17851309. GENERATING PREDICTED INK STROKE INFORMATION USING TEXT-BASED SEMANTICS simplified abstract (Microsoft Technology Licensing, LLC)
Contents
GENERATING PREDICTED INK STROKE INFORMATION USING TEXT-BASED SEMANTICS
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Steven N. Bathiche of Bellevue WA (US)
Moshe R. Lutz of Bellevue WA (US)
GENERATING PREDICTED INK STROKE INFORMATION USING TEXT-BASED SEMANTICS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17851309 titled 'GENERATING PREDICTED INK STROKE INFORMATION USING TEXT-BASED SEMANTICS
Simplified Explanation
The patent application describes systems and methods for generating predicted ink strokes based on text-based semantics. Here is a simplified explanation of the abstract:
- Ink stroke data is received and input into a first model.
- Text data corresponding to the ink stroke data is received from the first model.
- The text data and a semantic context are input into a second model.
- The second model determines a predicted ink stroke.
- An indication of the predicted ink stroke is generated.
Potential applications of this technology:
- Digital handwriting recognition and prediction systems.
- Virtual reality or augmented reality applications that require real-time ink stroke generation.
- Collaborative writing tools that can predict and generate ink strokes based on text input.
Problems solved by this technology:
- Improves the accuracy and efficiency of handwriting recognition systems.
- Enables real-time generation of ink strokes based on text input, reducing the need for manual drawing or writing.
- Enhances the user experience in digital writing and drawing applications.
Benefits of this technology:
- Provides more accurate and intuitive digital handwriting recognition.
- Saves time and effort by automatically generating ink strokes based on text input.
- Enables seamless integration of text and ink-based input in various applications.
Original Abstract Submitted
In some examples, systems and methods for generating predicted ink strokes, using text-based semantics, are provided. Ink stroke data may be received, the ink stroke data may be input into a first model, and text data may be received from the first model. The text data may correspond to the ink stroke data. The text data and a semantic context may be input into a second model. A predicted ink stroke may be determined, from the second model. Further, an indication of the predicted ink stroke may be generated.