Systems and methods to enhance interactive engagement with shared content by a contextual virtual agent
Systems and methods are described to enhance interactive engagement during simultaneous delivery of serial or digital content (e.g., audio, video) to a plurality of users. A machine-based awareness of the context of the content and/or one or more user reactions to the presentation of the content may be used as a basis to interrupt content delivery in order to intersperse a snippet that includes a virtual agent with an awareness of the context(s) of the content and/or the one or more user reactions. This “contextual virtual agent” (CVA) enacts actions and/or dialog based on the one or more machine-classified contexts coupled with identified interests and/or aspirations of individuals within the group of users. The CVA may also base its activities on a machine-based awareness of “future” content that has not yet been delivered to the group, but classified by natural language and/or computer vision processing. Interrupting the delivery of content substantially simultaneously to a group of users and initiating dialog regarding content by a CVA enhances opportunities for users to engage with each other about their shared interactive experience.
1. A method to encourage human engagement, comprising:
providing a plurality of electronic devices, each electronic device comprising a processor, an output device operatively coupled to the processor, and a sensor operatively coupled to the processor for monitoring reactions of a user of the electronic device;
delivering, substantially simultaneously on output devices of all of the electronic devices, serial content for users of all of the electronic devices to view;
detecting, by one or more of one or more processors of the electronic devices and one or more sensors of the electronic devices, a user pause indication related to emotional or facial reactions of one or more reacting users to the serial content;
pausing, substantially simultaneously on all of the output devices, the delivering of the serial content based on the user pause indication;
determining, by the one or more processors, one or more ensuing serial content contexts related to one or more upcoming segments of the serial content that have not yet been presented to the users after the pausing of the delivering of the serial content;
generating, by the one or more processors, a virtual agent as a character with voice on one or more of the output devices; and
initiating an interaction related to the one or more ensuing serial content contexts by the virtual agent with one or more of the users.
2. The method of claim 1 , wherein the character generated on the one or more output devices comprises one or more of one or more: displayed cartoon figures, displayed animals, displayed persons, displayed avatars, displayed icons, displayed animations, projected holograms, interactive robots, and animated toys.
3. The method of claim 1 , wherein the interaction includes a conversation based on one or more of: the one or more ensuing serial content contexts, the emotional or facial reactions of the one or more reacting users, and one or more predetermined interests of the one or more reacting users related to the one or more ensuing serial content contexts.
4. The method of claim 3 , wherein the interaction includes the conversation based on the one or more predetermined interests, and wherein the one or more predetermined interests include one or more of reacting user preferences, reacting user viewpoints, reacting user desires, reacting user likes and reacting user dislikes.
5. The method of claim 1 , wherein the interaction is initiated with one or both of the one or more reacting users as a group and one or more non-reacting users as the group.
6. The method of claim 1 , wherein the serial content comprises one or more of: audiovisual data, a video stream, a movie, an audio recording, a plurality of images, a multimedia presentation, a podcast, an audio book, output produced by an application, and an animation.
7. The method of claim 1 , wherein each of the electronic devices comprises one or more of one or more: tablet devices, mobile phones, laptop computers, desktop computers, gaming devices, monitors, televisions, smart displays, speakers, smart speakers, projection devices, tactile electronic displays, virtual reality headsets, augmented reality headwear, and holographic displays.
8. The method of claim 1 , wherein the ensuing serial content context is determined by one or more of: acquiring context labelling of one or more segments of the serial content, classifying the serial content by natural language processing, and classifying the serial content by image recognition processing.
9. The method of claim 1 , wherein the one or more sensors comprise one or more cameras that are used to identify one or more of facial expressions and gestures of one or more of the users to identify the emotional or facial reactions.
10. The method of claim 1 , wherein the one or more processors determine the one or more ensuing serial content contexts using one or more of image recognition, speech recognition, and natural language processing.
11. The method of claim 1 , wherein the interaction relates to the one or more segments of serial content immediately following the paused serial content.
