Augmented data insight generation and provision

Abstract

In the present disclosure, artificial intelligence (AI) processing is trained and leveraged to learn user-specific insights that are contextually relevant to a state of a user communication. Contextual information about a state of a user communication may be collected and analyzed. That contextual information may be cross-referenced with an extensive knowledge graph that is constructed from user context data. Exemplary AI processing may further be trained to apply a relevance analysis to assist with processing described herein including generation and curation of data insights that are most relevant to a state of a user communication. In some examples, the data insight generation process may be augmented by pre-generating data insights that may be relevant to a user communication prior to occurrence of the user communication. Further technical examples pertain to the rendering and presentation of representations of data insights through a graphical user interface (GUI).

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 collecting context information about a current state of an electronic meeting based on analyzing meeting data associated with the electronic meeting, wherein the collected context information comprises:
 user-specific identification for two or more users associated with the meeting data of the electronic meeting, 
 one or more topics of the electronic meeting, and 
 one or more electronic files associated with the meeting data of the electronic meeting; 
   accessing a stored knowledge graph to identify user context data for the two or more users using the context information collected about the current state of the electronic meeting, wherein the user context data comprises:
 user-specific entity data for each of the two or more users, 
 file access data indicating electronic files accessed by a first one of the two or more users, and 
 file access data indicating electronic files accessed by a second one of the two or more users; 
   generating a plurality of data insights from specific portions of the user context data that satisfy a threshold distance evaluation which evaluates a distance between nodes in the stored knowledge graph after accessing the stored knowledge graph using the context information;   executing a relevance scoring on each of the plurality of data insights using one or more trained relevance models;   selecting, from the plurality of data insights, one or more data insights for presentation based on a result of the relevance scoring; and   transmitting, to a client device, data for rendering the one or more data insights.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the one or more trained relevance models score a relevance of a data insight to the context information collected about the current state of the electronic meeting. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the collected context information further comprises a temporal designation indicating a point in time relative to an occurrence of the electronic meeting. 
     
     
         4 . The computer-implemented method of  claim 3 , wherein the user-specific identification is identified at the temporal designation. 
     
     
         5 . The computer-implemented method of  claim 3 , wherein the one or more topics are identified at the temporal designation. 
     
     
         6 . The computer-implemented method of  claim 3 , wherein the temporal designation is used to select the one or more trained relevance models from a plurality of trained relevance models usable for executing the relevance scoring. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the user context data further comprises:
 collaborative relationships previously existing between the two or more users; and   topics identified from prior communications of the two or more users.   
     
     
         8 . The computer-implemented method of  claim 1 , wherein:
 the user-specific identification comprises data for at least one user that has not joined the electronic meeting but is determined to potentially join the meeting based on the performance of predictive analysis.   
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 determining that the first one of the two or more users and the second one of the two or more users have not interacted before;   generating, based on determining that the first one of the two or more users and the second one of the two or more users have not interacted before, an insight comprising an augmented annotation including a specialty of the first one of the two or more users; and   transmitting, to the client device, the insight comprising the augmented annotation.   
     
     
         10 . The computer-implemented method of  claim 9 , wherein the augmented annotation comprises a real-time amendment to a contact card of the first one of the two or more users. 
     
     
         11 . The computer-implemented method of  claim 1 , wherein:
 the one or more data insights selected from the plurality of data insights are identified at a first temporal designation, and the method further comprises:   identifying a plurality of additional data insights at a second temporal designation;   executing a relevance scoring on each of the plurality of additional data insights using one or more trained relevance models;   selecting, from the plurality of additional data insights, a second one or more data insights for presentation based on a result of the relevance scoring; and   transmitting, to the client device, data for rendering the second one or more data insights for presentation.   
     
     
         12 . The computer-implemented method of  claim 11 , further comprising:
 generating a dynamic timeline of data insights for the electronic meeting that provides an aggregated visualization of the one or more data insights and the second one or more data insights; and   transmitting, to the client device, the dynamic timeline of data insights for rendering.   
     
