US-12619756-B2 - Systems and methods for linking a screen capture to a user support session

US12619756B2US 12619756 B2US12619756 B2US 12619756B2US-12619756-B2

Abstract

Systems and methods for linking a screen capture to a user support session are disclosed. The system may receive a screen capture initiation request from a user device. The system may capture a first data object indicative of a first graphical user interface associated with the user device. The system may provide, to the user device, the first graphical user interface for a predetermined period of time. The system may track, by the one or more processors, one or more inputs from the user device that indicate the presence of one or more articles of sensitive information within the graphical user interface. The system may mask the one or more articles of sensitive information within the graphical user interface, generate a second data object indicative of the graphical user interface having the masked articles of sensitive information, and store the second data object in a data repository.

Inventors

THOMAS H. SCOTT
Jude Pierre ANASTA
Fayaz Khan
Patrick Blinkhorn
Mary Sweeney
Tejen Shrestha
Joseph Amburgey

Assignees

CAPITAL ONE SERVICES, LLC

Dates

Publication Date: 20260505
Application Date: 20240802

Claims (20)

1 . A system comprising: one or more processors; and a non-transitory memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to: receive metadata from a user device, the metadata associated with a screen capture initiation request; receive a first data object indicative of a first graphical user interface associated with the user device; provide, to the user device, the first graphical user interface comprising a request to identify one or more first articles of sensitive information within the first graphical user interface; track one or more inputs received from the user device indicating a position of the one or more first articles of sensitive information within the first graphical user interface; mask the one or more first articles of sensitive information within the first graphical user interface; identify one or more second data entries within the first data object indicative of one or more second articles of sensitive information displayed by the first graphical user interface; mask the one or second articles of sensitive information within the first graphical user interface by modifying the one or more second data entries; and generate a second data object indicative of a second graphical user interface, the second graphical user interface comprising the masked one or more first articles of sensitive information and the masked one or more second articles of sensitive information.
2 . The system of claim 1 , wherein the instructions, when executed by the one or more processors, are configured to cause the system to: receive, from an agent terminal, a request for the second data object; and provide the second data object to the agent terminal, thereby facilitating display of the second graphical user interface on the agent terminal.
3 . The system of claim 2 , wherein the metadata comprises a user identifier, a user session identifier, and a timestamp associated with the screen capture initiation request.
4 . The system of claim 1 , wherein the instructions, when executed by the one or more processors, are configured to cause the system to: store the second data object in a data repository.
5 . The system of claim 4 , wherein identifying the one or more second articles of sensitive information displayed by the first graphical user interface further comprises implementing a trained machine learning model to identify the one or more second articles of sensitive information.
6 . The system of claim 5 , wherein the trained machine learning model is configured to identify articles of sensitive information based on or more heuristics comprising identifying data entry fields associated with one or more articles of sensitive information, identifying one or more phrases proximate to the identified data entry fields indicative of one or more articles of sensitive information, a format of one or more data entry fields indicative of one or more articles of sensitive information, and combinations thereof.
7 . The system of claim 6 , wherein the tracked one or more inputs further comprise: an indication of one or more second articles of sensitive information identified by the trained machine learning model that should be unmasked prior to the second data object being stored in the data repository or a data entry field associated with a user support session, and wherein an indication of the one or more first articles of sensitive information received from the user device are used to update the trained machine learning model to automatically identify the one or more first articles of sensitive information.
8 . The system of claim 1 , wherein the one or more first articles of sensitive information comprise sensitive information selected from a password, a social security number, an account number, a credit card number, and combinations thereof.
9 . The system of claim 1 , wherein the screen capture initiation request is received by an API in response to a chatbot user support session initiated by a user of the user device.
10 . A system comprising: one or more processors; and a non-transitory memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to: receive metadata from a user device, the metadata associated with a screen capture initiation request; receive a first data object indicative of a first graphical user interface associated with the user device; identify one or more first data entries within the first data object indicative of one or more first articles of sensitive information displayed by the first graphical user interface; mask the one or more first articles of sensitive information within the first graphical user interface by modifying the one or more first data entries; provide, to the user device, a modified graphical user interface comprising the masked one or more first articles of sensitive information and a request to identify one or more second articles of sensitive information within the modified graphical user interface; track one or more inputs indicating a position of the one or more second articles of sensitive information within the modified graphical user interface; mask the one or more second articles of sensitive information within the modified graphical user interface; and generate a second data object indicative of a second graphical user interface, the second graphical user interface comprising the masked one or more first articles of sensitive information and masked one or more second articles of sensitive information.
11 . The system of claim 10 , wherein identifying the one or more first articles of sensitive information displayed by the first graphical user interface further comprises implementing a trained machine learning model to identify the one or more first articles of sensitive information.
12 . The system of claim 11 , wherein the trained machine learning model is configured to identify articles of sensitive information based on or more heuristics comprising identifying data entry fields associated with one or more articles of sensitive information, identifying one or more phrases proximate to the identified data entry fields indicative of one or more articles of sensitive information, a format of one or more data entry fields indicative of one or more articles of sensitive information, and combinations thereof.
13 . The system of claim 12 , wherein the tracked one or more inputs are received from the user device and are used to update the trained machine learning model to automatically identify the one or more second articles of sensitive information.
14 . The system of claim 10 , wherein the one or more first articles of sensitive information and the one or more second articles of sensitive information comprise sensitive information selected from a password, a social security number, an account number, a credit card number, and combinations thereof.
