DOCUMENT SCORING BASED ON DOCUMENT CONTENT UPDATE

• US 20110264671A1
• Filed: 06/30/2011
• Published: 10/27/2011
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Hoelzie, Urs, Henzinger, Monika, Lawrence, Steve, Pfleger, Karl, Acharya, Anurag, Sercinoglu, Olcan, Tong, Simon, Cutts, Matt, Haahr, Paul, Dean, Jeffrey
• Granted Patent: US 8,527,524 B2
• Time in Patent Office: Days
• US Class Current: 707/749
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A system may determine a measure of how a content of a document changes over time, generate a score for the document based, at least in part, on the measure of how the content of the document changes over time, and rank the document with regard to at least one other document based, at least in part, on the score.

Claims

1-34. -34. (canceled)

35. A system, comprising:

one or more devices to;

determine a set of topics associated with a document;

identify, over a time period, how much the set of topics has changed during the time period;

generate a score for the document based on how much the set of topics, associated with the document, has changed during the time period; and

rank the document with regard to at least one other document based on the score.

36. The system of claim 35, where the one or more devices are further to:

identify a spike in a quantity of topics in the set of topics; and

classify the document as spam upon identifying the spike in the quantity of topics in the set of topics.

37. The system of claim 36, where when generating the score, the one or more devices are to:

alter the score based on classifying the document as spam.

38. The system of claim 35, where when determining the set of topics associated with the document, the one or more devices are to use at least one of:

a categorization of the document,

a Universal Resource Locator (URL) analysis of the document,

an analysis of content of the document,

a clustering of the document, or

a summarization of the document.

39. The system of claim 35, where the one or more devices are further to:

detect a removal of a topic that was previously associated with the document; and

classify the document as spam upon detecting the removal of the topic that was previously associated with the document.

40. The system of claim 39, where the generated score is a first score, where the one or more devices are further to:

generate a second score, for the document, that is based on a relevance of the document to a search query; and

combine the first and second scores to generate an overall score,

where when ranking the document, the one or more devices are to rank the document with regard to the at least one other document based on the overall score.

41. The system of claim 40, where when combining the first and second scores, the one or more devices are to:

adjust the second score by an amount that is based on the first score.

42. A method performed by one or more devices, the method comprising:

determining, by at least one of the one or more devices, a set of topics associated with a document;

identifying, by at least one of the one or more devices and over a time period, how much the set of topics has changed during the time period;

generating, by at least one of the one or more devices, a score for the document based on how much the set of topics, associated with the document, has changed during the time period; and

ranking, by at least one of the one or more devices, the document with regard to at least one other document based on the score.

43. The method of claim 42, further comprising:

identifying a spike in a quantity of topics in the set of topics; and

classifying the document as spam upon identifying the spike in the quantity of topics in the set of topics.

44. The method of claim 43, where generating the score comprises:

altering the score based on classifying the document as spam.

45. The method of claim 42, where determining the set of topics associated with the document is based on at least one of:

a categorization of the document,

a Universal Resource Locator (URL) analysis of the document,

an analysis of content of the document,

a clustering of the document, or

a summarization of the document.

46. The method of claim 42, further comprising:

detecting a removal of a topic that was previously associated with the document; and

classifying the document as spam upon detecting the removal of the topic that was previously associated with the document.

47. The method of claim 46, where the generated score is a first score, the method further comprising:

generating a second score, for the document, that is based on a relevance of the document to a search query; and

combining the first and second scores to generate an overall score,

where ranking the document includes ranking the document with regard to the at least one other document based on the overall score.

48. The method of claim 47, where combining the first and second scores includes:

adjusting the second score by an amount that is based on the first score.

49. A computer-readable memory device storing programming instructions that are executable by one or more processors of one or more devices, the programming instructions comprising:

one or more instructions to determine a set of topics associated with a document;

one or more instructions to identify, over a time period, how much the set of topics has changed during the time period;

one or more instructions to generate a score for the document based on how much the set of topics, associated with the document, has changed during the time period; and

one or more instructions to rank the document with regard to at least one other document based on the score.

50. The computer-readable memory device of claim 49, where the programming instructions further comprise:

one or more instructions to identify a spike in a quantity of topics in the set of topics; and

one or more instructions to classify the document as spam upon identifying the spike in the quantity of topics in the set of topics.

51. The computer-readable memory device of claim 50, where the one or more instructions to generate the score include:

one or more instructions to alter the score based on classifying the document as spam.

52. The computer-readable memory device of claim 49, where the one or more instructions to determine the set of topics associated with the document include one or more instructions to determine the set of topics based on:

a categorization of the document,

a Universal Resource Locator (URL) analysis of the document,

an analysis of content of the document,

a clustering of the document, or

a summarization of the document.

53. The computer-readable memory device of claim 49, where the programming instructions further comprise:

one or more instructions to detect a removal of a topic that was previously associated with the document; and

one or more instructions to classify the document as spam upon detecting the removal of the topic that was previously associated with the document.

54. The computer-readable memory device of claim 53, where the generated score is a first score, where the programming instructions further comprise:

one or more instructions to generate a second score, for the document, that is based on a relevance of the document to a search query; and

one or more instructions to combine the first and second scores to generate an overall score,

where the one or more instructions to rank the document include one or more instructions to rank the document with regard to the at least one other document based on the overall score.

55. The computer-readable memory device of claim 54, where the one or more instructions to combine the first and second scores include:

one or more instructions to adjust the second score by an amount that is based on the first score.