Unified Linguistic Resource for Multi-Modal Input Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing multi-modal input systems for computing devices face challenges in providing a unified user experience due to recognition inconsistencies and excessive memory requirements when switching between typing, handwriting, and stroke input modes, primarily because of the need for large linguistic resources.
Innovation Solution
A system and method that optimizes the parameters of a class-based n-gram language model to provide a unified linguistic resource for multiple input types, such as handwriting and typing, to enhance recognition performance while maintaining a predetermined size, thereby reducing memory usage and improving user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate linguistic resources are used for handwriting and typing recognition, then recognition accuracy is improved, but memory usage increases excessively
Solution Approach 1:
The patent merges handwriting recognition and typing recognition into a single unified linguistic resource that processes both input types simultaneously. This consolidation eliminates the need for separate linguistic resources while maintaining recognition accuracy through a shared parameter space that adapts to both handwriting and typing patterns.
Solution Approach 2:
The unified linguistic resource is designed to serve multiple functions by handling both handwriting and typing recognition within a single system. This multi-functional approach allows the same resource to improve recognition accuracy for both input types without requiring additional memory allocation for separate resources.
2Reliability
If large linguistic resources are allocated for multi-modal input recognition, then recognition performance is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple recognition systems into a unified linguistic resource that handles both handwriting and typing. This merging reduces system complexity by eliminating redundant components while maintaining high recognition performance through a single, optimized resource that processes both input types.
3Quantity of substance
If a unified linguistic resource is used for multiple input types, then memory usage is reduced, but recognition consistency across input modes deteriorates
Solution Approach 1:
The unified linguistic resource implements local quality by having specialized processing paths for handwriting and typing inputs. Each input type receives tailored parameter adjustments and processing optimization within the unified resource, ensuring consistent recognition performance across different input modes while maintaining a single memory footprint.
Data Source
AI summary
A system, method and computer program product for use in providing a linguistic resource for input recognition of multiple input types on a computing device are provided. The computing device is connected to an input interface. A user is able to provide input by applying pressure to or gesturing above the input interface using a finger or an instrument such as a stylus or pen. The computing device has an input management system for recognizing the input. The input management system is configured to allow setting, in the computing device memory, parameters of a linguistic resource for a language model of one or more languages, and cause recognition of input to the input interface of the different input types using the linguistic resource. The resource parameters are set to optimize recognition performance characteristics of each input type while providing the linguistic resource with the pre-determined size.