Efficient instant messaging using a telephony interface

• US 6,816,578 B1
• Filed: 11/27/2001
• Issued: 11/09/2004
• Est. Priority Date: 11/27/2001
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nortel Networks Limited (Nortel Networks Corporation)
• Inventors: Avino, Margaret, Bergman, Richard, Kredo, Thomas J.
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): Chow, Ming
• Application Number:
  US09/995,113
• Time in Patent Office: 1,078 Days
• Field of Search: 379/88.17, 379/88.13, 379/88.18, 379/88.01, 379/88.02, 379/88.04, 704/1, 704/2, 704/3, 704/270.1, 704/4, 709/204, 709/207, 709/203, 709/217, 709/218, 709/219
• US Class Current: 379/88.17
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2203/4536 Voicemail combined with text-based messaging
• CPC Class Codes: H04M 7/0048 where the text-based messaging service is a Short Message Service
• CPC Class Codes: H04M 7/12 for working between exchanges having different types of switching equipment, e.g. power-driven and step by step or decimal and non-decimal
• CPC Class Codes: H04M 7/1235 where one of the core networks is a wireless network

Abstract

The present invention allows telephony users and on line users to communicate with one another using an instant massaging (AIM) service. The on line IM user will provide and receive textual messages, wherein the telephony user will provide and receive corresponding audible messages. To allow more efficient interaction with the telephony user, responses to queries posed to the telephony user are structured with possible answers. The answers are used to define and limit the voice recognition grammar for processing the telephony user'"'"'s response. Predefining the grammar for responses increases the effectiveness of the speech recognition system and the integrity of the IM session. Further, voice commands may be predefined to facilitate better control of the IM session as well as provide more effective communications.

Claims

1. A method for facilitating instant messaging (IM) for a telephony user comprising:

a) receiving an IM message, which contains information and is directed to the telephony user, from a text-based IM user via an IM service;

b) creating a speech recognition grammar based on the information in the IM message, wherein said speech recognition grammar constrains speech recognition of an audible response to a subset of a universe of potentially spoken words; and

c) sending the speech recognition grammar to a speech recognition system to control speech recognition of the audible response from the telephony user.

2. The method of claim 1 wherein the information includes a plurality of defined responses to a query from a text-based IM user and the speech recognition grammar defines each of the plurality of defined responses.

3. The method of claim 2 wherein the information includes the query along with the plurality of defined responses.

4. The method of claim 3 wherein the query and the plurality of answers are delineated with at least one character and further comprising determining the plurality of responses based on the at least one character delineating the plurality of responses.

5. The method of claim 1 further comprising:

a) receiving an audible response from the telephony user via the speech recognition system;

b) creating an instant message based on the audible response; and

c) sending the instant message to the text-based user via the instant message service.

6. The method of claim 1 further comprising:

a) receiving a command from the telephony user via the speech recognition system;

b) creating an instant message based on the command; and

c) sending the instant message to the text-based user via the instant messaging service.

7. The method of claim 1 further comprising effecting conversion of at least part of the information in the IM message into an audible message and audibly delivering the audible message to the telephony user.

8. The method of claim 1 further comprising effecting delivery of an alert to the telephony user via at least one of the group consisting of initiating a call, sending an email, sending a message via a short message service, and sending a page to a telephony device of the telephony user.

9. The method of claim 1 further comprising:

a) providing a predefined specialized speech recognition grammar to the speech recognition system; and

b) responding to responses from the telephony user defined by the predefined specialized speech recognition grammar by delivering a predefined IM message to the text-based user.

10. The method of claim 1 further comprising;

a) providing a predefined specialized speech recognition grammar to the speech recognition system; and

b) responding to the responses from the telephony user defined by the predefined specialized speech recognition grammar by controlling the IM service.

