Universal text input

• US 8,738,356 B2
• Filed: 05/18/2011
• Issued: 05/27/2014
• Est. Priority Date: 05/18/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Suzuki, Hisami, Dendi, Vikram, Quirk, Christopher Brian, Choudhury, Pallavi, Gao, Jianfeng, Chalabi, Achraf
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US13/110,484
• Publication Number:
  US 20120296627A1
• Time in Patent Office: 1,105 Days
• Field of Search: 704 1- 10, 704/251, 704/255, 704/257, 704/270, 704/235, 707/767, 715/863, 715/262
• US Class Current: 704/2
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

The universal text input technique described herein addresses the difficulties of typing text in various languages and scripts, and offers a unified solution, which combines character conversion, next word prediction, spelling correction and automatic script switching to make it extremely simple to type any language from any device. The technique provides a rich and seamless input experience in any language through a universal IME (input method editor). It allows a user to type in any script for any language using a regular qwerty keyboard via phonetic input and at the same time allows for auto-completion and spelling correction of words and phrases while typing. The technique also provides a modeless input that automatically turns on and off an input mode that changes between different types of script.

Claims

1. A computer-implemented process for speeding up typing, comprising:

using a computing device for;

receiving text in the form of a phonetic string from a user creating a document;

determining a context of the input phonetic string;

converting the input phonetic string into a supported language and a supported script using the determined context;

generating a list of candidates in the supported language and the supported script to replace the phonetic string using the determined context of the input phonetic string, while performing spelling correction, word auto-completion, next word prediction and automatic script changing based on the context of the input string;

ranking the candidates in the list of candidates;

sending the ranked list of candidates back to the user;

the user selecting one of the candidates on the ranked list of candidates to replace the input phonetic string; and

replacing the input phonetic string with the user-selected candidate in the supported language and the supported script in the text of the document the user is creating.

2. The computer-implemented process of claim 1, wherein the context of the phonetic string is determined based on phonetic strings previously entered by the user and other users.

3. The computer-implemented process of claim 1, wherein the candidate list is generated by using at least one lexicon or at least one language model.

4. The computer-implemented process of claim 1, wherein the lexicon maps the user input string with output candidates, with or without associated probabilities.

5. The computer-implemented process of claim 1, wherein generating a list of candidates and ranking the candidates further comprises using a source channel model.

6. The computer-implemented process of claim 1, wherein a language model ranks the list of candidates by their likelihood of being what the user intends to type with the input phonetic string.

7. The computer-implemented process of claim 1, further comprising using the candidate selected by the user to improve the creation of the list of candidates for future user input.

8. The computer-implemented process of claim 1, further comprising using the candidate selected by the user to improve the ranking of the list of candidates for future user input.

9. The computer-implemented process of claim 1, further comprising using a user ID and user session ID is to correlate the input phonetic string with the particular user and user session.

10. A computer-implemented process for increasing the speed of text entry, comprising:

using a computing device for;

receiving text in the form of a phonetic string;

determining the language and the script of the phonetic string;

generating a list of candidates in the determined language and the determined script to replace the phonetic string, while performing automatic script changing when a user changes from typing the text in a first script to typing text in a second script;

ranking the candidates in the list of candidates;

sending the ranked list of candidates back to the user;

the user selecting one of the candidates on the ranked list of candidates to replace the input phonetic string; and

replacing the input phonetic string with the user-selected candidate in the text the user is typing.

11. The computer-implemented process of claim 10, further comprising determining the language of the first script and the language of the second script before the user changes from typing in the first script to the second script.

12. The computer-implemented process of claim 10, wherein the list of candidates is determined by the context of the input phonetic string and phonetic strings previously entered by the user.

13. The computer-implemented process of claim 10, further comprising displaying the ranked candidates with additional information comprising translation of words and usage examples.

14. The computer-implemented process of claim 10, wherein the lexicon and the language model are scalable to accommodate differences in user input devices.

15. The computer-implemented process of claim 10, wherein a language model ranks the list of candidates by their likelihood of being what the user is attempting to type with the input phonetic string.

16. The computer-implemented process of claim 10, further comprising correcting spelling errors while generating the list of candidates by using at least one spelling correction lexicon and any associated ranking model.

17. The computer-implemented process of claim 10, further comprising predicting the next word or words while generating the list of candidates by using at least one next word prediction lexicon and an associated ranking model.

18. The computer-implemented process of claim 10, further comprising performing word auto completion while generating the list of candidates by using at least one auto completion lexicon and any associated ranking model.

19. The computer-implemented process of claim 10, wherein the input text in the form of a phonetic string is received from the user as a verbal command and is converted to text.

20. A system for speeding up the input of text displayed on the display of a computing device, comprising:

a general purpose computing device;

a computer program comprising program modules executable by the general purpose computing device, wherein the computing device is directed by the program modules of the computer program to,

provide a user interface for a user to input text in the form of a phonetic string for the creation of a document;

generate a ranked list of candidates to replace the phonetic string while simultaneously performing spelling correction, word auto-completion, next word prediction and automatic script changing;

display the generated list of candidates to the user; and

allow the user to select a candidate from the list of candidates to replace the phonetic string in text in the document the user is typing.