公开(公告)号：US11290564B1

公开(公告)日：2022-03-29

申请号：US17220582

申请日：2021-04-01

Applicant: Thrive Market, Inc.

Inventor： Yang Liu ,  Mo Lin ,  Mohammad Sabah

IPC: G06N20/00 ,  H04L29/08 ,  H04L67/306

Abstract: Embodiments are provided that facilitate training and utilization of specially configured multi-armed bandit model(s). Such embodiments configure multi-armed bandit model(s) to provide selected network asset scoring model(s) from a network asset scoring model set and/or a selected data tagged network asset set from a set of data tagged network asset sets. Such selections are performable for a particular user profile, for example to perform accurate and/or efficient process(es) for provision of network asset data object(s) to the user profile(s). Some embodiments access enterprise network interaction data, access a set of data tagged network asset sets, train a multi-armed bandit model to provide a selected network asset scoring model and a selected data tagged network asset set, and provides one or more network asset data objects based on the selected network asset scoring model and the selected data tagged network asset set.

公开(公告)号：US12014394B2

公开(公告)日：2024-06-18

申请号：US18179649

申请日：2023-03-07

Applicant: Thrive Market, Inc.

Inventor： Pradyumna Siddhartha ,  Mohammad Sabah ,  Qiqi Ai ,  Mo Lin ,  Aakash Pathak

IPC: G06Q30/0242 ,  G06Q30/0217 ,  G06Q30/0251

CPC classification number: G06Q30/0245 ,  G06Q30/0218 ,  G06Q30/0269

Abstract: Embodiments of the present disclosure provide mechanisms for selection of a user survey data object from a set of user data objects, and processing of survey engagement data associated with a selected user survey data object. The user survey data object selected is appropriate for providing associated with a particular user data object, and the survey engagement data received associated therewith enables programmatic selection and use of particular ranking model(s) for use in generating and providing an output ranked item data object set. Example embodiments utilize selected ranking model(s) of a set of ranking models to programmatically generate and output an output ranked item data object set for a particular user profile.

公开(公告)号：US11876869B2

公开(公告)日：2024-01-16

申请号：US17654666

申请日：2022-03-14

Applicant: Thrive Market, Inc.

Inventor： Yang Liu ,  Mo Lin ,  Mohammad Sabah

IPC: H04L67/306 ,  G06N20/00

CPC classification number: H04L67/306 ,  G06N20/00

Abstract: Embodiments of the present disclosure provide for improved management, selection, and provision of network asset data objects. For example, embodiments described throughout are configured to score various network assets corresponding to real-world assets, items, products, and/or the like, for selection and provision associated with one or more particular user profile identifiers. Embodiments are configured to train network asset scoring model(s) based on specific data, such as prioritized network asset data set(s), such that the trained network asset scoring model(s) efficiently generate more accurate, improved scores for network asset data objects. Additional or alternative embodiments are configured to provide data tagged network asset set(s) utilizing specially trained model(s), such as one or more multi-armed bandit models and/or one or more network asset scoring model(s).

公开(公告)号：US11631106B2

公开(公告)日：2023-04-18

申请号：US17139904

申请日：2020-12-31

Applicant: Thrive Market, Inc.

Inventor： Pradyumna Siddhartha ,  Mohammad Sabah ,  Qiqi Ai ,  Mo Lin ,  Aakash Pathak

IPC: G06Q30/02 ,  G06Q30/0242 ,  G06Q30/0217 ,  G06Q30/0251

Abstract: Embodiments of the present disclosure provide mechanisms for selection of a user survey data object from a set of user data objects, and processing of survey engagement data associated with a selected user survey data object. The user survey data object selected is appropriate for providing associated with a particular user data object, and the survey engagement data received associated therewith enables programmatic selection and use of particular ranking model(s) for use in generating and providing an output ranked item data object set. Example embodiments utilize selected ranking model(s) of a set of ranking models to programmatically generate and output an output ranked item data object set for a particular user profile.