11. A system for facilitating instant messaging for a telephony user comprising:

a) a communication interface for communicating with an instant messaging (IM) service and an audio interface associated with a speech recognition function and capable of communicating with the telephony user; and

b) a control system associated with the communication interface and adapted to;

i) receive an IM message, which contains information and is directed to a telephony user, from a text-based IM user via the IM service;

ii) create a speech recognition grammar based on the information in the IM message, wherein said speech recognition grammar constrains speech recognition of an audible response to a subset of a universe of potentially spoken words; and

iii) send the speech recognition grammar to the audio interface to control speech recognition of an audible response form the telephony user.

12. The system of claim 11 wherein the information includes a plurality of defined responses to a query from a text-based IM user and the speech recognition grammar defines each of the plurality of defined responses.

13. The system of claim 12 wherein the information includes the query along with the plurality of defined responses.

14. The system of claim 13 wherein the query and the plurality of answers are delineated with at least one character and the control system is further adapted to determine the plurality of responses based on the at least one character delineating the plurality of responses.

15. The system of claim 11 wherein the control system is further adapted to:

a) receive an audible response from the telephony user via the audio interface;

b) create an instant message based on the audible response; and

c) send the instant message to the text-based user via the instant messaging service.

16. The system of claim 11 wherein the control system is further adapted to:

a) receive a command from the telephony user via the audio interface;

b) create an instant message based on the command; and

c) send the instant message to the text-based user via the instant messaging service.

17. The system of claim 11 further comprising an audio browser adapted to implement the audio interface and the speech recognition system wherein the audio browser is adapted to effect conversion of at least part of the information from the IM message into an audible message and deliver the audible message to the telephony user.

18. The system of claim 11 wherein the control system is further adapted to effect delivery of an alert to the telephony user via at least one of the group consisting of initiating a call, sending an email, sending a message via a short message service, and sending a page to a telephony device of the telephony user.

19. The system of claim 11 wherein the control system is further adapted to:

a) provide a predefined specialized speech recognition grammar to the speech recognition system; and

b) respond to responses from the telephony user defined by the predefined specialized speech recognition grammar by delivering a predefined IM message to the text-based user.

20. The system of claim 11 wherein the control system is further adapted to:

a) provide a predefined specialized speech recognition grammar to the speech recognition system; and

b) respond to responses from the telephony user defined by the predefined specialized speech recognition grammar by controlling the IM service.

21. A computer readable medium with software facilitating instant messaging for a telephony user and comprising instructions for a computer to:

a) receive an IM message, which contain information and is directed to the telephony user, from a text-based IM user via an IM service;

b) create a speech recognition grammar based on the information in the IM message, wherein said speech recognition grammar constrains speech recognition of an audible response to a subset of a universe of potentially spoken words; and

c) send the speech recognition grammar to an audio interface to control speech recognition of an audible response from the telephony user.

22. The computer readable medium of claim 21 wherein the information includes a plurality of defined responses to a query from a text-based IM user and the speech recognition grammar defines each of the plurality of defied responses.

23. The computer readable medium of claim 22 wherein the information includes the query along with the plurality of defined responses.

24. The computer readable medium of claim 23 wherein the query and the plurality of answers are delineated with at least one character and comprises further instructions to determine the plurality of responses based on the at least one character delineating the plurality of responses.

25. The computer readable medium of claim 21 comprising further instructions to:

a) receive an audible response from the telephony user via an audio interface;

b) create an instant message based on the audible response; and

c) send the instant message to the text-based user via the instant messaging service.

26. A method for facilitating instant messaging (IM) for a telephony user comprising:

receiving an IM message, which contains information and is directed to the telephony user, from a text-based IM user via an IM service, said information containing a query and a number of predefined acceptable responses separated by predefined punctuation marks;

creating a speech recognition grammar based on said information in the IM message;

creating an audible message from the information, said audible message including the query and the number of predefined acceptable responses;

sending the audible message to the telephony user; and

sending the speech recognition grammar to a speech recognition system to control the predefined acceptable responses.

27. The method of claim 26 further comprising receiving an audible reply from the telephony user, said audible reply containing an audible version of one of the predefined acceptable responses.

28. The method of claim 26 wherein the predefined punctuation marks comprise question marks.

29. The method of claim 26 wherein receiving an IM message comprises receiving an IM message at an IM server.