Assisting users with efficient information sharing among social connections

1. A method comprising, by one or more computing systems:

receiving, from a client system associated with a first user via a first assistant xbot, a user input;

determining that the user input is a sharing request to share content, wherein the sharing request comprises an ambiguous reference to one or more content objects generated during a current dialog session;

identifying, based on a natural-language understanding module, the one or more content objects by disambiguating the ambiguous reference associated with the sharing request, wherein the one or more content objects were previously generated during the current dialog session;

determining, based on a user profile associated with first user, a plurality of second users the sharing request is directed to;

determining, for each second user, one or more modalities associated with the respective second user based on the one or more content objects, a user profile associated with the respective second user, and modalities supported by a client system the respective second user is currently engaged with, the respective second user being associated with two or more client systems; and

sending, to one or more client systems currently associated with the plurality of second users via one or more second assistant xbots, instructions for accessing one or more of the identified content objects based on the determined one or more modalities for each second user.

2. The method of claim 1 , wherein the user input comprising one or more of a character string, an image, a video, or an audio clip.

3. The method of claim 1 , wherein determining that the user input is a sharing request is based on one or more machine-learning models.

4. The method of claim 1 , wherein identifying the one or more content objects comprises:

determining one or more slots associated with the user input;

accessing a user context engine; and

identifying the one or more content objects based on the one or more slots and the user context engine.

5. The method of claim 1 , wherein identifying the one or more content objects comprises:

determining one or more slots associated with the user input;

accessing a dialog state associated with the current dialog session, wherein the dialog state is stored in a data store and comprises information associated with the one or more content objects previously generated during the current dialog session; and

identifying the one or more content objects based on the one or more slots and the dialog state.

6. The method of claim 5 , wherein the dialog state further comprises the one or more content objects previously generated during the current dialog session.

7. The method of claim 1 , wherein each of the one or more content objects is associated with one or more of an identifier of the first user or an expiration time.

8. The method of claim 7 , wherein each of the one or more of the identified content objects is selected if it is associated with an elapsed time less than the respective expiration time associated with it.

9. The method of claim 1 , wherein determining the plurality of second users the sharing request is directed to comprises:

determining a plurality of slots associated with the user input, wherein the plurality of slots comprise a plurality of user slots; and

resolving the plurality of user slots to identify a plurality of entities associated with the plurality of second users based on the user profile associated with the first user.

10. The method of claim 1 , wherein the one or more of the identified content objects are determined based on privacy settings associated with the respective content objects.

11. The method of claim 1 , wherein the one or more previously generated content objects correspond to a previous assistance request from the first user during the current dialog session.

12. The method of claim 1 , wherein the one or more modalities comprise text, audio, image, video, or a combination thereof.

13. The method of claim 1 , further comprising:

generating a plurality of communication contents for the plurality of second users, respectively, wherein each communication content is based on the determined one or more modalities for the respective second user.

14. The method of claim 1 , further comprising:

determining whether the sending of the one or more of the identified content objects to the respective client system currently associated with each of the plurality of second users is successful based on one or more signals from the respective second user.

15. The method of claim 14 , further comprising:

generating, for the first user, a plurality of communication contents, wherein each communication content comprises a status associated with the sharing request to each second user, the status indicating whether the sending of the one or more of the identified content objects to the respective client system is successful; and

sending, to the client system associated with the first user via the first assistant xbot, the plurality of communication contents for display in the current dialog session.

16. The method of claim 15 , further comprising:

upon determining the sending of the one or more of the identified content objects to the respective client system is successful, initiating a message thread between the first user and the respective second user.

17. The method of claim 1 , wherein the sending of the one or more of the identified content objects to each client system currently associated with the respective second user is associated with a notification indicating that the one or more of the identified content objects are shared by the first user.

18. The method of claim 1 , wherein disambiguating the ambiguous reference comprises resolving a slot corresponding to the ambiguous reference to the one or more content objects.

19. The method of claim 1 , wherein the current dialog session is associated with a dialog state indicating the current dialog session is not completed.

20. The method of claim 1 , further comprising:

determining the client system the respective second user is currently engaged with from the two or more client systems associated with the respective second user.

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

receive, from a client system associated with a first user via a first assistant xbot, a user input;

determine that the user input is a sharing request to share content, wherein the sharing request comprises an ambiguous reference to one or more content objects generated during a current dialog session;

identify, based on a natural-language understanding module, the one or more content objects by disambiguating the ambiguous reference associated with the sharing request, wherein the one or more content objects were previously generated during the current dialog session;

determine, based on a user profile associated with first user, a plurality of second users the sharing request is directed to;

determine, for each second user, one or more modalities associated with the respective second user based on the one or more content objects, a user profile associated with the respective second user, and modalities supported by a client system the respective second user is currently engaged with, the respective second user being associated with two or more client systems; and

send, to one or more client systems currently associated with the plurality of second users via one or more second assistant xbots, instructions for accessing one or more of the identified content objects based on the determined one or more modalities for each second user.

22. 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, from a client system associated with a first user via a first assistant xbot, a user input;

determine that the user input is a sharing request to share content, wherein the sharing request comprises an ambiguous reference to one or more content objects generated during a current dialog session;

identify, based on a natural-language understanding module, the one or more content objects by disambiguating the ambiguous reference associated with the sharing request, wherein the one or more content objects were previously generated during the current dialog session;

determine, based on a user profile associated with first user, a plurality of second users the sharing request is directed to;

determine, for each second user, one or more modalities associated with the respective second user based on the one or more content objects, a user profile associated with the respective second user, and modalities supported by a client system the respective second user is currently engaged with, the respective second user being associated with two or more client systems; and

send, to one or more client systems currently associated with the plurality of second users via one or more second assistant xbots, instructions for accessing one or more of the identified content objects based on the determined one or more modalities for each second user.