Generating Context-Aware Rendering of Media Contents for Assistant Systems

Abstract

In one embodiment, a method includes receiving a media content associated with a priority level for delivery to a first user, determining a filter level for providing a notification associated with the media content based on context information associated with the first user, wherein the context information is determined based on multimodal signals from a head-mounted device, determining a delivery level for providing the notification associated with the media content based on the priority level of the media content and the filter level, wherein the delivery level has an inverse relationship with the filter level, and presenting the notification associated with the media content to the first user at the head-mounted device, wherein the notification is presented in modalities determined based on the delivery level for the media content.

What is claimed is: 
     
         1 . A method comprising, by a head-mounted device:
 receiving a media content for delivery to a first user, wherein the media content is associated with a priority level;   determining a filter level for providing a notification associated with the media content based on context information associated with the first user, wherein the context information is determined based on one or more multimodal signals from the head-mounted device;   determining a delivery level for providing the notification associated with the media content based on the priority level of the media content and the filter level, wherein the delivery level has an inverse relationship with the filter level; and   presenting, at the head-mounted device, the notification associated with the media content to the first user, wherein the notification is presented in one or more modalities determined based on the delivery level for the media content.   
     
     
         2 . The method of  claim 1 , further comprising:
 determining whether the received media content should be delivered to the first user based on the priority level associated with the media content.   
     
     
         3 . The method of  claim 1 , further comprising:
 determining, based on the delivery level for the media content, an intensity for each of the one or more modalities, wherein the notification is presented in the one or more modalities corresponding to their respective intensities.   
     
     
         4 . The method of  claim 3 , wherein the intensity comprises one or more of a low intensity, a moderate intensity, or a high intensity. 
     
     
         5 . The method of  claim 1 , wherein the head-mounted device is a pair of smart glasses, a virtual-reality device, or an augmented-reality device. 
     
     
         6 . The method of  claim 1 , wherein the media content comprises one or more of text, an image, a video clip, an audio clip, or a voice utterance. 
     
     
         7 . The method of  claim 1 , wherein the media content originates from a second user, and wherein the priority level associated with the media content is determined based on a degree of separation between the first user and the second user within an online social network. 
     
     
         8 . The method of  claim 1 , wherein the context information associated with the first user comprises attention-context information, and wherein the method further comprises:
 determining the attention-context information based on optical signals from the head-mounted device.   
     
     
         9 . The method of  claim 1 , wherein the context information associated with the first user comprises physio-social context information, and wherein the method further comprises:
 determining the physio-social context information based on human detection around the first user, wherein the human detection is based on one or more of facial recognition or speech recognition.   
     
     
         10 . The method of  claim 1 , wherein the one or more modalities comprise one or more of a text modality, an imagery modality, a video modality, an XR modality, a sound modality, a voice modality, or a light modality. 
     
     
         11 . The method of  claim 1 , wherein the delivery level comprises one or more of a visual-only level, a visual-forward level, an auditory-forward level, or an auditory-only level. 
     
     
         12 . The method of  claim 11 , wherein the visual-only level corresponds to presenting the notification only in a visual modality, and wherein the visual modality comprises one or more of a text modality, an imagery modality, a video modality, an XR modality, or a light modality. 
     
     
         13 . The method of  claim 11 , wherein the visual-forward level corresponds to presenting the notification in at least a first modality and a second modality, and wherein the first modality is associated with a high intensity and the second modality is associated with a moderate intensity. 
     
     
         14 . The method of  claim 13 , wherein the first modality comprises one or more of a text modality, an imagery modality, a video modality, an XR modality, or a light modality, and wherein the second modality comprises one or more of a sound modality or a voice modality. 
     
     
         15 . The method of  claim 11 , wherein the auditory-forward level corresponds to presenting the notification in at least a first modality and a second modality, and wherein the first modality is associated with a moderate intensity and the second modality is associated with a high intensity. 
     
     
         16 . The method of  claim 15 , wherein the first modality comprises one or more of a text modality, an imagery modality, a video modality, an XR modality, or a light modality, and wherein the second modality comprises one or more of a sound modality or a voice modality. 
     
     
         17 . The method of  claim 11 , wherein the auditory-only level corresponds to presenting the notification only in an auditory modality, and wherein the auditory modality comprises one or more of a sound modality or a voice modality. 
     
     
         18 . The method of  claim 1 , wherein the filter level comprises no filter, low filter, moderate filter, high filter, or everything-off filter. 
     
     
         19 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 receive a media content for delivery to a first user, wherein the media content is associated with a priority level;   determine a filter level for providing a notification associated with the media content based on context information associated with the first user, wherein the context information is determined based on one or more multimodal signals from a head-mounted device;   determine a delivery level for providing the notification associated with the media content based on the priority level of the media content and the filter level, wherein the delivery level has an inverse relationship with the filter level; and   present, at the head-mounted device, the notification associated with the media content to the first user, wherein the notification is presented in one or more modalities determined based on the delivery level for the media content.   
     
     
         20 . A system comprising: one or more processors; and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
 receive a media content for delivery to a first user, wherein the media content is associated with a priority level;   determine a filter level for providing a notification associated with the media content based on context information associated with the first user, wherein the context information is determined based on one or more multimodal signals from a head-mounted device;   determine a delivery level for providing the notification associated with the media content based on the priority level of the media content and the filter level, wherein the delivery level has an inverse relationship with the filter level; and   present, at the head-mounted device, the notification associated with the media content to the first user, wherein the notification is presented in one or more modalities determined based on the delivery level for the media content.