SYSTEM AND METHOD FOR DELIVERING TARGETED ADVERTISEMENTS AND TRACKING ADVERTISEMENT INTERACTIONS IN VOICE RECOGNITION CONTEXTS

• US 20140012577A1
• Filed: 09/03/2013
• Published: 01/09/2014
• Est. Priority Date: 02/06/2007
• Status: Active Grant

• Current Assignee: VB Assets, LLC
• Original Assignee: VoiceBox Technologies Corporation (Microsoft Corporation)
• Inventors: Freeman, Tom, Kennewick, Mike
• Granted Patent: US 8,886,536 B2
• Time in Patent Office: Days
• US Class Current: 704/249
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The system and method described herein may use various natural language models to deliver targeted advertisements and track advertisement interactions in voice recognition contexts. In particular, in response to an input device receiving an utterance, a conversational language processor may select and deliver one or more advertisements targeted to a user that spoke the utterance based on cognitive models associated with the user, various users having similar characteristics to the user, an environment in which the user spoke the utterance, or other criteria. Further, subsequent interaction with the targeted advertisements may be tracked to build and refine the cognitive models and thereby enhance the information used to deliver targeted advertisements in response to subsequent utterances.

Claims

1-20. -20. (canceled)

21. A computer-implemented method of obtaining conversationally-related promotional content, the method being implemented by a computer system that includes one or more physical processors executing one or more computer program instructions which, when executed, perform the method, the method comprising:

receiving, by the one or more physical processors, a first natural language utterance;

providing, by the one or more physical processors, a response to the first natural language utterance;

receiving, by the one or more physical processors, a second natural language utterance relating to the first natural language utterance;

determining, by the one or more physical processors, promotional content based on the first natural language utterance and the second natural language utterance; and

presenting, by the one or more physical processors, the promotional content to a user.

22. The method of claim 21, wherein the first natural language utterance and the second natural language utterance are received during an interactive session between the user and the computer system, and wherein determining the promotional content comprises:

determining, by the one or more physical processors, an activity relating to the first natural language utterance or the second natural language utterance; and

determining, by the one or more physical processors, the promotional content based on the activity.

23. The method of claim 21, further comprising:

performing, by the one or more physical processors, speech recognition to recognize one or more words of the second natural language utterance;

determining, by the one or more physical processors, context information for the one or more recognized words based on the first natural language utterance; and

processing, by the one or more physical processors based on the context information, the one or more recognized words to determine an interpretation of the one or more recognized words,

wherein determining the promotional content comprises determining the promotional content based on the interpretation of the one or more recognized words.

24. The method of claim 21, further comprising:

performing, by the one or more physical processors, speech recognition to recognize one or more words of the second natural language utterance;

determining, by the one or more physical processors, domain information for the one or more recognized words based on the first natural language utterance; and

processing, by the one or more physical processors based on the domain information, the one or more recognized words to determine an interpretation of the one or more recognized words,

wherein determining the promotional content comprises determining the promotional content based on the interpretation of the one or more recognized words.

25. The method of claim 24, wherein processing the one or more recognized words comprises:

determining, by the one or more physical processors, one or more domains associated with the second natural language utterance based on the domain information; and

providing, by the one or more physical processors, the one or more recognized words to one or more domain agents associated with the one or more domains.

26. The method of claim 24, wherein processing the one or more recognized words comprises:

providing, by the one or more physical processors, the one or more recognized words to a first domain agent associated with a first domain and a second domain agent associated with a second domain;

obtaining, by the one or more physical processors, a first interpretation of the one or more recognized words from the first domain agent;

obtaining, by the one or more physical processors, a second interpretation of the one or more recognized words from the second domain agent; and

determining, by the one or more physical processors, the interpretation based on the first interpretation and the second interpretation.

27. The method of claim 26, wherein the first interpretation is determined by the first domain agent based on the first domain, and wherein the second interpretation is determined by the second domain agent based on the second domain.

28. The method of claim 26, further comprising:

associating, by the one or more physical processors, the first interpretation with a first interpretation score; and

associating, by the one or more physical processors, the second interpretation with a second interpretation score,

wherein determining the interpretation comprises determining the first interpretation as the interpretation based on the first interpretation score and the second interpretation score.

29. The method of claim 28, wherein the first interpretation is determined as the interpretation based on the first interpretation score being greater than the second interpretation score.

30. The method of claim 21, further comprising:

receiving, by the one or more physical processors, a third natural language utterance relating to the first natural language utterance or the second natural language utterance;

performing, by the one or more physical processors, speech recognition to recognize one or more words of the third natural language utterance; and

determining, by the one or more physical processors, an interpretation of the one or more recognized words based on the promotional content.

31. The method of claim 30, wherein the first natural language utterance, the second natural language utterance, and the third natural language utterance are received during an interactive session between the user and the computer system.

32. The method of claim 31, wherein the third natural language utterance is received after the second natural language utterance.

33. The method of claim 30, wherein the one or more recognized words include one or more reference words that refer to an item associated with the promotional content.

34. The method of claim 33, wherein the item includes a purchasable good.

35. The method of claim 30, further comprising:

initiating, based on the interpretation by the one or more physical processors, a purchase transaction associated with the promotional content.

