System and method for inputting text into electronic devices

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;
• generate at least one first text prediction, each first text prediction comprising a first term and a first associated probability value, based on the text input by a user, using a first language model;
• generate at least one second text prediction, each second text prediction comprising a second term and a second associated probability value, based on the text input by a user, using a second language model;
• generate at least one weighted probability of the at least one first text prediction from the first language model using a first context-specific weighting factor, wherein the context-specific weighting factor is dependent on previous user's use of that language model when inputting text for that context;
• and
• generate final text predictions from the at least one weighted prediction generated from the first language model and the at least one second text prediction generated from the second language model.

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;
• generate at least one first text prediction, each first text prediction comprising a first term and a first associated probability value, based on the text input by the user, using a general language model;
• generate at least one second text prediction, each second text prediction comprising a second term and a second associated probability value, based on the text input by the user, using one of a plurality of recipient-specific dynamic language models, wherein each recipient-specific dynamic language model is trained on text sent to that recipient;
• and
• combine the at least one first text prediction generated from the general language model and the at least one second text prediction from the one of the plurality of recipient-specific dynamic language models.

A non-transient computer readable medium containing program instructions which, when executed by a processor, configure the processor to:

• generate at least one first text prediction, each first text prediction comprising a first term and a first associated probability value, based on the text input by the user, using a general language model;
• generate at least one second text prediction, each second text prediction comprising a second term and a second associated probability value, based on the text input by the user, using one of a plurality of recipient-specific language models, wherein each recipient-specific language model is trained on text sent to that recipient;
• and
• combine the at least one first text prediction generated from the general language model and the at least one second text prediction from the one of a plurality of recipient-specific language models.

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;
• generate at least one first text prediction, each first text prediction comprising a term and a first associated probability value, based on the received text input, using a general language model;
• generate at least one second text prediction, each second text prediction comprising a second term and a second associated probability value, based on the received text input, using a context-specific language model, wherein the context-specific language model is trained on user input text inputted from a specific location;
• combine the at least one first text prediction generated using the general language model and the at least one second text prediction generated using the context-specific language model;
• and
• output one or more of the combined text predictions.