| CPC H04L 63/0407 (2013.01) [H04L 9/3213 (2013.01)] | 18 Claims |

|
1. A method comprising:
detecting, by a computing system, customer personal information in text data received from a customer-facing service using multiple detection layers to detect different types of customer personal information having different structures;
generating, by the computing system, tokenized data based on output of the multiple detection layers, wherein generating the tokenized data comprises replacing each instance of the customer personal information detected in the text data with a respective token;
generating, by the computing system, signaling information that defines the tokenization of the customer personal information, wherein the signaling information identifies, for each token in the tokenized data, one or more of a location of the token, a type of the token, or an algorithm applied to generate the token for a respective instance of the customer personal information;
sending, by the computing system, a request including the tokenized data to an application;
receiving, by the computing system, a response to the request from the application, wherein the response includes one or more tokens from the tokenized data;
recovering, by the computing system, at least a portion of the customer personal information from the one or more tokens included in the response based on the signaling information; and
based on the response from the application and the recovered portion of the customer personal information, sending, by the computing system, a response to the customer-facing service.
|