Real-time bidding and advertising content generation

• US 10,192,238 B2
• Filed: 12/21/2012
• Issued: 01/29/2019
• Est. Priority Date: 12/21/2012
• Status: Active Grant

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Inventors: Chatwin, Richard Edward, Nukala, Murthy V., Coleman, Alan, Lokeswarappa, Kiran Garaga, Kondaji, Srinidhi Ramesh
• Primary Examiner(s): Stoltenberg, David J
• Application Number:
  US13/725,821
• Publication Number:
  US 20140180815A1
• Time in Patent Office: 2,230 Days
• Field of Search: 705 1446, 705 1453, 705 1452, 705 1449, 705 1445, 705 1454, 705 1466, 705 1472, 705 144, 705 1441, 705 1443, 705 1455, 705 1473
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0275 Auctions

Abstract

In one embodiment, a method includes receiving, in real-time, user information associated with a user of a client computing device. One or more user features are derived from the user information associated with the user. The one or more user features include one or more user intents. The one or more user intents are matched with one or more of a plurality of advertiser intents. The user information is determined to be accepted. In response to accepting the user information, an advertisement is generated based on the matching of the one or more user intents and the one or more of the plurality of advertiser intents.

Claims

1. A method of generating a personalized Internet advertisement, the method comprising:

receiving, by one or more server computing devices and in real-time, user information associated with a user of a client computing device;

deriving one or more user features from the user information associated with the user, the one or more user features comprising one or more user intents;

generating, by the one or more server computing devices, one or more intent graphs relative to the user and an advertiser having a plurality of advertiser intents;

matching, by the one or more server computing devices, using the one or more intent graphs, the one or more user intents with one or more of the plurality of advertiser intents associated with products or services offered by the advertiser, wherein matching the one or more user intents with the one or more of the plurality of advertiser intents comprises;

accepting, at an intent matcher processing subsystem of the one or more server computing devices, one or more intent match context objects, wherein the one or more intent match context objects comprise a list of topic-term pairs as output, each of the one or more intent match context objects are associated with at least one of the one or more user intents, the one or more intent match context objects are accepted as input and returned as output at each of a plurality of processing subsystems of a processing pipeline of the one or more server computing devices implementing an intent match runtime system, the plurality of processing subsystems comprising the intent matcher processing subsystem, and each respective processing subsystem of the plurality of processing subsystems is configured to change only a context field of a context object of the one or more intent match context objects corresponding to a responsibility of the each respective processing subsystem;

computing, by the one or more server computing devices, and using one or more statistical models, a similarity score between the one or more user features and the one or more of the plurality of advertiser intents;

determining, by the one or more server computing devices, that the user information is accepted, including determining that the similarity score exceeds a threshold; and

in response to accepting the user information, generating, by the one or more server computing devices, the personalized Internet advertisement based on the matching of the one or more user intents and the one or more of the plurality of advertiser intents.

2. The method of claim 1, wherein receiving the user information associated with the user comprises receiving a search engine query of the user.

3. The method of claim 2, further comprising:

parsing the search engine query submitted by the user to determine a presence of one or more sets of words; and

deriving the one or more user intents based on the one or more sets of words in the search engine query.

4. The method of claim 3, wherein determining that the user information is accepted comprises determining that every one of the one or more sets of words in the search engine query matches at least one of the plurality of advertiser intents.

5. The method of claim 1, wherein:

the user information comprises one or more present online activities of the user; and

deriving the one or more user features further comprises;

determining the one or more user features based on the one or more present online activities of the user.

6. The method of claim 1, wherein determining that the user information is accepted comprises determining that every one of the one or more user intents matches at least one of the plurality of advertiser intents.

7. The method of claim 1, wherein determining that the user information is accepted comprises:

determining that at least one of the one or more user intents matches at least one of a first specified subset of the plurality of advertiser intents; and

determining that every one of the one or more user intents does not match any one of a second specified subset of the plurality of advertiser intents.

8. The method of claim 1, further comprising:

deriving a plurality of keywords from the plurality of advertiser intents,

wherein determining that the user information is accepted comprises determining that one or more of the plurality of keywords matches with the one or more user intents.

9. The method of claim 1, further comprising:

generating, by the one or more server computing devices, a bid based on the one or more user features and the matching of the one or more user intents and the one or more of the plurality of advertiser intents,

wherein the bid comprises a maximum payment amount that an advertiser placing the bid agrees to pay if the bid is selected.

10. The method of claim 9, wherein the bid further comprises the personalized Internet advertisement.

45. The method of claim 1, wherein:

generating the personalized Internet advertisement comprises;

selecting an advertisement template based at least in part on the one or more user intents; and

customizing the advertisement template based at least in part on the one or more user intents.

