Context based word prediction

• US 7,912,700 B2
• Filed: 02/08/2007
• Issued: 03/22/2011
• Est. Priority Date: 02/08/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Davis, Peter, Morimoto, Kenichi, Robbins, Daryn, Bower, Jason, Liu, Simon, Furuuchi, Kenji, Laughlin, Chet
• Primary Examiner(s): Sked; Matthew J
• Application Number:
  US11/704,381
• Publication Number:
  US 20080195388A1
• Time in Patent Office: 1,503 Days
• Field of Search: None
• US Class Current: 704/9
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06V 30/32 Digital ink
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules

Abstract

Context-based word prediction is provided. A software application utilizes words contained in an application document to provide context-based word prediction in the same or a related document. The software application creates an application defined data source and populates the data source with words occurring in a document. When the same or a related document is being edited via an input method, for example, typing, speech recognition, electronic handwriting, etc., a prediction engine presents candidate words from the application defined data source that match current text input, and the user may choose from the presented candidate words for automatic population into the document being edited. Information from the application defined data source may be transferred between computing devices, for example, between a mobile computing device and a desktop (non-mobile) computing device.

Claims

1. A computer-implemented method for providing context-based word prediction, comprising:

parsing documents associated with different applications and obtaining words contained in the documents;

creating context-based data sources for the words including creating a context-based data source for each different application, each context-based data source comprising an instance of an application defined candidate provider and an application defined data store for storing the words for an associated application;

receiving a text input in a document having an associated context-based data source;

retrieving one or more words associated with the text input received in the document from the associated context-based data source by utilizing words stored in the associated context-based data source before utilizing words from an existing text prediction data source as part of prediction of candidates using the text input; and

displaying the one or more words retrieved from the associated context-based data source in the document and allowing selection of one of the one or more words displayed in the document for automatically completing the text input received in the document.

2. The method of claim 1, wherein displaying the one or more words retrieved from the associated context-based data source in the document includes displaying the one or more words retrieved from the associated context-based data source in a word candidate list displayed in the document.

3. The method of claim 1, further comprising passing the text input received in the document to the associated context-based data source prior to retrieving one or more words associated with the text input received in the document from the associated context-based data source and retrieving one or more words containing the text input received in the document.

4. The method of claim 3, wherein passing the text input received in the document to the associated context-based data source includes passing a request for the one or more words associated with the text input received in the document from an input method used for receiving the text input in the document to a text prediction engine operative to retrieve the one or more words from the associated context-based data source.

5. The method of claim 4, further comprising associating the associated context-based data source with one or more existing data sources, each of the one or more existing data sources containing one or more words that may be entered into the document.

6. The method of claim 5, further comprising retrieving from the one or more existing data sources one or more words associated with the text input received in the document.

7. The method of claim 6, further comprising displaying the one or more words retrieved from the one or more existing data sources along with the one or more words retrieved from the associated context-based data source in the document and allowing selection of one of the one or more words retrieved from the one or more existing data sources for automatically completing the text input received in the document.

8. The method of claim 7, wherein displaying the one or more words retrieved from the one or more existing data sources along with the one or more words retrieved from the associated context-based data source includes displaying the one or more words retrieved from the one or more existing data sources along with the one or more words retrieved from the associated context-based data source in a word candidate list displayed in the document.

9. The method of claim 4, wherein passing a request for the one or more words associated with the text input received in a second document from an input method used for receiving the text input in the second document, includes passing the request from a keyboard input method.

10. The method of claim 4,

wherein passing a request for the one or more words associated with the text input received in a second document from an input method used for receiving the text input in the second document, includes passing the request from a speech recognition input method;

and

further comprising causing the speech recognition input method to use a word selected from the one or more words displayed in the second document to improve performance of the speech recognition input method by confirming that the text input received in the second document via the speech recognition input method is matches the selected word.

11. The method of claim 4,

wherein passing a request for the one or more words associated with the text input received in a second document from an input method used for receiving the text input in the second document, includes passing the request from a handwriting recognition input method;

and

further comprising causing the handwriting recognition input method to use a word selected from the one or more words displayed in the second document to improve performance of the handwriting recognition input method by confirming that the text input received in the second document via the handwriting recognition input method matches the selected word.

