Computer system and method for analyzing data sets and providing personalized recommendations

• US 9,396,492 B2
• Filed: 10/14/2011
• Issued: 07/19/2016
• Est. Priority Date: 10/15/2010
• Status: Active Grant

• Current Assignee: OpenTable, Inc. (Booking Holdings, Inc., fka Priceline Group Inc.)
• Original Assignee: OpenTable, Inc. (Booking Holdings, Inc., fka Priceline Group Inc.)
• Inventors: Schiff, Jeremy, Reese, Corey, Wang, Yige, Goodson, Scott, Twohey, Paul Kenneth
• Primary Examiner(s): Garg, Yogesh C
• Application Number:
  US13/274,235
• Publication Number:
  US 20120095863A1
• Time in Patent Office: 1,740 Days
• Field of Search: 705/26.7, 705/26.1, 705/14.66, 705/14.53, 705/14.68, 705/14.55, 705/7.31, 705/1.1, 705/14.38, 725/109, 725/110, 725/93, 725/116, 709/224, 707/732, 707/749, 707/802, 348/207.99
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Embodiments of the invention relate to a computer-implemented method and system for providing personalized recommendations for a target user based at least on stored data about the target user. The method comprises obtaining a plurality of feedback data from a plurality of users, wherein the feedback data comprises an indication of a media object, a response obtained from target user related to the feedback data, and at least one demographic data element associated with the target user. A set of personalized recommendations for the target user are identified based at least on stored data about the target user and the feedback data related to the user. The personalized recommendations system identifies media objects to potentially provide to the target user, and selects or filters the identified media objects to form a set of personalized media objects associated with the set of personalized recommendations.

Claims

1. A computer-implemented method for providing personalized recommendation results for a target user based at least on stored data about the target user, comprising:

obtaining, at a server computer, a plurality of feedback data items from a plurality of user mobile devices, wherein the plurality of feedback data items comprise;

an indication of a high quality photo with a type,

a response to the high quality photo obtained from a user mobile device of the plurality of user mobile devices, and

at least one demographic data element associated with a user of the user mobile device;

storing the plurality of feedback data items in a feedback database, wherein the feedback database is searchable by high quality photos;

determining, by an engine executing on the server computer, a set of personalized recommendation results for a target user mobile device, based at least on the stored data about the target user of the target user mobile device and feedback data related to the target user;

identifying, by the server computer, high quality photos to potentially provide to the target user mobile device in connection with the set of personalized recommendation results including a plurality of high quality photos that are associated with a particular recommendation result of the set of personalized recommendation results;

by the server computer, filtering the identified high quality photos to form a set of personalized high quality photos that are to be provided to the target user mobile device, wherein the filtering comprises;

identifying, a set of one or more demographic data elements associated with the target user of the target user mobile device;

determining, from the plurality of feedback data items, a particular type of photo that elicits a desired response from a plurality of other users associated with that set of one or more demographic data elements; and

in response to determining the particular type of photo, selecting, to display in association with the particular recommendation result, a particular high quality photo from the plurality of high quality photos associated with the particular recommendation result based on feedback data items of the plurality of other users all having demographic data elements that are aligned with the set of one or more demographic data elements associated with the target user of the target user mobile device;

providing, by the server computer to the target user mobile device;

the set of personalized recommendation results including the particular recommendation result,

the set of personalized high quality photos including the particular high quality photo; and

a particular message relating to the particular recommendation result;

receiving, from the target user mobile device, a particular response to the provided set of personalized high quality photos, the particular response comprising a click on the set of personalized high quality photos displayed on the target user mobile device; and

creating one or more additional feedback data items from the received click based on observed user behavior.

2. The method of claim 1, wherein the set of personalized recommendation results are for entities, comprising venues, merchants, media, products, and/or service providers.

3. The method of claim 1, wherein each recommendation in the set of personalized recommendation results corresponds to a respective high quality photo.

4. The method of claim 3, wherein the desired response is a click-through of the type of high quality photo.

5. The method of claim 3, wherein the desired response is a purchase, a visit to a website related to an entity, a visit to the entity, or a transaction related to the high quality photo.

6. The method of claim 3, wherein the high quality photos are arranged in a personalized layout, wherein the personalized layout is determined by a computer process that considers which layout of the high quality photos are associated with the desired response.

7. The method of claim 6, wherein the personalized layout is displayed on a device, wherein the device comprises a touchscreen.

8. The method of claim 7, further comprising shaking the device displaying the personalized layout of the set of personalized high quality photos associated with the set personalized recommendation results refreshes the set of personalized recommendation results.

