Determining a meaning of a knowledge item using document-based information

• US 9,811,776 B2
• Filed: 04/05/2013
• Issued: 11/07/2017
• Est. Priority Date: 09/22/1999
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Elbaz, Gilad Israel, Weissman, Adam J.
• Primary Examiner(s): Hill, Stanley K
• Assistant Examiner(s): Coughlan, Peter
• Application Number:
  US13/857,325
• Publication Number:
  US 20130232099A1
• Time in Patent Office: 1,677 Days
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06F 16/3338 Query expansion
• 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
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

Systems and methods that determine a meaning of a knowledge item using related information are described. In one aspect, a knowledge item is received, related information associated with the knowledge item is received, at least one related meaning based on the related information is determined, and a knowledge item meaning for the knowledge item based at least in part on the related meaning is determined. Several algorithms and types of related information useful in carrying out such systems and methods are described.

Claims

1. A computer-implemented method comprising:

identifying, by a server system comprising one or more computers, first terms based on an evaluation of a web page;

identifying, by the server system, one or more related resources that are associated with the first terms, and identifying, for each related resource, one or more second terms associated with the related resource based on an evaluation of the related resource;

associating, by the server system, each of (i) the first terms identified based on the evaluation of the web page and (ii) the one or more second terms respectively associated with the one or more related resources with a respective node in a directed graph;

providing, by the server system, one or more connections between the nodes in the directed graph, wherein the one or more connections indicate magnitudes and directions that represent one or more relationships between (i) the first terms identified based on the evaluation of the web page, and (ii) the one or more second terms respectively associated with the one or more related resources;

selecting, by the server system, a subset of the first terms based on the connections representing the one or more relationships between (i) the first terms identified based on the evaluation of the web page, and (ii) the one or more second terms respectively associated with the one or more related resources;

associating, by the server system, the selected subset of the first terms with the web page;

storing, by the server system and in a database, data that indicates that the selected subset of the first terms are associated with the web page;

selecting, by the server system, a knowledge item from among a plurality of knowledge items based on the selected subset of the first terms that the database indicates are associated with the web page; and

providing, by the server system, the selected knowledge item for display with the web page at a client device.

2. The method of claim 1, wherein identifying the first terms comprises identifying first terms that are each associated with one or more terms that are parsed from the web page.

3. The method of claim 1, wherein each of the first terms is defined by data that specifies (i) a set of terms associated with the one or more second terms, (ii) one or more relationships with one or more other second terms, (iii) one or more attributes of the one or more second terms, and (iv) one or more statistics regarding the one or more second terms.

4. The method of claim 1, wherein identifying first terms based on an evaluation of a web page comprises identifying first terms that are each associated with one or more terms included in the web page.

5. The method of claim 1, wherein selecting a subset of the first terms comprises selecting first terms that are most prominent in the web page.

6. The method of claim 1, wherein selecting a subset of the first terms comprises selecting first terms that are each also associated with the related resources.

7. The method of claim 1, wherein selecting a subset of the first terms comprises selecting first terms that are each also associated with the related resources by more than a predetermined degree.

8. The method of claim 1, wherein selecting a subset of the first terms comprises generating a ranked list of the first terms.

9. The method of claim 1, further comprising:

providing a comparison between the magnitudes and the directions of the one or more connections, and

determining a strength of the one or more relationships based on the comparison.

10. The method of claim 1, wherein providing the selected knowledge item for display with the web page at the client device comprises providing the selected knowledge item for placement in a frame on the web page at the client device.

11. 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;

identifying, by a server system comprising one or more computers, first terms based on an evaluation of a web page;

identifying, by the server system, one or more related resources that are associated with the first terms and identifying, for each related resource, one or more second terms associated with the related resource based on an evaluation of the related resource;

associating, by the server system, each of (i) the first terms identified based on the evaluation of the web page and (ii) the one or more second terms respectively associated with the one or more related resources with a respective node in a directed graph;

providing, by the server system, one or more connections between the nodes in the directed graph, wherein the one or more connections indicate magnitudes and directions that represent one or more relationships between (i) the first terms identified based on the evaluation of the web page, and (ii) the one or more second terms respectively associated with the one or more related resources;

selecting, by the server system, a subset of the first terms based on the connections representing the one or more relationships between (i) the first terms identified based on the evaluation of the web page, and (ii) the one or more second terms respectively associated with the one or more related resources;

associating, by the server system, the selected subset of the first terms with the web page;

storing, by the server system and in a database, data that indicates that the selected subset of the first terms are associated with the web page;

selecting, by the server system, a knowledge item from among a plurality of knowledge items based on the selected subset of the first terms that the database indicates are associated with the web page; and

providing, by the server system, the selected knowledge item for display with the web page at a client device.

12. The system of claim 11, wherein identifying the first terms comprises identifying first terms that are each associated with one or more terms that are parsed from the web page.

13. The system of claim 11, wherein each one or more second terms is defined by data that specifies (i) a set of terms associated with one or more second terms, (ii) one or more relationships with one or more other second terms, (iii) one or more attributes of the one or more second terms, and (iv) one or more statistics regarding the one or more second terms.

14. The system of claim 11, wherein identifying first terms based on an evaluation of a web page comprises identifying first terms that are each associated with one or more terms included in the web page.

15. The system of claim 11, wherein selecting a subset of the first terms comprises selecting one or more of the first terms that are most prominent in the web page.

16. The system of claim 11, further comprising:

accessing association data indicating associations between terms, wherein at least some of the associations indicate a magnitude and direction for a relationship between terms; and

determining one or more scores indicating relationships between the first terms identified based on the evaluation of the web page and the one or more second terms associated with the one or more related resources based on the association data;

wherein selecting the subset of the first terms based on the one or more relationships comprises selecting the subset of the first terms based on the one or more scores.

17. The system of claim 11, wherein identifying the one or more second terms associated with the one or more related resources comprises identifying a destination web page each referenced by one of the plurality of knowledge items;

and

wherein identifying the one or more second terms associated with the one or more related resources comprises identifying one or more second terms associated with the destination web page based on content of the destination web page.

18. 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:

identifying, by a server system comprising one or more computers, first terms based on an evaluation of a web page;

identifying, by the server system, one or more related resources that are associated with the first terms, and identifying, for each related resource, one or more second terms associated with the related resource based on an evaluation of the related resource;

associating, by the server system, each of (i) the first terms identified based on the evaluation of the web page and (ii) the one or more second terms respectively associated with the one or more related resources with a respective node in a directed graph;

providing, by the server system, one or more connections between the nodes in the directed graph, wherein the one or more connections indicate magnitudes and directions that represent one or more relationships between (i) the first terms identified based on the evaluation of the web page, and (ii) the one or more second terms respectively associated with the one or more related resources;

selecting, by the server system, a subset of the first terms based on the connections representing the one or more relationships between (i) the first terms identified based on the evaluation of the web page, and (ii) the one or more second terms respectively associated with the one or more related resources;

associating, by the server system, the selected subset of the first terms with the web page;

storing, by the server system and in a database, data that indicates that the selected subset of the first terms are associated with the web page;

selecting, by the server system, a knowledge item from among a plurality of knowledge items based on the selected subset of the first terms that the database indicates are associated with the web page; and

providing, by the server system, the selected knowledge item for display with the web page at a client device.