Voice enabled content tracker

Abstract

Certain aspects of the present disclosure provide techniques and systems for automatically detecting, tracking, and processing certain information content, based on voice input from a user. A voice enabled content tracking system receives natural language content corresponding to audio input from a user. A determination is made as to whether the natural language content includes a first type of information, based on evaluating the natural language content with a first machine learning model. In response to determining the natural language content comprises the first type of information, a temporal association of the first type of information is determined, based on evaluating the natural language content with a second machine learning model, and a message including an indication of the temporal association of the first type of information is transmitted to the user.

What is claimed is: 
     
         1 . A method comprising:
 monitoring a chat window of a first user interface of a first computing device associated with a first user during an interaction session between the first user of an application and a second user of the application, wherein the chat window comprises one or more elements for uploading at least one attachment;   detecting, based on the monitoring, an upload of the at least one attachment;   in response to detecting the upload of the at least one attachment, blocking access to the at least one attachment from a second computing device associated with the second user;   
       identifying and extracting content from the at least one attachment; 
       determining a type of the at least one attachment based on the content; and 
       determining whether the second user is authorized to access the type of the at least one attachment based on a set of permissions associated with the second user, a type of engagement between the first user and the second user during the interactive session, and the type of the at least one attachment, the type of the engagement between the first user and the second user comprising a selection from a plurality of types of engagement corresponding to a plurality of possible attachment types for the at least one attachment. 
     
     
         2 . The method of  claim 1 , further comprising:
 storing the at least one attachment in a storage system in response to detecting the upload of the at least one attachment,   wherein identifying and extracting the content from the at least one attachment comprises retrieving the at least one attachment from the storage system and performing optical character recognition on the at least one attachment retrieved from the storage system.   
     
     
         3 . The method of  claim 2 , wherein:
 the access to the at least one attachment is blocked for a first period of time,   and the method further comprises, upon determining that the second user is unauthorized to access the type of the at least one attachment:   continuing to block access to the at least one attachment from the second computing device for a second period of time after the first period of time has elapsed; and   removing the at least one attachment from the storage system.   
     
     
         4 . The method of  claim 3 , wherein continuing to block access to the at least one attachment comprises permanently blocking access to the at least one attachment after the first period of time has elapsed. 
     
     
         5 . The method of  claim 2 , wherein:
 the access to the at least one attachment is blocked for a period of time,   and the method further comprises, upon determining that the second user is authorized to access the type of the at least one attachment:   allowing access to the at least one attachment from the second computing device after the period of time has elapsed; and   removing the at least one attachment from the storage system.   
     
     
         6 . The method of  claim 1 , wherein the type of the at least one attachment is determined based on evaluating the content using at least one of a rules engine or a machine learning model. 
     
     
         7 . The method of  claim 6 , wherein evaluating the content comprises classifying the at least one attachment into one of a plurality of different types of tax documents based on the content, the plurality of different types of tax documents including a plurality of business type tax documents and a plurality of personal type tax documents, where the at least one of the rules engine or machine learning model is used to classify the at least one attachment into a business type tax document or a personal type tax document, the type of engagement is selected from a business type engagement or a personal type engagement, and the determining whether the second user is authorized to access the type of the at least one attachment is based on the type of engagement matching the type of the at least one attachment. 
     
     
         8 . The method of  claim 7 , wherein evaluating the content further comprises classifying the at least one attachment into one of a plurality of different types of tax documents by:
 generating a confidence score for each respective type of tax document based on the content; and   selecting the type of tax document having a highest confidence score as the one of the plurality of different types of tax documents.   
     
     
         9 . The method of  claim 1 , wherein the upload of the at least one attachment is to a first storage system, the method further comprising obtaining, from a second storage system the set of permissions associated with the second user, the type of engagement between the first user and the second user during the interactive session, and the type of the at least one attachment. 
     
     
         10 . The method of  claim 1 , wherein the second user is a human support agent or a virtual support agent. 
     
