Selective User State Sampling for Alert Mediation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in determining the optimal time to interrupt users with alerts, as they often inundate users with information, leading to decreased effectiveness, especially in stressful situations, and fail to provide high-value, user-appropriate information.
Innovation Solution
The system employs selective sampling of data to enhance model performance by inferring user interruptability based on computer activity and contextual information, using lifelong learning and selective supervision to create personalized models that determine the cost of interruption and expected utility, thereby guiding alert mediation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the system provides alerts frequently to ensure information delivery, then information coverage is improved, but user productivity deteriorates due to excessive interruptions
Solution Approach 1:
The patent replaces manual judgment of interruptability with an automated machine learning model that analyzes computer activity data and contextual information to predict user interruptability, thereby substituting mechanical human decision-making with an automated system that balances information delivery and productivity
Solution Approach 2:
The system dynamically adjusts alert delivery parameters based on predicted user state by changing the timing and frequency of alerts, transforming static alert schedules into adaptive parameter adjustments that respond to real-time user conditions
2Measurement precision
If the system collects comprehensive data to improve model accuracy, then model performance is improved, but system complexity increases
Solution Approach 1:
The patent segments the data collection process into distinct modules: computer activity data collection, contextual information gathering, and model training components, allowing comprehensive data acquisition while maintaining manageable system complexity through modular architecture
Solution Approach 2:
The system introduces an intermediary alert mediation service that coordinates between data collection components, model inference, and alert delivery, simplifying the overall system architecture by providing a central coordination layer that manages the complexity of comprehensive data processing
Data Source
AI summary
Model enhancement architecture that provides selective sampling of data to enhance model performance where model testing is deemed to be poor. Sampling can include direct interaction with the user while the user is logged-in to the computing system. The system can be used to infer a computer user's current interruptability based on computer activity and relevant contextual information. Personalized models can then be created that are utilized to determine a cost of interruption and an expected utility. A modeling component is provided that builds and runs models based on data. The data can be any type of data such as application data, user profile data, tracking data, user state data, user situation data, and so on. A sampling component samples the data based on failure analysis of the model. The architecture is a utility-centric approach to gathering data to maximally enhance the current model.