Contextual insight system

Abstract

Aspects of systems and methods for providing contextual and event driven insights are provided. The system monitors information about the users and their conversations. Upon receiving a natural language request for information for a topic, the system utilizes a model to extract one or more topics from the request. The system utilizes the topic to query a resource for candidate users with knowledge about the topic. The system then queries a resource to identify candidate content items associated with the topic and the candidate users. Thereafter, the system refines the candidate users and the candidate content items to identify relevant users and content items that are meaningful to the user.

1 .- 20 . (canceled) 
     
     
         21 . A system comprising:
 a processing unit; and   a memory coupled storing instructions that, when executed, perform operations comprising:
 receiving a request from a user as part of a conversation between the user and a conversation participant; 
 extracting one or more keywords from the request, the one or more keywords identifying a topic of the request; 
 querying, using the one or more keywords as input, one or more resources to identify:
 candidate users that are at least one of knowledgeable about the topic or included within the request; and 
 candidate content items that are associated with the topic and with which the candidate users have interacted; and 
 
 providing the candidate users and the candidate content items to the user as results to the request. 
   
     
     
         22 . The system of  claim 21 , wherein the conversation participant is an electronic agent of a communication application. 
     
     
         23 . The system of  claim 21 , wherein the system monitors the conversation to identify:
 static context data associated with the user; and   dynamic context data related to one or more topics, the one or more topics including the topic of the request.   
     
     
         24 . The system of  claim 23 , wherein the static context data includes data about the user that does not change during the conversation. 
     
     
         25 . The system of  claim 23 , wherein the dynamic context data:
 includes data about subject matter of the conversation that changes during the conversation; and   is monitored for a timeframe during the conversation.   
     
     
         26 . The system of  claim 25 , wherein the timeframe corresponds to an amount of most recent messages in the conversation or a subset of time in a total time for the conversation. 
     
     
         27 . The system of  claim 23 , the operations further comprising:
 ranking the candidate users and the candidate content items to generate ranked results based on at least one of the static context data or the dynamic context data; and   providing the ranked results as the results to the request.   
     
     
         28 . The system of  claim 27 , wherein the ranked results are ranked based on at least one of:
 a role of the user;   a trending status of the candidate users or the candidate content items; or   a modification time for the candidate content items.   
     
     
         29 . The system of  claim 21 , wherein providing the candidate users and the candidate content items comprises providing a top number of highest ranking results from a combination of the candidate users and the candidate content items, the top number of highest ranking results being a subset of a total number of the candidate users and the candidate content items. 
     
     
         30 . The system of  claim 21 , wherein the results further comprises additional information for each candidate user of the candidate users, the additional information including at least one of:
 a role of the candidate user;   contact information for the candidate user;   or a selectable user interface for engaging in a discussion with the candidate user.   
     
     
         31 . The system of  claim 21 , wherein the one or more resources are associated with an enterprise of which the user is a member, the one or more resources including:
 a document resource storing content items of the enterprise; and   a people resource storing users that are members of the enterprise.   
     
     
         32 . The system of  claim 31 , wherein the document resource is a document database or an information management index. 
     
     
         33 . The system of  claim 31 , wherein the people resource is an enterprise directory or a social network data store. 
     
     
         34 . The system of  claim 31 , wherein the one or more resources are stored in a relational graph of the enterprise, the one or more resources being stored as nodes of the relational graph and relationships between the one or more resources being stored as edges of the relational graph. 
     
     
         35 . A method comprising:
 receiving, at a computing device, a dialogue entry from a user as part of a conversation between the user and a conversation participant;   extracting one or more keywords from the dialogue entry, the one or more keywords identifying a topic of the dialogue entry;   querying, using the one or more keywords as input, one or more resources to identify:
 candidate users that are at least one of knowledgeable about the topic or included within the dialogue entry; and 
 candidate content items that are associated with the topic and with which the candidate users have interacted; and 
   providing the candidate users and the candidate content items to the user as results to the dialogue entry.   
     
     
         36 . The method of  claim 35 , wherein the conversation is monitored by an insight system that provides contextual and event driven insights, the insight system being associated with a communication application facilitating the conversation. 
     
     
         37 . The method of  claim 36 , wherein:
 the user is a first user and the conversation participant is a second user; and   the communication application provides a graphical user interface for the first user and the second user to communicate during the conversation.   
     
     
         38 . The method of  claim 36 , wherein the insight system stores:
 static context data collected during the conversation in a first data store of the insight system; and   dynamic context data during the conversation in a first data store of the insight system.   
     
     
         39 . The method of  claim 36 , wherein the insight system ranks the results based on a relevance score assigned to each of the candidate users and the candidate content items. 
     
     
         40 . A device comprising:
 a processing unit; and   a memory coupled storing instructions that, when executed, perform operations comprising:
 receiving, by a contextual insight system, a communication from a user during a conversation between the user and a conversation participant, wherein the contextual insight system monitors the conversation; 
 extracting, by the contextual insight system, one or more keywords from the communication, the one or more keywords identifying a topic of the communication; 
 querying, using the one or more keywords as input, one or more resources accessible to the contextual insight system to identify:
 candidate users that are at least one of knowledgeable about the topic or included within the communication; and 
 candidate content items that are associated with the topic and with which the candidate users have interacted; and 
 
 providing at least a subset of the candidate users and the candidate content items to the user as results to the communication.