9. The method of claim 7, further comprising lobbing the device toward another user passes a personalized recommendation result for the target user to the other user.

10. The method of claim 7, further comprising blowing on the device removes the set of personalized recommendation results.

11. The method of claim 7, further comprising pressing and holding down on a high quality photo displayed on the device reveals more information related to a recommendation result associated with the high resolution image.

12. The method of claim 7, further comprising swiping a given personalized high quality photo associated with a given personalized recommendation towards another user mobile device to pass the personalized recommendation for the target user mobile device to the other user mobile device.

13. The method of claim 7, further comprising pulling two fingers together on the touchscreen to simulate crinkling a given high quality photo associated with a given personalized recommendation result to remove the given personalized recommendation result.

14. The method of claim 1, wherein at least some of the feedback data items have an associated location, where the associated location represents an entity that provides a venue, goods, and/or services for which the feedback data item pertains, the method further comprising:

identifying at least a suggested location from raw feedback data;

mapping the suggested location to a known, enumerated location associated with an entity in an entity database, thereby canonicalizing locations and canonicalizing entities associated with the raw feedback data; and

using a canonicalized location or canonicalized entity when identifying high quality photos to potentially provide to the target user mobile device.

15. The method of claim 14, further comprising:

creating a personal profile for the target user of the target user mobile device based on at least stored data about the target user and a feedback data item related to the target user;

determining, from raw feedback data used to generate the feedback data item, a feedback message;

identifying, by the server computer, a sentiment response to the canonicalized location or canonicalized entity from the feedback data item, wherein the identifying is determined by a computer process that interprets the feedback message;

updating the personal profile of the target user based on the sentiment response;

updating the entity database based on the sentiment response; and

using the updated personal profile when determining the set of personalized recommendation results for the target user mobile device.

16. The method of claim 15, wherein the target user is a primary user, the method further comprising:

analyzing, at the server computer, the personal profile of the primary user and a personal profile of at least one or more secondary users;

cross-referencing, at the server computer, the personal profile of the primary user, with the personal profiles of the at least one or more secondary users;

determining a relationship between the primary user and the at least one or more secondary users;

determining a group relevance based on the relationship between the primary user and the at least one or more secondary users;

determining, by the server computer, a set of group personalized recommendation results for the primary user and the at least one or more secondary users, based at least on stored data about the primary user, stored data about the at least one or more secondary users, the plurality of feedback data items related to the primary user, and feedback data related to the at least one or more secondary users;

identifying, by the server computer, group high quality photos to potentially provide to the target user mobile device in connection with the set of group personalized recommendation results;

selecting or filtering the identified high quality photos to form a set of group personalized high quality photos that are to be provided to the target user mobile device, wherein the selecting or filtering is determined by a computer process that considers which high quality photos are associated with the desired response of users having demographic data elements aligned with demographic data about the primary user and the at least one or more secondary users; and

providing the set of group personalized recommendation results, including the set of group personalized high quality photos to the primary user and the at least one or more secondary users.

17. The method of claim 16, wherein the set of group personalized high quality photos and the set of group personalized recommendation results for the primary user are based on the updated profile of a secondary user.

18. The method of claim 16, further comprising providing a set of personalized summaries to the target user mobile device, wherein each personalized summary in the set is related to a corresponding high quality photo and a corresponding personalized recommendation result in the set of personalized recommendation results, wherein each personalized summary in the set of personalized summaries comprises summary content related to the corresponding personalized recommendation result.

19. The method of claim 18, wherein the summary content is determined by a computer process that considers what summary content is associated with the desired response.

20. The method of claim 19, wherein the set of personalized summaries comprises a set of personalized explanations to provide to the target user mobile device, to inform why the set of recommendation results are personalized to the target user.

21. The method of claim 20, wherein the set of personalized explanations to provide to the target user mobile device is based on the canonicalized location or canonicalized entity from the entity database.

22. The method of claim 19, wherein the summary content comprises the feedback data from the at least one or more secondary users associated with the primary user.

23. The method of claim 16, wherein the relationship between the primary user and the at least one or more secondary users is determined by a computer process that considers similarities in the feedback message of the primary user and the feedback messages of the at least one or more secondary users.

24. The method of claim 16, further comprising:

analyzing the feedback data related to the primary user and the feedback data related to the at least one or more secondary users;

identifying the associated location of the primary user and the associated locations of the at least one or more secondary users based on the feedback data related to the primary user and the feedback data related to the at least one or more secondary users, respectively; and

updating the relationship between the primary user and the at least one or more secondary users, wherein the relationship between the primary user and the at least one or more secondary users is updated by a computer process that determines whether the associated location of the primary user is in close proximity of the associated location of the at least one or more secondary users.

