Detecting Serving Area of a Web Resource

• US 20070233864A1
• Filed: 03/28/2006
• Published: 10/04/2007
• Est. Priority Date: 03/28/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ma, Wei-Ying, Xie, Xing, Zhang, Qi, Wang, Lee
• Granted Patent: US 7,606,875 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/185 by embedding added-value information into content, e.g. geo-tagging

Abstract

Methods and systems for determining the serving area of a web resource by address, by query content, and by business category are provided. A location system may determine the serving area of a web resource based on addresses of users who access the web resource. The location system may determine the serving area for a web site (or other web resource) based on query terms that resulted in a click-through to the web site. The location system may determine the serving area of a web site (or other web resource) based on the business category of the web site and a “provider location” associated with the web site.

Claims

1. A computer system for determining a serving area of a web resource based on addresses of users, comprising:

an access information store that includes, for each access of the web resource, the address of the user who accessed the web resource;

an address mapping component that maps an address of the access information to a location within a hierarchy of locations; and

an identification component that identifies a location of the hierarchy as a serving area of the web resource based on the number of accesses of the web resource by users within that location and based on the spread of the number of accesses of the web resource by users within locations that are hierarchically within the location.

2. The computer system of claim 1 wherein the address is an IP address.

3. The computer system of claim 1 wherein the access information is derived from a click-through log.

4. The computer system of claim 1 wherein the identification component calculates a weight for a location that is based on the ratio of the access rate of the location to the access rate of the parent location of the location.

5. The computer system of claim 4 wherein the weight is represented as follows:

$\mathrm{Weight}<br><br>\left(w,l\right)=\frac{\mathrm{Click}<br><br>\left(w,l\right)/\mathrm{Population}<br><br>\left(l\right)}{\mathrm{Click}<br><br>\left(w,\mathrm{Parent}<br><br>\left(l\right)\right)/\mathrm{Population}<br><br>\left(\mathrm{Parent}<br><br>\left(l\right)\right)}$

where Weight(w,l) represents the weight of location l for web resource w, Click(w,l) represents the number of click-throughs from location l to website w, Population(l) represents the population of location l, and Parent(l) represents the parent location of location l.

6. The computer system of claim 1 wherein the identification component calculates a spread for a location that indicates a distribution of the accesses of the location among its child locations.

7. The computer system of claim 6 wherein the spread is represented as follows:

$\mathrm{Spread}<br><br>\left(w,l\right)=\frac{-\underset{i=1}{\overset{n}{\sum <br><br>}}<br><br>\frac{\mathrm{Weight}<br><br>\left(w,l_i\right)}{\underset{j=1}{\overset{n}{\sum <br><br>}}<br><br>\mathrm{Weight}<br><br>\left(w,l_j\right)}\times <br><br>\log \left(\frac{\mathrm{Weight}<br><br>\left(w,l_i\right)}{\underset{j=1}{\overset{n}{\sum <br><br>}}<br><br>\mathrm{Weight}<br><br>\left(w,l_j\right)}\right)}{\log <br><br>\text{\hspace{1em}<br><br>}<br><br>n}$

where Spread(w,l) represents the spread of location l for web resource w, Weight(w,l) represents the weight of location l for web resource w, l_x represents a child location of location l, and n represents the number of child locations of location l.

8. The computer system of claim 1 wherein the address is an IP address, the access information is derived from a click-through log, the identification component calculates a weight for a location that is based on the ratio of the access rate of the location to the access rate of the parent location of the location, and the identification component calculates a spread for a location that indicates a distribution of the accesses of the location among its child locations.

9. A computer system for determining a serving area of a web resource based on query terms, comprising:

a click-through store that indicates queries whose search results included references to web resources that users selected;

a location terms identification component that identifies terms of the queries that are location terms; and

a serving area identification component that identifies a serving area by applying a content location detection algorithm to the identified terms to identify a content location as the serving area.

10. The computer system of claim 9 including a component that generates a document containing the identified location terms and wherein the serving area identification component applies the content location detection algorithm to the generated document.

11. The computer system of claim 9 including a disambiguation component that disambiguates location terms.

12. The computer system of claim 9 wherein the locations are defined within a hierarchy and wherein the content location detection algorithm identifies a location of the hierarchy as a content location based on weights for location terms and based on spread of the weights within locations that are hierarchically within the location.

13. The computer system of claim 12 wherein the weights are based on weights of aliases of the location.

14. The computer system of claim 12 wherein the content location detection algorithm generates a power for each location that factors in the weight of ancestor and descendant locations.

15. The computer system of claim 9 including a component that disambiguates location terms and a component that generates a document containing the identified location terms, wherein the serving area identification component applies the content location detection algorithm to the generated document, wherein the locations are defined within a hierarchy, and wherein the content location detection algorithm identifies a location of the hierarchy as a content location based on weights for location terms and based on spread of the weights within locations that are hierarchically within the location.

16. A computer system for determining a serving area of a web resource based on business category, comprising:

a classifier component that classifies the web resource into a business category;

a business category-to-scope mapping that maps business categories to a scope of the area served by businesses within that business category;

a location provider component that determines a provider location from content of the web resource; and

a serving area identification component that identifies a location within a hierarchy of locations that includes the provider location and corresponds to the scope of the business category of the web resource.

17. The computer system of claim 16 wherein the location provider component uses a classifier to identify a provider location from content extracted from the web resource.

18. The computer system of claim 16 wherein the scope of an area includes city, state, and country.

19. The computer system of claim 16 wherein the scope corresponds to a distance that represents a radius of the serving area.

20. The computer system of claim 16 wherein the location provider component uses a classifier to identify a provider location from content extracted from the web resource and wherein the scope of an area includes city, state, and country.