Real-time in-stream compliance monitoring facility

Abstract

Disclosed herein are systems and methods for redacting sensitive information. Certain methods involve caching an incoming communication in a cache of the machine, optionally, when the communication is a vocal stream, using a speech processor, converting the vocal stream to text before analyzing, and automatically analyzing the communication and identifying sensitive information in accordance with one or more rules and identifying the location of the sensitive information in the communication. The sensitive information is automatically redacted from the communication and the redacted communication is at least one of stored and transmitted.

What is claimed is: 
     
         1 . A method, comprising:
 caching an incoming communication in a cache of the machine;   optionally, when the communication is a vocal stream, using a speech processor, converting the vocal stream to text before analyzing;   automatically analyzing the communication and identifying sensitive information in accordance with one or more rules and identifying the location of the sensitive information in the communication;   automatically redacting the sensitive information from the communication; and   at least one of storing and transmitting the redacted communication.   
     
     
         2 . The method of  claim 1 , wherein the communication is at least one of a vocal stream, a text message, a chat transcript, an SMS, and an email. 
     
     
         3 . The method of  claim 1 , wherein redacting comprises at least one of removing, muting and bleeping. 
     
     
         4 . The method of  claim 1 , wherein the vocal stream is at least one of an incoming telephonic voice communication and a cloud-based vocal stream. 
     
     
         5 . The method of  claim 1 , wherein the sensitive information is at least one of all numbers where two or more numbers are found in sequence, a credit card number, a security code, an expiration date, a PIN number, a date of birth, a driver's license data, authentication data, cardholder data, a social security number and financial account data. 
     
     
         6 . The method of  claim 1 , wherein converting the vocal stream is done using at least one of large vocabulary speech recognition technology, phonetic engines, direct phrase recognition and cloud-based speech recognition. 
     
     
         7 . The method of  claim 1 , wherein the rules for identifying sensitive information comprise contextual analysis to identify information that is at least one of private, PCI sensitive, PII, protected by lawyer/client privilege and protected by doctor/patient privilege. 
     
     
         8 . The method of  claim 1 , further comprising archiving the communication, redacting sensitive information from the archived redacted communication in accordance with one or more second rules and archiving the further redacted communication. 
     
     
         9 . A method for redacting incoming sensitive information from an incoming communication prior to receipt by an agent, comprising:
 caching the incoming communication in a cache of the machine;   optionally, when the communication is a vocal stream, automatically converting the vocal stream to text using a speech processor of the machine;   automatically analyzing the communication and identifying sensitive information in accordance with one or more rules and identifying the location of the sensitive information in the communication;   automatically redacting the sensitive information from the communication; and   transmitting the redacted communication to an agent.   
     
     
         10 . The method of  claim 9 , wherein the communication is at least one of a vocal stream, a text message, a chat transcript, an SMS, and an email. 
     
     
         11 . The method of  claim 9 , further comprising transferring the unredacted incoming communication to an alternate method of receiving sensitive information. 
     
     
         12 . The method of  claim 9 , wherein the rules for identifying sensitive information comprise contextual analysis to identify information that is at least one of private, PCI sensitive, PII, protected by lawyer/client privilege and protected by doctor/patient privilege. 
     
     
         13 . The method of  claim 9 , wherein the sensitive information is at least one of all numbers where two or more numbers are found in sequence, a credit card number, a security code, an expiration date, a PIN number, a date of birth, a driver's license data, authentication data, cardholder data, a social security number and financial account data. 
     
     
         14 . The method of  claim 9 , wherein redacting comprises at least one of removing, muting and bleeping. 
     
     
         15 . A machine for redacting sensitive information prior to transmission, wherein the machine is programmed to carry out the steps of an algorithmic method, comprising:
 identifying the recipient of an outgoing communication;   comparing the recipient to a set of approved recipients; and   for recipients not in the set of approved recipients:
 caching the outgoing communication; 
 optionally, when the communication is a vocal stream, converting the outgoing vocal stream to text for analysis using speech analytics technology; 
 analyzing the communication and identifying sensitive information in accordance with one or more rules; 
 identifying the location of the sensitive information in the communication; 
 redacting the sensitive information from the communication; and 
 transmitting the redacted communication to the unapproved recipient. 
   
     
     
         16 . The machine of  claim 15 , wherein the communication is at least one of a vocal stream, a text message, a chat transcript, an SMS, and an email. 
     
     
         17 . The machine of  claim 15 , further comprising, transmitting the communication to the approved recipients. 
     
     
         18 . The machine of  claim 15 , wherein the rules for identifying sensitive information comprise contextual analysis to identify information that is at least one of private, PCI sensitive, PII, protected by lawyer/client privilege and protected by doctor/patient privilege.