Forming event-based recommendations

Abstract

Systems and methods for forming collaboration recommendations. Techniques for forming event-based recommendations use time-decayed event values. A shared content management system supports a plurality of users that generate events by interacting with content objects of the shared content management system. Events over the content objects are captured as event objects. Method steps are invoked upon receiving event objects that describes user-to-object interaction events that arise from interactions by users over content objects. Different types of interactions carry different importance values. The importance values can be applied as weights when scoring user-to-object interaction activities. The importance can decay over time. As time progresses and as the importance of older interactions decay, score components of a user-to-object interaction can be updated based at least in part on a time decay function. The system emits collaboration recommendations based on the decayed user-to-user collaboration scores.

1 . A method for forming event-based collaboration recommendations, the method comprising:
 identifying a plurality of users that access a distributed computing and storage platform to interact with a plurality of content objects that are managed by the distributed computing and storage platform;   receiving at least one event object, the at least one event object describing at least one user-to-object interaction event that associates an interaction by at least one user from the plurality of users with at least one content object from the plurality of content objects;   generating one or more collaboration recommendations based at least in part on a time-decayed value being applied to a score of the at least one user-to-object interaction event; and   emitting the one or more collaboration recommendations.   
     
     
         2 . The method of  claim 1 , further comprising:
 generating a separate time-decayed value based at least in part upon a separate event object that describes a separate user-to-object interaction event that associates a separate interaction by the user or a different user from the plurality of users with the content object or a separate content object of the plurality of content objects.   
     
     
         3 . The method of  claim 2 , further comprising:
 updating the one or more collaboration recommendations based at least in part on a separate time-decayed value being applied to a separate score of the separate user-to-object interaction event, wherein the user-to-object interaction event and the separate user-to-object interaction form a time sequence of interactions.   
     
     
         4 . The method of  claim 1 , wherein the time sequence of interactions is received at the distributed computing and storage platform as a sequence of packets of a data stream. 
     
     
         5 . The method of  claim 1 , further comprising:
 quantifying a characteristic of a plurality of user-to-object interactions by using at least the score of the at least one user-to-object interaction event.   
     
     
         6 . The method of  claim 1 , further comprising:
 generating, at least by adding a row or a column to a data structure, a relationship between a first user and a second user based at least in part upon affinity between a first content object and a second content object of the plurality of content objects.   
     
     
         7 . The method of  claim 6 , wherein the relationship is generated at least by comprising:
 determining the affinity between the first content object and the second content object of the plurality of content objects;   determining the first user that accesses the first content object; and   determining the second user that accesses the second content object.   
     
     
         8 . The method of  claim 6 , further comprising:
 updating the relationship between the first user and the second user into a time-decayed relationship between the first user and the second user based at least in part upon a time period from a first time point at which the relationship is determined and a second time point following the first time point.   
     
     
         9 . The method of  claim 6 , further comprising:
 determining a separate affinity that ceases to exist, the affinity between a third content object and a fourth content object of the plurality of content objects; and   in response to a determination that the separate affinity ceases to exist, removing a first row or a first column corresponding to the separate affinity in the data structure;   
     
     
         10 . The method of  claim 6 , wherein the data structure comprises a first key column, a second key column, and an affinity type column, the first key column comprises a first object identifier of a first object, the second key column comprises a second object identifier of a second object, and the affinity type column comprises information pertaining to corresponding affinity between the first and the second objects. 
     
     
         11 . A computer program product embodied on a non-transitory computer readable medium having stored thereon a sequence of instructions which, when executed by a processor, causes the processor to perform a set of acts, the set of acts comprising:
 identifying a plurality of users that access a distributed computing and storage platform to interact with a plurality of content objects that are managed by the distributed computing and storage platform;   receiving at least one event object, the at least one event object describing at least one user-to-object interaction event that associates an interaction by at least one user from the plurality of users with at least one content object from the plurality of content objects;   generating one or more collaboration recommendations based at least in part on a time-decayed value being applied to a score of the at least one user-to-object interaction event; and   emitting the one or more collaboration recommendations.   
     
     
         12 . The computer program product of  claim 11 , the set of acts further comprising:
 generating a separate time-decayed value based at least in part upon a separate event object that describes a separate user-to-object interaction event that associates a separate interaction by the user or a different user from the plurality of users with the content object or a separate content object of the plurality of content objects.   
     
     
         13 . The computer program product of  claim 12 , the set of acts further comprising:
 updating the one or more collaboration recommendations based at least in part on a separate time-decayed value being applied to a separate score of the separate user-to-object interaction event, wherein the user-to-object interaction event and the separate user-to-object interaction form a time sequence of interactions.   
     
     
         14 . The computer program product of  claim 11 , wherein the time sequence of interactions is received at the distributed computing and storage platform as a sequence of packets of a data stream. 
     
     
         15 . The computer program product of  claim 11 , the set of acts further comprising:
 determining affinity between a first content object and a second content object of the plurality of content objects;   determining a first user that accesses the first content object; and   determining a second user that accesses the second content object.   generating, at least by adding a row or a column to a data structure, a relationship between the first user and the second user based at least in part upon affinity between the first content object and the second content object of the plurality of content objects.   
     
     
         16 . A system, comprising:
 a processor;   a memory storing therein programming code which, when executed by the processor, causes the processor to perform a set of acts, the set of acts comprising:   identifying a plurality of users that access a distributed computing and storage platform to interact with a plurality of content objects that are managed by the distributed computing and storage platform;   receiving at least one event object, the at least one event object describing at least one user-to-object interaction event that associates an interaction by at least one user from the plurality of users with at least one content object from the plurality of content objects;   generating one or more collaboration recommendations based at least in part on a time-decayed value being applied to a score of the at least one user-to-object interaction event; and   emitting the one or more collaboration recommendations.   
     
     
         17 . The system of  claim 16 , wherein the time sequence of interactions is received at the distributed computing and storage platform as a sequence of packets of a data stream. 
     
     
         18 . The system of  claim 16 , further comprising:
 determining affinity between a first content object and a second content object of the plurality of content objects;   determining a first user that accesses the first content object;   determining a second user that accesses the second content object; and   generating, at least by adding a row or a column to a data structure, a relationship between the first user and the second user based at least in part upon the affinity between the first content object and the second content object of the plurality of content objects.   
     
     
         19 . The system of  claim 18 , the set of acts further comprising:
 updating the relationship between the first user and the second user into a time-decayed relationship between the first user and the second user based at least in part upon a time period from a first time point at which the relationship is determined and a second time point following the first time point.   
     
     
         20 . The system of  claim 18 , wherein the data structure comprises a first key column, a second key column, and an affinity type column, the first key column comprises a first object identifier of a first object, the second key column comprises a second object identifier of a second object, and the affinity type column comprises information pertaining to corresponding affinity between the first and the second objects.