公开(公告)号：US20250053853A1

公开(公告)日：2025-02-13

申请号：US18232468

申请日：2023-08-10

Applicant: ROKU, INC.

Inventor： FEI XIAO ,  ZIDONG WANG ,  LIAN LIU ,  NAM VO ,  WEICONG DING ,  ABHISHEK BAMBHA ,  AMIT VERMA ,  AASISH SIPANI ,  ROHIT MAHTO ,  HOSSEIN DABIRIAN ,  JOSE SANCHEZ

IPC: G06N20/00

Abstract: Disclosed are system, method and/or computer program product embodiments for improving the performance of a machine learning based algorithm used to provide a user experience to a user via a media device. An embodiment selects a first set of hyperparameter values, implements a first iteration of the algorithm based on the first set of hyperparameter values, utilizes the first iteration of the algorithm to provide a first user experience to the user, determines a response of the user to the first user experience, selects, by a hyperparameter tuning ML model implemented as a contextual multi-arm bandit model or a reinforcement learning model and based on at least the response of the user, a second set of hyperparameter values, implements a second iteration of the algorithm based on the second set of hyperparameter values, and utilizes the second iteration of the algorithm to provide a second user experience to the user.

公开(公告)号：US20240129565A1

公开(公告)日：2024-04-18

申请号：US17965176

申请日：2022-10-13

Applicant: ROKU, INC.

Inventor： RAKESH RAVURU ,  ABHISHEK BAMBHA ,  JING LU ,  ZIDONG WANG ,  JING XIE

IPC: H04N21/25

CPC classification number: H04N21/251

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for candidate ranking for content recommendation. An embodiment operates by receiving category candidates over a network, wherein each of the category candidates comprises content candidates associated with one or more applications operating on media devices. The embodiment then ranks the category candidates based on a machine model trained using a learning algorithm based on the time series data, and ranks the content candidates in the each of category candidates based on the time series data. The embodiment then causes the ranked category candidates and the ranked content candidates to be outputted for display.

公开(公告)号：US20240214619A1

公开(公告)日：2024-06-27

申请号：US18089343

申请日：2022-12-27

Applicant: ROKU, INC.

Inventor： FEI XIAO ,  RONICA JETHWA ,  JING YE ,  ABHISHEK BAMBHA ,  ZIDONG WANG ,  JOSE SANCHEZ ,  NAM VO ,  KHALDUN AIDARABSAH ,  PULKIT AGGARWAL ,  LIAN LIU ,  ANIRBAN DAS ,  ROHIT MAHTO

IPC: H04N21/25 ,  H04N21/24 ,  H04N21/472

CPC classification number: H04N21/252 ,  H04N21/2407 ,  H04N21/472

Abstract: A set of content items can be accessed by a community of users having a set of interests. A set of interest based clusters for the set of content items correspond to the set of interests. For a user, a recommendation system can determine a group of user interest clusters selected from the set of interest based clusters. A popularity score for each content item of the set of content items with respect to the community of users can be generated, and an interest based popularity score for a content item within the interest based cluster can be generated based on a rank of the content item based on the popularity score of the content item. Recommendation candidates for the user can be generated based on the interest based popularity score of the content item for each content item in the group of user interest clusters.

公开(公告)号：US20240086466A1

公开(公告)日：2024-03-14

申请号：US17943526

申请日：2022-09-13

Applicant: ROKU, INC.

Inventor： FEI XIAO ,  RONICA JETHWA ,  ZIDONG WANG ,  JING LU ,  JING YE ,  NAM VO ,  JOSE SANCHEZ ,  ABHISHEK BAMBHA ,  KHALDUN AIDARABSAH

IPC: G06F16/906

CPC classification number: G06F16/906

Abstract: Disclosed herein are various embodiments, for a content display and clustering system. An example embodiment operates by receiving a request to display the plurality of content items. At each of multiple levels different pairs of content items are identified and a similarity score is computed for each pair. A subset of pairs for which their similarity score exceeds a similarity threshold for the respective level are identified and clustered. This process is repeated for one or more iterations at the same level, and then the process is repeated for each of the multiple levels. A final clustered subset is identified, and output for display, responsive to the request to display the plurality of content items.

公开(公告)号：US20240064354A1

公开(公告)日：2024-02-22

申请号：US17890491

申请日：2022-08-18

Applicant: ROKU, INC.

Inventor： FEI XIAO ,  ZIDONG WANG ,  JOSE SANCHEZ ,  ABHISHEK BAMBHA ,  RONICA JETHWA

IPC: H04N21/25 ,  H04N21/258

CPC classification number: H04N21/252 ,  H04N21/25891

Abstract: Disclosed are mechanisms for selecting a recommended item for a current item being viewed by a user account based on a view history of the user account with reduced bias. For a current item being viewed by the user account represented by a current node of a co-watch graph, embodiments can select a recommended item represented by an associated node in the co-watch graph likely being viewed by the user account, and determine a probability of the recommended item likely being viewed. The co-watch graph can be generated based on a view history of the user account. An edge between a first node and a second node of the co-watch graph can have a weight representing a number of co-occurrence times when the first item represented by the first node and the second item represented by the second node are viewed in sequence within a predetermined time interval.