Patents by Inventor Xiaohui Xie

Xiaohui Xie has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12182212
    Abstract: The present disclosure relates to a method and an apparatus, an electronic device and a storage medium for web search. The method includes: acquiring a steady-state visual evoked potential in EEG information, where the steady-state visual evoked potential is generated when a user gazes at a key on a query inputting keyboard in a visual spelling page; sending the steady-state visual evoked potential to a server, such that the server, based on the steady-state visual evoked potential, determines a character string inputted by the user, and a landing page corresponding to the character string; and in response to receiving the landing page sent by the server, displaying the landing page.
    Type: Grant
    Filed: November 7, 2022
    Date of Patent: December 31, 2024
    Assignee: Tsinghua University
    Inventors: Yiqun Liu, Xuesong Chen, Xiaohui Xie, Ziyi Ye, Shuqi Zhu, Weihang Su, Xiaorong Gao, Yike Sun, Min Zhang, Shaoping Ma
  • Patent number: 12096082
    Abstract: In some embodiments, a method determines a reward metric based on feedback for an instance of content. A delivery status for a delivery constraint of the instance of content is applied to the reward metric to generate a constrained reward metric. The method uses the constrained reward metric to train a model. The model is used to select from a plurality of instances of content. One of the plurality of instances of content is selected for delivery using the model.
    Type: Grant
    Filed: December 6, 2022
    Date of Patent: September 17, 2024
    Assignee: HULU, LLC
    Inventors: Pengfei Gao, Dingming Wu, Chunyang Wei, Xiaohui Xie, Shulei Ma
  • Publication number: 20240276058
    Abstract: A video-based interaction method includes playing a video on a video playback interface to which a target object is logged in, acquiring a local viewing marking record of the video and scene identifiers of markable scene clips in the video, comparing the local viewing marking record with the scene identifiers to determine an unmarked target scene clip in the video, displaying, in response to playing to the target scene clip and on the video playback interface, a target scene clip marking entry that indicates performing viewing marking on the target scene clip, and displaying a viewing marking credential for the target clip in response to a viewing marking trigger operation on the target scene clip marking entry. The viewing marking credential covers a part of the video playback interface, is an independent operable object, and includes description information of the video and identity information of the target object.
    Type: Application
    Filed: April 23, 2024
    Publication date: August 15, 2024
    Inventors: Xiaoxiao LIN, Jiandong LIU, Youhua HE, Yibin ZHANG, Yihong CAI, Dingpan CHEN, Kongkang ZHU, Xiangbao SU, Xiaohui XIE, Hao ZHANG
  • Publication number: 20240137620
    Abstract: In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.
    Type: Application
    Filed: January 2, 2024
    Publication date: April 25, 2024
    Applicant: HULU, LLC
    Inventors: Pengyu Zhao, Chunxu Xu, Xianghui Mao, Xiaohui Xie
  • Patent number: 11902628
    Abstract: In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.
    Type: Grant
    Filed: July 13, 2021
    Date of Patent: February 13, 2024
    Assignee: HULU, LLC
    Inventors: Pengyu Zhao, Chunxu Xu, Xianghui Mao, Xiaohui Xie
  • Patent number: 11880376
    Abstract: In some embodiments, a method receives a sequence of subsidiary features that are associated with a sequence of main features. A subsidiary feature provides subsidiary information for a main feature. A sequence of first weights for the sequence of subsidiary features is generates where a first weight in the sequence of first weights is generated based on a respective subsidiary feature. The method processes the sequence of first weights to generate a sequence of second weights. The processing uses relationships in the sequence of first weights to generate values of the second weights. The method uses the sequence of second weights to process the sequence of main features to generate an output for the sequence of main features.
    Type: Grant
    Filed: August 3, 2021
    Date of Patent: January 23, 2024
    Assignee: HULU, LLC
    Inventors: Pengyu Zhao, Chunxu Xu, Xianghui Mao, Xiaohui Xie
  • Publication number: 20230291946
    Abstract: In some embodiments, a method receives a line item factor for a line item at a first model. The method receives a competition factor at a second model. The first model generates a first value for a representation parameter based on the line item factor. The representation parameter is used to generate a representation for estimating selection of the instance of supplemental content for the line item for delivery. The second model generates a modification factor based on the competition factor. The modification factor is configured to modify the first value for the representation parameter based on competition from other line items to select the instance of supplemental content for the line item for delivery. The method modifies the first value for the representation parameter using the modification factor to generate a second value for the representation parameter where the second value is used to generate the representation.
    Type: Application
    Filed: March 30, 2022
    Publication date: September 14, 2023
    Inventors: Qingying CHEN, Hanqi WANG, Dingming WU, Chunyang WEI, Xiaohui XIE
  • Publication number: 20230169130
    Abstract: The present disclosure relates to a method and an apparatus, an electronic device and a storage medium for web search. The method includes: acquiring a steady-state visual evoked potential in EEG information, where the steady-state visual evoked potential is generated when a user gazes at a key on a query inputting keyboard in a visual spelling page; sending the steady-state visual evoked potential to a server, such that the server, based on the steady-state visual evoked potential, determines a character string inputted by the user, and a landing page corresponding to the character string; and in response to receiving the landing page sent by the server, displaying the landing page.