     
         11 . A system comprising:
 a memory having executable instructions stored thereon; and   a processor configured to execute the executable instructions to cause the system to:   monitor a chat window of a first user interface of a first computing device associated with a first user during an interaction session between the first user of an application and a second user of the application, wherein the chat window comprises one or more elements for uploading at least one attachment;   detect, based on the monitoring, an upload of the at least one attachment;   in response to detecting the upload of the at least one attachment, block access to the at least one attachment from a second computing device associated with the second user;   
       identify and extracting content from the at least one attachment; 
       determine a type of the at least one attachment based on the content; and 
       determine whether the second user is authorized to access the type of the at least one attachment based on a set of permissions associated with the second user, a type of engagement between the first user and the second user during the interactive session, and the type of the at least one attachment, the type of the engagement between the first user and the second user comprising a selection from a plurality of types of engagement corresponding to a plurality of possible attachment types for the at least one attachment. 
     
     
         12 . The system of  claim 11 , wherein the processor is further configured to execute the executable instructions to cause the system to:
 store the at least one attachment in a storage system in response to detecting the upload of the at least one attachment;   retrieve the at least one attachment from the storage system; and   perform optical character recognition on the at least one attachment retrieved from the storage system to identify and extract the content from the at least one attachment.   
     
     
         13 . The system of  claim 12 , wherein:
 the access to the at least one attachment is blocked for a first period of time; and   the processor is further configured to execute the executable instructions to cause the system to, upon determining that the second user is unauthorized to access the type of the at least one attachment:   continue to block access to the at least one attachment from the second computing device for a second period of time after the first period of time has elapsed; and   remove the at least one attachment from the storage system.   
     
     
         14 . The system of  claim 13 , wherein continuing to block access to the at least one attachment comprises permanently blocking access to the at least one attachment after the first period of time has elapsed. 
     
     
         15 . The system of  claim 12 , wherein:
 the access to the at least one attachment is blocked for a period of time; and   the processor is further configured to execute the executable instructions to cause the system to, upon determining that the second user is authorized to access the type of the at least one attachment:   allow access to the at least one attachment from the second computing device after the period of time has elapsed; and   remove the at least one attachment from the storage system.   
     
     
         16 . The system of  claim 11 , wherein the type of the at least one attachment is determined based on evaluating the content using at least one of a rules engine or a machine learning model. 
     
     
         17 . The system of  claim 16 , wherein evaluating the content comprises classifying the at least one attachment into one of a plurality of different types of tax documents based on the content, the plurality of different types of tax documents including a plurality of business type tax documents and a plurality of personal type tax documents, where the at least one of the rules engine or machine learning model is used to classify the at least one attachment into a business type tax document or a personal type tax document, the type of engagement is selected from a business type engagement or a personal type engagement, and the determining whether the second user is authorized to access the type of the at least one attachment is based on the type of engagement matching the type of the at least one attachment. 
     
     
         18 . The system of  claim 17 , wherein evaluating the content further comprises classifying the at least one attachment into one of a plurality of different types of tax documents by:
 generating a confidence score for each respective type of tax document based on the content; and   selecting the type of tax document having a highest confidence score as the one of the plurality of different types of tax documents.   
     
     
         19 . The system of  claim 11 , wherein the upload of the at least one attachment is to a first storage system, and the processor is further configured to execute the executable instructions to cause the system to obtain, from a second storage system the set of permissions associated with the second user, the type of engagement between the first user and the second user during the interactive session, and the type of the at least one attachment. 
     
     
         20 . A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to:
 monitor a chat window of a first user interface of a first computing device associated with a first user during an interaction session between the first user of an application and a second user of the application, wherein the chat window comprises one or more elements for uploading at least one attachment;   detect, based on the monitoring, an upload of the at least one attachment;   in response to detecting the upload of the at least one attachment, block access to the at least one attachment from a second computing device associated with the second user;   
       identify and extracting content from the at least one attachment; 
       determine a type of the at least one attachment based on the content; and 
       determine whether the second user is authorized to access the type of the at least one attachment based on a set of permissions associated with the second user, a type of engagement between the first user and the second user during the interactive session, and the type of the at least one attachment, the type of the engagement between the first user and the second user comprising a selection from a plurality of types of engagement corresponding to a plurality of possible attachment types for the at least one attachment.