Associating documents with classifications and ranking documents based on classification weights

• US 20060129550A1
• Filed: 01/18/2006
• Published: 06/15/2006
• Est. Priority Date: 09/17/2002
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Hongyuan Zha, Sean Suchter
• Inventors: Zha, Hongyuan, Suchter, Sean
• Granted Patent: US 7,533,119 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method and apparatus for associating documents with classification values and ranking documents based on classification weights is provided. It is determined if a document is associated a classification. If the document is associated with a classification, then it is determined if a classification value, which is associated with the document, is associated with a weight. If the classification value is associated with a weight, then a rank of the document is adjusted based on the weight that is associated with the classification value.

Claims

1-9. -9. (canceled)

10. A method of associating region information with documents, the method comprising the steps of:

determining a language associated with a document;

determining whether the language belongs to a first set of languages;

if the language belongs to the first set of languages, then associating with said document one or more regions associated with said language; and

if the language does not belong to the first set of languages, then associating with said document one or more regions based on factors other than said language.

11. A method of associating region information with documents, the method comprising the steps of:

determining a host associated with a document;

determining whether the host associated with the document has a strong relationship between one or more regions;

if the host associated with the document has a strong relationship between one or more regions, then associating with said document said one or more regions associated with said host.

12. The method of claim 11 wherein the step of determining whether the host associated with the document has a strong relationship between one or more regions includes the steps of:

determining if a top-level domain of said host is a regional domain;

if the top-level domain of the host is a regional domain, then associating the document with at least one region that is associated with the top-level domain of the host; and

if the top-level domain of the host is not a regional domain, then determining which regions said host is associated with based on factors other than said top-level domain of said host.

13. The method of claim 12 wherein the step of determining which regions said host is associated with based on factors other than said top-level domain of said host includes the steps of:

determining if a language of the document is associated with one or more regions;

if the language of the document is associated with one or more regions, then associating the document with at least one region that is associated with the language of the document;

determining if the host is associated with one or more regions; and

if the host is associated with one or more regions, then associating the document with at least one region that is associated with the host.

14. A method of associating a particular host with one or more regions, the method comprising:

determining if a top-level domain of the particular host is a regional top-level domain; and

if the top-level domain of the particular host is not a regional top-level domain, then determining one or more regions associated with the host based on which other hosts contain documents that reference documents on said host.

15. The method of claim 14 wherein the step of determining one or more regions associated with the host based on which other hosts contain documents that reference documents on said host includes the steps of:

determining a diversity of domains in which there are other hosts that link to the particular host;

determining whether the diversity is greater than a specified threshold; and

if the diversity is greater than the specified threshold, then associating the particular host with a classification value that indicates that the particular host is of equivalent interest to multiple regions.

16. The method of claim 15, further comprising:

if the diversity is not greater than the specified threshold, then performing, for one or more particular regions, the steps of;

determining a signal for a particular region based on a number of other hosts, which are associated with the particular region, that are linked, via inbound or outbound links, with the particular host;

determining if the signal for the particular region is significant; and

if the signal is significant, then associating the particular host with the particular region.

17. The method of claim 15, wherein determining the diversity of domains in which there are other hosts that link to the particular host comprises:

determining, for each domain, a relative domain frequency;

determining, for each domain, an intermediate value that is equal to the relative domain frequency of the domain divided by a summation of relative domain frequencies for all domains; and

determining an entropy value for the particular host as the summation of the products, for all domains, of the intermediate values for those domains and a logarithm of the intermediate values for those domains.

18. A method of presenting a ranked list of documents to a user, comprising:

receiving search query terms from the user;

ranking a set of documents based on said search query terms and based on region information associated with a document; and

presenting, to said user, a list of documents that includes a first document whose rank was improved based on region information associated with said first document;

wherein said list includes a second document whose rank was not improved based on region information associated with said second document.

19-36. -36. (canceled)