Patents by Inventor Yuan-Lin Yang

Yuan-Lin Yang 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: 11521602
    Abstract: A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.
    Type: Grant
    Filed: May 10, 2021
    Date of Patent: December 6, 2022
    Assignee: International Business Machines Corporation
    Inventors: Zhong Fang Yuan, Kun Yan Yin, Yuan Lin Yang, Tong Liu, He Li
  • Publication number: 20210264906
    Abstract: A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.
    Type: Application
    Filed: May 10, 2021
    Publication date: August 26, 2021
    Inventors: Zhong Fang Yuan, Kun Yan Yin, Yuan Lin Yang, Tong Liu, He Li
  • Patent number: 11069346
    Abstract: A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.
    Type: Grant
    Filed: April 22, 2019
    Date of Patent: July 20, 2021
    Assignee: International Business Machines Corporation
    Inventors: Zhong Fang Yuan, Kun Yan Yin, Yuan Lin Yang, Tong Liu, He Li
  • Patent number: 11032217
    Abstract: Automated multi-round task-based conversation with a user is disclosed. In a first round conversation between a user and a data processing system involving first task(s), the data processing system cognitively identifies first entity(ies) and one or more first intent(s), based on a first input statement received by the data processing system from the user. In a subsequent second round conversation between the user and the data processing system involving second task(s) different from the first task(s), the data processing system cognitively identifies second entity(ies) and second intent(s), based on a second input statement received by the data processing system from the user. The data processing system reuses at least one of the first entity(ies) in the second round conversation.
    Type: Grant
    Filed: November 30, 2018
    Date of Patent: June 8, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Xin Liu, Hai Ji, Yuan Lin Yang, Zhu Lin Zhang
  • Patent number: 10878197
    Abstract: A machine-learning component of a conversational user-interface system retrieves records of human question-and-answer sessions from heterogenous sources. A sequence of image-processing operations converts each source into a set of grayscale images. Each image is segmented into disjoint sections as a function of the textures, edges, and contours that make up the image's content. Each section is tagged with a vector of parametric values that identify characteristics of the section's content from which may be inferred semantic meaning. A cognitive function intelligently analyzes the vectors to classify each section as containing a question, an answer to a question, non-textual media, or other types of content. Another cognitive function merges and organizes the sections into question-answer pairs and the vectors associated with each pair are stored in a corpus that is submitted to the self-learning user interface during a machine-learning training session.
    Type: Grant
    Filed: November 27, 2018
    Date of Patent: December 29, 2020
    Assignee: International Business Machines Corporation
    Inventors: Kun Yan Yin, He Li, Yuan Lin Yang, Jian Hui Bj Chen, Shun Sp Wen, Zhong Fang Yuan
  • Publication number: 20200335095
    Abstract: A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.
    Type: Application
    Filed: April 22, 2019
    Publication date: October 22, 2020
    Inventors: Zhong Fang Yuan, Kun Yan Yin, Yuan Lin Yang, Tong Liu, He Li
  • Publication number: 20200177527
    Abstract: Automated multi-round task-based conversation with a user is disclosed. In a first round conversation between a user and a data processing system involving first task(s), the data processing system cognitively identifies first entity(ies) and one or more first intent(s), based on a first input statement received by the data processing system from the user. In a subsequent second round conversation between the user and the data processing system involving second task(s) different from the first task(s), the data processing system cognitively identifies second entity(ies) and second intent(s), based on a second input statement received by the data processing system from the user. The data processing system reuses at least one of the first entity(ies) in the second round conversation.
    Type: Application
    Filed: November 30, 2018
    Publication date: June 4, 2020
    Inventors: Xin LIU, Hai JI, Yuan Lin YANG, Zhu Lin ZHANG
  • Publication number: 20200167420
    Abstract: A machine-learning component of a conversational user-interface system retrieves records of human question-and-answer sessions from heterogenous sources. A sequence of image-processing operations converts each source into a set of grayscale images. Each image is segmented into disjoint sections as a function of the textures, edges, and contours that make up the image's content. Each section is tagged with a vector of parametric values that identify characteristics of the section's content from which may be inferred semantic meaning. A cognitive function intelligently analyzes the vectors to classify each section as containing a question, an answer to a question, non-textual media, or other types of content. Another cognitive function merges and organizes the sections into question-answer pairs and the vectors associated with each pair are stored in a corpus that is submitted to the self-learning user interface during a machine-learning training session.
    Type: Application
    Filed: November 27, 2018
    Publication date: May 28, 2020
    Inventors: Kun Yan Yin, He Li, Yuan Lin Yang, Jian Hui BJ Chen, Shun SP Wen, Zhong Fang Yuan
  • Patent number: 10664440
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Grant
    Filed: February 9, 2017
    Date of Patent: May 26, 2020
    Assignee: International Business Machines Corporation
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Patent number: 10545911
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Grant
    Filed: April 24, 2019
    Date of Patent: January 28, 2020
    Assignee: International Business Machines Corporation
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Patent number: 10545912
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Grant
    Filed: April 24, 2019
    Date of Patent: January 28, 2020
    Assignee: International Business Machines Corporation
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Publication number: 20190251059
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Application
    Filed: April 24, 2019
    Publication date: August 15, 2019
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Publication number: 20190251060
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Application
    Filed: April 24, 2019
    Publication date: August 15, 2019
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Patent number: 10216743
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Grant
    Filed: February 19, 2018
    Date of Patent: February 26, 2019
    Assignee: International Business Machines Corporation
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Publication number: 20180225294
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Application
    Filed: February 9, 2017
    Publication date: August 9, 2018
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Publication number: 20180225295
    Abstract: A computing system performs file conversion upon format expiration. A computing system evaluates a risk of expiration of a first format associated with a first format object. The computing system determines if the risk of expiration is above a threshold. The computing system identifies in response to determining the risk of expiration is above the threshold, one or more files stored in the first format for conversion. The computing system converts one or more files stored in the first format to a second format. The computing system saves the one or more files in the second format.
    Type: Application
    Filed: February 19, 2018
    Publication date: August 9, 2018
    Inventors: Yu Fen Chang, Peng Hui Jiang, Dong Rui Li, Lin Sun, Li Xiang, Ting Xie, Yuan Lin Yang
  • Publication number: 20130056070
    Abstract: Disclosed is an apparatus and method for generating inverted organic solar cells and which required no electron selective layer, were fabricated and their power conversion efficiency was found to improve irreversibly with post-processing light soaking for a period. X-Ray photoelectron spectroscopy characterization further revealed segregation in surface composition at the interface and was found to explain the current density-voltage measurements. In addition, the light soaked devices were found to exhibit an extended lifetime as compared to conventional devices. Since no electron selective layer was required, light soaking may be considered as a cost-effective method to achieve efficient inverted organic solar cells.
    Type: Application
    Filed: December 22, 2011
    Publication date: March 7, 2013
    Inventors: Sheng-Fu Horng, Jen-Chun Wang, Cheng-Yueh Lu, Jui-Lin Hsu, Ming-Kun Lee, Yun-Ru Hong, Hsin-Fei Meng, Yuan-Lin Yang, Tsung-Te Chen