Concept Network

• US 20080281821A1
• Filed: 07/28/2008
• Published: 11/13/2008
• Est. Priority Date: 05/01/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ma, Wei-Ying, Chen, Zheng, Liu, Shengping
• Granted Patent: US 8,065,298 B2
• Time in Patent Office: Days
• US Class Current: 707/6
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9532 Query formulation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: Y10S 707/954 Relational
• CPC Class Codes: Y10S 707/959 Network
• CPC Class Codes: Y10S 707/96 Object-relational
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A concept network that can be generated in response to a user query. Various embodiments include analysis of structure information, for example, where such information is based at least in part on Universal Resource Locators (URLs) of Web sites or data storage locations. A concept network may be used with a search tool where the search tool searches a plurality of sites (e.g., Web sites, data storage locations, etc.). In such an example, each site location is arranged with a node. Certain ones of the nodes are connected by at least one link. The concept network selects a portion of certain ones of the nodes based on the link, wherein the at least one link is used for content purposes.

Claims

1. A method, comprising:

receiving a plurality of Universal Resource Locators (URLs) that correspond to a plurality of Web pages;

analyzing the plurality of URLs to determine the content of the plurality of URLs; and

structuring a plurality of web blocks into a concept network based on the analyzed plurality of URLs.

2. The method of claim 1, further comprising displaying the concept network.

3. The method of claim 2, further comprising receiving user input in response to the displayed concept network.

4. The method of claim 1, further comprising determining whether a particular link is an upward link, a downward link, a sibling link, or a crosswise link based on a URL.

5. A method comprising:

considering a plurality of domain-specific Web sites;

deriving a domain specific taxonomy by mining information based on structure information and relative content of the plurality of domain-specific Web sites wherein the structure information comprises information based at least in part on Universal Resource Locators (URLs) associated with the plurality of domain-specific Web sites; and

formulating a concept network based on the domain specific taxonomy.

6. The method of claim 5, wherein the information mining is based on link structure and content.

7. The method of claim 5, wherein the concept network is formulated based on entropy.

8. The method of claim 5, wherein the concept network is formulated based on mutual information.

9. The method of claim 5, wherein the concept network is formulated based on similarity.

10. A method, comprising:

generating a concept network including

analyzing structure information about a plurality of Web sites based on a query submitted from a user wherein the structure information comprises information based at least in part on Universal Resource Locators (URLs) associated with the plurality of Web sites;

determining responses for a “

top N”

type query based on the structure information of the plurality of Web site; and

returning information to the user relating to the determined responses.

11. The method of claim 10, wherein the structural information comprises information based at least in part on hidden concepts within each Web page.

12. A method, comprising:

generating a concept network including

analyzing structure information about a plurality of data storage locations based on a query submitted from a user wherein the structure information comprises information based at least in part on Universal Resource Locators (URLs) associated with the plurality of data storage locations;

determining responses for a relevancy type query based at least in part on the analyzed structure information of the plurality of data storage locations; and

returning information to the user relating to the determined responses.

13. The method of claim 12, wherein the structural information comprises information based at least in part on hidden concepts within each data storage locations.

14. The method of claim 12, wherein the data storage location comprises a Web page.

15. A computer readable medium having computer executable instructions for generating a concept network, comprising:

analyzing structure information about a plurality of Web sites based on a query submitted from a user wherein the structure information comprises information based at least in part on Universal Resource Locators (URLs) associated with the plurality of Web sites;

determining responses for a relevancy type query based at least in part on the analyzed structure information of the plurality of Web sites; and

returning information to the user relating to the determined responses.

16. A method comprising:

automatically deriving a domain specific taxonomy by;

analyzing structure information about a plurality of data storage locations based on a query submitted from a user wherein the structure information comprises information based at least in part on Universal Resource Locators (URLs) associated with the plurality of data storage locations; and

determining responses for a relevancy type query based at least in part on the analyzed structure information of the plurality of data storage locations; and

generating a concept network using the domain specific taxonomy.