25. The method of claim 1, wherein the plurality of feedback data items include a set of feedback data items obtained from the target user mobile device to iteratively identify the set of personalized recommendation results for the target user mobile device.

26. The method of claim 25, further comprising:

using the feedback data items previously obtained and stored in the feedback database to create a feedback history of the target user;

analyzing the feedback history of the target user;

creating a feedback filter based on the feedback history; and

applying the feedback filter to filter the set of personalized recommendation results.

27. The method of claim 1, wherein the particular response further comprises a clickstream of clicks observed on the set of personalized high quality photos displayed on the target user mobile device.

28. A system for providing personalized recommendation results for a target user based at least on stored data about the target user, the system comprising a server computer comprising a process and a computer readable medium, the computer readable medium comprising code executable by the processor to perform a method, the method comprising:

obtaining, at a server computer, a plurality of feedback data items from a plurality of user mobile devices, wherein the plurality of feedback data items comprise;

an indication of a high quality photo,

a response to the high quality photo obtained from a user mobile device of the plurality of user mobile devices, and

at least one demographic data element associated with a user of the user mobile device;

storing the plurality of feedback data items in a feedback database, wherein the feedback database is searchable by high quality photos;

determining, by an engine executing on the server computer, a set of personalized recommendation results for a target user mobile device, based at least on the stored data about the target user of the target user mobile device and feedback data related to the target user;

identifying, by the server computer, high quality photos to potentially provide to the target user mobile device in connection with the set of personalized recommendation results including a plurality of high quality photos associated with a particular recommendation result of the set of personalized recommendation results;

by the server computer, filtering the identified high quality photos to form a set of personalized high quality photos that are to be provided to the target user mobile device, wherein the filtering comprises;

identifying, a set of one or more demographic data elements associated with the target user of the target user mobile device;

determining, from the plurality of feedback data items, a particular type of photo that elicits a desired response from a plurality of other users associated with that set of one or more demographic data elements;

in response to determining the particular type of photo, selecting, to display in association with the particular recommendation result, a particular high quality photo from the plurality of high quality photos associated with the particular recommendation result based on feedback of the plurality of other users all having demographic data elements that are aligned with the set of one or more demographic data elements associated with the target user of the target user mobile device; and

providing, from the server computer to the target user mobile device;

the set of personalized recommendation results including the particular recommendation result,

the set of personalized high quality photos including the particular high quality photo; and

a particular message relating to the particular recommendation result;

receiving, from the target user mobile device, a particular response to the provided set of personalized high quality photos, the particular response comprising a click on the set of personalized high quality photos displayed on the target user mobile device; and

creating one or more additional feedback data items from the received click based on observed user behavior.

29. The system of claim 28, wherein the set of personalized recommendation results are for entities, comprising venues, merchants, media, products, and/or service providers.

30. The system of claim 28, wherein each recommendation in the set of personalized recommendation results corresponds to a high quality photo in the set of personalized high quality photos.

31. The system of claim 30, wherein the desired response is a click-through of the high quality photo.

32. The system of claim 30, wherein the desired response is a purchase, a visit to a website related to an entity, a visit to the entity, or a transaction related to the high quality photo.

33. The system of claim 30, wherein the high quality photos are arranged in a personalized layout, wherein the personalized layout is determined by a computer process that considers which layout of the high quality photos are associated with the desired response.

34. The system of claim 33, further comprising a device displaying the personalized layout, wherein the device comprises a touchscreen.

35. The system of claim 34, wherein shaking the device displaying the personalized layout of the set of personalized high quality photos associated with the set personalized recommendation results refreshes the set of personalized recommendation results.

36. The system of claim 34, wherein lobbing the device toward another user passes a personalized recommendation for the target user to the other user.

37. The system of claim 34, wherein blowing on the device removes the set of personalized recommendation results.

38. The system of claim 34, wherein pressing and holding down on a given high quality photo displayed on the device reveals more information related to a given recommendation result associated with the high quality photo.

39. The system of claim 34, wherein pulling two fingers apart on the touchscreen simulates tearing a given high quality photo associated with a given personalized recommendation result to remove the given personalized recommendation result.

40. The system of claim 34, wherein swiping a personalized high quality photo associated with a personalized recommendation result on the touch screen towards another user mobile device passes the personalized recommendation for the target user mobile device to the other user mobile device.

41. The system of claim 34, wherein pulling two fingers together on the touchscreen simulates crinkling a given high quality photo associated with a personalized recommendation to remove the personalized recommendation.

