Systems and methods for belief learning

Abstract

Systems, methods, and non-transitory computer readable media are configured to determine an interaction between a first entity and a first item. A second entity can be determined. The first entity can have formed a connection with the second entity on a social networking system. A belief that the second entity will interact with the first item can then be generated.

1 . (canceled) 
     
     
         2 . A computer-implemented method comprising:
 determining, by a computing system, a first belief generated for a first entity that the first entity will interact with the item;   determining, by the computing system, the first entity has interacted with the item;   generating, by the computing system, a second belief that a second entity will interact with the item based on a similarity between the first entity and a second entity determined based on first interactions associated with the first entity and second interactions associated with the second entity, wherein the similarity is weighted based on the first belief; and   providing, by the computing system, a first recommendation for the second entity for the item based on the second belief.   
     
     
         3 . The computer-implemented method of  claim 2 , further comprising:
 generating, by the computing system, log information associated with the first entity based on the determining the first entity has interacted with the item.   
     
     
         4 . The computer-implemented method of  claim 2 , further comprising:
 determining, by the computing system, information associated with previous interactions corresponding with an interaction between the first entity and the item.   
     
     
         5 . The computer-implemented method of  claim 2 , wherein the first belief is a probability the first entity will interact with the item. 
     
     
         6 . The computer-implemented method of  claim 2 , further comprising:
 determining, by the computing system, the second entity has interacted with the item;   generating, by the computing system, a third belief that the first entity will interact with a past item with which the second entity has interacted; and   providing, by the computing system, a second recommendation for the first entity for the past item based on the third belief.   
     
     
         7 . The computer-implemented method of  claim 2 , further comprising:
 generating, by the computing system, a list of beliefs associated with the second entity, wherein the list of beliefs includes the second belief.   
     
     
         8 . The computer-implemented method of  claim 7 , wherein an identifier associated with the second entity is a key for the list of beliefs associated with the second entity. 
     
     
         9 . The computer-implemented method of  claim 7 , wherein the second belief is scaled based on a sum of beliefs in the list of beliefs. 
     
     
         10 . The computer-implemented method of  claim 7 , further comprising:
 associating, by the computing system, a checkpoint with the list of beliefs; and   performing, by the computing system, a checkpoint restore operation based on the checkpoint.   
     
     
         11 . The computer-implemented method of  claim 7 , further comprising:
 removing, by the computing system, the second belief based on a satisfaction of a threshold number of beliefs generated for the second entity.   
     
     
         12 . A system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:
 determining a first belief generated for a first entity that the first entity will interact with the item; 
 determining the first entity has interacted with the item; 
 generating a second belief that a second entity will interact with the item based on a similarity between the first entity and a second entity determined based on first interactions associated with the first entity and second interactions associated with the second entity, wherein the similarity is weighted based on the first belief; and 
 providing a first recommendation for the second entity for the item based on the second belief. 
   
     
     
         13 . The system of  claim 12 , the operations further comprising:
 generating log information associated with the first entity based on the determining the first entity has interacted with the item.   
     
     
         14 . The system of  claim 12 , the operations further comprising:
 determining information associated with previous interactions corresponding with an interaction between the first entity and the item.   
     
     
         15 . The system of  claim 12 , wherein the first belief is a probability the first entity will interact with the item. 
     
     
         16 . The system of  claim 12 , the operations further comprising:
 determining the second entity has interacted with the item;   generating a third belief that the first entity will interact with a past item with which the second entity has interacted; and   providing a second recommendation for the first entity for the past item based on the third belief.   
     
     
         17 . A non-transitory computer-readable storage medium including instructions that, when executed by at least on processor of a computing system, cause the computing system to perform operations comprising:
 determining a first belief generated for a first entity that the first entity will interact with the item;   determining the first entity has interacted with the item;   generating a second belief that a second entity will interact with the item based on a similarity between the first entity and a second entity determined based on first interactions associated with the first entity and second interactions associated with the second entity, wherein the similarity is weighted based on the first belief; and   providing a first recommendation for the second entity for the item based on the second belief.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , the operations further comprising:
 generating log information associated with the first entity based on the determining the first entity has interacted with the item.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , the operations further comprising:
 determining information associated with previous interactions corresponding with an interaction between the first entity and the item.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein the first belief is a probability the first entity will interact with the item. 
     
     
         21 . The non-transitory computer-readable storage medium of  claim 17 , the operations further comprising:
 determining the second entity has interacted with the item;   generating a third belief that the first entity will interact with a past item with which the second entity has interacted; and   providing a second recommendation for the first entity for the past item based on the third belief.