     
         13 . A system comprising:
 at least one processor; and   a memory, operatively connected with the at least one processor, storing computer-executable instructions that, when executed by the at least one processor, causes the at least one processor to execute a method that comprises:
 collecting context information about a current state of an electronic meeting based on analyzing meeting data associated with the electronic meeting, wherein the collected context information comprises:
 user-specific identification for two or more users associated with the meeting data of the electronic meeting, 
 one or more topics of the electronic meeting, and 
 one or more electronic files associated with the meeting data of the electronic meeting; 
 
 accessing a stored knowledge graph to identify user context data for the two or more users using the context information collected about the current state of the electronic meeting, wherein the user context data comprises:
 user-specific entity data for each of the two or more users, 
 file access data indicating electronic files accessed by a first one of the two or more users, and 
 file access data indicating electronic files accessed by a second one of the two or more users; 
 
 generating a plurality of data insights from specific portions of the user context data that satisfy a threshold distance evaluation which evaluates a distance between nodes in the stored knowledge graph after accessing the stored knowledge graph using the context information; 
 executing a relevance scoring on each of the plurality of data insights using one or more trained relevance models; 
 selecting, from the plurality of data insights, one or more data insights for presentation based on a result of the relevance scoring; and 
 transmitting, to a client device, data for rendering the one or more data insights. 
   
     
     
         14 . The system of  claim 13 , wherein the one or more trained relevance models score a relevance of a data insight to the context information collected about the current state of the electronic meeting. 
     
     
         15 . The system of  claim 13 , wherein the collected context information further comprises a temporal designation indicating a point in time relative to an occurrence of the electronic meeting. 
     
     
         16 . The system of  claim 13 , wherein the user-specific identification comprises data for at least one user that has not joined the electronic meeting but is determined to potentially join the meeting based on the performance of predictive analysis. 
     
     
         17 . The system of  claim 13 , wherein the method, executed by the at least one processor, further comprises:
 determining that the first one of the two or more users and the second one of the two or more users have not interacted before;   generating, based on determining that the first one of the two or more users and the second one of the two or more users have not interacted before, an insight comprising an augmented annotation including a specialty of the first one of the two or more users; and   transmitting, to the client device, the insight comprising the augmented annotation.   
     
     
         18 . A computer-readable storage device comprising executable instructions that, when executed by a processor, assist with generating data insights, the computer-readable storage device including instructions executable by the processor for:
 collecting context information about a current state of an electronic meeting based on analyzing meeting data associated with the electronic meeting, wherein the collected context information comprises:
 user-specific identification for two or more users associated with the meeting data of the electronic meeting, 
 one or more topics of the electronic meeting, and 
 one or more electronic files associated with the meeting data of the electronic meeting; 
   accessing a stored knowledge graph to identify user context data for the two or more users using the context information collected about the current state of the electronic meeting, wherein the user context data comprises:
 user-specific entity data for each of the two or more users, 
 file access data indicating electronic files accessed by a first one of the two or more users, and 
 file access data indicating electronic files accessed by a second one of the two or more users; 
   generating a plurality of data insights from specific portions of the user context data that satisfy a threshold distance evaluation which evaluates a distance between nodes in the stored knowledge graph after accessing the stored knowledge graph using the context information;   executing a relevance scoring on each of the plurality of data insights using one or more trained relevance models;   selecting, from the plurality of data insights, one or more data insights for presentation based on a result of the relevance scoring; and   transmitting, to a client device, data for rendering the one or more data insights.   
     
     
         19 . The computer-readable storage device of  claim 18 , wherein:
 the one or more data insights selected from the plurality of data insights are identified at a first temporal designation, and the instructions are further executable by the processor for:   identifying a plurality of additional data insights at a second temporal designation;   executing a relevance scoring on each of the plurality of additional data insights using one or more trained relevance models;   selecting, from the plurality of additional data insights, a second one or more data insights for presentation based on a result of the relevance scoring; and   transmitting, to the client device, data for rendering the second one or more data insights for presentation.   
     
     
         20 . The computer-readable storage device of  claim 19 , wherein the instructions are further executable by the processor for:
 generating a dynamic timeline of data insights for the electronic meeting that provides an aggregated visualization of the one or more data insights and the second one or more data insights; and   transmitting, to the client device, the dynamic timeline of data insights for rendering.