PREDICTIVE TEXT INPUT

• US 20150347382A1
• Filed: 05/22/2015
• Published: 12/03/2015
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: DOLFING, Jannes, RAMERTH, Brent, DAVIDSON, Douglas, BELLEGARDA, Jerome, MOORE, Jennifer, EMINIDIS, Andreas, SHAFFER, Joshua
• Granted Patent: US 9,760,559 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates

Abstract

Systems and processes for predictive text input are provided. In one example process, a text input can be received. The text input can be associated with an input context. A frequency of occurrence of an m-gram with respect to a subset of a corpus can be determined using a language model. The subset can be associated with a context. A weighting factor can be determined based on a degree of similarity between the input context and the context. A weighted probability of a predicted text given the text input can be determined based on the frequency of occurrence of the m-gram and the weighting factor. The m-gram can include at least one word in the text input and at least one word in the predicted text.

Claims

1. A method for text prediction comprising:

at an electronic device;

receiving a text input, the text input associated with an input context;

determining, using a first language model, a first frequency of occurrence of an m-gram with respect to a first subset of a corpus, wherein the first subset is associated with a first context, and wherein the m-gram includes at least one word in the text input;

determining, based on a degree of similarity between the input context and the first context, a first weighting factor to apply to the first frequency of occurrence of the m-gram; and

determining, based on the first frequency of occurrence of the m-gram and the first weighting factor, a first weighted probability of a first predicted text given the text input, wherein the m-gram includes at least one word in the first predicted text.

2. The method of claim 1, further comprising:

determining, using the first language model, a second frequency of occurrence of the m-gram with respect to a second subset of the corpus, wherein the second subset is associated with a second context;

determining, based on a degree of similarity between the input context and the second context, a second weighting factor to apply to the second frequency of occurrence of the m-gram, wherein the first weighted probability of the first predicted text given the text input is determined based on the second frequency of occurrence of the m-gram and the second weighting factor.

3. The method of claim 1, further comprising:

determining, using the first language model, a first frequency of occurrence of an (m−

1)-gram with respect to the first subset of the corpus, wherein;

the m-gram includes one or more words in the (m−

1)-gram;

the first weighted probability of the first predicted text given the text input is determined based on a first weighted frequency of occurrence of the (m−

1)-gram; and

the first weighting factor is applied to the first frequency of occurrence of the (m−

1)-gram to obtain the first weighted frequency of occurrence of the (m−

1)-gram.

4. The method of claim 1, wherein the first language model is a user language model that is built from the corpus, and wherein the corpus includes a collection of user input text received prior to receiving the text input.

5. The method of claim 1, further comprising updating the first language model using the text input.

6. The method of claim 1, further comprising:

determining, using a second language model, a probability of the first predicted text given the text input;

determining a second weighted probability of the first predicted text given the text input based on the first weighted probability of the first predicted text given the text input and the probability of the first predicted text given the text input.

7. The method of claim 6, wherein determining the second weighted probability of the first predicted text given the text input includes:

applying a third weighting factor to the first weighted probability of the first predicted text given the text input; and

applying a fourth weighting factor to the probability of the first predicted text given the text input.

8. The method of claim 1, wherein:

the first language model is built from the corpus;

the corpus includes a plurality of subsets;

each subset is associated with a context of a plurality of contexts; and

each context of the plurality of contexts is represented by one or more hierarchical context tags of the first language model.

9. The method of claim 1, wherein the first language model comprises a plurality of n-grams including the m-gram, and wherein each n-gram of the plurality of n-grams is associated with one or more hierarchical context tags and a frequency of occurrence of the n-gram with respect to a subset of the corpus.

10. The method of claim 1, wherein the first language model includes a plurality of sub-models arranged in a hierarchical context tree, and wherein each sub-model is associated with a specific context.