12. The method of claim 1, prior to parsing a document and obtaining one or more words contained in the document, receiving an indication of editing the document.

13. The method of claim 1, wherein creating a context-based data source includes creating the context-based data source by a software application responsible for receiving the document and for receiving an indication of an opening of the document.

14. The method of claim 13, further comprising at the associated context-based data source, ranking the one or more stored words based on a likelihood that the one or more stored words will be entered into the document.

15. The method of claim 1,

wherein receiving a text input in the document includes receiving a text input in a second document that is related to the document;

and

wherein displaying the one or more words retrieved from the associated context-based data source in the document and allowing selection of one of the one or more words displayed in the document for automatically completing the text input received in the document includes displaying the one or more words retrieved from the associated context-based data source in the second document and allowing selection of one of the one or more words displayed in the second document for automatically completing the text input received in the second document.

16. A method for providing distributed context-based word prediction, comprising:

receiving documents at a first computing device;

parsing the documents associated with different applications and obtaining words in the documents including a first document and obtaining one or more words contained in the first document;

creating context-based data sources for the words including creating a context-based data source for each different application, each context-based data source comprising an instance of an application defined candidate provider and an application defined data store for storing the words for an associated application at the first computing device;

compiling one or more of the context-based data sources into a format for utilization by a second computing device;

notifying the second computing device of the availability of a compiled context-based data source for use at the second computing device;

in response to receiving a text input in a second document at the second computing device, allowing the second computing device to retrieve one or more words associated with the text input received in the second document at the second computing device from the compiled context-based data source by utilizing words stored in an associated application defined data store for the first document available from the first computing device before utilizing words from an existing text prediction data source as part of prediction of candidates using the text input; and

allowing from the first computing device a displaying of the one or more words retrieved from the compiled context-based data source in the second document at the second computing device and allowing selection of one of the one or more words displayed in the second document at the second computing device for automatically completing the text input received in the second document at the second computing device.

17. The method of claim 16, prior to notifying the second computing device of the availability of the compiled context-based data source for use at the second computing device, establishing a synchronization session between the first computing device and the second computing device for allowing data transfer between the first and second computing devices.

18. The method of claim 17, wherein notifying the second computing device of the availability of the compiled context-based data source for use at the second computing device includes allowing the second computing device to detect an installation of the compiled context-based data source at the second computing device.

19. A computer-readable storage medium containing computer executable instructions which, when executed by a computer, perform a method for providing context-based word prediction, comprising:

parsing documents associated with different applications to obtain parsed words including parsing a first document and obtaining one or more words contained in the first document that may be used for text input in a second document;

creating context-based data sources for the parsed words including creating a context-based data source for each different application, each context-based data source comprising an instance of an application defined candidate provider and an application defined data store, the creating including creating an associated context-based data source for storing the one or more words obtained from the first document;

receiving an indication of the opening of the second document, the second document being related to the first document;

associating the associated context-based data source with one or more existing data sources, each of the one or more existing data sources containing one or more words that may be used for text input in the second document;

receiving a text input in the second document;

retrieving one or more words associated with the text input received in the second document from the associated context-based data source and from one or more of the existing data sources; and

displaying the one or more words retrieved from the associated context-based data source and from the one or more existing data sources in a word candidate list displayed in the second document in a display order based on contextual relevance to the text input, and allowing selection of one of the one or more words displayed in the second document for automatically completing the text input received in the second document.

20. The computer readable storage medium of claim 19,

wherein retrieving one or more words associated with the text input received in the second document from the associated context-based data source and from one or more of the existing data sources includes passing a request for the one or more words associated with the text input received in the second document from an input method used for receiving the text input in the second document, includes passing the request from a non-typing input method;

and

further comprising causing the non-typing input method to use a word selected from the one or more words displayed in the second document to improve performance of the non-typing input method by confirming that the text input received in the second document via the non-typing input method matches the selected word.