Concept Search and Semantic Annotation for Mobile Messaging

• US 20130166280A1
• Filed: 12/21/2011
• Published: 06/27/2013
• Est. Priority Date: 12/21/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Quast, Holger, Labsky, Martin, Kleindienst, Jan, Macek, Tomas, Curin, Jan
• Granted Patent: US 8,903,714 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04M 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails

Abstract

A textual message processing system and method are described for use in a mobile environment. A user messaging application processes at least one user textual message during a user messaging session. A semantic annotation module identifies one or more semantically salient terms in the user textual message, and annotates the user textual message with annotation terms having a low semantic distance to the semantically salient terms. A user message history stores the annotated textual messages. The semantic annotation module may further annotate the user textual message with situational meta-data characterizing the user textual message. There may be a message search module for using one or more keywords to search the user message history including the annotation terms, and identifying as a search match any annotated textual messages within a semantic distance threshold of the one or more keywords.

Claims

1. A textual message processing system for use in a mobile environment, the system comprising:

a user messaging application for processing at least one user textual message during a user messaging session;

a semantic annotation module for;

a. identifying one or more semantically salient terms in the user textual message, and

b. annotating the user textual message with annotation terms having a low semantic distance to the semantically salient terms; and

a user message history for storing the annotated textual messages.

2. A system according to claim 1, wherein the semantic annotation module further annotates the user textual message with situational meta-data characterizing the user textual message.

3. A system according to claim 2, wherein the situational meta-data includes at least one of time data, location data, activity data, and user-specific terms associated with the user textual message.

4. A system according to claim 1, further comprising:

a message search module for using one or more keywords to search the user message history including the annotation terms, and identifying as a search match any annotated textual messages within a semantic distance threshold of the one or more keywords.

5. A system according to claim 4, further comprising:

a user interface for presenting the search match textual messages to a user with the annotation terms.

6. A system according to claim 5, wherein the user interface uses a text-to-speech arrangement for presenting the search match textual messages to the user.

7. A system according to claim 4, wherein the message search module obtains the keywords based on a hands-free, eyes-free user interface.

8. A system according to claim 1, wherein the user textual message includes instant messaging text.

9. A system according to claim 1, wherein the user textual message includes automatic speech recognition text dictated via automatic speech recognition.

10. A system according to claim 9, further comprising:

a speech recognition language model adapted to the annotated textual messages in the user message history.

11. A method of processing textual messages in a mobile environment, the method comprising:

processing a user textual message during a user messaging session;

identifying semantically salient terms in the user textual message;

annotating the user textual message with annotation terms having a low semantic distance to the semantically salient terms; and

adding the annotated textual message to a user message history.

12. A method according to claim 11, further comprising:

further annotating the user textual message with situational meta-data characterizing the user textual message.

13. A method according to claim 12, wherein the situational meta-data includes at least one of time data, location data, activity data, and user-specific terms associated with the user textual message.

14. A method according to claim 11, further comprising:

using one or more keywords to search the user message history including the annotation terms; and

identifying as a search match any annotated textual messages within a semantic distance threshold of the one or more keywords.

15. A method according to claim 14, further comprising:

presenting the search match textual messages to a user with the annotation terms.

16. A method according to claim 15, wherein a text-to-speech arrangement is used for presenting the search match textual messages to the user.

17. A method according to claim 14, wherein the keywords are obtained based on a hands-free, eyes-free user interface.

18. A method according to claim 11, wherein the user textual message includes instant messaging text.

19. A method according to claim 11, wherein the user textual message includes automatic speech recognition text dictated via automatic speech recognition.

20. A method according to claim 19, further comprising:

adapting a speech recognition language model to the annotated textual messages in the user message history.