User-described video streams
A user-described virtual environment method, system, and apparatus obtains a representation of an object and receives a natural language-based communication from a user requesting that a computer-implemented system embody the object within a virtual environment that is described by the user. The natural language description of the virtual environment is interpreted by applying a computer-implemented trained neural network A video stream that embodies the object within a computer-generated virtual environment that is in accordance with the user-described virtual environment is generated by applying a trained neural network and then delivered to the user. The user may then describe desired modifications to the virtual environment and a second video stream is generated in accordance with the desired modifications.
1. A computer-implemented method, comprising:
obtaining a representation of a first object;
receiving a natural language-based communication from a user requesting that a computer-implemented system embody the first object within a first virtual environment based on a description provided by the user, wherein the description of the first virtual environment is in a form of natural language that comprises a plurality of syntactical elements;
interpreting automatically the description of the first virtual environment by applying a first computer-implemented trained neural network;
generating automatically by the computer-implemented system, responsive to the communication from the user, a first video stream comprising the first object embodied within a computer-generated virtual environment that is in accordance with the first virtual environment, wherein the first video stream is generated by, at least in part, applying a second computer-implemented trained neural network; and
delivering the first video stream to the user.
2. The computer-implemented method of claim 1 , further comprising obtaining the representation of the first object by interpreting using a trained neural network a plurality of pixels that are within one or more images.
3. The computer-implemented method of claim 1 , further comprising obtaining the representation of the first object by interpreting using a trained neural network a natural language-based description of the first object that is communicated by the user.
4. The computer-implemented method of claim 1 , further comprising the description of the first virtual environment, wherein the description comprises a desired sentiment.
5. The computer-implemented method of claim 1 , further comprising generating the first video stream comprising the first object embodied within the computer-generated virtual environment, wherein the generating of the first video stream is in accordance with a preference of the user that is inferred from a plurality of user behaviors.
6. The computer-implemented method of claim 1 , further comprising delivering the first video stream to the user and receiving from the user a request for information about the representation of a second object within the first video stream and delivering to the user in natural language form attributes that are associated with the second object.
7. The computer-implemented method of claim 1 , further comprising:
delivering the first video stream to the user and receiving from the user a request that is in natural language form to modify the first video stream in accordance with a second virtual environment description that is provided by the user; and
generating a second video stream that is in accordance with the second virtual environment description.
8. A computer-implemented system comprising one or more processor-based devices configured to:
obtain a representation of a first object;
receive a natural language-based communication from a user requesting that the computer-implemented system embody the first object within a first virtual environment based on a description provided by the user, wherein the description of the first virtual environment is in a form of natural language that comprises a plurality of syntactical elements;
interpret automatically the description of the first virtual environment by applying a first computer-implemented trained neural network;
generate automatically by the computer-implemented system, responsive to the communication from the user, a first video stream comprising the first object embodied within a computer-generated virtual environment that is in accordance with the first virtual environment, wherein the first video stream is generated by, at least in part, applying a second computer-implemented trained neural network; and
deliver the first video stream to the user.
9. The computer-implemented system of claim 8 , further comprising obtaining the representation of the first object by interpreting using a trained neural network a plurality of pixels that are within one or more images.
10. The computer-implemented system of claim 8 , further comprising obtaining the representation of the first object by interpreting using a trained neural network a natural language-based description of the first object that is communicated by the user.
11. The computer-implemented system of claim 8 , further comprising the description of the first virtual environment, wherein the description comprises a desired level of humor.
12. The computer-implemented system of claim 8 , further comprising generating the first video stream comprising the first object embodied within the computer-generated virtual environment, wherein the generating of the first video stream is in accordance with a preference of the user that is inferred from a plurality of user behaviors.
13. The computer-implemented system of claim 8 , further comprising delivering the first video stream to the user and receiving from the user a request for information about the representation of a second object within the first video stream and delivering to the user in natural language form attributes that are associated with the second object.
14. The computer-implemented system of claim 8 , further comprising:
delivering the first video stream to the user and receiving from the user a request that is in natural language form to modify the first video stream in accordance with a second virtual environment description that is provided by the user; and
generating a second video stream that is in accordance with the second virtual environment description.
15. An apparatus comprising:
one or more cameras;
a microphone; and
one or more processors configured to:
obtain a representation of a first object by interpreting information that is from the one or more cameras;
receive a natural language-based communication from the microphone requesting that the first object be embodied within a first virtual environment based on a description provided by a user of the apparatus, wherein the description of the first virtual environment is in a form of natural language that comprises a plurality of syntactical elements;
interpret automatically the description of the first virtual environment by applying a first computer-implemented trained neural network;
generate automatically by the one or more processors, responsive to the natural language-based communication from the user, a first video stream comprising the first object embodied within a computer-generated virtual environment that is in accordance with the first virtual environment, wherein the first video stream is generated by, at least in part, applying a second computer-implemented trained neural network; and
deliver the first video stream to the user.
16. The apparatus of claim 15 , further comprising the one or more processors configured to obtain the representation of the first object by interpreting using a trained neural network a plurality of pixels that is included in the information from the one or more cameras.
17. The apparatus of claim 16 , further comprising the one or more processors configured to obtain the representation of the first object by using the trained neural network, wherein the trained neural network is a convolutional neural network.
18. The apparatus of claim 15 , further comprising the one or more processors configured to generate the first video stream, wherein the first video stream is generated in accordance with a preference of the user that is inferred from a plurality of user behaviors.
19. The apparatus of claim 15 , further comprising the one or more processors configured to deliver the first video stream to the user and receive from the user a request for information about the representation of a second object within the first video stream and delivering to the user a plurality of attributes that are associated with the second object.
20. The apparatus of claim 15 , further comprising the one or more processors configured to:
deliver the first video stream to the user and receive from the microphone a request to modify the first video stream in accordance with a second virtual environment description that is provided by the user using the microphone; and
generate a second video stream that is in accordance with the second virtual environment description.