METHODS AND SYSTEMS FOR DYNAMICALLY UPDATING WEB SERVICE PROFILE INFORMATION BY PARSING TRANSCRIBED MESSAGE STRINGS

• US 20090083032A1
• Filed: 09/17/2008
• Published: 03/26/2009
• Est. Priority Date: 09/17/2007
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Jablokov, Victor Roditis, Jablokov, Igor Roditis
• Granted Patent: US 9,973,450 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• 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 1/72436 for text messaging, e.g. short messaging services [SMS] or e-mails
• CPC Class Codes: H04M 1/72445 for supporting Internet browser applications
• CPC Class Codes: H04W 8/20 Transfer of user or subscriber data

Abstract

Systems, methods, and software for parsing and/or filtering message strings of text messages and/or instant messages in order to identify keywords, phrases, or fragments as a function of which user preferences of user profiles are dynamically updated are disclosed. Such systems, methods, and software are utilized in the context of a communication system including text messaging, instant messaging, or both. Furthermore, such communication system preferably includes an automatic speech recognition (ASR) system. Additionally, ad impressions are selected and delivered to users based, at least in part, on the parsing and/or filtering and/or data maintained in user profiles as dynamically updated from time to time. The ad impression preferably is delivered within a text message or within an instant message conversation and is generally unobtrusive. Revenues preferably may be generated from the delivering of the ad impressions, whereby a provider of instant messaging or text messaging may further derive monetary benefit from providing such service and whereby users of such service may be provided with contextually relevant information in an unobtrusive manner.

Claims

1. A method of providing profile information, derived from an utterance, from a mobile communication device to a web service, comprising the steps of:

(a) receiving, at the mobile communication device, audio data representing an utterance;

(b) transcribing the audio data to text;

(c) processing the transcribed text, including parsing the text for profile information appropriate for use at one or more web services; and

(d) communicating, to the web service, the profile information parsed from the transcribed text.

2. The method of claim 1, wherein the processing step is performed by a profile filter.

3. The method of claim 2, further comprising providing an interface to a user for manual user editing of the transcribed text.

4. The method of claim 2, wherein the transcription step is performed at the mobile communication device.

5. The method of claim 2, wherein the transcription step is performed by a separate automatic speech recognition system.

6. The method of claim 2, wherein the audio data is a voicemail.

7. The method of claim 2, further comprising delivering ad impressions to a user based on the processed text.

8. The method of claim 2, further comprising communicating the transcribed text, as a text-based message, from the mobile communication device to a recipient.

9. The method of claim 8, wherein the recipient is a cell phone.

16. The method of claim 8, wherein the text-based message is a text message, communicated using Short Message Service.

17. The method of claim 8, wherein the text-based message is an instant message, communicated via an instant message service.

10-15. -15. (canceled)

18-33. -33. (canceled)

34. A method of providing profile information, derived from an utterance, from a mobile communication device to a web service, comprising the steps of:

(a) receiving, at the mobile communication device, audio data representing an utterance that is to be sent from the mobile communication device to a recipient;

(b) transcribing the utterance to text;

(c) parsing the transcribed text to identify relevant profile information for input to a web service; and

(d) communicating the transcribed text, as a text-based message, from the mobile communication device to the recipient.

35. The method of claim 34, wherein the parsing step is performed by a profile filter.

36. The method of claim 35, further comprising providing an interface to a user for manual user editing of the transcribed text.

37. The method of claim 35, wherein the transcription step is performed at the mobile communication device.

38. The method of claim 35, wherein the transcription step is performed by a separate automatic speech recognition system.

39. The method of claim 35, wherein the audio data is a voicemail.

40. The method of claim 35, further comprising delivering ad impressions to a user based on the parsed text.

41. The method of claim 35, further comprising communicating, to the web service, the profile information parsed from the transcribed text.

42. The method of claim 35, wherein the recipient is a cell phone.

49. The method of claim 35, wherein the text-based message is a text message, communicated using Short Message Service.

50. The method of claim 35, wherein the text-based message is an instant message, communicated via an instant message service.

43-48. -48. (canceled)

51-105. -105. (canceled)