Recommending content for sharing in online meetings
An online system receives, from a client device of a user participating an online meeting, a request to share content with another user participating the online meeting. The online system identifies content items from applications running on the client device. For each identified content item, the online system determines, e.g., by using a trained model or instructing the client device to use the trained model, a sharing score that indicates a likelihood that the user would select the content item to share with the other user. Candidate content items are selected form the identified content items based on the sharing scores. The candidate content items are provided for display to the user in a user interface running on the client device. The user interface allows the user to select one of the candidate content items to share with the other user.
1. A computer-implemented method, comprising,
receiving, from a first client device associated with a first user participating in an online video call, a request to share an application running on the first client device associated with the first user during the video call with a second user participating in the online video call, wherein the first user and second user are users of an online system that maintains a first user profile for the first user and a second user profile for the second user;
identifying one or more applications running on the first client device;
for each of the one or more applications running on the first client device, determining a sharing score indicating a likelihood that the first user would select the respective application to display to the second user in response to being presented with a user interface option for sharing the respective application, wherein determining the sharing score of the respective application comprises:
determining an attribute of the first user based on the first user profile;
determining an attribute of the second user based on the second user profile
inputting the attribute of the first user, the attribute of the second user, and at least one or more attributes of the respective application into a model, the model trained to predict likelihoods of users selecting applications to share with other users based at least on attributes of the applications; and
determining the sharing score of the respective application based on an output of the model;
ranking the one or more applications based on the sharing scores for the identified one or more applications; and
providing the one or more applications for display to the first user in a user interface running on the first client device associated with the first user, where the user interface arranges the one or more applications based on the ranking, the user interface allowing the first user to select an application operating on the first client device associated with the first user from the one or more applications to display to the second user during the online video call.
2. The method of claim 1 , wherein the one or more attributes of the respective application comprise one or more of: a type of an application from which the respective application is identified, an object detected from the respective application, a title of the respective application, or some combination thereof.
3. The method of claim 1 , wherein the attribute of the first user comprises one or more of: a description of the first user, a description of an entity associated with the first user, a relationship between the first user and the second user, an affinity of the first user for the second user in the online system, or some combination thereof.
4. The method of claim 1 , wherein inputting at least one or more attributes of the respective application into a model comprises:
inputting the one or more attributes of the respective application and information associated with the online video call into the model.
5. The method of claim 4 , wherein the information associated with the online video call comprises one or more of: a purpose of the online video call, a title of the online video call, information associated with an invitation of the online video call, information associated with attendees of the online video call, information associated with content of the online video call; time of the online video call, or some combination thereof.
6. The method of claim 1 , wherein identifying applications from one or more applications running on the first client device comprises:
selecting the one or more applications from a plurality of processes running on the first client device; and
identifying one or more files from each application of the one or more applications, each of the one or more files being one of the identified applications.
7. The method of claim 1 , wherein providing the one or more applications for display to the first user in a user interface running at the first client device comprises:
determining an order of presenting the one or more applications based on the likelihoods of the one or more applications; and
providing the one or more applications for display in the determined order.
8. The method of claim 1 , further comprising:
further training the model based on the one or more attributes of each respective application and whether the respective application was selected by the first user.
9. A computer program product comprising a non-transitory computer-readable storage medium containing computer program code for:
receiving, from a first client device associated with a first user participating in an online video call, a request to an application running on the first client device associated with the first user during the video call with a second user participating in the online video call, wherein the first user and second user are users of an online system that maintains a first user profile for the first user and a second user profile for the second user;
identifying one or more applications running on the first client device;
for each of the one or more applications running on the first client device, determining a sharing score indicating a likelihood that the first user would select the respective application to display to the second user in response to being presented with a user interface option for sharing the respective application, wherein determining the sharing score of the respective application comprises:
determining an attribute of the first user based on the first user profile;
determining an attribute of the second user based on the second user profile
inputting the attribute of the first user, the attribute of the second user, and at least one or more attributes of the respective application into a model, the model trained to predict likelihoods of users selecting applications to share with other users based at least on attributes of the applications; and
determining the sharing score of the respective application based on an output of the model;
ranking the one or more applications based on the sharing scores for the identified one or more applications; and
providing the one or more applications for display to the first user in a user interface running on the first client device associated with the first user, where the user interface arranges the one or more applications based on the ranking, the user interface allowing the first user to select an application operating on the first client device associated with the first user from the one or more applications to display to the second user during the online video call.
10. The computer program product of claim 9 , wherein the one or more attributes of the respective application comprise one or more of: a type of an application from which the respective application is identified, an object detected from the respective application, a title of the respective application, or some combination thereof.
11. The computer program product of claim 9 , wherein the attribute of the first user comprises one or more of: a description of the first user, a description of an entity associated with the first user, a relationship between the first user and the second user, an affinity of the first user for the second user in the online system, or some combination thereof.
12. The computer program product of claim 9 , wherein inputting at least one or more attributes of the respective application into a model comprises:
inputting the one or more attributes of the respective application and information associated with the online video call into the model.
13. The computer program product of claim 12 , wherein the information associated with the online video call comprises one or more of: a purpose of the online video call, a title of the online video call, information associated with an invitation of the online video call, information associated with attendees of the online video call, information associated with content of the online video call; time of the online video call, or some combination thereof.
14. The computer program product of claim 9 , wherein identifying applications from one or more applications running on the first client device comprises:
selecting the one or more applications from a plurality of processes running on the first client device; and
identifying one or more files from each application of the one or more applications, each of the one or more files being one of the identified applications.
15. The computer program product of claim 9 , wherein providing the one or more applications for display to the first user in a user interface running at the first client device comprises:
determining an order of presenting the one or more applications based on the likelihoods of the one or more applications; and
providing the one or more applications for display in the determined order.
16. The computer program product of claim 9 , wherein the non-transitory computer-readable storage medium further contains computer program code for:
further training the model based on the one or more attributes of each respective application and whether the respective application was selected by the first user.