Web-Based Data Extraction and Linkage

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.

1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method for generating a content item, comprising:
 receiving, from a user device, a content item request for a content item;   receiving, from a content provider, a uniform resource locator (URL), the URL identifying a resource;   detecting a plurality of contacting information from the resource identified by the URL;   calculating a prominence score for each of the plurality of contact information;   selecting, based on the calculated prominence score for each of the plurality of contact information, a first contact information from the plurality of contact information; and   generating the content item from the resource identified by the URL, wherein the first contact information is associated with the content item.   
     
     
         22 . The method of  claim 21 , wherein the calculation of the prominence score for the first contact information includes searching for one or more signals associated with the first contact information. 
     
     
         23 . The method of  claim 22 , wherein a signal score is calculated for each signal in the one or more signals, and wherein one or more signal scores are combined to calculate the prominence score associated with the first contact information. 
     
     
         24 . The method of  claim 23 , wherein a signal can include a number of times the first contact information is detected on the resource, a number of other contact information on the resource, a textual emphasis of the first contact information in the resource, or a location of the first contact information within the resource. 
     
     
         25 . The method of  claim 21 , further comprising:
 determining a performance metric for the content item, the performance metric being a click-through rate (CTR); and   selecting the content item to server based on a predicted click through rate (pCTR).   
     
     
         26 . The method of  claim 21 , further comprising:
 receiving, from the content provider, selection criteria that may include one or more content item conditions for serving the content item; and   serving the content item based on the selection criteria.   
     
     
         27 . The method of  claim 21 , wherein the first contact information is displayed along with the content item when the content item is displayed to the user device. 
     
     
         28 . The method of  claim 21 , wherein the first contact information is embedded within the content item when the content item is displayed to the user device. 
     
     
         29 . The method of  claim 21 , Wherein the content item is banner content item, interstitial content item, pop-up content item, rich media content item, hybrid content item, cross-domain iframe content item. 
     
     
         30 . The method of  claim 21 , wherein the content item includes embedded information, wherein the embedded information includes hyperlinks, metadata, machine-executable instructions, or annotations. 
     
     
         31 . The method of  claim 21 , wherein the resource is an article, a comment thread, music information, video information, a search result, or an information feed. 
     
     
         32 . The method of  claim 21 , wherein the resource is a web page, a document, or an application. 
     
     
         33 . The method of  claim 21 , wherein the content item request includes device information, wherein the device information includes a previous resource request from the user device. 
     
     
         34 . The method of  claim 33 , wherein the device information includes a previous content item received by the user device. 
     
     
         35 . The method of  claim 34 , Wherein the content item request includes resource information, wherein the resource information includes one or more keywords associated with the resource, text of content of the resource, a title of the resource, a category of the resource, or a type of the resource. 
     
     
         36 . The method of  claim 21 , wherein the first contact information is used by the user device to contact the content provider. 
     
     
         37 . The method of  claim 21 , Wherein the first contact information is a video chat handle, an instant messaging handle, a social media profile, payment information, or a bank routing number. 
     
     
         38 . The method of  claim 21 , wherein the content provider is a third-party content provider, and only the URI, is received from the third-parry content provider. 
     
     
         39 . A system for web-based data extraction and linkage, comprising:
 a data processing system including one or more processors, the data processing system to:   receiving, from a user device, a content item request for a content item;   receiving, from a content provider, a uniform resource locator (URL), the URL identifying a resource;   detecting a plurality of contacting information from the resource identified by the URL;   calculating a prominence score for each of the plurality of contact information;   selecting, based on the calculated prominence score for each of the plurality of contact information, a first contact information from the plurality of contact information; and   generating the content item from the resource identified by the URL, wherein the first contact information is associated with the content item.   
     
     
         40 . A computer readable medium carrying a computer program comprising computer readable instructions configured to cause a computer to:
 receiving, from a user device, a content item request for a content item;   receiving, from a content provider, a uniform resource locator (URL), the URL identifying a resource;   detecting a plurality of contacting information from the resource identified by the URL;   calculating a prominence score for each of the plurality of contact information;   selecting, based on the calculated prominence score for each of the plurality of contact information, a first contact information from the plurality of contact information; and   generating the content item from the resource identified by the URL, wherein the first contact information is associated with the content item.