IME Input Scope Prediction for Mobile Text Entry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Handheld mobile devices with small input controls and displays face challenges in user experience due to limited input devices, making manual input cumbersome and time-consuming, which existing text prediction methods only partially address.
Innovation Solution
An input method editor (IME) system that provides candidates based on a prediction model and input scope values associated with the input interface, storing entered strings with input scope values to predict future inputs, applicable across various input types and languages, including text, handwriting, and speech.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If text prediction methods are implemented, then the amount of manual input required is reduced, but the complexity of the input system increases
Solution Approach 1:
An input method editor (IME) is introduced as an intermediary component between the user and the application. The IME captures input scope values from the application, stores them associatively with entered strings, and uses them to refine candidate suggestions. This mediator handles the complexity of context-aware prediction internally while presenting a simple interface to the user, resolving the contradiction between improved productivity and increased system complexity.
2Measurement precision
If context-aware prediction is used to improve accuracy, then more information about input context must be processed and stored
Solution Approach 1:
Instead of storing comprehensive context information for all possible inputs, the system stores input scope values locally and associatively with specific entered strings. Each string is enhanced with relevant context metadata (input scope values) that is stored efficiently in a data structure. This approach provides high prediction accuracy for relevant contexts while minimizing unnecessary data storage, resolving the contradiction between precision and quantity.
Data Source
AI summary
Embodiments are configured to provide one or more candidates based in part on an input identifier associated with an input interface. In an embodiment, a system includes an input method editor (IME) that can be configured to provide one or more candidates based in part on a prediction model and one or more input scope values associated with an input interface. The IME can also operate to store an entered string including one or more associated input scope values to a storage component. The stored information can be used when suggesting candidates.