Real-time compliance monitoring facility

Abstract

Disclosed herein are systems and methods for redacting sensitive information. Certain methods involve receiving a copy of a communication and automatically, under computer control, 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, under computer control, the sensitive information is redacted from the communication.

What is claimed is: 
     
         1 . A tangible article of manufacture having instructions stored thereon that, when executed, cause a machine to perform operations for removing sensitive information from a vocal stream, comprising:
 receiving a copy of the vocal stream;   automatically, using a speech processor of the machine, converting the vocal stream to text;   automatically, under computer control, analyzing the text and identifying sensitive information in accordance with one or more rules and identifying the location of the sensitive information in the vocal stream; and   automatically, under computer control, redacting the sensitive information from the vocal stream.   
     
     
         2 . The tangible article of manufacture 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. 
     
     
         3 . The tangible article of manufacture of  claim 1 , wherein redacting comprises at least one of removing, muting and bleeping. 
     
     
         4 . The tangible article of manufacture of  claim 1 , wherein the vocal stream is an incoming telephonic voice communication. 
     
     
         5 . The tangible article of manufacture of  claim 1 , wherein the vocal stream is an archived voice recording. 
     
     
         6 . The tangible article of manufacture 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 tangible article of manufacture of  claim 1 , wherein the vocal stream is a cloud-based vocal stream. 
     
     
         8 . The tangible article of manufacture of  claim 7 , further comprising, storing the redacted cloud-based vocal stream in a cloud-based storage system. 
     
     
         9 . The tangible article of manufacture 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. 
     
     
         10 . The tangible article of manufacture of  claim 1 , further comprising archiving the text, redacting sensitive information from the archived redacted text in accordance with one or more second rules and archiving the further redacted text. 
     
     
         11 . The tangible article of manufacture of  claim 1 , further comprising archiving the redacted vocal stream, and redacting sensitive information from the archived redacted vocal stream in accordance with one or more second rules to obtain a further redacted vocal stream. 
     
     
         12 . A system for redacting sensitive information:
 a hardware buffer for storing an input vocal stream;   a speech-to-text converter for converting the input vocal stream to text;   a text analysis module for analyzing the text and identifying sensitive information in the vocal stream in accordance with one or more rules;   a redaction module for redacting the sensitive information from the vocal stream; and   a storage facility for storing the redacted vocal stream.   
     
     
         13 . The system of  claim 12 , wherein at least one of the text analysis module and the storage facility are located at least in part on at least one server. 
     
     
         14 . The system of  claim 12 , 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. 
     
     
         15 . A method to perform operations for removing sensitive information, comprising:
 receiving a copy of a communication;   automatically, under computer control, 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; and   automatically, under computer control, redacting the sensitive information from the communication.   
     
     
         16 . The method of  claim 15 , wherein the communication is at least one of a vocal stream, a telephonic communication, a text message, a chat transcript, an SMS, and an email. 
     
     
         17 . The method of  claim 15 , 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. 
     
     
         18 . The method of  claim 15 , wherein redacting comprises at least one of removing, muting and bleeping. 
     
     
         19 . The method 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. 
     
     
         20 . The method of  claim 15 , further comprising archiving the redacted communication and redacting sensitive information from the archived redacted communication in accordance with one or more second rules to obtain a further redacted communication.