Application Recommendation via Triggering Event Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern mobile devices with numerous applications require users to spend excessive time searching for desired apps, making it inefficient to access frequently used applications.
Innovation Solution
The system detects triggering events and uses prediction models based on contextual and historical information to suggest applications, providing access through a user interface on the lock screen or home screen, reducing the need for users to manually search for apps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If users manually search for applications amongst hundreds of available apps, then they can find the desired application, but it consumes excessive time and is inefficient
Solution Approach 1:
The system performs preliminary actions by continuously monitoring input devices for triggering events and pre-computing application recommendations based on contextual information and historical patterns before the user actually needs to access an application. When a triggering event is detected, the system has already prepared relevant application suggestions, eliminating the need for users to manually search through hundreds of applications.
Solution Approach 2:
The system provides self-service by automatically analyzing user behavior patterns, contextual data, and historical information to generate application recommendations without requiring user initiation. The system monitors itself for triggering events and autonomously presents relevant applications, making the application discovery process automatic and eliminating manual searching.
2Productivity
If the system provides application recommendations based on triggering events and contextual information, then application access is streamlined and user experience is enhanced, but the system complexity increases due to multiple prediction models and data processing requirements
Solution Approach 1:
The system segments the application recommendation process into distinct modules: triggering event detection, contextual information gathering, historical pattern analysis, prediction model selection, and recommendation presentation. Each module handles a specific aspect of the complex task, making the overall system more manageable and maintainable despite the sophistication required for accurate recommendations.
Solution Approach 2:
The system introduces intermediary components such as prediction models and contextual information processors that mediate between raw triggering events and final application recommendations. These intermediaries transform complex data into actionable insights, managing the complexity by breaking down the decision-making process into manageable transformation steps.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An event can be detected by an input device. The event may be determined to be a triggering event by comparing the event to a group of triggering events. A first prediction model corresponding to the event is then selected. Contextual information about the device specifying one or more properties of the computing device in a first context is then received, and a set of one or more applications is identified. The set of one or more applications may have at least a threshold probability of being accessed by the user when the event occurs in the first context. Thereafter, a user interface is provided to a user for interacting with the set of one or more applications.