Methods and systems for employing virtual support representatives in connection with mutli-pane video communications
Systems and methods are disclosed for establishing a video connection between a mobile device and a support terminal while enabling the support terminal to concurrently push display elements to the mobile device through a separate connection. In particular, in one or more embodiments, the disclosed systems and methods establish a first connection between the support terminal and the mobile device and conduct a video chat between the devices transmitted through the first connection. The disclosed systems and methods enable the support terminal to push a display element to the mobile device through a second connection. In response to receiving the display element, the disclosed systems and methods divide the display screen of the mobile device into at least a first pane and a second pane, providing the video chat for display on the first pane and the display element for display on the second pane.
1. A method comprising:
establishing a first connection between a mobile device and a support terminal;
providing a virtual support representative that automatically conducts a video chat with the mobile device via the first connection;
determining by the virtual support representative, automatically and without user intervention, a display element to provide to the mobile device;
providing the display element to the mobile device via a second connection during the video chat, wherein the display element causes the mobile device to display the video chat in a first pane and the display element in a second pane;
maintaining a tasks transcript of actions performed by the virtual support representative during the video chat;
determining to transfer the video chat from the virtual support representative to a support representative user based on applying a workflow, a framework, or an input constraint to user input received from the mobile device;
transferring, from the support terminal, the video chat from the virtual support representative to the support representative user via the first connection; and
providing the tasks transcript to the support representative user upon transferring the video chat from the virtual support representative to the support representative user.
2. The method of claim 1 , wherein determining the display element to provide to the mobile device is based on a machine learning model.
3. The method of claim 2 , further comprising training the machine learning model based on the tasks transcript.
4. The method of claim 1 , further comprising determining the support representative user from a plurality of support representative users based on one or more of availability, language, specialty requirements, user priority, or user rating.
5. The method of claim 1 , further comprising providing, to the mobile device, a trigger via the first connection, which causes the mobile device to execute code stored on the mobile device that activates a peripheral of the mobile device.
6. The method of claim 1 , wherein the second connection is a WebSocket server connection provided via the support terminal.
7. The method of claim 1 , further comprising receiving, in response to providing the display element, user input from the mobile device.
8. The method of claim 7 , wherein the user input from the mobile device comprises:
user input entered into a fillable field displayed in the second pane of the mobile device;
a signed document displayed in the second pane of the mobile device; or
an accepted or rejected set of terms displayed in the second pane of the mobile device.
9. The method of claim 1 , wherein the display element is a document, a slide, a video clip, an image, or a Tillable field.
10. A system comprising:
at least one processor; and
at least one non-transitory computer readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
establish a first connection between a mobile device and a support terminal;
provide a virtual support representative that automatically conducts a video chat with the mobile device via the first connection;
determine by the virtual support representative, automatically and without user intervention, a display element to provide to the mobile device;
provide the display element to the mobile device via a second connection during the video chat, wherein the display element causes the mobile device to display the video chat in a first pane and the display element in a second pane;
maintain a tasks transcript of actions performed by the virtual support representative during the video chat;
determine to transfer the video chat from the virtual support representative to a support representative user based on applying a workflow, a framework, or a document constraint to user input received from the mobile device;
transfer, from the support terminal, the video chat from the virtual support representative to the support representative user via the first connection; and
provide the tasks transcript to the support representative user upon the transfer of the video chat from the virtual support representative to the support representative user.
11. The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to provide, to the mobile device, a trigger via the second connection during the video chat, which causes the mobile device to execute code stored on the mobile device that activates a camera or microphone of the mobile device.
12. The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to provide a default display element to the mobile device upon establishing the video chat via the first connection.
13. The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to receive user input from the mobile device via a third secured connection.
14. A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause a computer system to:
establish a first connection between a mobile device and a support terminal;
provide a virtual support representative that automatically conducts a video chat with the mobile device via the first connection;
determine by the virtual support representative, automatically and without user intervention, a display element to provide to the mobile device;
provide the display element to the mobile device via a second connection during the video chat, wherein the display element causes the mobile device to display the video chat in a first pane and the display element in a second pane;
maintain a tasks transcript of actions performed by the virtual support representative during the video chat;
determine, to transfer the video chat from the virtual support representative to a support representative user based on applying a workflow or a framework to user input received from the mobile device;
transfer, from the support terminal, the video chat from the virtual support representative to the support representative user via the first connection; and
provide the tasks transcript to the support representative user upon the transfer of the video chat from the virtual support representative to the support representative user.
15. The non-transitory computer readable medium of claim 14 , wherein the display element is a document, a slide, a video clip, an image, or a fillable field.
16. The non-transitory computer readable medium of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the computer system to provide, to the mobile device, a trigger via the second connection during the video chat, which causes the mobile device to execute code stored on the mobile device that activates a camera or microphone of the mobile device.
17. The non-transitory computer readable medium of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the computer system to determine the display element to provide to the mobile device is based on a machine learning model.
18. The non-transitory computer readable medium of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the computer system to provide a default display element to the mobile device via the second connection upon establishing the video chat via the first connection.
19. The non-transitory computer readable medium of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the computer system to receive, in response to providing the display element, user input from the mobile device.
20. The non-transitory computer readable medium of claim 19 , wherein the user input from the mobile device comprises:
user input entered into a fillable field displayed in the second pane of the mobile device;
a signed document displayed in the second pane of the mobile device; or
an accepted or rejected set of terms displayed in the second pane of the mobile device.