System and method for inputting text into electronic devices
AssigneeTouchtype Limited
InventorsBenjamin William Medlock, Jonathan Paul Reynolds
Life of this patent
Estimating the term…
Abstract
The present invention provides a system comprising a user interface configured to receive text input by a user, a text prediction engine comprising a plurality of language models and configured to receive the input text from the user interface and to generate concurrently text predictions using the plurality of language models, and wherein the text prediction engine is further configured to provide text predictions to the user interface for display and user selection. An analogous method and an interface for use with the system and method are also provided.
Claims26
A system comprising:
- a processor;
- and
- memory storing instructions that, when executed by the processor, configure the processor to:
- receive text input by a user, wherein the text input by the user corresponds to a sequence of one or more characters input by the user via a keyboard;
- generate independently, by a plurality of different language models, a plurality of text predictions from the received text input, wherein each of the plurality of text predictions comprises a term and an associated probability, wherein the plurality of different language models are pruned by comparing a sequence of terms stored in one language model among the plurality of different language models to a sequence of terms stored in one or more other language models among the plurality of different language models and retaining most probable duplicate or multiple entries by removing less probable duplicate or multiple entries from the plurality of different language models;
- combine the plurality of text predictions into final text predictions;
- and
- output at least one of the final text predictions.
A method for processing user text input and generating text predictions, comprising;
- receiving text input, wherein the text input corresponds to a sequence of one or more characters input via a keyboard;
- generating independently, by a plurality of different language models, a plurality of text predictions from the received text input, wherein each of the plurality of text predictions comprises a term and an associated probability, wherein the plurality of different language models are pruned by comparing a sequence of terms stored in one language model among the plurality of different language models to a sequence of terms stored in one or more other language models among the plurality of different language models and retaining most probable duplicate or multiple entries by removing less probable duplicate or multiple entries from the plurality of different language models;
- combining the plurality of text predictions into final text predictions;
- and
- outputting at least one of the final text predictions.
Dependencies are inferred from the claim text.