Methods and apparatus for ranking documents

• US 10,496,652 B1
• Filed: 09/12/2016
• Issued: 12/03/2019
• Est. Priority Date: 09/20/2002
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Bharat, Krishna, Dean, Jeffrey A., Curtiss, Michael, Singhal, Amitabh, Schmitt, Michael
• Primary Examiner(s): Truong, Dennis
• Application Number:
  US15/262,189
• Time in Patent Office: 1,177 Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods and apparatus are described for scoring documents in response, in part, to parameters related to the document, source, and/or cluster score. Methods and apparatus are also described for scoring a cluster in response, in part, to parameters related to documents within the cluster and/or sources corresponding to the documents within the cluster. In one embodiment, the invention may detect at least one document within the cluster; analyze a parameter corresponding to the document; and compute a cluster score based, in part, on the parameter, wherein the cluster score corresponds with at least one document within the cluster.

Claims

1. A method comprising:

identifying, by one or more server devices, a first document;

analyzing, by the one or more server devices, content of the first document to determine a first topic;

identifying a set of sources by determining, for each source of a plurality of sources, a source score for the source and including the source in the set when the source score determined for the source satisfies a threshold, wherein determining the source score for each source of the plurality of sources comprises;

detecting, by the one or more server devices, original articles published by the source, wherein each original article is a document that was first published by the source;

analyzing, by the one or more server devices, content of the original articles to determine a given category for the content of the original articles from the source;

assigning, by the one or more server devices, a source score for the source for the given category;

determining, by the one or more server devices, that the source score for the source satisfies the threshold for the given category; and

selecting the source to include in the set of sources;

determining, by the one or more server devices and from the set of sources satisfying the threshold, a number of documents from the set of sources, each of the documents having content related to a topic that is similar to the first topic;

forming, by the one or more server devices, a first subject cluster for the first topic including the number of documents from the set of sources satisfying the threshold and the first document;

receiving, by the one or more server devices, a second document;

analyzing, by the one or more server device, content of the second document to determining a second topic; and

responsive to the second topic being similar to the first topic of the first subject cluster, placing the second document in the first subject cluster.

2. The method of claim 1, further comprising:

determining a number of sources that published a plurality of documents with the similar topic; and

responsive to the number of the sources that published the plurality of documents with the similar topic satisfying a second predetermined threshold, forming a second subject cluster.

3. The method of claim 1, further comprising determining a centroid for the first subject cluster based on the first topic of the first subject cluster.

4. The method of claim 3, wherein the centroid of the first subject cluster may be updated based on the second topic of the second document.

5. The method of claim 3, wherein the centroid of the subject cluster includes a summary of the topic of the subject cluster.

6. The method of claim 1, wherein analyzing the content of the first document further comprises:

determining a document vector for the first document, the document vector including a subject matter of the first document; and

determining the topic for the first document based on the document vector.

7. The method of claim 1, wherein analyzing the content of the first document further comprises:

determining a document vector for the first document, the document vector including a key term characterizing the topic of the document; and

determining the topic for the first document based on the document vector.

8. A computer program product comprising a non-transitory computer readable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to perform operations comprising:

identifying a first document;

analyzing content of the first document to determine a first topic;

identifying a set of sources by determining, for each source of a plurality of sources, a source score for the source and including the source in the set when the source score determined for the source satisfies a threshold, wherein determining the source score for each source of the plurality of sources comprises;

detecting, by the one or more server devices, original articles published by the source, wherein each original article is a document that was first published by the source;

analyzing, by the one or more server devices, content of the original articles to determine a given category for the content of the original articles from the source;

assigning, by the one or more server devices, a source score for the source for the given category;

determining, by the one or more server devices, that the source score for the source satisfies the threshold for the given category; and

selecting the source to include in the set of sources;

determining from the set of sources satisfying the threshold a number of documents from the set of sources, each of the documents having content related to a topic that is similar to the first topic;

forming a first subject cluster for the first topic including the number of documents from the set of sources satisfying the threshold and the first document;

receiving a second document;

analyzing content of the second document to determining a second topic; and

responsive to the second topic being similar to the first topic of the first subject cluster, placing the second document in the first subject cluster.

9. The computer program product of claim 8, wherein the operations further comprise:

determining a number of sources that published a plurality of documents with the similar topic; and

responsive to the number of the sources that published the plurality of documents with the similar topic satisfying a second predetermined threshold, forming a second subject cluster.

10. The computer program product of claim 8, wherein the operations further comprise determining a centroid for the first subject cluster based on the first topic of the first subject cluster.

11. The computer program product of claim 10, wherein the centroid of the first subject cluster may be updated based on the second topic of the second document.

12. The computer program product of claim 10, wherein the centroid of the subject cluster includes a summary of the topic of the subject cluster.

13. The computer program product of claim 8, wherein analyzing the content of the first document further comprises:

determining a document vector for the first document, the document vector including a subject matter of the first document; and

determining the topic for the first document based on the document vector.

14. The computer program product of claim 8, wherein analyzing the content of the first document further comprises:

determining a document vector for the first document, the document vector including a key term characterizing the topic of the document; and

determining the topic for the first document based on the document vector.

15. A system comprising:

a processor; and

a memory storing instructions that, when executed, cause the system to perform operations comprising;

identifying a first document;

analyzing content of the first document to determine a first topic;

identifying a set of sources by determining, for each source of a plurality of sources, a source score for the source and including the source in the set when the source score determined for the source satisfies a threshold, wherein determining the source score for each source of the plurality of sources comprises;

detecting, by the one or more server devices, original articles published by the source, wherein each original article is a document that was first published by the source;

analyzing, by the one or more server devices, content of the original articles to determine a given category for the content of the original articles from the source;

assigning, by the one or more server devices, a source score for the source for the given category;

determining, by the one or more server devices, that the source score for the source satisfies the threshold for the given category; and

selecting the source to include in the set of sources;

determining from the set of sources satisfying the threshold a number of documents from the set of sources, each of the documents having content related to a topic that is similar to the first topic;

forming a first subject cluster for the first topic including the number of documents from the set of sources satisfying the threshold and the first document;

receiving a second document;

analyzing content of the second document to determining a second topic; and

responsive to the second topic being similar to the first topic of the first subject cluster, placing the second document in the first subject cluster.

16. The system of claim 15, wherein the operations further comprise:

determining a number of sources that published a plurality of documents with the similar topic; and

responsive to the number of the sources that published the plurality of documents with the similar topic satisfying a second predetermined threshold, forming a second subject cluster.

17. The system of claim 15, wherein the operations further comprise determining a centroid for the first subject cluster based on the first topic of the first subject cluster.

18. The system of claim 17, wherein the centroid of the first subject cluster may be updated based on the second topic of the second document.

19. The system of claim 17, wherein the centroid of the subject cluster includes a summary of the topic of the subject cluster.

20. The system of claim 15, wherein the operations further comprise:

determining a document vector for the first document, the document vector including a subject matter of the first document; and

determining the topic for the first document based on the document vector.

21. The system of claim 15, wherein the operations further comprise:

determining a document vector for the first document, the document vector including a key term characterizing the topic of the document; and

determining the topic for the first document based on the document vector.