Searchable Index

• US 20150317357A1
• Filed: 05/02/2014
• Published: 11/05/2015
• Est. Priority Date: 05/02/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Harmsen, Jeremiah, Chandra, Tushar Deepak, Fontoura, Marcus
• Granted Patent: US 10,255,319 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/319 Inverted lists
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data

Abstract

Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.

Claims

1-25. -25. (canceled)

26. A computer-implemented method comprising:

receiving, from a predictive model, data indicating a predicted likelihood of a user selecting a particular item of content, wherein the predicted likelihood is generated by the predictive model based at least on one or more features relating to (i) the user, (ii) a search query submitted by the user, (iii) the particular item of content, (iv) a device associated with the user, or (v) a current condition; and

storing, in a search index, data that associates (i) the particular item of content, (ii) the predicted likelihood, and (iii) one or more of the features.

27. The method of claim 26, wherein the one or more features relating to the current condition comprises a current time or a current event.

28. The method of claim 26, wherein the one or more features relating to the device associated with the user comprises a location of the device, a configuration of the device, an operating system of the device, a screen resolution of the device, or a bandwidth of a connection to the device.

29. The method of claim 26, wherein the one or more features relating to the user comprises a language used by the user, demographics of the user, or an account of the user.

30. The method of claim 26, comprising:

training the predictive model using training data that associates a selection of an item of content and one or more corresponding features.

31. The method of claim 26, wherein the predictive likelihood is further generated by applying weights to each of the one or more features.

32. The method of claim 26, wherein the particular item of content is a video, document, advertisement, image, or an audio file.

33. The method of claim 26, comprising:

determining the search query submitted by the user based on a characteristics of a selection of an additional item of content, wherein the characteristics are related to an identity of the additional item of content or a top of the additional item of content.

34. The method of claim 26, wherein the search index is an inverted index or a posting list.

35. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving, from a predictive model, data indicating a predicted likelihood of a user selecting a particular item of content, wherein the predicted likelihood is generated by the predictive model based at least on one or more features relating to (i) the user, (ii) a search query submitted by the user, (iii) the particular item of content, (iv) a device associated with the user, or (v) a current condition; and

storing, in a search index, data that associates (i) the particular item of content, (ii) the predicted likelihood, and (iii) one or more of the features.

36. The system of claim 35, wherein the one or more features relating to the current condition comprises a current time or a current event.

37. The system of claim 35, wherein the one or more features relating to the device associated with the user comprises a location of the device, a configuration of the device, an operating system of the device, a screen resolution of the device, or a bandwidth of a connection to the device.

38. The system of claim 35, wherein the one or more features relating to the user comprises a language used by the user, demographics of the user, or an account of the user.

39. The system of claim 35, wherein the operations further comprise:

training the predictive model using training data that associates a selection of an item of content and one or more corresponding features.

40. The system of claim 35, wherein the predictive likelihood is further generated by applying weights to each of the one or more features.

41. The system of claim 35, wherein the particular item of content is a video, document, advertisement, image, or an audio file.

42. The system of claim 35, wherein the operations further comprise:

determining the search query submitted by the user based on a characteristics of a selection of an additional item of content, wherein the characteristics are related to an identity of the additional item of content or a top of the additional item of content.

43. The system of claim 35, wherein the search index is an inverted index or a posting list.

44. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving, from a predictive model, data indicating a predicted likelihood of a user selecting a particular item of content, wherein the predicted likelihood is generated by the predictive model based at least on one or more features relating to (i) the user, (ii) a search query submitted by the user, (iii) the particular item of content, (iv) a device associated with the user, or (v) a current condition; and

storing, in a search index, data that associates (i) the particular item of content, (ii) the predicted likelihood, and (iii) one or more of the features.

45. The medium of claim 44, wherein the one or more features relating to the current condition comprises a current time or a current event.

46. The medium of claim 44, wherein the one or more features relating to the device associated with the user comprises a location of the device, a configuration of the device, an operating system of the device, a screen resolution of the device, or a bandwidth of a connection to the device.

47. The medium of claim 44, wherein the one or more features relating to the user comprises a language used by the user, demographics of the user, or an account of the user.

48. The medium of claim 44, wherein the operations further comprise:

training the predictive model using training data that associates a selection of an item of content and one or more corresponding features.

49. The medium of claim 44, wherein the predictive likelihood is further generated by applying weights to each of the one or more features.

50. The medium of claim 44, wherein the operations further comprise:

determining the search query submitted by the user based on a characteristics of a selection of an additional item of content, wherein the characteristics are related to an identity of the additional item of content or a top of the additional item of content.