Generating and providing team member recommendations for content collaboration
The present disclosure is directed toward systems, methods, and non-transitory computer readable media for identifying and recommending team members for target users from a content management system utilizing a machine learning approach. In particular, the disclosed systems can generate a set of candidate team members from among users of the content management system based on various factors such as access to a common digital content item. In some embodiments, the disclosed systems further determine recommended team members from among the set of candidate team members. For example, the disclosed systems can utilize a machine learning approach to generate or predict recommended team members based on particular features extracted or determined for, or with respect to, the various candidate team members. In certain implementations, the disclosed systems further provide a recommended-team-member notification to notify a target user of a recommended team member.
1 . A computer-implemented method comprising:
providing, to a machine learning model, a set of digital features associated with candidate recommendations for a target user account;
generating, utilizing the machine learning model, a suggested recommendation for the target user account based on the set of digital features;
generating a recommendation rationale for the suggested recommendation based on two or more features from the set of digital features, wherein the recommendation rationale comprises a generated text description explaining how respective features of the two or more features contributed to the suggested recommendation; and
triggering a client device associated with the target user account to display a recommendation notification comprising the suggested recommendation and the recommendation rationale within a content-management user interface associated with creating or modifying one or more digital content items accessible by the target user account.
2 . The computer-implemented method of claim 1 , wherein:
the recommendation notification that comprises the suggested recommendation and the recommendation rationale further comprises a selectable option to accept the suggested recommendation; and
further comprising performing, in response to an indication of user selection of the selectable option, the suggested recommendation.
3 . The computer-implemented method of claim 1 , wherein determining the recommendation rationale comprises generating a natural language sentence that references the two or more features from the set of digital features on which the recommendation rationale is based.
4 . The computer-implemented method of claim 1 , further comprising identifying the two or more features from the set of digital features based on determining the two or more features contributed most heavily to generating the suggested recommendation.
5 . The computer-implemented method of claim 1 , further comprising providing an indication of the two or more features on which the recommendation rationale is based within the recommendation notification.
6 . The computer-implemented method of claim 1 , wherein providing the set of digital features associated with the candidate recommendations for the target user account comprises identifying at least one of source features, team features, or candidate-team-member features.
7 . The computer-implemented method of claim 1 , further comprising:
determining a contribution measure associated with each feature of the set of digital features associated with the candidate recommendations for the target user account;
ranking each feature of the set of digital features based on the contribution measure corresponding with each feature; and
identifying the two or more features from the set of digital features from which to determine the recommendation rationale based on the ranking of each feature per the corresponding contribution measure.
8 . The computer-implemented method of claim 1 , wherein the suggested recommendation is a recommendation to add a user account to a team associated with the target user account.
9 . A system comprising:
at least one processor; and
a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to:
provide a set of digital features to a machine learning model, the set of digital features associated with a target user account;
generate a suggested recommendation for the target user account by processing the set of digital features with the machine learning model;
generate a recommendation rationale for the suggested recommendation based on two or more features from the set of digital features, wherein the recommendation rationale comprises a generated text description explaining how respective features of the two or more features contributed to the suggested recommendation; and
trigger a client device associated with the target user account to display a recommendation notification comprising the suggested recommendation and the recommendation rationale within a content-management user interface associated with creating or modifying one or more digital content items accessible by the target user account.
10 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to perform the suggested recommendation in response to an indication of a user selection of a selectable option provided within the recommendation notification.
11 . The system of claim 9 , wherein determining the recommendation rationale comprises generating a natural language sentence based on the two or more features on which the recommendation rationale is based.
12 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to provide, within the recommendation notification, an indication of the two or more features on which the recommendation rationale is based.
13 . The system of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the system to:
determine a contribution measure associated with each feature of the set of digital features; and
identify the two or more features based on the contribution measure associated with each feature of the set of digital features.
14 . The system of claim 13 , wherein identifying the two or more features based on the contribution measure associated with each feature of the set of digital features comprises:
determining a ranking of each feature of the set of digital features based on the contribution measure corresponding with each feature of the set of digital features; and
identifying the two or more features from the set of digital features based on the ranking of each feature of the set of digital features.
15 . The system of claim 9 , wherein:
the suggested recommendation is a recommendation to add a user account to a team associated with the target user account; and
the recommendation rationale indicates a reason the user account should be added to the team associated with the target user account.
16 . A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a computing device to:
provide a set of digital features to a machine learning model, the set of digital features associated with a target user account;
generate a suggested recommendation for the target user account by processing the set of digital features with the machine learning model;
generate a recommendation rationale for the suggested recommendation based on two or more features from the set of digital features, wherein the recommendation rationale comprises a generated text description explaining how respective features of the two or more features contributed to the suggested recommendation; and
trigger a client device associated with the target user account to display a recommendation notification comprising the suggested recommendation and the recommendation rationale within a content-management user interface associated with creating or modifying one or more digital content items accessible by the target user account.
17 . The non-transitory computer readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
generate the generated text description to include an indication of a number of common digital content items that both the target user account and the suggested recommendation have collaborated on.
18 . The non-transitory computer readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to perform the suggested recommendation in response to an indication of a user selection of a selectable option provided within the recommendation notification.
19 . The non-transitory computer readable medium of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
generate the generated text description to include an indication of a frequency of collaboration between the target user account and the suggested recommendation on a digital content item.
20 . The non-transitory computer readable medium of claim 16 , wherein the suggested recommendation is a recommendation to add a user account to a team associated with the target user account.