Intelligent serendipitous document discovery notifications

1 . A method of notifying a user of a cloud-based content management platform of a document, the method comprising:

responsive to a login request of the user to login to the cloud-based content management platform, selecting, from a plurality of documents associated with a user account of the user on the cloud-based content management platform, one or more target documents that are likely to be of interest to the user and that have not been opened by the user or have been last opened by the user more than a predetermined time period ago, wherein selecting the one or more target documents comprises:

identifying, by a server of the cloud-based content management platform and among the plurality of documents associated with the user account of the user, a first set of serendipitous documents, wherein the first set of serendipitous documents associated with the user account of the user comprises documents uploaded to the cloud-based content management platform by the user and documents uploaded to the cloud-based content management platform by other users, wherein each serendipitous document in the first set is a document that has either expired from a cache or has been last opened by the user more than the predetermined time period ago; and

identifying, by the server of the cloud-based content management platform, the one or more target documents from the first set of serendipitous documents for the user based on (i) an amount of overlap in topicality between a serendipitous document from the first set of serendipitous documents, which have either expired from the cache or have been last opened by the user more than the predetermined time period ago, and a user's working set of documents, which the user has last opened within the predetermined time period, (ii) a number of view events of the serendipitous document, and (iii) a number of collaborative events associated with the serendipitous document; and

providing, by the server of the cloud-based content management platform and in response to the login request of the user, a home screen graphical user interface (GUI) of the cloud-based content management platform for presentation to the user, the home screen GUI identifying the one or more target documents.

2 . The method of claim 1 , wherein the identifying of the first set of serendipitous documents comprises:

determining a second set of documents associated with one or more collaborators of the user based on events by the one or more collaborators and importance weights assigned to the one or more collaborators;

determining a third set of documents that are related to documents in the user's working set of documents; and

generating the first set of serendipitous documents by combining the second set of documents and the third set of documents and eliminating one or more documents opened by the user within the predetermined time period.

3 . The method of claim 2 , wherein the determining of the second set of documents associated with the one or more collaborators of the user based on events by the one or more collaborators and importance weights assigned to the one or more collaborators comprises:

determining the one or more collaborators by identifying one or more other users of the cloud-based content management platform providing at least one of a view event, edit event, or comment event to a document shared with the user in the cloud-based content management platform within the predetermined time period;

determining an importance weight for each collaborator based on importance of a respective collaborator in a social network associated with the cloud-based content management platform; and

determining the second set of documents comprising one or more documents with events by the one or more collaborators and importance weights assigned to the one or more collaborators.

4 . The method of claim 2 , wherein the determining of the third set of documents that are related to documents in the user's working set of documents comprises:

identifying a key text of each document in the user's working set of documents; and

determining the third set of documents comprising one or more documents having the key texts.

5 . The method of claim 2 , wherein at least one of the second set of documents or the third set of documents includes one or more documents which the user has not accessed.

6 . The method of claim 2 , wherein the generating of the first set of serendipitous documents comprises at least one of:

eliminating one or more documents to which the user does not have access and have events by less than a predetermined number of the one or more collaborators; or

eliminating one or more documents set to be not discoverable by search performed via the cloud-based content management platform.

7 . The method of claim 1 , wherein the identifying of the one or more target documents for the user comprises at least one of:

determining the number of view events of the serendipitous document by either other users or the one or more collaborators; or

determining the number of collaborative events in view of a number of user's interactive events with the serendipitous document, a number of the one or more other users' interactive events with the serendipitous document and a likelihood of the user performing an interactive event with one or more other users involved in the serendipitous document, wherein an interactive event is an event generated in response to an event by another user.

8 . The method of claim 1 , wherein the identifying of the one or more target documents for the user comprises:

for each document in the first set of documents,

applying the amount of overlap in topicality between the serendipitous document and the user's working set of documents, the number of view events of the serendipitous document, and the number of collaborative events associated with the serendipitous document to a machine learning model as an input; and

obtaining, from the machine learning model, an output, the output indicating a probability of the user being interested in the serendipitous document.

9 . The method of claim 1 , wherein the home screen GUI comprises one or more suggestion cards, each suggestion card identifying each target document, and each suggestion card comprising:

a title information including a document type and a title of a respective document;

an image representation of the respective document;

an action button providing access to the respective document; and

a reason text describing a reason for the identification of the respective document.

10 . A system comprising:

a server of a cloud-based content management platform, the server comprising:

a memory device; and

a processing device operatively coupled to the memory device, the processing device to:

responsive to a login request of a user to login to the cloud-based content management platform, select, from a plurality of documents associated with a user account of the user on the cloud-based content management platform, one or more target documents that are likely to be of interest to the user and that have not been opened by the user or have been last opened by the user more than a predetermined time period ago, wherein to select the one or more target documents, the processing device is further to:

identify, among the plurality of documents associated with the user account of the user, a first set of serendipitous documents, wherein the first set of serendipitous documents associated with the user account of the user comprises documents uploaded to the cloud-based content management platform by the user and documents uploaded to the cloud-based content management platform by other users, wherein each serendipitous document in the first set is a document that has either expired from a cache or has been last opened by the user more than the predetermined time period ago; and

identify the one or more target documents from the first set of serendipitous documents for the user based on (i) an amount of overlap in topicality between a serendipitous document from the first set of serendipitous documents, which have either expired from the cache or have been last opened by the user more than the predetermined time period ago, and a user's working set of documents, which the user has last opened within the predetermined time period, (ii) a number of view events of the serendipitous document, and (iii) a number of collaborative events associated with the serendipitous document; and

provide, in response to the login request of the user, a home screen graphical user interface (GUI) of the cloud-based content management platform for presentation to the user, the home screen GUI identifying the one or more target documents.

