Context-Aware String Prediction for Mobile Typing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile device typing experiences are slow and frustrating due to the lack of contextual consideration in word predictions, leading to broad or inappropriate suggestions, as they do not account for the application being used, conversation partners, location, date, time, or user mood.
Innovation Solution
A mobile device determines context based on characteristics such as the current application, conversation partners, date, time, and conversation style, generating string predictions that are tailored to the specific context, providing more accurate and relevant suggestions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If word predictions are generated by matching entered characters against a dictionary using general population probability, then the system is simple to implement, but the predictions become too broad and inappropriate for specific contexts
Solution Approach 1:
The system changes the parameters used for prediction by introducing context variables (application type, conversation partner, location, time) that modify the prediction model's behavior. Instead of using a static dictionary with fixed probabilities, the system dynamically adjusts prediction criteria based on contextual parameters, resolving the contradiction between simplicity and adaptability.
Solution Approach 2:
The prediction system is segmented into multiple context categories (e.g., different applications, different conversation partners). Each segment has its own prediction rules and vocabulary, allowing the system to handle different contexts appropriately without requiring a completely complex unified model.
2Measurement precision
If contextual information is collected and processed to generate tailored predictions, then prediction accuracy improves, but the system complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-defining context categories and associated vocabulary before actual prediction occurs. Context information is collected and processed in advance to establish the appropriate prediction model, reducing the complexity of real-time processing while maintaining high accuracy.
Solution Approach 2:
An intermediary context management layer is introduced between the input processing and prediction generation stages. This intermediary layer handles context collection, categorization, and model selection, simplifying the overall system architecture while enabling accurate contextual predictions.
3Adaptability or versatility
If a comprehensive context analysis is performed considering multiple factors, then the relevance of predictions improves, but the processing time increases
Solution Approach 1:
The system applies partial action by selecting and processing only the most relevant context factors for each prediction scenario rather than analyzing all possible context variables. This selective approach maintains prediction relevance while reducing processing time by avoiding unnecessary analysis of irrelevant context elements.
Data Source
AI summary
In a mobile device, a context is determined for the mobile device. The context is determined based on a variety of characteristics of the mobile device environment including, for example, the current application being used, any contacts that a user of the mobile device is interacting with or having a conversation with, the current date and/or time, a current topic of the conversation, a current style of the conversation, etc. Based on a set of strings associated with the determined context and user generated text, one or more string predictions are generated for the user generated text. The string predictions may be presented to the user as suggested completions of the user generated text.