36. The method of claim 21, wherein the first natural language utterance and the second natural language utterance are received during an interactive session between the user and the computer system, the method further comprising:

performing, by the one or more physical processors, speech recognition to recognize one or more words of the second natural language utterance;

processing, by the one or more physical processors based on the first natural language utterance, the one or more recognized words to determine an interpretation of the one or more recognized words;

receiving, by the one or more physical processors, a third natural language utterance during the interactive session between the user and the computer system; and

processing, by the one or more physical processors based on the third natural language utterance, the one or more recognized words to determine a reinterpretation of the second natural language utterance.

37. The method of claim 36, wherein determining the promotional content comprises determining the promotional content based on the reinterpretation.

38. The method of claim 36, wherein determining the promotional content comprises determining the promotional content based on the interpretation, the method further comprising:

determining, by the one or more physical processors, other promotional content based on the reinterpretation; and

presenting, by the one or more physical processors, the other promotional content to the user.

39. The method of claim 21, further comprising:

identifying, by the one or more physical processors, one or more requests associated with the second natural language utterance,

wherein determining the promotional content comprises obtaining the promotional content based on a determination that the promotional content relates to the one or more requests.

40. The method of claim 39, further comprising:

determining, by the one or more physical processors, one or more activities in the one or more requests; and

performing, by the one or more physical processors, the one or more activities,

wherein determining the promotional content comprises determining the promotional content based on the one or more activities.

41. The method of claim 40, wherein determining the one or more activities comprises determining a call to be initiated for the user in response to the one or more requests, wherein performing the one or more activities comprises initiating the call for the user, and wherein determining the promotional content comprises determining the promotional content based on the call.

42. The method of claim 40, wherein determining the one or more activities comprises determining a navigation route to be calculated for the user in response to the one or more requests, wherein performing the one or more activities comprises calculating the navigation route for the user, and wherein determining the promotional content comprises determining the promotional content based on the navigation route.

43. The method of claim 40, wherein determining the one or more activities comprise determining a media item to be presented in response to the one or more requests, wherein performing the one or more activities comprises presenting the media item to the user, and wherein determining the promotional content comprises determining the promotional content based on the media item, the promotional content being different than the media item.

44. The method of claim 40, wherein determining the one or more activities comprises determining a reservation to be made on behalf of the user in response to the one or more requests, and wherein determining the promotional content comprises determining the promotional content based on information relating to the reservation.

45. The method of claim 40, wherein determining the one or more activities comprises determining a first reservation to be made on behalf of the user in response to the one or more requests, and wherein determining the promotional content comprises determining the promotional content based on information relating to a second reservation that is an alternative to the first reservation.

46. The method of claim 40, further comprising:

receiving, by the one or more physical processors, a third natural language utterance relating to the first natural language utterance or the second natural language utterance;

performing, by the one or more physical processors, speech recognition to recognize one or more words of the third natural language utterance;

determining, by the one or more physical processors, an interpretation of the one or more recognized words based on the promotional content; and

initiating, based on the interpretation by the one or more physical processors, a purchase transaction associated with the promotional content.

47. The method of claim 39, further comprising:

determining, by the one or more physical processors, that at least one request of the one or more requests is incomplete or ambiguous;

monitoring, by the one or more physical processors, interaction of the user with the promotional content; and

interpreting, by the one or more physical processors, the at least one incomplete or ambiguous request based on the interaction.

48. The method of claim 39, wherein the one or more requests includes a first request associated with a first application and a second request associated with a second application different than the first application, and wherein the promotional content relates to the first request or the second request.

49. The method of claim 39, wherein a first application type of the first application is a navigation application, a music application, a commerce application, or a calling application, and wherein the second application is of an application type other than the first application type.

50. The method of claim 39, wherein the one or more requests includes a first request to be processed by a first device associated with the user and a second request to be processed by a second device associated with the user, and wherein the promotional content relates to the first request or the second request.

51. The method of claim 39, wherein a first device type of the first device is a mobile phone, a navigation device, or a media player device, and wherein the second device is of a device type other than the first device type.

52. The method of claim 39, wherein the first device and the second device are operably independent of one another.

53. The method of claim 21, further comprising:

obtaining, by the one or more physical processors, user profile information associated with the user, wherein the user profile information specifies prior user interactions with items;

performing, by the one or more physical processors, speech recognition to recognize one or more words of the first natural language utterance or the second natural language utterance; and

identifying, by the one or more physical processors, categories of items from the prior user interactions specified by the user profile information,

wherein determining the promotional content comprises determining a promotional item associated with one of the categories.

54. The method of claim 21, further comprising:

obtaining, by the one or more physical processors, user profile information associated with the user, wherein the user profile information specifies prior user interactions with items;

identifying, by the one or more physical processors, one or more requests associated with the first natural language utterance or the second natural language utterance;

determining, by the one or more physical processors, one or more applications for processing the one or more requests; and

identifying, by the one or more physical processors, categories of items from the prior user interactions specified by the user profile information,

wherein determining the promotional content comprises determining a promotional item associated with one of the categories.

55. A system for obtaining conversationally-related promotional content, the system comprising:

one or more physical processors programmed to execute one or more computer program instructions which, when executed, cause the one or more physical processors to;

receive a first natural language utterance;

provide a response to the first natural language utterance;

receive a second natural language utterance relating to the first natural language utterance; and

determine promotional content based on the first natural language utterance and the second natural language utterance.