Predicting likelihood of and preventing end users inappropriately inputting sensitive data
Disclosed aspects pertain to predicting a likelihood that a user enters sensitive data inappropriately and mitigating such a risk. An electronic form is monitored for user interaction. Non-biometric behavior data can be received or otherwise acquired for the user. A machine learning model can be invoked to determine a likelihood that the user will input sensitive data inappropriately into a form field based on the similarity of user non-biometric behavior data with historic non-biometric behavior data. User assistance, such as a message or warning, can be initiated when the likelihood satisfies a predetermined threshold to mitigate the risk of input of sensitive data inappropriately. The field can also be monitored to detect the presence of inappropriate sensitive data. The user can be prompted to redact or remove the sensitive data if detected.
1 . A system, comprising:
a processor coupled to a memory that includes instructions associated with user assistance that are executable by the processor to cause the processor to:
detect interaction with an electronic form by a user;
determine non-biometric behavioral data of the user, wherein the non-biometric behavioral data of the user includes digital interaction data representing how the user interacts with a customer agent;
invoke a machine learning model based on the non-biometric behavioral data of the user including the digital interaction data representing how the user interacts with the customer agent, wherein the machine learning model has been trained to (i) predict a likelihood that the user will enter sensitive data in an electronic form field inappropriately, such that the sensitive data will be unmasked, by comparing similarities of the non-biometric behavioral data of the user to non-biometric behavioral data of other users, including past interactions of the other users with the electronic form, and (ii) output the sensitive data after determining that the user incorrectly entered the sensitive data in the electronic form field; and
initiate user assistance by receiving questions from the user via an interactive display and responding to the user with information that mitigates risk of inappropriate entry of sensitive data in the electronic form field when the likelihood satisfies a predetermined threshold.
2 . The system of claim 1 , wherein the user assistance corresponds to a message that provides information regarding sensitive data input.
3 . The system of claim 1 , wherein the user assistance corresponds to a chatbot that informs the user how to enter sensitive data correctly.
4 . The system of claim 1 , wherein the instructions further cause the processor to:
detect an electronic form field with inappropriate sensitive data; and
request the user remove the sensitive data from the electronic form field.
5 . The system of claim 4 , wherein the instructions further cause the processor to prevent further input into another electronic form field until the sensitive data is removed.
6 . The system of claim 5 , wherein the instructions further cause the processor to prevent the user from moving to a next screen until the sensitive data is removed.
7 . The system of claim 1 , wherein the instructions further cause the processor to perform natural language processing to identify sensitive data entered incorrectly.
8 . The system of claim 5 , wherein the instructions further cause the processor to activate a light or audible indicator when the sensitive data is entered incorrectly.
9 . The system of claim 1 , wherein the non-biometric behavioral data further includes at least one of customer data or customer service agent data, wherein the digital interaction data representing how the user interacts with the customer agent includes:
data associated with the interaction between the user and the customer agent;
data representing how often the user interacts with a website or application associated with the customer agent; and
data representing an internet protocol (IP) address of the user; and
wherein determining that the user incorrectly entered the sensitive data in the electronic form field includes determining that the user accidentally and incorrectly entered the sensitive data in the electronic form field.
10 . The system of claim 1 , wherein the digital interaction data comprises digital engagement analytics including at least one of time of engagement, frequency of engagement, or frequency of data violations.
11 . A method, comprising:
executing on a processor, instructions that cause the processor to perform operations, the operations comprising:
detecting interaction with an electronic form by a user;
determining non-biometric behavioral data of the user comprising profile data and digital interaction data representing how the user interacts with a customer agent;
invoking a machine learning model based on the non-biometric behavioral data of the user comprising the profile data and the digital interaction data representing how the user interacts with the customer agent, wherein the machine learning model has been trained to (i) predict a likelihood that the user will enter sensitive data in an electronic form field inappropriately, such that the sensitive data will be unmasked, by comparing similarities of the non-biometric behavioral data of the user to non-biometric behavioral data of other users, including past interactions of the other users with the electronic form, and (ii) output the sensitive data after determining that the user incorrectly entered the sensitive data in the electronic form field; and
triggering user assistance by receiving questions from the user via an interactive display and responding to the user with information that mitigates risk of inappropriate entry of sensitive data in the electronic form field when the likelihood satisfies a predetermined threshold.
12 . The method of claim 11 , wherein the operations further comprise triggering display of a tooltip associated with the electronic form field as the user assistance to indicate a likelihood that the sensitive data will be inappropriately included in the field.
13 . The method of claim 11 , wherein the operations further comprise invoking a chatbot to inform the user on how to enter sensitive data correctly.
14 . The method of claim 11 , wherein the operations further comprise displaying a message that provides information regarding sensitive data input as the user assistance.
15 . The method of claim 11 , further comprising determining customer service agent data as part of the non-biometric behavioral data, wherein the digital interaction data representing how the user interacts with the customer agent includes:
data associated with the interaction between the user and the customer agent;
data representing how often the user interacts with a website or application associated with the customer agent; and
data representing an internet protocol (IP) address of the user; and
wherein determining that the user incorrectly entered the sensitive data in the electronic form field includes determining that the user accidentally and incorrectly entered the sensitive data in the electronic form field.
16 . The method of claim 11 , wherein the operations further comprise:
detecting an electronic form field with inappropriate sensitive data; and
requesting the user remove the sensitive data from the electronic form field.
17 . The method of claim 16 , wherein the operations further comprise preventing the user from advancing to a next screen until the sensitive data is removed.
18 . A computer-implemented method, comprising:
detecting interaction with an electronic form by a user;
receiving non-biometric behavioral data of the user comprising user profile data and digital engagement data representing how the user interacts with a customer agent;
executing a machine learning model based on the non-biometric behavioral data of the user comprising the user profile data and the digital engagement data representing how the user interacts with the customer agent as input, wherein the machine learning model has been trained to (i) predict a likelihood that the user will enter sensitive data in an electronic form field inappropriately, such that the sensitive data will be unmasked, by comparing similarities of the non-biometric behavioral data of the user to non-biometric behavioral data of other users, including pasted interactions of the other users with the electronic form, and (ii) output the sensitive data after determining that the user incorrectly entered the sensitive data in the electronic form field; and
initiating user assistance by receiving questions from the user via an interactive display and responding to the user with information that mitigates risk of inappropriate entry of sensitive data in the electronic form field when the likelihood satisfies a predetermined threshold.
19 . The method of claim 18 , further comprising triggering display of a tooltip associated with the electronic form field as the user assistance to indicate a likelihood that the sensitive data will be inappropriately included in the field.
20 . The method of claim 19 , further comprising:
detecting sensitive data in the electronic form field;
requesting the user redact the sensitive data; and
preventing input in other electronic form fields until the sensitive data is redacted.