11 . The system of claim 10 , wherein to identify the first set of serendipitous documents the processing device further to:

determine a second set of documents associated with one or more collaborators of the user based on events by the one or more collaborators and importance weights assigned to the one or more collaborators;

determine a third set of documents that are related to documents in the user's working set of documents; and

generate the first set of documents by combining the second set of documents and the third set of documents and eliminating one or more documents opened by the user within the predetermined time period.

12 . The system of claim 11 , wherein to determine the second set of documents associated with the one or more collaborators of the user based on events by the one or more collaborators and importance weights assigned to the one or more collaborators, the processing device further to:

determine the one or more collaborators by identifying one or more other users of the cloud-based content management platform providing at least one of a view event, edit event, or comment event to a document shared with the user in the cloud-based content management platform within the predetermined time period; and

determine an importance weight for each collaborator based on importance of a respective collaborator in a social network associated with the cloud-based content management platform; and

determine the second set of documents comprising one or more documents with events by the one or more collaborators and importance weights assigned to the one or more collaborators.

13 . The system of claim 11 , wherein to determine the third set of documents that are related to documents in the user's working set of documents the processing device further to:

identify a key text of each document in the user's working set of documents; and

determine the third set of documents comprising one or more documents having the key texts.

14 . The system of claim 10 , wherein to identify the one or more target documents for the user the processing device further to at least one of:

determine the number of view events of the serendipitous document by either other users or the one or more collaborators; or

determine the number of collaborative events in view of a number of the user's interactive events with the serendipitous document, a number of one or more other users' interactive events with the serendipitous document and a likelihood of the user performing an interactive event with one or more other users involved in the serendipitous document, wherein an interactive event is an event generated in response to an event by another user.

15 . The system of claim 10 , wherein the home screen GUI comprises one or more suggestion cards, each suggestion card identifying each target document, and each suggestion card comprising:

a title information including a document type and a title of a respective document;

an image representation of the respective document;

an action button providing access to the respective document; and

a reason text describing a reason for the identification of the respective document.

16 . A non-transitory, computer readable medium storing instructions that, when executed, cause a processing device of a cloud-based content management platform to:

responsive to a login request of a user to login to the cloud-based content management platform, select, from a plurality of documents associated with a user account of the user on the cloud-based content management platform, one or more target documents that are likely to be of interest to the user and that have not been opened by the user or have been last opened by the user more than a predetermined time period ago, wherein to select the one or more target documents, the processing device is further to:

identify, among the plurality of documents associated with the user account of the user, a first set of serendipitous documents, wherein the first set of serendipitous documents associated with the user account of the user comprises documents uploaded to the cloud-based content management platform by the user and documents uploaded to the cloud-based content management platform by other users, wherein each serendipitous document in the first set is a document that has either expired from a cache or has been last opened by the user more than the predetermined time period ago; and

identify the one or more target documents from the first set of serendipitous documents for the user based on (i) an amount of overlap in topicality between a serendipitous document from the first set of serendipitous documents, which have either expired from the cache or have been last opened by the user more than the predetermined time period ago, and a user's working set of documents, which the user has last opened within the predetermined time period, (ii) a number of view events of the serendipitous document, and (iii) a number of collaborative events associated with the serendipitous document; and

provide, in response to the login request of the user, a home screen graphical user interface (GUI) of the cloud-based content management platform for presentation to the user, the home screen GUI identifying the one or more target documents.

17 . The computer readable medium of claim 16 , wherein to identify the first set of serendipitous documents, the instructions further cause the processing device to:

determine a second set of documents associated with one or more collaborators of the user based on events by the one or more collaborators and importance weights assigned to the one or more collaborators;

determine a third set of documents that are related to documents in the user's working set of documents; and

generate the first set of documents by combining the second set of documents and the third set of documents and eliminating one or more documents opened by the user within the predetermined time period.

18 . The computer readable medium of claim 17 , wherein to determine the second set of documents associated with the one or more collaborators of the user based on events by the one or more collaborators and importance weights assigned to the one or more collaborators, the instructions further cause the processing device to:

determine the one or more collaborators by identifying one or more other users of the cloud-based content management platform providing at least one of a view event, edit event, or comment event to a document shared with the user in the cloud-based content management platform within the predetermined time period;

determine an importance weight for each collaborator based on importance of a respective collaborator in a social network associated with the cloud-based content management platform; and

determine the second set of documents comprising one or more documents with events by the one or more collaborators and importance weights assigned to the one or more collaborators.

19 . The computer readable medium of claim 17 , wherein to determine the third set of documents that are related to documents in the user's working set of documents, the instructions further cause the processing device to:

identify a key text of each document in the user's working set of documents; and

determine the third set of documents comprising one or more documents having the key texts.

20 . The computer readable medium of claim 16 , wherein the home screen GUI comprises one or more suggestion cards, each suggestion card identifying each target document, and each suggestion card comprising:

a title information including a document type and a title of a respective document;

an image representation of the respective document;

an action button providing access to the respective document; and

a reason text describing a reason for the identification of the respective document.

21 . The method of claim 1 , wherein the home screen GUI presents a message indicating that the one or more target documents are suggested to the user based on a serendipitous discovery.