Patent attributes
Techniques are described that include detecting customer personal information within any appropriate set of data, such as customer communications produced by customer-facing services offered by an organization. Once detected, the customer personal information may be tokenized within the customer communications, making the data appropriate for external systems, such as cloud-hosted applications. The disclosed techniques include a masking service that may be plugged into an on-premises pipeline of any customer-facing service that makes requests to an off-premises, cloud-hosted application. The masking service may apply rule-based detection and/or machine learning-based detection to detect both structured and unstructured customer personal information included in customer communications. The masking service may further tokenize or otherwise obfuscate or replace the detected customer personal information. The tokenized customer communications may then be included in the requests to the cloud-hosted application or otherwise transmitted to external systems without exposing the customer personal information.
