Ephemeral content digests for assistant systems

One or more computer-readable non-transitory non-volatile storage media embodying software that is operable when executed to:

• receive, by an assistant xbot, a user input in a first modality, wherein the first modality is an audio modality;
• analyze, by a natural-language understanding module, the user input in the first modality to determine the user input comprises a request for a content digest;
• retrieve one or more content objects corresponding to the request for the content digest;
• determine, for each of the retrieved content objects, a representative image of the respective content object;
• generate, for each of the retrieved content objects, a summary of the respective content object based on content of the respective content object;
• generate one or more slides for the one or more retrieved content objects, respectively, wherein each slide comprises (1) the representative image of the respective content object and (2) the summary of the respective content object;
• provide, by the assistant xbot, instructions for presenting the content digest in a second modality responsive to the request for the content digest from the user input in the first modality, wherein the second modality is a visual modality, wherein the content digest comprises the one or more slides, and wherein one or more of the slides of the content digest are removed from the content digest after a predetermined time period;
• determine, for each retrieved content object, a category for the retrieved content object from a plurality of categories;
• and
• select one or more of the retrieved content objects to incorporate into the content digest based on their respective categories,
• wherein the representative image for each of the selected content objects is based on the content of the selected content object and the category of the selected content object.

A system comprising:

• one or more processors;
• and a non-transitory non-volatile memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
• receive, by an assistant xbot, a user input in a first modality, wherein the first modality is an audio modality;
• analyze, by a natural-language understanding module, the user input in the first modality to determine the user input comprises a request for a content digest;
• retrieve one or more content objects corresponding to the request for the content digest;
• determine, for each of the retrieved content objects, a representative image of the respective content object;
• generate, for each of the retrieved content objects, a summary of the respective content object based on content of the respective content object;
• generate one or more slides for the one or more retrieved content objects, respectively, wherein each slide comprises (1) the representative image of the respective content object and (2) the summary of the respective content object;
• provide, by the assistant xbot, instructions for presenting the content digest in a second modality responsive to the request for the content digest from the user input in the first modality, wherein the second modality is a visual modality, wherein the content digest comprises the one or more slides, and wherein one or more of the slides of the content digest are removed from the content digest after a predetermined time period;
• determine, for each retrieved content object, a category for the retrieved content object from a plurality of categories;
• and
• select one or more of the retrieved content objects to incorporate into the content digest based on their respective categories,
• wherein the representative image for each of the selected content objects is based on the content of the selected content object and the category of the selected content object.