Automatic analysis of digital messaging content method and apparatus

Abstract

Disclosed are systems and methods for improving interactions with and between computers searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The methods and systems analyze digital message content in digital communication systems to automatically identify shared user interest(s), to automatically create computerized relationship matrix data identifying user connections, or relationships, using identified shared user interest(s), and to automatically provide a recommendation using the shared user interest and user relationships formed using the shared user interest.

1 . A method comprising:
 obtaining, at a computing device, a plurality of digital messages of a user;   using, via the computing device, the plurality of digital messages of the user to:
 determine interests of the user; 
 determine a plurality of contacts of the user; and 
 determine each contact's interaction frequency with the user; 
   selecting, via the computing device, at least one contact from the plurality of contacts using the interaction frequency determined for each of the plurality of contacts, each selected contact having a higher interaction frequency with the user than unselected contacts of the plurality of contacts;   determining, via the computing device, an interest shared by the user and the at least one selected contact, the determining comprising comparing the interests of the user with each selected contact's interests to identify the shared interest; and   automatically making, via the computing device, a recommendation directed to at least one of the user and the at least one contact, the recommendation identifying the shared interest and recommending at least one online activity related to the shared interest.   
     
     
         2 . The method of  claim 1 , further comprising:
 automatically maintaining, via the computing device, a relationship data structure to include information indicating a relationship between the user and the at least one selected contact, the relationship identifying the shared interest between the user and the at least one selected contact.   
     
     
         3 . The method of  claim 1 , further comprising:
 generating, via the computing device, a machine-trained model using a machine-learning algorithm and a training data set; and   identifying, via the computing device, the interests of the user using the machine-trained model.   
     
     
         4 . The method of  claim 3 , identifying the interests of the user using the machine-trained model further comprising:
 obtaining, via the computing device, a plurality of probabilities corresponding to a plurality of interests from the machine-trained model; and   identifying, via the computing device, the interests of the user using a probability threshold, wherein each interest of the user has a corresponding probability that satisfies the probability threshold.   
     
     
         5 . The method of  claim 1 , the digital messages comprise different types of digital messages. 
     
     
         6 . The method of  claim 1 , the digital messages comprise a same type of digital message. 
     
     
         7 . The method of  claim 1 , the digital messages are obtained from a number of different messaging services. 
     
     
         8 . The method of  claim 1 , the digital messages are obtained from one messaging service. 
     
     
         9 . The method of  claim 1 , determining a contact's interaction frequency with the user comprising using a number of the plurality of digital messages that indicate the contact. 
     
     
         10 . The method of  claim 1 , determining a contact's interaction frequency with the user comprising using a number of the plurality of digital messages sent by the user that indicate the contact. 
     
     
         11 . The method of  claim 1 , determining a contact's interaction frequency with the user comprising using a number of the plurality of digital messages received by the user that indicate the contact. 
     
     
         12 . The method of  claim 1 , determining a contact's interaction frequency with the user comprising using a number of the plurality of digital messages received and opened by the user that indicated the contact. 
     
     
         13 . The method of  claim 1 , determining a contact's interaction frequency with the user comprising using a number of the plurality of digital messages received and responded to by the user that indicated the contact. 
     
     
         14 . The method of  claim 1 , further comprising:
 generating, via the computing device, a hierarchical interest matrix comprising the interests of the user identified using the plurality of digital messages.   
     
     
         15 . A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a processor associated with a computing device perform a method comprising:
 obtaining a plurality of digital messages of a user;   using the plurality of digital messages of the user to:
 determine interests of the user; 
 determine a plurality of contacts of the user; and 
 determine each contact's interaction frequency with the user; 
   selecting at least one contact from the plurality of contacts using the interaction frequency determined for each of the plurality of contacts, each selected contact having a higher interaction frequency with the user than unselected contacts of the plurality of contacts;   determining an interest shared by the user and the at least one selected contact, the determining comprising comparing the interests of the user with each selected contact's interests to identify the shared interest; and   automatically making a recommendation directed to at least one of the user and the at least one contact, the recommendation identifying the shared interest and recommending at least one online activity related to the shared interest.   
     
     
         16 . The non-transitory computer-readable storage medium of  claim 15 , the method further comprising:
 automatically maintaining a relationship data structure to include information indicating a relationship between the user and the at least one selected contact, the relationship identifying the shared interest between the user and the at least one selected contact.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 15 , the method further comprising:
 generating a machine-trained model using a machine-learning algorithm and a training data set; and   identifying the interests of the user using the machine-trained model.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , identifying the interests of the user using the machine-trained model further comprising:
 obtaining, a plurality of probabilities corresponding to a plurality of interests from the machine-trained model; and   identifying the interests of the user using a probability threshold, wherein each interest of the user has a corresponding probability that satisfies the probability threshold.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 15 , the method further comprising:
 generating a hierarchical interest matrix comprising the interests of the user identified using the plurality of digital messages.   
     
     
         20 . A computing device comprising:
 a processor; and   a non-transitory storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
 obtaining logic executed by the processor for obtaining a plurality of digital messages of a user; 
 using logic executed by the processor for using the plurality of digital messages of the user to:
 determine interests of the user; 
 determine a plurality of contacts of the user; and 
 determine each contact's interaction frequency with the user; 
 
 selecting logic executed by the processor for selecting at least one contact from the plurality of contacts using the interaction frequency determined for each of the plurality of contacts, each selected contact having a higher interaction frequency with the user than unselected contacts of the plurality of contacts; 
 determining logic executed by the processor for determining an interest shared by the user and the at least one selected contact, the determining comprising comparing the interests of the user with each selected contact's interests to identify the shared interest; and 
 making logic executed by the processor for automatically making a recommendation directed to at least one of the user and the at least one contact, the recommendation identifying the shared interest and recommending at least one online activity related to the shared interest.