公开(公告)号：US10747786B2

公开(公告)日：2020-08-18

申请号：US16051447

申请日：2018-07-31

Applicant: Box, Inc.

Inventor： Sesh Jalagam ,  Matthew DeLand ,  Victor De Vansa Vikramaratne

IPC: G06F16/28 ,  H04L29/06 ,  H04L29/08 ,  G06F16/27 ,  G06Q10/10

Abstract: Systems for forming and maintaining spontaneous networks of collaborators in shared content management systems. A shared content management system supports user interactions with content objects. A service of the content management system monitors occurrences of interactions between users and objects. The users are associated with collaboration groups. To generate recommendations of groups other than the collaboration group or groups in which a particular user is already a member, a method embodiment receives entity relationship scores from the service. An entity relationship score quantifies a relationship between two subject entities that are common to a particular entity interaction event. The method then assigns the subject entities to one or more spontaneously-generated clusters. As clusters are formed and populated, cluster affinity scores are continuously calculated. Periodically, a recommended cluster is selected based on a corresponding cluster affinity score. A recommended cluster is named based on the member entities of the recommended cluster.

公开(公告)号：US20190034885A1

公开(公告)日：2019-01-31

申请号：US16051442

申请日：2018-07-31

Applicant: Box, Inc.

Inventor： Matthew DeLand ,  Victor De Vansa Vikramaratne

IPC: G06Q10/10 ,  G06Q10/02 ,  G06F17/30

Abstract: Systems and methods for forming collaboration recommendations. Techniques for forming event-based recommendations use time-decayed event values. A shared content management system supports a plurality of users that generate events by interacting with content objects of the shared content management system. Events over the content objects are captured as event objects. Method steps are invoked upon receiving event objects that describes user-to-object interaction events that arise from interactions by users over content objects. Different types of interactions carry different importance values. The importance values can be applied as weights when scoring user-to-object interaction activities. The importance can decay over time. As time progresses and as the importance of older interactions decay, score components of a user-to-object interaction can be updated based at least in part on a time decay function. The system emits collaboration recommendations based on the decayed user-to-user collaboration scores.

公开(公告)号：US20230401537A1

公开(公告)日：2023-12-14

申请号：US18333496

申请日：2023-06-12

Applicant: Box, Inc.

Inventor： Matthew DeLand ,  Victor De Vansa Vikramaratne

IPC: G06Q10/1093 ,  G06Q10/02 ,  G06F16/435 ,  G06F16/48

CPC classification number: G06Q10/1093 ,  G06Q10/02 ,  G06F16/437 ,  G06F16/489

Abstract: Systems and methods for forming collaboration recommendations. Techniques for forming event-based recommendations use time-decayed event values. A shared content management system supports a plurality of users that generate events by interacting with content objects of the shared content management system. Events over the content objects are captured as event objects. Method steps are invoked upon receiving event objects that describes user-to-object interaction events that arise from interactions by users over content objects. Different types of interactions carry different importance values. The importance values can be applied as weights when scoring user-to-object interaction activities. The importance can decay over time. As time progresses and as the importance of older interactions decay, score components of a user-to-object interaction can be updated based at least in part on a time decay function. The system emits collaboration recommendations based on the decayed user-to-user collaboration scores.

公开(公告)号：US11710102B2

公开(公告)日：2023-07-25

申请号：US16051442

申请日：2018-07-31

Applicant: Box, Inc.

Inventor： Matthew DeLand ,  Victor De Vansa Vikramaratne

IPC: G06Q10/00 ,  G06Q10/1093 ,  G06Q10/02 ,  G06F16/435 ,  G06F16/48

CPC classification number: G06Q10/1093 ,  G06F16/437 ,  G06F16/489 ,  G06Q10/02

Abstract: Systems and methods for forming collaboration recommendations. Techniques for forming event-based recommendations use time-decayed event values. A shared content management system supports a plurality of users that generate events by interacting with content objects of the shared content management system. Events over the content objects are captured as event objects. Method steps are invoked upon receiving event objects that describes user-to-object interaction events that arise from interactions by users over content objects. Different types of interactions carry different importance values. The importance values can be applied as weights when scoring user-to-object interaction activities. The importance can decay over time. As time progresses and as the importance of older interactions decay, score components of a user-to-object interaction can be updated based at least in part on a time decay function. The system emits collaboration recommendations based on the decayed user-to-user collaboration scores.

公开(公告)号：US20190034520A1

公开(公告)日：2019-01-31

申请号：US16051447

申请日：2018-07-31

Applicant: Box, Inc.

Inventor： Sesh Jalagam ,  Matthew DeLand ,  Victor De Vansa Vikramaratne

IPC: G06F17/30 ,  H04L29/08 ,  H04L29/06

CPC classification number: G06F16/288 ,  G06F16/27 ,  G06F16/285 ,  G06Q10/101 ,  H04L65/403 ,  H04L65/4084 ,  H04L65/605 ,  H04L67/10 ,  H04L67/1097 ,  H04L67/22

Abstract: Systems for forming and maintaining spontaneous networks of collaborators in shared content management systems. A shared content management system supports user interactions with content objects. A service of the content management system monitors occurrences of interactions between users and objects. The users are associated with collaboration groups. To generate recommendations of groups other than the collaboration group or groups in which a particular user is already a member, a method embodiment receives entity relationship scores from the service. An entity relationship score quantifies a relationship between two subject entities that are common to a particular entity interaction event. The method then assigns the subject entities to one or more spontaneously-generated clusters. As clusters are formed and populated, cluster affinity scores are continuously calculated. Periodically, a recommended cluster is selected based on a corresponding cluster affinity score. A recommended cluster is named based on the member entities of the recommended cluster.