Predicted Ink Stroke Generation Using Semantic Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional inking applications on computing devices have limited functionality compared to text-editing applications, leading to inefficiencies and frustration during editing, which decreases productivity.
Innovation Solution
A system and method for generating predicted ink stroke information using ink-based or text-based semantics, involving a processor and memory that execute operations such as receiving ink stroke data, inputting it into trained machine-learning models, and generating indications of predicted ink strokes based on semantic context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional inking applications are used, then users can provide ink stroke information to the computing device, but the functionality is limited compared to text-editing applications, leading to inefficiency and frustration
Solution Approach 1:
The patent applies universality by enabling the inking application to perform multiple functions: it not only captures ink strokes but also converts them to text, provides predictive text suggestions, and offers predictive ink stroke completions. This multi-functionality bridges the gap between simple inking apps and full-featured text editors, allowing users to benefit from both natural writing and intelligent assistance within a single application.
Solution Approach 2:
The patent introduces intermediary components including machine learning models that act as mediators between the user's ink strokes and the final text output. These models convert ink strokes to text, generate predictive suggestions, and facilitate seamless interaction between the user's natural writing and the application's intelligent processing capabilities.
2Productivity
If predictive text suggestions are provided based on ink stroke data, then writing efficiency is improved, but additional processing time and computational resources are required
Solution Approach 1:
The patent applies preliminary action by pre-processing ink stroke data as it is being written, continuously converting strokes to text and generating predictive suggestions in real-time rather than waiting for complete input. This allows the system to prepare predictions ahead of when the user actually needs them, reducing perceived processing time.
Solution Approach 2:
The system implements skipping by providing predictive ink stroke suggestions that allow users to skip writing entire words or phrases manually. Users can select predicted strokes to complete their writing faster, effectively rushing through portions of the writing process that would otherwise require detailed manual input.
3Measurement precision
If machine learning models are used to generate predicted ink strokes, then prediction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the complex prediction task into multiple specialized machine learning models: one model converts ink strokes to text, another generates predictive text suggestions, and a third generates predictive ink stroke completions. Each model focuses on a specific aspect of the prediction process, improving overall accuracy while managing complexity through modular architecture.
Data Source
AI summary
In some examples, systems and methods for generating predicted ink strokes, using ink-based semantics, are provided. Ink stroke data may be received, the ink stroke data and a semantic context may be input into a model. From the model, one or more predicted ink strokes may be determined. Further, an indication of the one or more predicted ink strokes may be generated.