METHOD AND SYSTEM FOR WEB RESOURCE LOCATION CLASSIFICATION AND DETECTION

• US 20100010945A1
• Filed: 08/11/2009
• Published: 01/14/2010
• Est. Priority Date: 03/10/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ma, Wei-Ying, Xie, Xing, Wang, Chuang
• Granted Patent: US 8,073,789 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• 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

Abstract

A method and system for identifying locations associated with a web resource is provided. The location system identifies three different types of geographic locations: a provider location, a content location, and a serving location. A provider location identifies the geographic location of the entity that provides the web resource. A content location identifies the geographic location that is the subject of the web resource. A serving location identifies the geographic scope that the web page reaches. An application can select to use the type of location that is of particular interest.

Claims

1. A computer system for identifying locations associated with a web resource, comprising:

a memory storing computer-executable instructions of

a component for identifying a provider location associated with the web resource;

a component for identifying a content location associated with the web resource; and

a component for identifying a serving location associated with the web resource; and

a processor for executing the computer-executable instructions stored in the memory.

2. The computer system of claim 1 wherein the provider location is the geographic location of the entity that provides the web resource.

3. The computer system of claim 1 wherein the component for identifying a provider location includes a classifier that has been trained to classify locations of the web resource as being or not being provider locations.

4. The computer system of claim 3 wherein the classifier is a support vector machine.

33. The computer system of claim 1 wherein the component for identifying a provider location includes:

a provider location classifier that inputs features of an address string of a web resource and outputs an indication of whether the address string represents a provider location of the web resource;

an address string identification component that identifies an address string within a web resource;

a feature extraction component that, for an identified address string, extracts from the web resource features of the identified address string; and

a component that receives a web resource, identifies an address string within the web resource using the address string identification component, extracts features for the identified address string using the feature extraction component, and submits the extracted features to the provider location classifier to determine whether the identified address string represents a provider location of the web resource.

34. The computer system of claim 33 including:

a component that generates the provider location classifier by;

providing a plurality of web resources;

identifying address strings of the web resources using the address string identification component;

extracting features of the identified address strings using the feature extraction component;

inputting labels for the identified address strings, a label indicating whether an identified address string represents a provider location of the web resource from which the identified address string was identified; and

training the provider location classifier based on the extracted features and labels of the identified address strings.

35. The computer system of claim 33 wherein the extracted features of an identified address string of a web page include level of the web page within a web site.

36. The computer system of claim 33 wherein an extracted feature of an identified address string of a web page includes terms within a uniform resource locator of the web page.

5-20. -20. (canceled)

21. A computing device for identifying provider locations associated with a web resource, the provider location of a web resource being a geographic location of an entity that provides the web resource, the computing device comprising:

a memory storing computer-executable instructions of

a provider location classifier that inputs features of an address string of a web resource and outputs an indication of whether the address string represents a provider location of the web resource;

an address string identification component that identifies an address string within a web resource;

a feature extraction component that, for an identified address string, extracts from the web resource features of the identified address string;

a component that receives a web resource, identifies an address string within the web resource using the address string identification component, extracts features for the identified address string using the feature extraction component, and submits the extracted features to the provider location classifier to determine whether the identified address string represents a provider location of the web resource; and

a component that outputs an indication of whether the identified address string represents a provider location of the web resource; and

a processor for executing the computer-executable instructions stored in the memory.

22. The computing device of claim 21 wherein the web resource is a web page.

23. The computing device of claim 22 wherein the extracted features of an identified address string of a web page include level of the web page within a web site and spatial position of the identified address string within the web page.

24. The computing device of claim 22 wherein an extracted feature of an identified address string of a web page includes terms within a uniform resource locator of the web page and within anchor text of the web page that indicate the web page may contain a provider location.

25. The computing device of claim 21 including:

a component that generates the provider location classifier by;

providing a plurality of web resources;

identifying address strings of the web resources using the address string identification component;

extracting features of the identified address strings using the feature extraction component;

inputting labels for the identified address strings, a label indicating whether an identified address string represents a provider location of the web resource from which the identified address string was identified; and

training the provider location classifier based on the extracted features and labels of the identified address strings.

26. The computing device of claim 25 wherein the training is based on a support vector machine.

27. A method performed by a computing device having computer-executable instructions stored in a memory of the computing device for generating a provider location classifier of a web resource, the provider location classifier for determining whether an address string of a web resource represents a provider location, the provider location of a web resource being a geographic location of an entity that provides the web resource, the method comprising:

providing a plurality of web resources;

identifying address strings of the web resources;

extracting features of the identified address strings;

inputting labels for the identified address strings, a label indicating whether an identified address string represents a provider location of the web resource from which the identified address string was identified; and

training the provider location classifier based on the extracted features and labels of the identified address strings.

28. The method of claim 27 wherein the training is based on a support vector machine.

29. The method of claim 27 wherein the web resource is a web page.

30. The method of claim 29 wherein the extracted features of an identified address string of a web page include spatial position of the identified address string within the web page.

31. The method of claim 29 wherein an extracted feature of an identified address string of a web page includes terms within anchor text of the web page that indicate the web page may contain a provider location.

32. The method of claim 27 including classifying an address string of a web resource by a method including:

receiving the web resource;

identifying an address string within the web resource;

extracting features for the identified address string; and

submitting the extracted features to the provider location classifier to determine whether the identified address string represents a provider location of the web resource.