WEB-BASED DATA EXTRACTION AND LINKAGE

• US 20180129905A1
• Filed: 06/29/2017
• Published: 05/10/2018
• Est. Priority Date: 04/07/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Soundararajan, Varun, Kothari, Anshul, Agrawal, Anurag
• Granted Patent: US 10,943,144 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9566 URL specific, e.g. using aliases, detecting broken or misspelled links
• CPC Class Codes: G06F 18/2113 by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0276 Advertisement creation

Abstract

Systems and methods for automatically extracting a plurality of contact information from a resource, calculating prominence scores of each contact information, and associating a selected contact information with a content item are provided. A content item and a uniform resource locator are received from a content provider. A resource identified by the uniform resource locator is loaded. A plurality of contact information is detected from the loaded resource. For each of the detected contact information, a prominence score is calculated. One of the plurality of contact information is selected based on the calculated prominence scores. The selected contact information is associated with the content item.

Claims

1-20. -20. (canceled)

21. A system for web-based data extraction and linkage, comprising:

a data processing system including one or more processors, the data processing system to;

receive a content item and uniform resource locator (URL) from a content provider computing device, the URL identifying a resource;

load the resource identified by the URL;

detect a plurality of contact information from the resource, the plurality of contact information comprising a first contact information and a second contact information;

determine, prior to association of contact information with the content item, a prominence score for each of the plurality of contact information based on an analysis of an object tree of the resource or an analysis of a result of optical character recognition of the resource;

select the first contact information and the second contact information of the plurality of contact information based on the prominence scores;

associate the selected first contact information and the second contact information with the content item;

receive, via speech input from a computing device, a request;

select, based on location information associated with the computing device, one of the first contact information or the second contact information;

modify the content item to indicate the one of the first contact information or the second contact information selected based on location information associated with the computing device; and

provide the content item to the computing device to cause the computing device to generate audio output comprising the content item to indicate, via the audio output, the one of the first content information or the second contact information selected based on location information associated with the computing device, the computing device to dial a number of the content provider with the one of the first contact information or the second contact information responsive to input from the computing device.

22. The system of claim 21, wherein the computing device comprises a digital assistant, the system to:

receive the speech input from the digital assistant.

23. The system of claim 21, wherein the computing device dials the number of the content provider responsive to a selection.

24. The system of claim 21, wherein the computing device dials the number of the content provider responsive to audio feedback.

25. The system of claim 21, comprising the one or more processors to:

modify, for presentation via a second computing device, the content item to include the one of the first contact information or the second contact information with a selectable button for the content item; and

serve the content item with the selectable button to the second computing device responsive to the request, the second computing device configured to dial the number of the content provider with the one of the first contact information or the second contact information responsive to a selection of the selectable button.

26. The system of claim 21, comprising the one or more processors to:

determine a domain of the received URL;

find a plurality of URLs under the domain, each of the plurality of URLs identifying a resource that is less than a predetermined number of arcs from the received URL; and

load a plurality of resources identified by the plurality of URLs.

27. The system of claim 21, comprising the one or more processors to:

parse the resource into the object tree;

render the resource using the object tree; and

detect the plurality of contact information using optical character recognition from the rendered resource.

28. The system of claim 21, comprising the one or more processors to:

filter a portion of the resource; and

detect the plurality of contact information from an unfiltered portion of the loaded resource.

29. The system of claim 21, wherein each prominence score for each of the plurality of contact information comprises a weighted sum of a plurality of signals associated with a respective contact information.

30. The system of claim 29, wherein a signal of the plurality of signals is computed based on at least one of:

a number of times the respective contact information is shown on the loaded resource;

a number of other contact information detected on the loaded resource;

a typographic emphasis of a respective contact information;

a location of the contact information within the loaded resource;

a text located near the respective contact information within the loaded resource;

or

a prominence of an image associated with the respective contact information referenced by the loaded resource.

31. A method of web-based data extraction and linkage, comprising:

receiving, by a data processing system including one or more processors, a content item and uniform resource locator (URL) from a content provider computing device, the URL identifying a resource;

loading, by the data processing system, the resource identified by the URL;

detecting, by the data processing system, a plurality of contact information from the resource, the plurality of contact information comprising a first contact information and a second contact information;

determining, by the data processing system, prior to association of contact information with the content item, a prominence score for each of the plurality of contact information based on an analysis of an object tree of the resource or an analysis of a result of optical character recognition of the resource;

selecting, by the data processing system, the first contact information and the second contact information of the plurality of contact information based on the prominence scores;

associating, by the data processing system, the selected first contact information and the second contact information with the content item;

receiving, by the data processing system, via speech input from a computing device, a request;

selecting, by the data processing system based on location information associated with the computing device, one of the first contact information or the second contact information;

modifying, by the data processing system, the content item to indicate the one of the first contact information or the second contact information selected based on location information associated with the computing device; and

providing, by the data processing system, the content item to the computing device to cause the computing device to generate audio output comprising the content item to indicate, via the audio output, the one of the first content information or the second contact information selected based on location information associated with the computing device, the computing device to dial a number of the content provider with the one of the first contact information or the second contact information responsive to input from the computing device.

32. The method of claim 31, wherein the computing device comprises a digital assistant, the method comprising:

receiving the speech input from the digital assistant.

33. The method of claim 31, comprising:

dialing, by the computing device, the number of the content provider responsive to a selection.

34. The method of claim 31, comprising:

dialing, by the computing device, the number of the content provider responsive to audio feedback.

35. The method of claim 31, comprising:

modifying, by the one or more processors, for presentation via a second computing device, the content item to include the one of the first contact information or the second contact information with a selectable button for the content item; and

serving the content item with the selectable button to the second computing device responsive to the request, the second computing device configured to dial the number of the content provider with the one of the first contact information or the second contact information responsive to a selection of the selectable button.

36. The method of claim 31, comprising:

determining, by the one or more processors, a domain of the received URL;

finding, by the one or more processors, a plurality of URLs under the domain, each of the plurality of URLs identifying a resource that is less than a predetermined number of arcs from the received URL; and

loading, by the one or more processors, a plurality of resources identified by the plurality of URLs.

37. The method of claim 31, comprising:

parsing, by the one or more processors, the resource into the object tree;

rendering, by the one or more processors, the resource using the object tree; and

detecting, by the one or more processors, the plurality of contact information using optical character recognition from the rendered resource.

38. The method of claim 31, comprising:

filtering, by the one or more processors, a portion of the resource; and

detecting, by the one or more processors, the plurality of contact information from an unfiltered portion of the loaded resource.

39. The method of claim 31, wherein each prominence score for each of the plurality of contact information comprises a weighted sum of a plurality of signals associated with a respective contact information.

40. The method of claim 39, wherein a signal of the plurality of signals is computed using at least one of:

a number of times the respective contact information is shown on the loaded resource;

a number of other contact information detected on the loaded resource;

a typographic emphasis of a respective contact information;

a location of the contact information within the loaded resource;

a text located near the respective contact information within the loaded resource;

or

a prominence of an image associated with the respective contact information referenced by the loaded resource.