    Type: Application
    Filed: November 7, 2022
    Publication date: June 1, 2023
    Inventors: YIQUN LIU, XUESONG CHEN, XIAOHUI XIE, ZIYI YE, SHUQI ZHU, WEIHANG SU, XIAORONG GAO, YIKE SUN, MIN ZHANG, Shaoping Ma
  • Publication number: 20230096951
    Abstract: In some embodiments, a method determines a reward metric based on feedback for an instance of content. A delivery status for a delivery constraint of the instance of content is applied to the reward metric to generate a constrained reward metric. The method uses the constrained reward metric to train a model. The model is used to select from a plurality of instances of content. One of the plurality of instances of content is selected for delivery using the model.
    Type: Application
    Filed: December 6, 2022
    Publication date: March 30, 2023
    Applicant: HULU, LLC
    Inventors: Pengfei Gao, Dingming Wu, Chunyang Wei, Xiaohui Xie, Shulei Ma
  • Publication number: 20230040419
    Abstract: In some embodiments, a method receives a sequence of subsidiary features that are associated with a sequence of main features. A subsidiary feature provides subsidiary information for a main feature. A sequence of first weights for the sequence of subsidiary features is generates where a first weight in the sequence of first weights is generated based on a respective subsidiary feature. The method processes the sequence of first weights to generate a sequence of second weights. The processing uses relationships in the sequence of first weights to generate values of the second weights. The method uses the sequence of second weights to process the sequence of main features to generate an output for the sequence of main features.
    Type: Application
    Filed: August 3, 2021
    Publication date: February 9, 2023
    Inventors: Pengyu ZHAO, Chunxu XU, Xianghui MAO, Xiaohui XIE
  • Patent number: 11564013
    Abstract: In some embodiments, a method receives a history of videos that were viewed on a video delivery system as a first sentence in a sequential order and a target video as a second sentence as input to a prediction network. The prediction network analyzes representations for the history of videos and a representation of the target video. The prediction network generates a session representation based on bidirectionally analyzing a sequence of the first representations and the second representation. The method uses the session representation to determine whether to recommend the target video.
    Type: Grant
    Filed: October 19, 2020
    Date of Patent: January 24, 2023
    Assignee: HULU, LLC
    Inventors: Peng Wang, Yunsheng Jiang, Diman Shen, Yaqi Wang, Xiaohui Xie, Brian Thomas Morrison
  • Publication number: 20230019564
    Abstract: In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.
    Type: Application
    Filed: July 13, 2021
    Publication date: January 19, 2023
    Inventors: Pengyu ZHAO, Chunxu XU, Xianghui MAO, Xiaohui XIE
  • Patent number: 11546665
    Abstract: In some embodiments, a method receives a request for supplemental content to be provided in association with main content. The method selects an instance of supplemental content based on a long-term reward metric and a short-term reward metric. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and a delivery status for a delivery constraint of one instance of supplemental content. The short-term reward metric is based on feedback from delivery of the one instance of supplemental content. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and the short-term reward metric is based on feedback from delivery of one instance of supplemental content. The instance of supplemental content is provided to a client device.
    Type: Grant
    Filed: May 7, 2021
    Date of Patent: January 3, 2023
    Assignee: HULU, LLC
    Inventors: Pengfei Gao, Dingming Wu, Chunyang Wei, Xiaohui Xie, Shulei Ma
  • Publication number: 20220360854
    Abstract: In some embodiments, a method receives a request for supplemental content to be provided in association with main content. The method selects an instance of supplemental content based on a long-term reward metric and a short-term reward metric. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and a delivery status for a delivery constraint of one instance of supplemental content. The short-term reward metric is based on feedback from delivery of the one instance of supplemental content. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and the short-term reward metric is based on feedback from delivery of one instance of supplemental content. The instance of supplemental content is provided to a client device.
    Type: Application
    Filed: May 7, 2021
    Publication date: November 10, 2022
    Inventors: Pengfei Gao, Dingming Wu, Chunyang Wei, Xiaohui Xie, Shulei Ma
  • Patent number: 11481438
    Abstract: In some embodiments, a method selects a sequence of programs watched by a user account. The method calculates a first set of weights based on comparing content of the sequence of programs to content of a target program and calculates a second set of weights based on an order of the sequence of the programs and the first of weights. The first set of weights and the second set of weights are applied to the sequence of programs to generate a prediction of a similarity of the sequence of programs to the target program. Then, the method outputs the prediction of the similarity for use in determining a recommendation for the user account.
