System and method for performing screen capture-based sensitive information protection within a call center environment
Portions of a customer interaction recording that include sensitive information can be identified by performing character recognition on the images in the recording. Field identifiers identified through character recognition are compared to a list of known identifiers of fields for entry of sensitive information. Based on the comparison, field identifiers identified through character recognition can be recognized as sensitive information field identifiers. Images that include the sensitive information field identifiers can be blurred in the stored recording. Further, agent behavior in relation to the screens with fields for entry of sensitive information can be analyzed for purposes such as identifying potentially malicious agent behavior, an agent being in need of assistance, or a recurring customer issue.
1. A system for screen capture-based sensitive information protection within a call center environment, comprising:
at least one video sensor; and
at least one server interfaced to the at least one video sensor, the at least one server comprising at least one computer processor configured to execute code to:
record, via the video sensor, a plurality of application screens displayed on a workstation of an agent of a call center during an interaction between the agent and a customer to generate a recording comprising a plurality of images, wherein one or more of the application screens comprises one or more field identifiers of fields for entering data items associated with the customer and wherein one or more of the images comprises the one or more application screens;
perform character recognition on the one or more images;
identify, based on the character recognition, the field identifiers within the one or more images;
perform a spell-check on the field identifiers identified within the one or more images;
correct one or more misspellings in the field identifiers;
compare the field identifiers to a list of sensitive information field identifiers;
identify one or more of the field identifiers as the sensitive information field identifiers based on the comparison; and
blur in the recording at least those portions of the one or more images that comprise the data items entered into the fields associated with the sensitive information field identifiers.
2. The system according to claim 1 , wherein the processor is further configured to execute code to:
measure a time that one of the application screens comprising the sensitive information field identifiers remains open on the workstation;
compare the time to a predefined threshold; and
take an action based on the comparison of the time to the predefined threshold.
3. The system according to claim 2 , wherein the action is taken when the time associated with the agent exceeds the threshold by a predefined amount.
4. The system according to claim 2 , wherein the processor is further configured to execute code to:
monitor speech of the agent;
perform speech recognition on the speech; and
identify a portion of the recognized speech that provides a legitimate reason for the time associated with the agent exceeding the threshold.
5. The system according to claim 4 , wherein the processor is further configured to execute code to:
store the portion of the recognized speech in a log for the interaction.
6. The system according to claim 1 , wherein the processor is further configured to execute code to:
receive from the agent a summary of the interaction;
identify a sequence of the application screens visited during the interaction;
identify summaries received from one or more other agents associated with the identified application screens;
compare the summary from the agent to one or more of the summaries received from the other agents; and
take an action based on the comparison of the summary from the agent to the one or more summaries received from the other agents.
7. The system according to claim 1 , wherein the processor is further configured to execute code to:
identify a sequence of the application screens visited by the agent during the interaction;
compare the sequence to a predefined script for the interaction;
identify a deviation from the predefined script based on the comparison of the sequence to the predefined script; and
take an action upon detecting the deviation.
8. The system according to claim 1 , wherein an entirety of the one or more images comprising the sensitive information field identifiers is blurred.
9. The system according to claim 1 , further comprising:
a database configured to store the recording with the blurred images.
10. A method for screen capture-based sensitive information protection within a call center environment, comprising:
recording, via a video sensor, a plurality of application screens displayed on a workstation of an agent of a call center during an interaction between the agent and a customer to generate a recording comprising a plurality of images, wherein one or more of the application screens comprises one or more field identifiers of fields for entering data items associated with the customer and wherein one or more of the images comprises the one or more application screens;
performing character recognition on the one or more images;
identifying, based on the character recognition, the field identifiers within the one or more images;
performing a spell-check on the field identifiers identified within the one or more images;
correcting one or more misspellings in the field identifiers;
comparing the field identifiers to a list of sensitive information field identifiers;
identifying one or more of the field identifiers as the sensitive information field identifiers based on the comparison; and
blurring in the recording at least those portions of the one or more images that comprise the data items entered into the fields associated with the sensitive information field identifiers.
11. The method according to claim 10 , further comprising:
measuring a time that one of the application screens comprising the sensitive information field identifiers remains open on the workstation;
comparing the time to a predefined threshold; and
taking an action based on the comparison of the time to the predefined threshold.
12. The method according to claim 10 , wherein the action is taken when the time associated with the agent exceeds the threshold by a predefined amount.
13. The method according to claim 10 , further comprising:
monitoring speech of the agent;
performing speech recognition on the speech; and
identifying a portion of the recognized speech that provides a legitimate reason for the time associated with the agent exceeding the threshold.
14. The method according to claim 13 , further comprising:
storing the portion of the recognized speech in a log for the interaction.
15. The method according to claim 10 , further comprising:
receiving from the agent a summary of the interaction;
identifying a sequence of the application screens visited during the interaction;
identifying summaries received from one or more other agents associated with the identified application screens;
comparing the summary from the agent to one or more of the summaries received from the other agents; and
taking an action based on the comparison.
16. The method according to claim 10 , further comprising:
identifying a sequence of the application screens visited by the agent during the interaction;
comparing the sequence to a predefined script for the interaction;
identifying a deviation from the predefined script based on the comparison of the sequence to the predefined script; and
taking an action upon detecting the deviation.
17. The method according to claim 10 , wherein an entirety of the one or more images comprising the sensitive information field identifiers is blurred.
18. The method according to claim 10 , further comprising:
storing the recording with the blurred images in a database.
19. The system according to claim 1 , wherein the processor is further configured to execute code to:
detect a presence of text in the one or more images, wherein character recognition is performed only on those images in which the presence of text is detected.
20. The method according to claim 10 , further comprising:
detecting a presence of text in the one or more images, wherein character recognition is performed only on those images in which the presence of text is detected.