SaaS Session Prediction for Cloud Application Launch
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud-based environments, users face difficulties in efficiently accessing and launching numerous shared applications, as they are typically presented with overwhelming menus requiring manual scrolling, which hampers productivity and user experience.
Innovation Solution
A system that records user interactions with shared applications, determines launch probabilities based on activation history, and displays a second menu featuring applications with high launch probabilities, either in a dedicated window or as a floating overlay, to streamline access and enhance user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If users are presented with all available shared applications in a menu, then users have access to all applications, but users spend excessive time manually scrolling and searching for applications
Solution Approach 1:
The system performs preliminary action by analyzing historical application launch data and pre-determining launch probabilities for applications before the user needs to access them. This allows the system to pre-sort and prioritize applications in the menu, so that when the user logs in, the most likely applications to be needed are already positioned at the top of the list, eliminating the need for manual scrolling through all applications.
Solution Approach 2:
The system implements self-service by automatically learning from user behavior patterns and autonomously generating personalized application recommendations. The system monitors and records which applications users launch most frequently and in what sequences, then uses this data to automatically sort and prioritize applications in the launch menu without requiring user intervention or manual configuration.
2Measurement precision
If the system records and analyzes user interaction data to determine launch probabilities, then application launch accuracy improves, but system complexity increases
Solution Approach 1:
The system applies feedback by continuously monitoring actual user application launch behavior and comparing it against predicted launch probabilities. This feedback loop allows the system to refine its prediction algorithms over time, improving accuracy by learning from real user interactions. The system records which applications users actually launch based on the predicted order and uses this information to adjust future predictions.
Solution Approach 2:
The system performs self-service by automatically collecting, storing, and analyzing user interaction data without requiring external intervention. The system maintains its own database of application launch histories and independently processes this data to generate personalized recommendations, eliminating the need for complex external data collection systems or manual configuration.
3Productivity
If the system displays a simplified menu with high-probability applications only, then application access speed improves, but users may miss less frequent applications
Solution Approach 1:
The system segments the application menu into distinct sections: a primary section displaying high-probability applications that users are most likely to need, and a secondary section containing other available applications. This segmentation allows the system to present the most relevant applications prominently while still providing access to less frequent applications, balancing speed of access with completeness of the application list.
Solution Approach 2:
The system implements dynamics by making the menu display adaptive and changeable based on user behavior patterns. The application sorting and prioritization dynamically adjusts over time as the system learns from user interactions, allowing the menu to evolve and adapt to changing user needs while maintaining both speed and completeness of application access.
Data Source
AI summary
A computing device may include a memory and a processor cooperating with the memory to record data indicative of interactions with shared applications following logons to the computing device, with the data including a number of times and a sequential order of the interactions. The processor may be further configured to determine probabilities of launching the shared applications following a next logon to the computing device from the recorded data, and following the next logon, display shared applications on the display based on the determined probabilities.