Patents by Inventor Peihong LI

Peihong LI 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: 12380180
    Abstract: A method and an apparatus for few-shot relation classification and filtering, and a device are provided. The method includes: constructing a coarse-grained filter for filtering an unlabeled corpus to obtain candidate instances with a same entity as a seed instance and with similar semantics to the seed instance; constructing a fine-grained filter for filtering the candidate instances to obtain a candidate instance with a same relation concept as the seed instance; defining the candidate instance as a positive instance set, and defining candidate instances with different relation concepts from the seed instance as a negative sample set; constructing a false positive instance correction module for adjusting and controlling a proportion of the negative sample set used by a classifier during training; training the classifier based on a small number of obtained labeled instances belonging to a newly emerging relation and the adjusted positive instance set and negative sample set.
    Type: Grant
    Filed: August 26, 2024
    Date of Patent: August 5, 2025
    Assignee: National University of Defense Technology
    Inventors: Fei Cai, Peihong Li, Honghui Chen, Jianming Zheng, Taihua Shao, Mengru Wang, Siyuan Wang, Dengfeng Liu, Yanying Mao
  • Patent number: 12299584
    Abstract: A method and apparatus for training a few-shot event detection model based on multilingual prompt learning are provided, which includes: acquiring a training data set, applying a multilingual prompt model to any instance to obtain a predicted probability distribution of a trigger tag, so as to obtain a first loss; generating a contrastive instance and a bilingual instance, and performing multilingual prompt and cross-lingual encoding according to the input instance and the bilingual instance by applying the multilingual prompt model to obtain joint event characterization; performing event tag prediction on the joint event characterization by applying a two-level hierarchical prototype network model, and calculating a second loss; performing contrastive learning on respective instances by applying a quaternary contrastive learning module to obtain a third loss; determining a total loss of the few-shot event detection model according to respective losses, and performing model training optimization based on the
    Type: Grant
    Filed: July 16, 2024
    Date of Patent: May 13, 2025
    Assignee: National University of Defense Technology
    Inventors: Fei Cai, Siyuan Wang, Jianming Zheng, Wanyu Chen, Dengfeng Liu, Peihong Li, Shixian Liu, Xueshan Luo
  • Publication number: 20250068700
    Abstract: A method and an apparatus for few-shot relation classification and filtering, and a device are provided. The method includes: constructing a coarse-grained filter for filtering an unlabeled corpus to obtain candidate instances with a same entity as a seed instance and with similar semantics to the seed instance; constructing a fine-grained filter for filtering the candidate instances to obtain a candidate instance with a same relation concept as the seed instance; defining the candidate instance as a positive instance set, and defining candidate instances with different relation concepts from the seed instance as a negative sample set; constructing a false positive instance correction module for adjusting and controlling a proportion of the negative sample set used by a classifier during training; training the classifier based on a small number of obtained labeled instances belonging to a newly emerging relation and the adjusted positive instance set and negative sample set.
    Type: Application
    Filed: August 26, 2024
    Publication date: February 27, 2025
    Inventors: Fei CAI, Peihong Li, Honghui Chen, Jianming Zheng, Taihua Shao, Mengru Wang, Siyuan Wang, Dengfeng Liu, Yanying Mao
  • Publication number: 20250028967
    Abstract: A method and apparatus for training a few-shot event detection model based on multilingual prompt learning are provided, which includes: acquiring a training data set, applying a multilingual prompt model to any instance to obtain a predicted probability distribution of a trigger tag, so as to obtain a first loss; generating a contrastive instance and a bilingual instance, and performing multilingual prompt and cross-lingual encoding according to the input instance and the bilingual instance by applying the multilingual prompt model to obtain joint event characterization; performing event tag prediction on the joint event characterization by applying a two-level hierarchical prototype network model, and calculating a second loss; performing contrastive learning on respective instances by applying a quaternary contrastive learning module to obtain a third loss; determining a total loss of the few-shot event detection model according to respective losses, and performing model training optimization based on the
    Type: Application
    Filed: July 16, 2024
    Publication date: January 23, 2025
    Inventors: Fei CAI, Siyuan WANG, Jianming ZHENG, Wanyu CHEN, Dengfeng LIU, Peihong LI, Shixian LIU, Xueshan LUO
  • Publication number: 20200057329
    Abstract: A thin film transistor (TFT) array substrate and a manufacturing method of same are provided. The TFT array substrate includes a TFT array layer, a color filter layer, and a passivation layer. The color filter layer includes a blue sub-pixel, and the passivation layer includes a passivation layer body and a plurality of protrusions protruding on the passivation layer body. By forming the protrusions of the passivation layer on two side areas of the blue sub-pixel of the color filter layer, a photoresist on the two side areas of the blue sub-pixel is increased, such that a thickness of the passivation layer is uniformized, this reduces chromaticity difference.
    Type: Application
    Filed: September 13, 2018
    Publication date: February 20, 2020
    Applicant: Wuhan China Star Optoelectronics Semiconductor Display Technology Co., Ltd.
    Inventors: Peihong LI, Jiangjiang SONG
  • Patent number: D887356
    Type: Grant
    Filed: July 9, 2018
    Date of Patent: June 16, 2020
    Assignee: GUANGZHOU CITY POOJIN ELECTRONIC TECHNOLOGY CO., LTD
    Inventor: Peihong Li
  • Patent number: D1052526
    Type: Grant
    Filed: December 8, 2023
    Date of Patent: November 26, 2024
    Assignee: Guangzhou Poojin Electronic Co., Ltd.
    Inventor: Peihong Li