Abstract: Various techniques described herein relate to analyzing and redacting information from customer interaction records such as call transcripts, to support transmission of the interaction records from a secured environment to various external analytics systems. Transcript texts may be received and processed by a redaction system, during which the transcript texts may be analyzed to generate conversations and convert numerical texts into numbers. One or more regular expressions defining search and replace patterns may be selected and used to redact confidential or sensitive information from the transcripts. In various implementations, the regular expressions used to redact transcripts may be determined or generated based on transcript categorization, the security characteristics of the transmission networks and/or external systems to which the redacted transcripts are to be transmitted, and/or other attributes of the transcript or the associated systems.

Abstract: A method for anonymizing data includes receiving call data of a call in an interaction recording system located behind a firewall of an internal network sub-environment, and within the internal network sub-environment: (i) storing the call data including interaction metadata, (ii) generating a speech-to-text transcript corresponding to words spoken by one or more callers, and (iii) generating an anonymized transcript by anonymizing personally identifiable information. A computing system includes a processor, and a memory including computer executable instructions that, when executed by the one processor, cause the system to perform the method. A non-transitory computer readable medium contains program instructions that when executed, cause a computer system to perform the method.

Abstract: A confidential sentiment analysis method includes receiving call data, storing the call data including interaction metadata, generating a speech-to-text transcript corresponding to words spoken by one or more callers, generating an anonymized transcript by anonymizing personally identifiable words, and generating a sentiment score by analyzing the anonymized transcript. A computing system includes a processor, and a memory including computer executable instructions that, when executed by the one processor, cause the system to receive call data, store the call data, generate a speech-to-text transcript, generate an anonymized transcript by anonymizing personally identifiable words, and generate a sentiment score based on the anonymized transcript.