Embedding content of interest in video conferencing
View Patent ↗A video- and/or audio-enabled communication system includes a processor, coupled with a camera, the camera acquiring an image of an object of interest during a video communication session involving multiple participants and a computer readable medium comprising instructions that cause the processor to perform automatically an action in response to and related to a sensed context during the video communication session. The action can be one or more of retrieve or provide content of interest to one or more of the participants, join a third party to the video communication session, recommend that a further action be performed by the processor, and schedule an activity involving one or more of the participants.
1. A communication system, comprising:
a control unit, coupled with a camera, the camera acquiring an image of an object of interest during a video communication session involving multiple participants, wherein the control unit comprises:
a processor; and
a computer readable medium comprising a virtual assistant that causes the processor to perform automatically an action in response to and related to a sensed context during the video communication session.
2. The system of claim 1 , wherein the action is to join a third party to the video communication session.
3. The system of claim 1 , wherein the action is to recommend that a further action be performed by the virtual assistants based on a review of a previous action by at least one of the multiple participants, and wherein the review occurs after the sensed context and based on the sensed context.
4. The system of claim 1 , wherein the action is to access content of at least one of a personal calendar and a personal email of at least one of the multiple participants.
5. The system of claim 1 , wherein the virtual assistant determines which image or layout or layout configuration is displayed to each of local or remote participants during the video communication session based on a determination of at least one of the multiple participants being local or remote.
6. The system of claim 1 , wherein the action occurs after the sensed context and the action is based on the sensed context.
7. The system of claim 1 , wherein the action is to access personal content of at least one of the multiple participants.
8. A method for performing a video communication session, comprising:
acquiring, by a camera, an image of an object of interest during a video communication session involving multiple participants; and
performing automatically, by a processor of a control unit, an action in response to and related to a sensed context during the video communication session, wherein the control unit comprises a computer readable medium comprising a virtual assistant, wherein the action is one or more of retrieving or providing content of interest to one or more of the multiple participants, joining a third party to the video communication session, recommending that a further action be performed by the virtual assistant, and scheduling an activity involving one or more of the multiple participants.
9. The method of claim 8 , wherein the virtual assistant maintains historical records of each of the multiple participants including prior communication sessions involving any of the multiple participants, wherein the historical records include a first topic discussed previously during prior communication sessions, and wherein the virtual assistant provides a service to the one or more of the multiple participants based on the first topic discussed during the prior communication sessions.
10. The method of claim 8 , wherein the sensed context is based on a retrieved content retrieved by the virtual assistant from a calendar event or an email related to the video communication session and further comprising, in the computer readable medium, a content monitor that monitors communications by any of the multiple participants with the virtual assistant during the video communication session based on the retrieved content, and wherein the monitored communications comprise audio and text communications.
11. The method of claim 8 , wherein the virtual assistant appears in a designated portion of a display provided during the video communication session, wherein the processor determines input by at least one of the multiple participants by analyzing at least one gesture of the at least one of the multiple participants, and wherein the virtual assistant presents content of interest during the video communication session to one or more of the multiple participants based on the input.
12. The method of claim 8 , further comprising:
selecting, by an image controller, an initial layout of the video communication session to be displayed to the multiple participants, wherein the initial layout cannot be overridden by any of the multiple participants, and
overriding the initial layout selected by the image controller with an updated layout configuration that is displayed to the multiple participants, wherein the updated layout configuration is determined by the virtual assistant.
13. The method of claim 8 , wherein the action is one or more of retrieve or provide content of interest to one or more of the multiple participants, wherein the content is advertising content received from a content source, and further comprising:
determining a value to the content source for the presentation of the advertising content to the multiple participants during the video communication session, wherein the value is derived from presenting the advertising content to the participants during the video communication session, and wherein the value has a limit on the value attainable that is related to the multiple participants.
14. The method of claim 8 , wherein the sensed context is a visual context within the image of the object of interest.
15. A communication system, comprising:
a control unit, comprising:
a computer readable medium comprising a virtual assistant; and
a processor, wherein the processor is coupled with a camera,
wherein the camera acquires an image of an object of interest during a video communication session involving multiple participants; and
the computer readable medium comprises instructions executing the virtual assistant that cause the processor to perform automatically an action in response to and related to a sensed context during the video communication session, wherein the action is one or more of retrieve or provide content of interest to one or more of the multiple participants, join a third party to the video communication session, recommend that a further action be performed by the processor, and schedule an activity involving one or more of the multiple participants.
16. The system of claim 15 , wherein the sensed context comprises one or more of facial images acquired by the camera of one or more of the multiple participants using face detection techniques, and wherein the action performed automatically in response to and related to the sensed context is one or more of join a third party to the video communication session, recommend that a further action be performed by the virtual assistant, and schedule the activity involving the one or more of the multiple participants.
17. The system of claim 15 , further comprising, in the computer readable medium, a content monitor that monitors video and textual communications between at least some of the multiple participants and by a participant with the processor during the video communication session to determine a use of a predetermined textual word or phrase from a textual communication that occurs during the video communication session.
18. The system of claim 15 , wherein the processor comprises a synthetically generated voice played through one or more speakers to one or more of the multiple participants, wherein each of the one or more of the multiple participants can communicate privately or publicly with the processor during the communication session, and wherein the processor presents content of interest during the video communication session to the one or more of the multiple participants.
19. The system of claim 15 , wherein the object of interest is at least one of the multiple participants, wherein the content of interest is provided to the at least one of the multiple participants, and wherein the processor controls a layout configuration that is displayed to the at least one of the multiple participants during the video communication session based on a contextual analysis of the communication session that includes the content of interest and the image that is the at least one of the multiple participants.
20. The system of claim 15 , wherein the image acquired by the camera comprises facial images of at least one of the multiple participants, wherein the system determines an identity of the at least one of the multiple participants based on identified biometric information and the facial images, wherein the action is one or more of retrieve or provide content of interest to one or more of the multiple participants, wherein the content is advertising content received from a content source, and wherein the processor maintains historical records of behavior of each of the one or more multiple participants using the biometric information.