Masking compliance measurement system
A system is adapted to automatically evaluate compliance to data masking rules by a service provider. The system includes a processor and a non-transitory computer readable medium carrying instructions. The instructions include receiving a list of private data elements for which masking is required, and receiving a transcript of a particular interaction between the service provider and a customer, where the transcript includes data elements, at least of which is a private data element. The instructions also include analyzing the transcript with natural language processing to identify times or locations within where private data elements are recorded; determining, based on a set of compliance rules and the analyzed transcript, whether any private data element are unmasked at the identified times or locations; and, if a private data element is unmasked, issuing an output related to the unmasked private data elements.
1 . A system adapted to automatically evaluate compliance to private data masking rules by a contact center service provider, the system comprising:
a processor and a non-transitory computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform operations which comprise:
receiving a list of private data elements for which masking is required;
receiving a customer-service provider interaction transcript of a particular interaction between the service provider and a customer, wherein the transcript comprises a plurality of data elements that includes at least one private data element of the list of private data elements;
analyzing the transcript with natural language processing to identify times or locations within the transcript where the at least one private data element is recorded;
determining based on a set of compliance rules and the analyzed transcript whether, at the identified times or locations, any private data element of the at least one private data element is unmasked;
based on a private data element of the at least one private data element being unmasked, incrementing a mask miss counter, wherein the mask miss counter tracks a total number of unmasked private data elements; and
based on the mask miss counter divided by a total number of expected masked data elements exceeding a threshold, issuing an output to a display of an agent, manager, or supervisor, wherein the output is related to the at least one unmasked private data element.
2 . The system of claim 1 , wherein the transcript includes a recording of at least one of a text interaction, a text translation of a voice interaction, or computer screen activity.
3 . The system of claim 1 , wherein the list of private data elements includes at least one of a social security number, a national identification number, a credit card number, a person's name, a company name, an organization name, a phone number, a postal code, a date of birth, an email address, a physical address, a postal address, an income level, a net asset value, a purchase history, or medical information.
4 . The system of claim 1 , wherein the output comprises a mask compliance coaching module, a link to the mask compliance coaching module, or instructions for accessing the mask compliance coaching module.
5 . The system of claim 1 , wherein the operations further comprise computing a compliance statistic for at least one of the particular interaction or a plurality of interactions including the particular interaction.
6 . The system of claim 5 , wherein the output comprises an evaluation of the service provider or a report comparing the service provider to another service provider.
7 . The system of claim 1 , wherein at least one private data element of the list of private data elements is required to be private by a law or government regulation.
8 . The system of claim 5 , wherein the compliance statistic comprises at least one of a total number of private data elements, a total number of masked private data elements, a total number of unmasked private data elements, a ratio, fraction, or percentage of private data elements that are masked, or a ratio, fraction, or percentage of private data elements that are unmasked, an average of any of the foregoing, or a ratio between any two of the foregoing.
9 . The system of claim 5 , wherein the compliance statistic comprises a compliance score for the service provider.
10 . The system of claim 9 , wherein based on the compliance score for the service provider being below a first threshold value, issuing a coaching output comprising at least one of a mask compliance coaching module, a link to the mask compliance coaching module, or instructions for accessing the mask compliance coaching module.
11 . The system of claim 9 , wherein based on the compliance score for the service provider being above a second threshold value, issuing a reward or recognition output.
12 . A computer-implemented method adapted to automatically evaluate compliance to private data masking rules by a contact center service provider, the method comprising:
receiving a list of private data elements for which masking is required;
receiving a customer-service provider interaction transcript of a particular interaction between the service provider and a customer, wherein the transcript comprises a plurality of data elements that includes at least one private data element of the list of private data elements;
with natural language processing, analyzing the transcript to identify times or locations within the transcript where the at least one private data element is recorded;
based on a set of compliance rules and the analyzed transcript, determining whether, at the identified times or locations, any private data element of the at least one private data element is unmasked; based on a private data element of the at least one private data element being unmasked, incrementing a mask miss counter, wherein the mask miss counter tracks a total number of unmasked private data elements; and
based on the mask miss counter divided by a total number of expected masked data elements exceeding a threshold, issuing an output to a display of an agent, manager, or supervisor, wherein the output is related to the at least one unmasked private data element.
13 . The computer-implemented method of claim 12 , wherein the transcript includes a recording of at least one of a text interaction, a text translation of a voice interaction, or computer screen activity.
14 . The computer-implemented method of claim 12 , wherein the list of private data elements includes at least one of a social security number, a national identification number, a credit card number, a person's name, a company name, an organization name, a phone number, a postal code, a date of birth, an email address, a physical address, a postal address, an income level, a net asset value, a purchase history, or medical information.
15 . The computer-implemented method of claim 12 , further comprising computing a compliance statistic for at least one of the particular interaction or a plurality of interactions including the particular interaction.
16 . The computer-implemented method of claim 15 , wherein the compliance statistic comprises at least one of a total number of private data elements, a total number of masked private data elements, a total number of unmasked private data elements, a ratio, fraction, or percentage of private data elements that are masked, or a ratio, fraction, or percentage of private data elements that are unmasked, an average of any of the foregoing, or a ratio between any two of the foregoing.
17 . The computer-implemented method of claim 15 , wherein based on the compliance statistic being below a first threshold value, the output comprises a coaching output comprising at least one of a mask compliance coaching module, a link to the mask compliance coaching module, or instructions for accessing the mask compliance coaching module.
18 . The computer-implemented method of claim 15 , wherein based on the compliance statistic being above a second threshold value, the output comprises a reward or recognition output.
19 . The computer-implemented method of claim 15 , wherein the output comprises an evaluation of the service provider including the compliance statistic or a report comparing the compliance statistic to a second compliance statistic of a second service provider.
20 . The computer-implemented method of claim 19 , wherein the rule-based machine learning algorithm is a learning classifier system, association rule learning system, or artificial immune system.