    Type: Grant
    Filed: October 6, 2020
    Date of Patent: October 25, 2022
    Assignee: HULU, LLC
    Inventors: Kaiwen Deng, Yunsheng Jiang, Xiaohui Xie, Brian Morrison, Jiarui Yang, Christopher Russell Kehler
  • Patent number: 11416546
    Abstract: In one embodiment, a method receives a set of frames from a video at a first classifier. The first classifier classifies the set of frames with classification scores that indicate a confidence that a frame contains end credit content using the first classifier using a first model that classifies content from the set of frames. A second classifier then refines the classification scores from neighboring frames in the set of frames using a second classifier using a second model that classifies classification scores from the first classifier. A boundary point is selected between a frame in the set of frames considered not including end credit content and a frame in the set of frames including end credit content based on the refined classification scores.
    Type: Grant
    Filed: March 20, 2018
    Date of Patent: August 16, 2022
    Assignee: HULU, LLC
    Inventors: Yunsheng Jiang, Xiaohui Xie, Liangliang Li
  • Patent number: 11383997
    Abstract: A method for ecologic configuration of an oil production wastewater artificial wetland to realize up-to-standard operation in winter. When artificial wetland is utilized to treat oil production high-salt wastewater, ecologic configuration of subsurface and surface flow artificial wetland is modified to realize up-to-standard operation in winter. Subsurface flow artificial wetland is composed of soil matrix, water distribution pipe disposed on bottom of soil matrix, wrapped with water-permeable nonwoven cloth and configured to deliver wastewater, and reeds with root systems growing on an inner side of wall of water distribution pipe, stems growing on outer side of wall of water distribution pipe and length being greater than thickness of soil matrix; and surface flow artificial wetland is composed of soil matrix, reeds growing on matrix, water, winter aquatic salt-resistant cold-liking plants, block-stocked fishes, shrimps, crabs, mussels, Mytilus edulis, oysters or clams and artificial sand dam.
    Type: Grant
    Filed: July 5, 2019
    Date of Patent: July 12, 2022
    Assignees: GUDONG PETROLEUM PRODUCTION FACTORY SHENGLI OILFIELD OF SINOPEC, DONGYING ZHENGZE ENVIRONMENTAL TECHNOLOGY CO., LTD., SHANDONG UNIVERSITY
    Inventors: Chunbo Liu, Wei Hu, Wanguo Hou, Xian Zhao, Zhaohui Shang, Jianbo Ma, Yongtao Gu, Haifeng He, Jingen Yan, Zhimin Peng, Guodong Meng, Xiaohui Xie
  • Publication number: 20220124409
    Abstract: In some embodiments, a method receives a history of videos that were viewed on a video delivery system as a first sentence in a sequential order and a target video as a second sentence as input to a prediction network. The prediction network analyzes representations for the history of videos and a representation of the target video. The prediction network generates a session representation based on bidirectionally analyzing a sequence of the first representations and the second representation. The method uses the session representation to determine whether to recommend the target video.
    Type: Application
    Filed: October 19, 2020
    Publication date: April 21, 2022
    Inventors: Peng WANG, Yunsheng JIANG, Diman SHEN, Yaqi WANG, Xiaohui XIE, Brian Thomas MORRISON
  • Publication number: 20210403355
    Abstract: A method for ecologic configuration of an oil production wastewater artificial wetland to realize up-to-standard operation in winter. When artificial wetland is utilized to treat oil production high-salt wastewater, ecologic configuration of subsurface and surface flow artificial wetland is modified to realize up-to-standard operation in winter. Subsurface flow artificial wetland is composed of soil matrix, water distribution pipe disposed on bottom of soil matrix, wrapped with water-permeable nonwoven cloth and configured to deliver wastewater, and reeds with root systems growing on an inner side of wall of water distribution pipe, stems growing on outer side of wall of water distribution pipe and length being greater than thickness of soil matrix; and surface flow artificial wetland is composed of soil matrix, reeds growing on matrix, water, winter aquatic salt-resistant cold-liking plants, block-stocked fishes, shrimps, crabs, mussels, Mytilus edulis, oysters or clams and artificial sand dam.
    Type: Application
    Filed: July 5, 2019
    Publication date: December 30, 2021
    Applicants: GUDONG PETROLEUM PRODUCTION FACTORY SHENGLI OILFIELD OF SINOPEC, DONGYING ZHENGZE ENVIRONMENTAL TECHNOLOGY CO., LTD., SHANDONG UNIVERSITY
    Inventors: Chunbo LIU, Wei HU, Wanguo HOU, Xian ZHAO, Zhaohui SHANG, Jianbo MA, Yongtao GU, Haifeng HE, Jingen YAN, Zhimin PENG, Guodong MENG, Xiaohui XIE
  • Publication number: 20210374178
    Abstract: In some embodiments, a method selects a sequence of programs watched by a user account. The method calculates a first set of weights based on comparing content of the sequence of programs to content of a target program and calculates a second set of weights based on an order of the sequence of the programs and the first of weights. The first set of weights and the second set of weights are applied to the sequence of programs to generate a prediction of a similarity of the sequence of programs to the target program. Then, the method outputs the prediction of the similarity for use in determining a recommendation for the user account.
    Type: Application
    Filed: October 6, 2020
    Publication date: December 2, 2021
    Inventors: Kaiwen Deng, Yunsheng Jiang, Xiaohui Xie, Brian Morrison, Jiarui Yang, Christopher Russell Kehler