11. A method comprising:

receiving, by one or more server computing devices and in real-time, user information associated with a user of a client computing device;

deriving one or more user features from the user information associated with the user, the one or more user features comprising one or more user intents;

generating, by the one or more server computing devices, one or more advertiser intent graphs, the one or more advertiser intent graphs comprising a plurality of advertiser intents;

matching, by the one or more server computing devices, using the one or more advertiser intent graphs, the one or more user intents with one or more of the plurality of advertiser intents, wherein matching the one or more user intents with the one or more of the plurality of advertiser intents comprises;

accepting, at an intent matcher processing subsystem of the one or more server computing devices, one or more intent match context objects, wherein the one or more intent match context objects comprise a list of topic-term pairs as output, each of the one or more intent match context objects are associated with at least one of the one or more user intents, the one or more intent match context objects are accepted as input and returned as output at each of a plurality of processing subsystems of a processing pipeline of the one or more server computing devices implementing an intent match runtime system, the plurality of processing subsystems comprising the intent matcher processing subsystem, and each respective processing subsystem of the plurality of processing subsystems is configured to change only a context field of a context object of the one or more intent match context objects corresponding to a responsibility of the each respective processing subsystem;

computing, by the one or more server computing devices and using one or more statistical models, a similarity score between the one or more user features and the one or more of the plurality of advertiser intents;

determining, by the one or more server computing devices, that the user information is accepted;

in response to accepting the user information, transmitting a request for an advertisement to an advertiser associated with the one or more of the plurality of advertiser intents;

receiving the advertisement from the advertiser associated with the one or more of the plurality of advertiser intents; and

displaying the advertisement received from the advertiser to the user.

12. The method of claim 11, wherein receiving the user information associated with the user comprises receiving a search engine query of the user.

13. The method of claim 12, further comprising:

parsing the search engine query submitted by the user to determine a presence of one or more sets of words; and

deriving the one or more user intents based on the one or more sets of words in the search engine query.

14. The method of claim 13, wherein determining that the user information is accepted comprises determining that every one of the one or more sets of words in the search engine query matches at least one of the plurality of advertiser intents.

15. The method of claim 11, wherein:

the user information comprises one or more present online activities of the user; and

deriving the one or more user features further comprises;

determining the one or more user features based on the one or more present online activities of the user.

16. The method of claim 11, wherein determining that the user information is accepted comprises determining that the one or more user intents match the one or more of the plurality of advertiser intents.

17. The method of claim 11, wherein determining that the user information is accepted comprises determining that every one of the one or more user intents matches at least one of the plurality of advertiser intents.

18. The method of claim 11, wherein determining that the user information is accepted comprises:

determining that at least one of the one or more user intents matches at least one of a first specified subset of the plurality of advertiser intents; and

determining that every one of the one or more user intents does not match any one of a second specified subset of the plurality of advertiser intents.

19. The method of claim 11, wherein further comprising:

deriving a plurality of keywords from the plurality of advertiser intents, and

wherein determining that the user information is accepted comprises determining that one or more of the plurality of keywords matches with the one or more user intents.

20. The method of claim 11, wherein determining that the user information is accepted comprises determining that the similarity score exceeds a threshold.

21. The method of claim 11, further comprising:

receiving one or more bids for the search engine query,

wherein a bid of the one or more bids comprises a maximum payment amount that an advertiser placing the bid agrees to pay if the bid is selected.

22. The method of claim 21, wherein the bid further comprises the advertisement.

23. A system comprising:

a memory comprising instructions; and

one or more processors coupled to the memory and operable to execute the instructions to;

receive, in real-time, user information associated with a user of a client computing device;

derive one or more user features from the user information associated with the user, the one or more user features comprising one or more user intents;

generate, by one or more server computing devices, one or more intent graphs;

match, using the one or more intent graphs, the one or more user intents with one or more of a plurality of advertiser intents for generating advertising bids by;

accepting, at an intent matcher processing subsystem of the one or more server computing devices, one or more intent match context objects, wherein the one or more intent match context objects comprise a list of topic-term pairs as output, each of the one or more intent match context objects are associated with at least one of the one or more user intents, the one or more intent match context objects are accepted as input and returned as output at each of a plurality of processing subsystems of a processing pipeline of the one or more server computing devices implementing an intent match runtime system, the plurality of processing subsystems comprising the intent matcher processing subsystem, and each respective processing subsystem of the plurality of processing subsystems is configured to change only a context field of a context object of the one or more intent match context objects corresponding to a responsibility of the each respective processing subsystem;

determine that the user information is accepted including determining that a similarity score exceeds a threshold; and

in response to accepting the user information, generate an advertisement based on the matching of the one or more user intents and the one or more of the plurality of advertiser intents.

24. The system of claim 23, wherein, when the one or more processors are operable to execute the instructions to receive the user information associated with the user, the one or more processors are further operable to execute the instructions to receive a search engine query of the user.

25. The system of claim 24, wherein the one or more processors are further operable to execute the instructions to:

parse the search engine query submitted by the user to determine a presence of one or more sets of words; and

derive the one or more user intents based on the one or more sets of words in the search engine query.

26. The system of claim 25, wherein, when the one or more processors are operable to execute the instructions to determine that the user information is accepted, the one or more processors are further operable to execute the instructions to determine that every one of the one or more sets of words in the search engine query matches at least one of the plurality of advertiser intents.