12. The method of claim 1 , wherein determining the one or more ensuing serial content contexts comprises:
acquiring, by the one or more processors, ensuing serial content that follows the serial content when the delivery of the serial content was paused; and
determining, by the one or more processors, the one or more ensuing serial content contexts from the ensuing serial content.
13. A method to encourage human engagement, comprising:
providing a plurality of electronic devices, each electronic device comprising a processor, and an output device operatively coupled to the processor;
delivering, substantially simultaneously on output devices of all of the electronic devices, serial content for users of all of the electronic devices to view;
determining, by one or more processors, a serial pause indication comprising one or both of a detected pause indication encoded with the serial content and that one or more serial content contexts match one or more predetermined contexts intended to be of interest to one or more interested users;
pausing, substantially simultaneously on all of the output devices, the delivering of the serial content based on the serial pause indication;
determining, by the one or more processors, one or more ensuing serial content contexts related to one or more upcoming segments of the serial content that have not yet been presented to the users after the pausing of the delivering of the serial content;
generating, by the one or more processors, a virtual agent as a character with voice on one or more of the output devices; and
initiating an interaction related to the one or more ensuing serial content contexts by the virtual agent with one or more of the users.
14. The method of claim 13 , wherein the character generated on the one or more output devices comprises one or more of one or more: displayed characters, displayed cartoon figures, displayed animals, displayed persons, displayed avatars, displayed icons, displayed animations, projected holograms, interactive robots, and animated toys.
15. The method of claim 13 , wherein the interaction includes a conversation based on one or more of: the one or more serial content contexts, and one or more predetermined interests of the one or more interested users related to the one or more ensuing serial content contexts.
16. The method of claim 15 , wherein the interaction includes the conversation based on the one or more predetermined interests, and wherein the one or more predetermined interests include one or more of: interested user preferences, interested user viewpoints, interested user desires, interested user likes and interested user dislikes.
17. The method of claim 13 , wherein the ensuing serial content context is determined by one or more of: acquiring context labelling of one or more segments of the serial content, classifying the serial content by natural language processing, and classifying the serial content by image recognition processing.
18. A method to encourage human engagement, comprising:
providing a plurality of electronic devices, each electronic device comprising a processor, and an output device operatively coupled to the processor;
delivering, substantially simultaneously on output devices of all of the electronic devices, serial content for users of all of the electronic devices to view;
determining, by one or more processors, a serial pause indication comprising one or both of a detected pause indication encoded with the serial content and that one or more serial content contexts match one or more predetermined contexts intended to be of interest to one or more interested users;
pausing, substantially simultaneously on all of the output devices, the delivering of the serial content based on the serial pause indication;
determining, by the one or more processors, one or more serial content contexts related to one or more upcoming segments of the serial content that have not yet been presented to the users coincident with the pausing of the delivering of the serial content;
generating, by the one or more processors, a virtual agent as a character with voice on one or more of the output devices; and
initiating an interaction related to the one or more serial content contexts by the virtual agent with one or more of the users.
19. The method of claim 18 , wherein the character generated on the one or more output devices comprises one or more of one or more: displayed characters, displayed cartoon figures, displayed animals, displayed persons, displayed avatars, displayed icons, displayed animations, projected holograms, interactive robots, and animated toys.
20. The method of claim 18 , wherein the interaction includes a conversation based on one or more of: the one or more serial content contexts, and one or more predetermined interests of the one or more interested users related to the one or more serial content contexts.
21. The method of claim 18 , wherein the interaction includes the conversation based on the one or more predetermined interests, and wherein the one or more predetermined interests include one or more of: interested user preferences, interested user viewpoints, interested user desires, interested user likes and interested user dislikes.
22. The method of claim 18 , wherein the one or more processors are instantiated with an artificial intelligence.
23. The method of claim 18 , wherein the users comprise a child and one or more adults, and wherein the virtual agent enhances interactive engagement between the child and the one or more adults.