42. The system of claim 28, wherein at least some of the feedback data items have an associated location, where the associated location represents an entity that provides a venue, goods, and/or services for which the feedback data item pertains, the method further comprising:

identifying at least a suggested location from raw feedback data;

mapping the suggested location to a known, enumerated location associated with an entity in an entity database, thereby canonicalizing locations and canonicalizing entities associated with the raw feedback data; and

using a canonicalized location or canonicalized entity when identifiying high quality photos to potentially provide to the target user mobile device.

43. The system of claim 42, the method further comprising:

creating a personal profile for the target user of the target user mobile device based on at least stored data about the target user and a feedback data item related to the target user;

determining, from raw feedback data used to generate the feedback data item, a feedback message;

identifying, by the server computer, a sentiment response to the canonicalized location or canonicalized entity from the feedback data item, wherein the identifying is determined by a computer process that interprets the feedback message;

updating the personal profile of the target user based on the sentiment response;

updating the entity database based on the sentiment response; and

using the updated personal profile when determining the set of personalized recommendation results to potentially provide to the target user mobile device.

44. The system of claim 43, wherein the target user is a primary user, the method further comprising:

analyzing, at the server computer, the personal profile of the primary user and a personal profile of at least one or more secondary users;

cross-referencing, at the server computer, the personal profile of the primary user, with the personal profiles of the at least one or more secondary users;

determining a relationship between the primary user and the at least one or more secondary users;

determining a group relevance based on the relationship between the primary user and the at least one or more secondary users;

determining, by the server computer, a set of group personalized recommendation results for the primary user and the at least one or more secondary users, based at least on stored data about the primary user, stored data about the at least one or more secondary users, feedback data related to the primary user, and the feedback data related to the at least one or more secondary users;

identifying, by the server computer, group high quality photos to potentially provide to the target user mobile device in connection with the set of group personalized recommendation results;

selecting or filtering the identified high quality photos form a set of group personalized high quality photos that are to be provided to the target user mobile device, wherein the selecting or filtering is determined by a computer process that considers which high quality photos are associated with the desired response of users having demographic data elements aligned with demographic data about the primary user and the at least one or more secondary users; and

providing the set of group personalized recommendation results, including the set of group personalized high quality photos to the primary user and the at least one or more secondary users.

45. The system of claim 44, wherein the set of group personalized high quality photos and the set of group personalized recommendation results for the primary user are based on the updated profile of a secondary user.

46. The system of claim 44, the method further comprising providing a set of personalized summaries to the target user mobile device, wherein each personalized summary in the set is related to a corresponding personalized high quality photos and a corresponding personalized recommendation result in the set of personalized recommendation results, wherein each personalized summary in the set of personalized summaries comprises summary content related to the corresponding personalized recommendation result.

47. The system of claim 46, wherein the summary content is determined by a computer process that considers what summary content is associated with the desired response.

48. The system of claim 47, wherein the set of personalized summaries comprises a set of personalized explanations to provide to the target user mobile device, to inform why the set of recommendation results are personalized to the target user.

49. The system of claim 48, wherein the set of personalized explanations to provide to the target user mobile device is based on the canonicalized location or canonicalized entity from the entity database.

50. The system of claim 47, wherein the summary content comprises the feedback data from the at least one or more secondary users associated with the primary user.

51. The system of claim 44, wherein the relationship between the primary user and the at least one or more secondary users is determined by a computer process that considers similarities in the feedback message of the primary user and the feedback messages of the at least one or more secondary users.

52. The system of claim 44, the method further comprising:

analyzing the plurality of feedback data related to the primary user and the feedback data related to the at least one or more secondary users;

identifying the associated location of the primary user and the associated locations of the at least one or more secondary users based on the plurality of feedback data related to the primary user and the feedback data related to the at least one or more secondary users, respectively; and

updating the relationship between the primary user and the at least one or more secondary users, wherein the relationship between the primary user and the at least one or more secondary users is updated by a computer process that determines whether the associated location of the primary user is in close proximity of the associated location of the at least one or more secondary users.

53. The system of claim 28, wherein the plurality of feedback data items include a set of feedback data items obtained from the target user mobile device to iteratively identify the set of personalized recommendation results for the target user mobile device.

54. The system of claim 53, the method further comprising:

using the plurality of feedback data items previously obtained and stored in the feedback database to create a feedback history of the target user;

analyzing the feedback history of the target user;

creating a feedback filter based on the feedback history; and

applying the feedback filter to filter the set of personalized recommendation results.

55. The system of claim 28, wherein the particular response further comprises a clickstream of clicks observed on the set of personalized high quality photos displayed on the target user mobile device.