Systems and methods for inferring matches and logging-in of online users across devices

Abstract

Systems and methods are disclosed for associating a plurality of Internet-enabled devices with a common user profile for targeting Internet content or advertising. One method includes: receiving, from a plurality of Internet-enabled devices, a plurality of requests for electronic content or advertising; extracting, from each of the plurality of requests, a source IP address and a unique identifier associated with the respective Internet-enabled device; identifying each possible pair of devices from which requests were received; calculating for each possible pair of devices a probability that the pair of devices are owned or operated by a common user; and prompting a user to either confirm a characteristic of a prior browsing session or to log-in to an account associated with the common user based on a comparison of the calculated probability to one or more thresholds.

What is claimed is: 
     
         1 - 20 . (canceled) 
     
     
         21 . A method for associating a plurality of devices with a common user profile, the method comprising:
 receiving, from a plurality of devices, a plurality of requests for content;   extracting, from each of the plurality of requests, an occurrence, an address, and a unique identifier associated with a respective device;   calculating a probability that a pair of devices are associated with a common user based on a weighted value of the plurality of requests, addresses for the pair of devices, and unique identifiers associated with the pair of devices; and   identifying the pair of devices with a common user profile based on the calculated probability exceeding a threshold level.   
     
     
         22 . The method of  claim 21 , further comprising:
 if the calculated probability exceeds a first threshold, prompting a user to confirm a characteristic of a prior browsing session; and if the calculated probability exceeds a second threshold, prompting the user to log-in to an account associated with the common user.   
     
     
         23 . The method of  claim 21 , further comprising:
 for each additional address with which the pair of devices are linked to, increasing the probability that the pair of devices are associated with a common user.   
     
     
         24 . The method of  claim 23 , further comprising:
 normalizing the probability and a second probability;   combining the probability and a second probability to create an combined probability; and   calculating an overall probability that the pair of devices are associated with a common user based at least in part on the combined probability.   
     
     
         25 . The method of  claim 21 , wherein calculating a probability that the pair of devices are owned or operated by a common user comprises:
 determining, for each pair of devices, whether the pair of devices initiated a web event at the address at a time period when users are statistically likely to be at home; and   weighting web events that occur when users are statistically expected to be at home less heavily, when calculating the probability, than web events that occur at time periods when users are statistically likely to be away from home.   
     
     
         26 . The method of  claim 21 , wherein calculating a probability that the pair of devices are owned or operated by a common user comprises:
 determining, for each pair of devices, whether the pair of devices initiated a web event at the address at a time period when users are statistically likely to be at home; and   weighting web events that occur when users are statistically expected to be at home at least as heavily, when calculating the probability, as web events that occur at time periods when users are statistically likely to be away from home.   
     
     
         27 . The method of  claim 21 , further comprising:
 inferring, from each of the plurality of requests, a device type and local time associated with each request; and   further calculating a probability that the pair of devices are owned or operated by a common user based on inferred device type and local time associated with the request of each device.   
     
     
         28 . The method of  claim 21 , further comprising:
 accessing, in a database, demographic or browsing history information generated from the common user’s use of a first device of the pair of devices, the demographic or browsing history information being stored in the database in relation to the unique identifier; and   identifying, based on the demographic or browsing history information, content to display at a second device of the pair of devices, wherein the demographic or browsing history information is synchronized and associated with the common user’s first device and the common user’s second device.   
     
     
         29 . A system for associating a plurality of devices with a common user profile for targeting content, the system including:
 a data storage device storing instructions for associating a plurality of Internet-enabled devices with a common user profile for targeting Internet content; and   a processor configured to execute the instructions to perform a method including:
 receiving, from a plurality of devices, a plurality of requests for content; 
 extracting, from each of the plurality of requests, an occurrence, an address, and a unique identifier associated with a respective device; 
 calculating a probability that a pair of devices are associated with a common user based on a weighted value of the plurality of requests, addresses for the pair of devices, and unique identifiers associated with the pair of devices; and 
 identifying the pair of devices with a common user profile based on the calculated probability exceeding a threshold level. 
   
     
     
         30 . The system of  claim 29 , wherein the processor is further configured for:
 if the calculated probability exceeds a first threshold, prompting a user to confirm a characteristic of a prior browsing session; and if the calculated probability exceeds a second threshold, prompting the user to log-in to an account associated with the common user.   
     
     
         31 . The system of  claim 29 , wherein the probability is determined at least in part by incorporating at least one second probability that the pair of devices are associated with a common user calculated over a second predetermined time period. 
     
     
         32 . The system of  claim 31 , wherein the processor is further configured for:
 normalizing the probability and the second probability;   combining the probability and the second probability to create an combined probability; and   calculating an overall probability that the pair of devices are associated with a common user based at least in part on the combined probability.   
     
     
         33 . The system of  claim 29 , wherein calculating a probability that the pair of devices are owned or operated by a common user comprises:
 determining, for each pair of devices, whether the pair of devices initiated a web event at the address at a time period when users are statistically likely to be at home; and   weighting web events that occur when users are statistically expected to be at home less heavily, when calculating the probability, than web events that occur at time periods when users are statistically likely to be away from home.   
     
     
         34 . The system of  claim 29  wherein calculating a probability that the pair of devices are owned or operated by a common user comprises:
 determining, for each pair of devices, whether the pair of devices initiated a web event at the address at a time period when users are statistically likely to be at home; and 
 weighting web events that occur when users are statistically expected to be at home at least as heavily, when calculating the probability, as web events that occur at time periods when users are statistically likely to be away from home. 
 
     
     
         35 . The system of  claim 29 , wherein the processor is further configured for:
 accessing, in a database, demographic or browsing history information generated from the common user’s use of a first device of the pair of devices, the demographic or browsing history information being stored in the database in relation to the unique identifier; and   identifying, based on the demographic or browsing history information, electronic content to display at a second device of the pair of devices, wherein the demographic or browsing history information is synchronized and associated with the common user’s first device and the common user’s second device.   
     
     
         36 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method of associating a plurality of devices with a common user profile for targeting content, the method including:
 receiving, from a plurality of devices, a plurality of requests for content;   extracting, from each of the plurality of requests, an occurrence, an address, and a unique identifier associated with a respective device;   calculating a probability that a pair of devices are associated with a common user based on a weighted value of the plurality of requests, addresses for the pair of devices, and unique identifiers associated with the pair of devices; and   identifying the pair of devices with a common user profile based on the calculated probability exceeding a threshold level.   
     
     
         37 . The non-transitory computer-readable medium of  claim 36 , the method further including:
 if the calculated probability exceeds a first threshold, prompting a user to confirm a characteristic of a prior browsing session; and if the calculated probability exceeds a second threshold, prompting the user to log-in to an account associated with the common user.   
     
     
         38 . The non-transitory computer-readable medium of  claim 36 , wherein the probability is determined at least in part by incorporating at least one second probability that the pair of devices are associated with a common user calculated over a second predetermined time period. 
     
     
         39 . The non-transitory computer-readable medium of  claim 38 , the method further including:
 normalizing the probability and the second probability;   combining the probability and the second probability to create an combined probability; and   calculating an overall probability that the pair of devices are associated with a common user based at least in part on the combined probability.   
     
     
         40 . The non-transitory computer-readable medium of  claim 36 , wherein the method of calculating a probability that the pair of devices are owned or operated by a common user further includes:
 determining, for each pair of devices, whether the pair of devices initiated a web event at the address at a time period when users are statistically likely to be at home; and   weighting web events that occur when users are statistically expected to be at home less heavily, when calculating the probability, than web events that occur at time periods when users are statistically likely to be away from home.