recommendations for recipients and applications based on the user's individual behavior patterns, eliminating the need for users to manually search through contacts.
2Adaptability or versatility
If numerous applications are provided for interacting with people, then the mobile device becomes more useful, but the user interface becomes more complex and requires additional actions for selection
Solution Approach 1:
The system introduces an intermediary layer in the form of a machine learning-based suggestion engine that mediates between the user's communication needs and the available applications/contacts. This intermediary automatically processes historical interactions, contextual data, and pattern recognition to generate intelligent recommendations, serving as a bridge that simplifies the selection process without reducing the underlying versatility of the system.
Solution Approach 2:
The system implements feedback mechanisms where user selections and interaction patterns are continuously fed back into the machine learning model to refine and update the pattern model. This feedback loop enables the system to learn from actual user behavior and improve its suggestions over time, making the interface increasingly intuitive and easier to operate while maintaining full functionality.
Data Source
AI summary
Systems and methods can suggest applications for use by a user of a computing device. The suggestions can be provided on a user interface for the user to select. A suggestion engine can use historical user interactions and contextual data to derive features for a machine learning mode. The machine learning model can determine which application to suggest according to the current context. Multiple models, such as a pattern model and a heuristics model, may be user to generate features for the machine learning model based in user interactions.