27. The system of claim 23, wherein the user information comprises one or more present online activities of the user and the one or more processors are further operable to:

determine the one or more user features based on the one or more present online activities of the user.

28. The system of claim 23, wherein, when the one or more processors are operable to execute the instructions to determine that the user information is accepted, the one or more processors are further operable to execute the instructions to determine that every one of the one or more user intents matches at least one of the plurality of advertiser intents.

29. The system of claim 23, wherein, when the one or more processors are operable to execute the instructions to determine that the user information is accepted, the one or more processors are further operable to execute the instructions to:

determine that at least one of the one or more user intents matches at least one of a first specified subset of the plurality of advertiser intents; and

determine that every one of the one or more user intents does not match any one of a second specified subset of the plurality of advertiser intents.

30. The system of claim 23, wherein the one or more processors are further operable to execute the instructions to:

derive a plurality of keywords from the plurality of advertiser intents, and

determine that one or more of the plurality of keywords matches with the one or more user intents when determining that the user information is accepted.

31. The system of claim 23, wherein the one or more processors are further operable to execute the instructions to:

use one or more statistical models to compute the similarity score and the similarity score is between the one or more user features and the one or more of the plurality of advertiser intents.

32. The system of claim 23, wherein the one or more processors are further operable to execute the instructions to:

generate a bid based on the one or more user features and the matching of the one or more user intents and the one or more of the plurality of advertiser intents, the bid comprising a maximum payment amount that an advertiser placing the bid agrees to pay if the bid is selected.

33. The system of claim 32, wherein the bid further comprises the advertisement.

46. The system of claim 23, wherein:

the one or more processors coupled to the memory and operable to execute the instructions to generate the advertisement comprises generating the advertisement by;

selecting an advertisement template based at least in part on the one or more user intents; and

customizing the advertisement template based at least in part on the one or more user intents.

34. A system comprising:

a memory comprising instructions; and

one or more processors coupled to the memory and operable to execute the instructions to;

receive, in real-time, user information associated with a user of a client computing device;

derive one or more user features from the user information associated with the user, the one or more user features comprising one or more user intents;

match, using one or more intent graphs, the one or more user intents with one or more of a plurality of advertiser intents by;

accepting, at an intent matcher processing subsystem of one or more server computer devices, one or more intent match context objects, wherein the one or more intent match context objects comprise a list of topic-term pairs as output, each of the one or more intent match context objects are associated with at least one of the one or more user intents, the one or more intent match context objects are accepted as input and returned as output at each of a plurality of processing subsystems of a processing pipeline of the one or more server computer devices implementing an intent match runtime system, the plurality of processing subsystems comprising the intent matcher processing subsystem, and each respective processing subsystem of the plurality of processing subsystems is configured to change only a context field of a context object of the one or more intent match context objects corresponding to a responsibility of the each respective processing subsystem;

use one or more statistical models to compute a similarity score between the one or more user features and the one or more of the plurality of advertiser intents;

determine that the user information is accepted including determining that the similarity score exceeds a threshold;

in response to accepting the user information, transmit a request for an advertisement to an advertiser associated with the one or more of the plurality of advertiser intents;

receive the advertisement from the advertiser associated with the one or more of the plurality of advertiser intents; and

display the advertisement received from the advertiser to the user.

35. The system of claim 34, wherein, the user information associated with the user comprises a search engine query of the user.

36. The system of claim 35, wherein the or more processors are further operable to:

parse the search engine query submitted by the user to determine a presence of one or more sets of words; and

derive the one or more user intents based on the one or more sets of words in the search engine query.

37. The method of claim 36, wherein:

when determining that the user information is accepted, the one or more processors are operable to determine that every one of the one or more sets of words in the search engine query matches at least one of the plurality of advertiser intents.

38. The system of claim 34, wherein the user information comprises one or more present online activities of the user and the one or more processors are further operable to determine the one or more user features based on the one or more present online activities of the user.

39. The system of claim 34, wherein, when determining that the user information is accepted, the one or more processors are further operable to determine that the one or more user intents match the one or more of the plurality of advertiser intents.

40. The system of claim 34, wherein, when determining that the user information is accepted, the one or more processors are further operable to determine that every one of the one or more user intents matches at least one of the plurality of advertiser intents.

41. The system of claim 34, wherein when determining that the user information is accepted, the one or more processors are further operable to:

determine that at least one of the one or more user intents matches at least one of a first specified subset of the plurality of advertiser intents; and

determine that every one of the one or more user intents does not match any one of a second specified subset of the plurality of advertiser intents.

42. The system of claim 34, wherein the one or more processors are further operable to:

derive a plurality of keywords from the plurality of advertiser intents, and

determine that one or more of the plurality of keywords matches with the one or more user intents when determining that the user information is accepted.

43. The system of claim 34, wherein the one or more processors are further operable to:

receive one or more bids for the search engine query, each bid of the one or more bids comprising a maximum payment amount that an advertiser placing the bid agrees to pay if the bid is selected.

44. The system of claim 43, wherein the bid further comprises the advertisement.