Intelligent people-centric predictions in a collaborative environment
A method for predicting one or more collaborators provided by a cloud-based content management platform includes identifying, for a user of a cloud-based content management platform, a plurality of other users of the cloud-based content management platform that have a relationship with the user and are associated with a plurality of documents hosted by the cloud-based content management platform, predicting one or more collaborators for the user based on collaboration attributes of the plurality of other users, and providing for presentation to the user, information identifying the one or more collaborators to direct the user to a subset of documents from the plurality of documents hosted by the cloud-based content management platform, the subset of documents each being associated with one of the predicted one or more collaborators.
1. A computer-implemented method comprising:
generating, by a processing device, training data to train a machine learning model, wherein generating the training data comprises:
generating first training input, the first training input comprising information identifying one or more action attributes of a plurality of pending actions associated with a plurality of documents hosted by a cloud-based content management platform, the plurality of pending actions corresponding to invitations to a first user, from other users of the cloud-based content management platform, to perform operations associated with the plurality of documents; and
generating a first target output for the first training input, wherein the first target output indicates responses of the first user to the plurality of pending actions to the first user, from the other users, to perform the operations associated with the plurality of documents; and
training the machine learning model on the training data comprising (i) a set of training inputs comprising the first training input, and
(ii) a set of target outputs comprising the first target output, wherein training the machine learning model comprising adjusting one or more weights of the machine learning model based on the training data,
wherein the trained machine learning model is configured to generate an output identifying a probability of a first response of the first user to a new pending action from a second user for a document hosted by the cloud-based content management platform, and
wherein the output of the trained machine learning model is to cause a user interface (UI) component to be provided to a client device associated with the first user based on the probability of the first response, the UI component configured to receive the first response to the new pending action.
2. The method of claim 1 , wherein the one or more action attributes comprise:
an action type of a respective action of the plurality of pending actions.
3. The method of claim 2 , wherein the one or more action attributes comprise:
a recency of the respective action of the plurality of pending actions.
4. The method of claim 2 , wherein the one or more action attributes comprise:
an identity of a user of the cloud-based content management platform who initiated the respective action.
5. The method of claim 1 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise ignoring a respective one of the invitations corresponding to a respective one of the plurality of pending actions.
6. The method of claim 5 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise editing a corresponding one of the plurality of documents.
7. The method of claim 1 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise performing an action related to a comment corresponding to one of the plurality of documents.
8. The method of claim 1 , wherein the plurality of pending actions directed to the first user by the other users comprises one or more of:
one or more invitations, by the other users, to the first user to share respective one or more documents from the plurality of documents,
one or more comments, by the other users, to the first user in relation to the plurality of documents, or
one or more edits, by the other users, for the first user with regards to the plurality of documents.
9. The method of claim 1 , wherein each training input of the set of training inputs is mapped to the first target output in the set of target outputs.
10. A system, comprising: a memory device; and
a processing device, couple to the memory device, to perform operations comprising:
generating training data to train a machine learning model, wherein generating the training data comprises:
generating first training input, the first training input comprising information identifying one or more action attributes of a plurality of pending actions associated with a plurality of documents hosted by a cloud-based content management platform, the plurality of pending actions corresponding to invitation, to a first user, from other users of the cloud-based content management platform, to perform operations associated with the plurality of documents; and
generating a first target output for the first training input, wherein the first target output indicates responses of the first user to the plurality of pending actions to the first user, from the other users, to perform the operations associated with the plurality of documents; and
training the machine learning model on the training data comprising (i) a set of training inputs comprising the first training input, and
(ii) a set of target outputs comprising the first target output, wherein training the machine learning model comprising adjusting one or more weights of the machine learning model based on the training data,
wherein the trained machine learning model is configured to generate an output identifying a probability of a first response of the first user to a new pending action from a second user for a document hosted by the cloud-based content management platform, and
wherein the output of the trained machine learning model is to cause a user interface (UI) component to be provided to a client device associated with the first user based on the probability of the first response, the UI component configured to receive the first response to the new pending action.
11. The system of claim 10 , wherein the one or more action attributes comprise:
an action type of a respective action of the plurality of pending actions.
12. The system of claim 11 , wherein the one or more action attributes comprise:
a recency of the respective action of the plurality of pending actions.
13. The system of claim 11 , wherein the one or more action attributes comprise:
an identity of a user of the cloud-based content management platform who initiated the respective action.
14. The system of claim 10 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise ignoring a respective one of the invitations corresponding to a respective one of the plurality of pending actions.
15. The system of claim 14 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise editing a corresponding one of the plurality of documents.
16. The system of claim 10 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise performing an action related to a comment corresponding to one of the plurality of documents.
17. The system of claim 10 , wherein the plurality of pending actions directed to the first user by the other users comprises one or more of:
one or more invitations, by the other users, to the first user to share respective one or more documents from the plurality of documents,
one or more comments, by the other users, to the first user in relation to the plurality of documents, or
one or more edits, by the other users, for the first user with regards to the plurality of documents.
18. The system of claim 10 , wherein each training input of the set of training inputs is mapped to the first target output in the set of target outputs.
19. A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, cause the processing device to perform operations comprising:
generating, by the processing device, training data to train a machine learning model, wherein generating the training data comprises:
generating first training input, the first training input comprising information identifying one or more action attributes of a plurality of pending actions associated with
a plurality of documents hosted by a cloud-based content management platform, the plurality of pending actions corresponding to invitations to a first user, from other users of the cloud-based content management platform, to perform operations associated with the plurality of documents; and
generating a first target output for the first training input, wherein the first target output indicates responses of the first user to the plurality of pending actions to the first user, from the other users, to perform the operations associated with the plurality of documents; and
training the machine learning model on the training data comprising (i) a set of training inputs comprising the first training input, and
(ii) a set of target outputs comprising the first target output, wherein training the machine learning model comprising adjusting one or more weights of the machine learning model based on the training data,
wherein the trained machine learning model is configured to generate an output identifying a probability of a first response of the first user to a new pending action from a second user for a document hosted by the cloud-based content management platform, and
wherein the output of the trained machine learning model is to cause a user interface (UI) component to be provided to a client device associated with the first user based on the probability of the first response, the UI component configured to receive the first response to the new pending action.
20. The non-transitory computer-readable medium of claim 19 , wherein the responses of the first user to the plurality of pending actions that correspond to the invitations to perform the operations comprise performing an action related to a comment corresponding to one of the plurality of documents.