11. The method of claim 1, wherein the first weighted probability of the first predicted text given the text input is greater than a predetermined threshold, and further comprising:

determining, using the first language model, a frequency of occurrence of an (m+1)-gram with respect to the first subset of the corpus, wherein the (m+1)-gram includes one or more words in the m-gram; and

determining, based on the frequency of occurrence of the (m+1)-gram and the first weighting factor, a weighted probability of a second predicted text given the text input and the first predicted text, wherein the (m+1)-gram includes at least one word in the second predicted text.

12. The method of claim 1, wherein the first context includes a first application of the electronic device, and wherein the first subset includes a collection of user text that is associated with the first application.

13. The method of claim 1, wherein the first context includes a first recipient, and wherein the first subset includes a collection of user text that is directed to the first recipient.

14. The method of claim 1, wherein the first context includes a physical context determined using a sensor of the electronic device, and wherein the first subset includes a collection of user text that is associated with the physical context.

15. The method of claim 1, wherein the first context includes a time period or a location, and wherein the first subset includes a collection of user text that is associated with the time period or the location.

16. The method of claim 1, wherein the first context includes an environment, a situation, or a circumstance, and wherein the first subset includes a collection of user text that is associated with the environment, the situation, or the circumstance.

17. The method of claim 1, wherein the text input is associated with a second application of the electronic device, and wherein the input context includes the second application.

18. The method of claim 1, wherein the text input is directed to a second recipient, and wherein the input context includes the second recipient.

19. The method of claim 18, wherein the second recipient is determined based on the text input and using the first language model.

20. The method of claim 1, wherein the input context is determined using a sensor of the electronic device.

21. The method of claim 1, wherein the input context is determined from data obtained from one or more applications of the electronic device.

22. The method of claim 1, further comprising presenting the first predicted text via a user interface of the electronic device.

23. A method for text prediction comprising:

at an electronic device;

receiving a first text input, the first text input associated with a first input context;

determining, using a language model and based on the first input context, a first weighted probability of a predicted text given the first text input;

receiving a second text input, the second text input associated with a second input context, wherein the second text input is received after the first text input is received, wherein the first text input is identical to the second text input, and wherein the first input context is different from the second input context; and

determining, using the language model and based on the second input context, a second weighted probability of the predicted text given the second text input, wherein the first weighted probability is different from the second weighted probability.

24. The method of claim 23, wherein:

the language model is built from the corpus;

the corpus includes a plurality of subsets;

each subset is associated with a context of a plurality of contexts; and

each context of the plurality of contexts is represented by one or more hierarchical tags of the language model.

25. The method of claim 23, wherein:

the first text input is associated with a first application of the electronic device and the first input context includes the first application;

the second text input is associated with a second application of the electronic device and the second input context includes the second application; and

the first application is different from the second application.

26. The method of claim 23, wherein:

the first text input is directed to a first recipient and the first input context includes the first recipient;

the second text input is directed to a second recipient and the second input context includes the second recipient; and

the first recipient is different from the second recipient.

27. A non-transitory computer-readable storage medium comprising instructions for causing one or more processors to:

receive a text input, the text input associated with an input context;

determine, using a first language model, a first frequency of occurrence of an m-gram with respect to a first subset of a corpus, wherein the first subset is associated with a first context, and wherein the m-gram includes at least one word in the text input;

determine, based on a degree of similarity between the input context and the first context, a first weighting factor to apply to the first frequency of occurrence of the m-gram; and

determine, based on the first frequency of occurrence of the m-gram and the first weighting factor, a first weighted probability of a first predicted text given the text input, wherein the m-gram includes at least one word in the first predicted text.

28. A system comprising:

one or more processors;

memory;

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for;

receiving a text input, the text input associated with an input context;

determining, using a first language model, a first frequency of occurrence of an m-gram with respect to a first subset of a corpus, wherein the first subset is associated with a first context, and wherein the m-gram includes at least one word in the text input;

determining, based on a degree of similarity between the input context and the first context, a first weighting factor to apply to the first frequency of occurrence of the m-gram; and

determining, based on the first frequency of occurrence of the m-gram and the first weighting factor, a first weighted probability of a first predicted text given the text input, wherein the m-gram includes at least one word in the first predicted text.