公开(公告)号：US11799835B2

公开(公告)日：2023-10-24

申请号：US17322360

申请日：2021-05-17

Applicant: Box, Inc.

Inventor： Kave Eshghi

IPC: H04L29/06 ,  H04L9/40 ,  G06F16/901 ,  G06N7/01

CPC classification number: H04L63/029 ,  G06F16/9024 ,  G06N7/01 ,  H04L63/1425

Abstract: Disclosed is an improved systems, methods, and computer program products that use a cluster-based probability model to perform anomaly detection, where the clusters are based upon entities and interactions that exist in content management platforms.

公开(公告)号：US20220086518A1

公开(公告)日：2022-03-17

申请号：US17163222

申请日：2021-01-29

Applicant: Box, Inc.

Inventor： Victor De Vansa Vikramaratne ,  Kave Eshghi ,  David Vengerov

IPC: H04N21/262 ,  H04N21/254

Abstract: Content object operations over content objects of a content management system are prioritized to be performed immediately, or at a later time. The immediate scheduling of an operation is determined by policies, rules, and/or predictive model outcomes. The determination for later time scheduling is based on analysis of a history of events on content objects. If the content object operation is deemed to be at least potentially delayable to a later time, then a scheduling model is consulted to determine an urgency of performing the content object operation on the content object. The urgency value resulting from consulting the scheduling model is combined with then-current resource availability to determine a timeframe for performance of the content object operation on the content object relative to other entries in a continuously updated list of to-be-performed operations. The performance of the content object operation on the content object is initiated in due course.

公开(公告)号：US20240137379A1

公开(公告)日：2024-04-25

申请号：US18492714

申请日：2023-10-22

Applicant: Box, Inc.

Inventor： Kave Eshghi ,  Victor De Vansa Vikramaratne

IPC: H04L9/40 ,  H04L67/1097 ,  H04L67/50

CPC classification number: H04L63/1425 ,  H04L63/1416 ,  H04L63/20 ,  H04L67/1097 ,  H04L67/535 ,  G06N20/00

Abstract: Disclosed is an improved systems, methods, and computer program products that performs user behavior analysis to identify malicious behavior in a computing system. The approach may be implemented by generating feature vectors for two time periods, performing scoring, and then performing anomaly detection.

公开(公告)号：US20220108065A1

公开(公告)日：2022-04-07

申请号：US16948831

申请日：2020-10-01

Applicant: Box, Inc.

Inventor： Kave Eshghi ,  Victor De Vansa Vikramaratne

IPC: G06F40/186 ,  G06F16/16 ,  G06F16/14

Abstract: Methods, systems and computer program products for content management systems. A content management system is configured to manage a plurality of content objects. Unsupervised learning is performed over the plurality of content objects to identify document templates that are associated with content objects taken from the plurality of content objects. When a document template is identified, then template metadata is associated with the document template. Additional content objects that are similar to the document template can take on the template metadata as well. In this way, many documents can be automatically populated with template metadata that corresponds to the identified document template. All or portions of the template metadata can be applied to policies, which policies serve to marshal ongoing document handling operations. During learning, document features are extracted and analyzed so as to define feature clusters, which feature clusters are in turn are used to form document template clusters.

公开(公告)号：US20220245477A1

公开(公告)日：2022-08-04

申请号：US17163243

申请日：2021-01-29

Applicant: Box, Inc.

Inventor： Kave Eshghi ,  Victor De Vansa Vikramaratne

IPC: G06N5/04 ,  G06N20/00 ,  G06F21/62

Abstract: Methods, systems, and computer program products for content management systems. An unlabeled dataset comprising documents that at least potentially comprise personally identifiable information (PII) is used when training a PII content classifier. Such a classifier is trained by (1) determining, based on applying a PII rule to a first portion of a document selected from the unlabeled dataset, a confidence value that the first portion of the document does contain personally identifiable information, (2) selecting a second portion of the document selected from the unlabeled dataset such that the second portion does not include the first portion; and (3) assigning, based on the confidence value, a likelihood value that corresponds to whether characteristics of the second portion are indicative that the document does contain personally identifiable information. Such a PII content classifier is used over selected portions of subject content objects to determine whether the selected portions contain PII.

公开(公告)号：US20210099475A1

公开(公告)日：2021-04-01

申请号：US16948779

申请日：2020-09-30

Applicant: Box, Inc.

Inventor： Kave Eshghi ,  Victor De Vansa Vikramaratne

IPC: H04L29/06 ,  H04L29/08

Abstract: Disclosed is an improved systems, methods, and computer program products that performs user behavior analysis to identify malicious behavior in a computing system. The approach may be implemented by generating feature vectors for two time periods, performing scoring, and then performing anomaly detection.

公开(公告)号：US20200076768A1

公开(公告)日：2020-03-05

申请号：US16115069

申请日：2018-08-28

Applicant: Box, Inc.

Inventor： Kave Eshghi

IPC: H04L29/06 ,  G06F17/30 ,  G06N7/00

Abstract: Disclosed is an improved systems, methods, and computer program products that use a cluster-based probability model to perform anomaly detection, where the clusters are based upon entities and interactions that exist in content management platforms.