Jannes G. Dolfing
29Patents
12h-index
44Co-inventors
81Inventor score
Filing activity: Oct 3, 1997 → Nov 22, 2021
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US8706472B2 | Method for disambiguating multiple readings in language conversion | Physics | 349 | Active |
| US10200824B2 | Systems and methods for proactively identifying and surfacing relevant content on a touch-sensitive device | Physics | 159 | Active |
| US6317507A | Signal verification device | Physics | 44 | Expired |
| US10097973B2 | Systems and methods for proactively identifying and surfacing relevant content on a touch-sensitive device | Electricity | 36 | Active |
| US6084985A | Method and apparatus for on-line handwriting recognition based on feature vectors that use aggregated observations derived from time-sequential frames | Physics | 36 | Expired |
| US6421640B1 | Speech recognition method using confidence measure evaluation | Physics | 32 | Expired |
| US9465985B2 | Managing real-time handwriting recognition | Physics | 27 | Active |
| US10757552B2 | System and method for proactively identifying and surfacing relevant content on an electronic device with a touch-sensitive display | Electricity | 26 | Active |
| US9495620B2 | Multi-script handwriting recognition using a universal recognizer | Physics | 23 | Active |
| US11070949B2 | Systems and methods for proactively identifying and surfacing relevant content on an electronic device with a touch-sensitive display | Physics | 21 | Active |
| US10366158B2 | Efficient word encoding for recurrent neural network language models | Physics | 19 | Active |
| US10521466B2 | Data driven natural language event detection and classification | Physics | 17 | Active |
| US10474753B2 | Language identification using recurrent neural networks | Physics | 12 | Active |
| US9760559B2 | Predictive text input | Physics | 11 | Active |
| US9898187B2 | Managing real-time handwriting recognition | Physics | 10 | Active |
| US9934430B2 | Multi-script handwriting recognition using a universal recognizer | Physics | 8 | Active |
| US11010550B2 | Unified language modeling framework for word prediction, auto-completion and auto-correction | Physics | 7 | Active |
| US11016658B2 | Managing real-time handwriting recognition | Physics | 7 | Active |
| US11182069B2 | Managing real-time handwriting recognition | Physics | 6 | Active |
| US10346035B2 | Managing real-time handwriting recognition | Physics | 6 | Active |
| US10827330B2 | Systems and methods for proactively identifying and surfacing relevant content on an electronic device with a touch-sensitive display | Electricity | 5 | Active |
| US8977059B2 | Integrating feature extraction via local sequential embedding for automatic handwriting recognition | Physics | 4 | Active |
| US10735905B2 | Systems and methods for proactively identifying and surfacing relevant content on an electronic device with a touch-sensitive display | Physics | 3 | Active |
| US10657328B2 | Multi-task recurrent neural network architecture for efficient morphology handling in neural language modeling | Physics | 2 | Active |
| US10579257B2 | Managing real-time handwriting recognition | Physics | 1 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.