Methods and systems for determining a meaning of a document to match the document to content

• US 20040243581A1
• Filed: 10/21/2003
• Published: 12/02/2004
• Est. Priority Date: 09/22/1999
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Weissman, Adam J., Elbaz, Gilad Israel
• Granted Patent: US 8,914,361 B2
• Time in Patent Office: Days
• US Class Current: 707/9
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

Systems and methods for determining a meaning of a document to match the document to content are described. In one aspect, a source article is accessed, a plurality of regions in the source article are identified, at least one local concept associated with each region is determined, the local concepts of each region are analyzed to identify any unrelated regions, the local concepts associated with any unrelated regions are eliminated to determine relevant concepts, the relevant concepts are analyzed to determine a source meaning for the source article, and the source meaning is matched with an item meaning associated with an item from a set of items.

Claims

1. A method, comprising:

accessing a source article;

identifying a plurality of regions in the source article;

determining at least one local concept associated with each region;

analyzing the local concepts of each region to identify any unrelated regions;

eliminating the local concepts associated with any unrelated regions to determine relevant concepts;

analyzing the relevant concepts to determine a source meaning for the source article; and

matching the source meaning with an item meaning associated with an item from a set of items.

2. The method of claim 1, further comprising displaying the matched item on the source article.

3. The method of claim 2, wherein the source article is a web page and the matched item is a keyword.

4. The method of claim 2, wherein the source article is a web page and the matched item is an advertisement.

5. The method of claim 1, further comprising displaying content associated with the matched item on the source article.

6. The method of claim 5, wherein the source article is a web page, the matched item is a keyword and the associated content is an advertisement.

7. The method of claim 5, wherein the source article is a first web page, the matched item is a second web page and the associated content is an advertisement.

8. The method of claim 5, wherein the source article is a first web page, the matched item is a second web page and the associated content is a link to the second web page.

9. The method of claim 1, wherein matching the source meaning with an item meaning comprises using biasing factors.

10. The method of claim 1, wherein the source meaning is a vector of weighted concepts.

11. The method of claim 1, wherein determining at least one local concept comprises determining a score for each local concept, wherein the local concept in each region with the highest scores are most relevant local concepts.

12. The method of claim 11, wherein identifying unrelated regions comprises determining a revised score for each local concept, determining a ranked global list of all local concepts based on the revised scores, removing local concepts whose combined revised score contributes less than a predetermined amount of a total score for the global list to produce a resulting list, determining unrelated regions with no most relevant local concepts on the resulting list, and removing local concepts associated with the unrelated regions from the resulting list to produce a list of relevant concepts.

13. The method of claim 12, wherein determining a source meaning comprises normalizing the revised scores for the relevant concepts.

25. The computer-readable medium of claim 1, wherein program code for determining at least one local concept comprises program code for determining a score for each local concept, wherein the local concept in each region with the highest scores are most relevant local concepts.

26. The computer-readable medium of claim 25, wherein program code for identifying unrelated regions comprises program code for determining a revised score for each local concept, program code for determining a ranked global list of all local concepts based on the revised scores, program code for removing local concepts whose combined revised score contributes less than a predetermined amount of a total score for the global list to produce a resulting list, program code for determining unrelated regions with no most relevant local concepts on the resulting list, and program code for removing local concepts associated with the unrelated regions from the resulting list to produce a list of relevant concepts.

27. The computer-readable medium of claim 26, wherein program code for determining a source meaning comprises program code for normalizing the revised scores for the relevant concepts.

14. A computer-readable medium containing program code, comprising:

program code for accessing a source article;

program code for identifying a plurality of regions in the source article;

program code for determining at least one local concept associated with each region;

program code for analyzing the local concepts of each region to identify any unrelated regions;

program code for eliminating the local concepts associated with any unrelated regions to determine relevant local concepts;

program code for analyzing the relevant local concepts to determine a source meaning for the source article; and

program code for matching the source meaning with an item meaning associated with an item from a set of items.

15. The computer-readable medium of claim 14, further comprising program code for displaying the matched item on the source article.

16. The computer-readable medium of claim 15, wherein the source article is a web page and the matched item is a keyword.

17. The computer-readable medium of claim 15, wherein the source article is a web page and the matched item is an advertisement.

18. The computer-readable medium of claim 14, further comprising program code for displaying content associated with the matched item on the source article.

19. The computer-readable medium of claim 18, wherein the source article is a web page, the matched item is a keyword and the associated content is an advertisement.

20. The computer-readable medium of claim 18, wherein the source article is a first web page, the matched item is a second web page and the associated content is an advertisement.

21. The computer-readable medium of claim 18, wherein the source article is a first web page, the matched item is a second web page and the associated content is a link to the second web page.

22. The computer-readable medium of claim 14, wherein program code for matching the source meaning with an item meaning comprises program code for using biasing factors.

23. The computer-readable medium of claim 14, wherein the source meaning is a vector of weighted concepts.

24. The computer-readable medium of claim 14, wherein program code for analyzing the relevant local concepts comprises program code for ranking the relevant local concepts.

28. A method, comprising:

accessing a source article;

identifying at least a first content region and a second content region in the source article;

determining at least a first local concept associated with the first content region and determining at least a second local concept associated with the second content region;

matching the first content region with a first item from a set of items based at least in part on the first local concept; and

matching the second content region with a second item from the set of items based at least in part on the second local concept.

29. The method of claim 28, further comprising displaying the matched items on the source article.

30. The method of claim 29, wherein the first item is displayed in the first content region and the second item is displayed in the second content region.

31. The method of claim 29, wherein the source article is a web page and the matched items are advertisements.

32. The method of claim 29, wherein the source article is a web page and the matched items are keywords.

33. The method of claim 28, further comprising displaying first content associated with the first item and displaying second content associated with the second item on the source article.

34. The method of claim 33, wherein the first content is displayed in the first content region and the second content is displayed in the second content region.

35. The method of claim 33, wherein the source article is a web page, the matched items are keywords and the associated content are advertisements.