15 . The system of claim 10 , wherein: the one or more inputs received from the user device further indicate a data entry field associated with a support request, and the instructions, when executed by the one or more processors, are configured to cause the system to: provide the second data object and a user identifier to an agent terminal; and transfer a chatbot support session to the agent terminal.
16 . A computer-implemented method comprising: receiving metadata from a user device, the metadata associated with a screen capture initiation request; receiving a first data object indicative of a first graphical user interface associated with the user device; identifying one or more first data entries within the first data object indicative of one or more first articles of sensitive information displayed by the first graphical user interface; masking the one or more first articles of sensitive information within the first graphical user interface by modifying the one or more first data entries; generating a modified graphical user interface comprising the masked one or more first articles of sensitive information and a request to identify one or more second articles of sensitive information within the modified graphical user interface; tracking one or more inputs indicating a position of the one or more second articles of sensitive information within the modified graphical user interface; masking the one or more second articles of sensitive information within the modified graphical user interface; and generating a second data object indicative of a second graphical user interface, the second graphical user interface comprising the masked one or more first articles of sensitive information and masked one or more second articles of sensitive information.
17 . The method of claim 16 , wherein identifying the one or more first articles of sensitive information displayed by the first graphical user interface further comprises implementing a trained machine learning model to identify the one or more first articles of sensitive information.
18 . The method of claim 17 , wherein the trained machine learning model is configured to identify articles of sensitive information based on or more heuristics comprising identifying data entry fields associated with one or more articles of sensitive information, identifying one or more phrases proximate to the identified data entry fields indicative of one or more articles of sensitive information, a format of one or more data entry fields indicative of one or more articles of sensitive information, and combinations thereof.
19 . The method of claim 18 , wherein the tracked one or more inputs are received from the user device and are used to update the trained machine learning model to automatically identify the one or more second articles of sensitive information.
20 . The method of claim 16 , wherein the one or more inputs received from the user device further indicate a data entry field associated with a support request.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of, and claims priority under 35 U.S.C. § 120 to, U.S. patent application Ser. No. 17/583,115, filed Jan. 24, 2022, the entire contents of which are fully incorporated herein by reference. FIELD The disclosed technology relates to systems and methods for screen capture, and more particularly systems and methods for identifying sensitive articles of information within a screen capture of a graphical user interface and masking the sensitive articles of information before storing the screen capture on a data repository. BACKGROUND Businesses often rely on automated systems to troubleshoot issues customers have with their products or services. For example, artificial intelligence (AI) chatbots are utilized to provide a convenient method of receiving immediate support for technical customer issues. However, often the customer needs to provide additional contextual information to the chatbot in order for the issue to be resolved. For example, a customer may wish to upload one or more screenshots associated with the issue the customer is facing with the business's product or service. In addition, some customer problems cannot be resolved by an AI chatbot and must be transferred to a human customer service representative. Indeed, current customer service solutions do not provide a seamless method of providing the additional contextual information (e.g., screenshot) to the human customer service representative when the AI chatbot is unable to resolve the customer's issue. Importantly, screenshots provided by the customer often includes sensitive information, which poses a security risk to both the customer and the business potentially collecting and storing the customer's sensitive information. Accordingly, there is a need for more robust AI chatbot integration systems capable of providing the customer a seamless method of capturing a screenshot, masking articles of sensitive information within the screenshot, and providing the masked screenshot to the AI chatbot system, a human customer service representative, or both. Embodiments of the present disclosure are directed to this and other considerations. SUMMARY Disclosed herein are systems and methods for linking a screen capture to a user support session. The system may include one or more processors and memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, cause the system to perform one or more steps of a method. The system may receive, by an API implemented by the one or more processors, a screen capture initiation request from a user device. The system may capture, by the API, a first data object indicative of a first graphical user interface associated with the user device. The system may provide, to the user device, the first graphical user interface for a predetermined period of time. The first graphical user interface may include a request for a user of the user device to identify one or more articles of sensitive information within the first graphical user interface. The system may track, by the one or more processors via the API, one or more inputs received from the user device that indicate a position of the one or more first articles of sensitive information within the first graphical user interface over the predetermined period of time. The system may mask, by the API, the one or more articles of sensitive information within the first graphical user interface. The system may automatically generate a second data object indicative of a second graphical user interface that includes the masked one or more first articles of sensitive information. The system may store, by the API, the second data object in a data repository. Consistent with the disclosed embodiments, a system for linking a screen capture to a user support session is disclosed. The system may include one or more processors and memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, cause the system to perform one or more steps of a method. The system may receive, from a user device, a support request comprising a user identifier. The system may initiate a chatbot support session with the user device. The system may transmit, by an API implemented by the one or more processors, a screen capture initiation request to the user device. The system may receive, by the API, an approval of the screen capture initiation request. The system may capture, by the API, a first data object indicative of a first graphical user interface associated with the user device. The system may identify, by the API, one or more first data entries within the first data object indicative of one or more first articles of sensitive information displayed by the first graphical user interface. The system may mask, by the API, the one or more first articles of sensitive information within the first gr