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

• US 20120150636A1
• Filed: 02/13/2012
• Published: 06/14/2012
• Est. Priority Date: 02/06/2007
• Status: Active Grant

• Current Assignee: VB Assets, LLC
• Original Assignee: VoiceBox Technologies, Inc. (Microsoft Corporation)
• Inventors: FREEMAN, Tom, KENNEWICK, Mike
• Granted Patent: US 8,527,274 B2
• Time in Patent Office: Days
• US Class Current: 705/14.49
• 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. A system to deliver targeted advertisements and track advertisement interactions in voice recognition contexts, comprising:

an advertisement repository configured to store advertisements that specify one or more marketing criteria and one or more pricing criteria; and

an advertising server coupled to the advertisement repository, wherein the advertising server includes one or more processors configured to;

receive a natural language utterance or information associated with the natural language utterance from a voice-enabled device;

extract one or more profile criteria from the natural language utterance or the information associated with the natural language utterance;

map a statistical profile to the one or more marketing criteria, the one or more pricing criteria, and the one or more extracted profile criteria to select one or more advertisements stored in the advertisement repository; and

deliver the one or more selected advertisements to the voice-enabled device.

2. The system recited in claim 1, wherein the one or more processors associated with the advertising server are further configured to track an interaction pattern associated with the one or more advertisements delivered to the voice-enabled device.

3. The system recited in claim 2, wherein the one or more processors associated with the advertising server are further configured to update the statistical profile based on the tracked interaction pattern associated with the one or more advertisements delivered to the voice-enabled device.

4. The system recited in claim 2, wherein the one or more processors associated with the advertising server are further configured to generate a bill or invoice to one or more entities associated with the one or more advertisements delivered to the voice-enabled device.

5. The system recited in claim 4, wherein the bill or invoice includes a first cost if the tracked interaction pattern does not include a click-through, a second cost if the tracked interaction pattern includes the click-through, and a third cost if the tracked interaction pattern includes the click-through and a subsequent transaction or sale.

6. The system recited in claim 1, wherein the one or more processors associated with the advertising server are further configured to prioritize the one or more selected advertisements over one or more similar advertisements if the one or more selected advertisements specify a prioritization premium in the one or more pricing criteria associated therewith.

7. The system recited in claim 1, wherein the one or more advertisements delivered to the voice-enabled device include audible or hands-free messages if the voice-enabled device operates in a telematics environment.

8. The system recited in claim 1, wherein the one or more marketing criteria associated with the advertisements stored in the advertisement repository include concepts, semantic indicators, categories, topics, contexts, target audience criteria, or campaign criteria.

9. The system recited in claim 1, wherein the one or more pricing criteria associated with the advertisements stored in the advertisement repository include static or dynamic insertion costs, per-click-throughs costs, per-transaction costs, or prioritization premiums.

10. The system recited in claim 1, wherein the one or more extracted profile criteria include one or more words, phrases, concepts, semantic indicators, categories, topics, contexts, or requests associated with the natural language utterance.

11. The system recited in claim 1, wherein the one or more processors associated with the advertising server are configured to extract the one or more profile criteria using a personalized cognitive model associated with a user that spoke the natural language utterance.

12. The system recited in claim 1, wherein the one or more processors associated with the advertising server are configured to extract the one or more profile criteria using a generalized cognitive model associated with multiple different users.

13. The system recited in claim 1, wherein the one or more processors associated with the advertising server are configured to extract the one or more profile criteria using an environmental model derived from conditions or surroundings associated with the voice-enabled device.

14. The system recited in claim 1, wherein the statistical profile maps the advertisements stored in the advertisement repository to demographic criteria, preference criteria, location criteria, presentation formats, conversion or click-through rates, and transaction or sale rates.

15. A method to deliver targeted advertisements and track advertisement interactions in voice recognition contexts, comprising:

storing, in an advertisement repository, advertisements that specify one or more marketing criteria and one or more pricing criteria;

receiving, at an advertising server coupled to the advertisement repository, a natural language utterance or information associated with the natural language utterance from a voice-enabled device;

extracting, at the advertising server, one or more profile criteria from the natural language utterance or the information associated with the natural language utterance;

mapping, at the advertising server, a statistical profile to the one or more marketing criteria, the one or more pricing criteria, and the one or more extracted profile criteria to select one or more advertisements stored in the advertisement repository; and

delivering the one or more selected advertisements from the advertising server to the voice-enabled device.

16. The method recited in claim 15, further comprising tracking at the advertising server, an interaction pattern associated with the one or more advertisements delivered to the voice-enabled device.

17. The method recited in claim 16, further comprising updating, at the advertising server, the statistical profile based on the tracked interaction pattern associated with the one or more advertisements delivered to the voice-enabled device.

18. The method recited in claim 16, further comprising generating, at the advertising server, a bill or invoice to one or more entities associated with the one or more advertisements delivered to the voice-enabled device.

19. The method recited in claim 18, wherein the bill or invoice includes a first cost if the tracked interaction pattern does not include a click-through, a second cost if the tracked interaction pattern includes the click-through, and a third cost if the tracked interaction pattern includes the click-through and a subsequent transaction or sale.

20. The method recited in claim 15, further comprising prioritizing, at the advertising server, the one or more selected advertisements over one or more similar advertisements if the one or more selected advertisements specify a prioritization premium in the one or more pricing criteria associated therewith.

21. The method recited in claim 15, wherein the one or more advertisements delivered to the voice-enabled device include audible or hands-free messages if the voice-enabled device operates in a telematics environment.

22. The method recited in claim 15, wherein the one or more marketing criteria associated with the advertisements stored in the advertisement repository include concepts, semantic indicators, categories, topics, contexts, target audience criteria, or campaign criteria.

23. The method recited in claim 15, wherein the one or more pricing criteria associated with the advertisements stored in the advertisement repository include static or dynamic insertion costs, per-click-throughs costs, per-transaction costs, or prioritization premiums.

24. The method recited in claim 15, wherein the one or more extracted profile criteria include one or more words, phrases, concepts, semantic indicators, categories, topics, contexts, or requests associated with the natural language utterance.

25. The method recited in claim 15, wherein the advertising server extracts the one or more profile criteria using a personalized cognitive model associated with a user that spoke the natural language utterance.

26. The method recited in claim 15, wherein the advertising server extracts the one or more profile criteria using a generalized cognitive model associated with multiple different users.

27. The method recited in claim 18, wherein the advertising server extracts the one or more profile criteria using an environmental model derived from conditions or surroundings associated with the voice-enabled device.

28. The method recited in claim 15, wherein the statistical profile maps the advertisements stored in the advertisement repository to demographic criteria, preference criteria, location criteria, presentation formats, conversion or click-through rates, and transaction or sale rates.