Techniques for automatically selecting a natural language for configuring an input method editor at a computing device

Patent metadata

Field	Value
Publication number	US-9280537-B2
Application number	US-201314066819-A
Country	US
Kind code	B2
Filing date	Oct 30, 2013
Priority date	Oct 30, 2013
Publication date	Mar 8, 2016
Grant date	Mar 8, 2016

Abstract

A computer-implemented method can include initializing, at a computing device including one or more processors, an input method editor for composing an electronic message. The method can include receiving, at the computing device, an input from a user identifying a recipient for the electronic message. The method can include obtaining, at the computing device, language information corresponding to the recipient, the language information indicating one or more suggested natural languages for composing the electronic message. The method can include selecting, at the computing device, a natural language for composing the electronic message based on the language information to obtain a selected natural language. The method can also include configuring, at the computing device, the input method editor based on the selected natural language.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
initializing, at a computing device including one or more processors, an input method editor for composing an electronic message;
receiving, at the computing device, an input from a user identifying a recipient for the electronic message;
obtaining, at the computing device, language information corresponding to the recipient, the language information indicating one or more suggested natural languages for composing the electronic message, each suggested natural language having a probability score indicating a likelihood that its suggested natural language is appropriate for communication with the recipient, wherein the language information is obtained from at least one of a memory of the computing device, a remote server, and a search of a network;
selecting, by the computing device, a suggested natural language having a highest probability score to obtain a selected natural language for composing the electronic message;
outputting, at the computing device, a confidence indication indicative of a degree of reliability of the selected natural language, wherein the degree of reliability corresponds to the probability score of the selected natural language;
configuring, at the computing device, the input method editor based on the selected natural language to obtain a configured input method editor;
receiving, at the computing device, a touch or speech input from the user;
generating, at the computing device, the electronic message using the configured input method editor and the touch or speech input; and
transmitting, from the computing device, the generated electronic message to another computing device associated with the recipient, wherein receipt of the generated electronic message causes the other computing device to render the generated electronic message and display the rendering.

2. A computer-implemented method, comprising:
initializing, at a computing device including one or more processors, an input method editor for composing an electronic message;
receiving, at the computing device, an input from a user identifying a recipient for the electronic message;
obtaining, at the computing device, language information corresponding to the recipient, the language information indicating one or more suggested natural languages for composing the electronic message;
selecting, at the computing device, a natural language for composing the electronic message based on the language information to obtain a selected natural language;
configuring, at the computing device, the input method editor based on the selected natural language;
receiving, at the computing device, a touch or speech input from the user;
generating, at the computing device, the electronic message using the configured input method editor and the touch or speech input; and
transmitting, from the computing device, the generated electronic message to another computing device associated with the recipient, wherein receipt of the generated electronic message causes the other computing device to render the generated electronic message and display the rendering.

3. The computer-implemented method of claim 2 , wherein selecting the natural language for composing the electronic message includes automatically selecting, by the computing device, the natural language for composing the electronic message based on the language information to obtain the selected natural language.

4. The computer-implemented method of claim 2 , wherein selecting the natural language for composing the electronic message includes:
prompting, by the computing device, the user for a selection of the one or more suggested natural languages; and
receiving, at the computing device, the selection by the user of one of the one or more suggested natural languages to obtain the selected natural language.

5. The computer-implemented method of claim 2 , wherein obtaining the language information corresponding to the recipient further includes:
searching a network for the language information corresponding to the recipient when the computing device has no language information corresponding to the recipient; and
receiving the language information from a server on the network in response to the searching.

6. The computer-implemented method of claim 2 , wherein obtaining the language information corresponding to the recipient includes retrieving at least a portion of the language information from a profile of the recipient stored at a memory of the computing device.

7. The computer-implemented method of claim 6 , wherein obtaining the language information corresponding to the recipient further includes receiving at least another portion of the language information from another profile of the recipient stored at a server located remotely from the computing device.

8. The computer-implemented method of claim 2 , wherein the language information corresponds to a group of one or more users that includes the recipient.

9. The computer-implemented method of claim 2 , wherein the language information includes information indicative of a probability score for each suggested natural language, each probability score indicating a likelihood that its corresponding suggested natural language is appropriate for communication with the recipient.

10. The computer-implemented method of claim 9 , wherein the language information includes the probability scores for the suggested natural languages.

11. The computer-implemented method of claim 10 , further comprising:
storing, at the computing device, the one or more probability scores at a memory of the computing device in response to obtaining the language information; and
selectively adjusting, at the computing device, the one or more probability scores based on other electronic communication between the user and the recipient.

12. The computer-implemented method of claim 9 , further comprising calculating, at the computing device, the probability scores for the natural languages based on the language information, wherein the language information includes statistics of past usage by the user of each of the one or more suggested natural languages.

13. The computer-implemented method of claim 12 , wherein the statistics of past usage by the user of a specific suggested natural language are on a per document basis or on a per word basis.

14. The computer-implemented method of claim 9 , further comprising outputting, at the computing device, a confidence indication indicative of a degree of reliability of the selected natural language, wherein the degree of reliability corresponds to the probability score corresponding to the selected natural language.

15. The computer-implemented method of claim 14 , wherein the input method editor is a speech-to-text input method editor configured to receive speech input and to convert the speech input to text for the electronic message, and wherein the confidence indication is output at the computing device prior to receiving speech input for conversion to text by the speech-to-text input method editor.

16. The computer-implemented method of claim 2 , wherein configuring the input method editor based on the selected natural language includes at least one of:
(i) configuring a spell checker based on the selected natural language;
(ii) configuring a grammar checker based on the selected natural language;
(iii) configuring a layout of a virtual keyboard displayed by the computing device based on the selected natural language;
(iv) configuring an auto-correction dictionary based on the selected natural language;
(v) configuring an

Assignees

• Google Inc

Inventors

• Trivi Jean-Michel Roland
• Bringert Bjorn Erik

Classifications

• G06F40/40 Primary

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F17/28 Primary

  Physics · mapped topic