System and methods for testing a video conference call using a virtual assistant
Embodiments are described for customizing a video conferencing user experience using a virtual assistant, and/or assisting a user in diagnosing issues concerning a video conferencing user experience. The virtual assistant may address issues based on automatically detected meeting quality measures as well as issues verbally communicated to the assistant by a user at an endpoint.
1. A method for customizing a teleconferencing user experience using a virtual agent instantiated at a server, the server comprising a processor, comprising:
receiving, by the processor, an upload audio stream and an upload video stream generated at an endpoint of a video conferencing system;
converting, by the processor, the upload audio stream to one or more text-user statements;
determining, by the processor, one or more meeting quality parameters based on a test video stream;
determining, by the processor, one or more user-intent names and a corresponding one or more user-context parameters based on the one or more text-user statements;
generating, by the processor, a responsive agent statement based on the one or more user-intent names or the one or more meeting quality parameters;
generating, by the processor, an action based on the one or more user-intent names or the one or more meeting quality parameters;
converting, by the processor, the responsive agent statement to an audio-agent-speech representation;
generating, by the processor, a download video stream comprising an animated agent representation based on the audio-agent-speech representation, and a chat transcript comprising the one or more text-user statements and the responsive agent statement;
providing, by the processor, a download audio stream comprising the audio-agent-speech representation and the download video stream; and
providing, by the processor, an instruction to a device to execute the action.
2. The method of claim 1 , wherein the test video stream is the upload video stream.
3. The method of claim 1 , wherein the responsive agent statement is generated based on the one or more meeting quality parameters having value that is outside of an acceptable range.
4. The method of claim 1 , wherein the responsive agent statement is generated based on the one or more user-intent name representing a response to a prompt-agent statement that is a request for information.
5. The method of claim 1 , wherein the responsive agent statement concerns a video quality issue, an audio quality issue, a network quality issue, or a meeting connection issue.
6. The method of claim 1 , wherein determining, by the processor, the one or more user-intent names and a corresponding one or more user-context parameters is further based upon a profile for the user.
7. The method of claim 1 , wherein the responsive agent statement is a notification that the action is or has been executed.
8. A video conferencing system, comprising:
one or more processors;
one or more storage devices communicatively coupled to the one or more processors; and
a set of instructions on the one or more storage devices that, when executed by the one or more processors, cause the processor to:
receive an upload audio stream and an upload video stream generated at an endpoint of the video conferencing system;
convert the upload audio stream to one or more text-user statements;
determine one or more meeting quality parameters based on a test video stream;
determine one or more user-intent names and a corresponding one or more user-context parameters based on the one or more text-user statements;
generate a responsive agent statement based on the one or more user-intent names or the one or more meeting quality parameters;
generate an action based on the one or more user-intent names or the one or more meeting quality parameters;
convert the responsive agent statement to an audio-agent-speech representation;
generate a download video stream comprising an animated agent representation based on the audio-agent-speech representation, and a chat transcript comprising the one or more text-user statements and the responsive agent statement;
provide a download audio stream comprising the audio-agent-speech representation and the download video stream; and
provide an instruction to a device to execute the action.
9. The system of claim 8 , wherein the test video stream is the upload video stream.
10. The system of claim 8 , wherein the responsive agent statement is generated based on the one or more meeting quality parameters having value that is outside of an acceptable range.
11. The system of claim 8 , wherein the responsive agent statement is generated based on the one or more user-intent name representing a response to a prompt-agent statement that is a request for information.
12. The system of claim 8 , wherein the responsive agent statement concerns a video quality issue, an audio quality issue, a network quality issue, or a meeting connection issue.
13. The system of claim 8 , wherein determining the one or more user-intent names and a corresponding one or more user-context parameters is further based upon a profile for the user.
14. The system of claim 8 , wherein the responsive agent statement is a notification that the action is or has been executed.
15. A non-transitory machine-readable storage medium comprising instructions that, when executed by a processor, cause the processor to:
receive an upload audio stream and an upload video stream generated at an endpoint of a video conferencing system;
convert the upload audio stream to one or more text-user statements;
determine one or more meeting quality parameters based on a test video stream;
determine one or more user-intent names and a corresponding one or more user-context parameters based on the one or more text-user statements;
generate a responsive agent statement based on the one or more user-intent names or the one or more meeting quality parameters;
generate an action based on the one or more user-intent names or the one or more meeting quality parameters;
convert the responsive agent statement to an audio-agent-speech representation;
generate a download video stream comprising an animated agent representation based on the audio-agent-speech representation, and a chat transcript comprising the one or more text-user statements and the responsive agent statement;
provide a download audio stream comprising the audio-agent-speech representation and the download video stream; and
provide an instruction to a device to execute the action.
16. The non-transitory machine-readable storage medium of claim 15 , wherein the test video stream is the upload video stream.
17. The non-transitory machine-readable storage medium of claim 15 , wherein the responsive agent statement is generated based on the one or more meeting quality parameters having value that is outside of an acceptable range.
18. The non-transitory machine-readable storage medium of claim 15 , wherein the responsive agent statement is generated based on the one or more user-intent name representing a response to a prompt-agent statement that is a request for information.
19. The non-transitory machine-readable storage medium of claim 15 , wherein the responsive agent statement concerns a video quality issue, an audio quality issue, a network quality issue, or a meeting connection issue.
20. The non-transitory machine-readable storage medium of claim 15 , wherein determining the one or more user-intent names and a corresponding one or more user-context parameters is further based upon a profile for the user.