Patents by Inventor Wenwen YE

Wenwen YE 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).

  • Publication number: 20250101185
    Abstract: A preparation method for a high-strength and high-biocompatibility silk fibroin hydrogel scaffold with a biomimetic microstructure for repair and reconstruction of tendons/ligaments. The preparation method includes processing a natural silk fibroin material through directional freezing and coaxial hot stretching. The heating temperature is higher than a glass transition temperature of the silk fibroin material, such that a maximum tensile strength of the silk fibroin hydrogel scaffold increases, a microscopic directional pore structure is formed, and finally a mechanically reinforced hydrogel scaffold with good biocompatibility is obtained. The artificial tendon/ligament scaffold prepared by using the hydrogel scaffold reaches mechanical strength similar to that of the tendons/ligaments in the human body and has good biocompatibility.
    Type: Application
    Filed: March 27, 2024
    Publication date: March 27, 2025
    Inventors: Weiliang SHEN, Wenwen HUANG, Hongwei OUYANG, Kexin NIE, Sicheng ZHOU, Boxuan WU, Jinchun YE
  • Patent number: 12223416
    Abstract: A neural network retraining method based on the aging sensing of memristors is provided. For the accuracy rate of hardware online reasoning decreases after cross-array aging, the extreme values of programmable weights under a current aging condition is calculated by using the known aging information of memristor, and a neural network model is retrained according to this, so as to improve the accuracy rate of the current hardware online reasoning. In the process of retraining, network weights exceeding the extreme values of programmable weights are automatically truncated. For the working life of the memristor, the sparsity of derivatives of the neural network is utilized to discard the derivatives with a small absolute value in hardware adjustment process, so as to ensure that the memristor corresponding to small derivatives would not be applied voltage, prevent the aging process of the memristors and prolong the service life thereof.
    Type: Grant
    Filed: April 29, 2022
    Date of Patent: February 11, 2025
    Assignee: ZHEJIANG UNIVERSITY
    Inventors: Xunzhao Yin, Wenwen Ye, Cheng Zhuo
  • Patent number: 12124528
    Abstract: Embodiments of the present disclosure disclose an image processing method and apparatus, and a computer readable storage medium. The method includes: obtaining at least one page image of a current full-screen page in a webpage application; converting the at least one page image into at least one file object, and creating at least one link path of the at least one file object, each of the at least one file object corresponding to the respective at least one link path; and creating at least one picture object, and associatively saving the at least one picture object and the at least one link path in webpage application cache to complete taking a screenshot of the current full-screen page. Through the embodiments of the present disclosure, the screenshot capturing performance of the webpage application can be improved.
    Type: Grant
    Filed: March 29, 2021
    Date of Patent: October 22, 2024
    Assignees: BEIJING WODONG TIANJUN INFORMATION TECHNOLOGY CO., LTD., BEIJING JINGDONG CENTURY TRADING CO., LTD.
    Inventors: Linsen Li, Wenwen Ye
  • Publication number: 20240005134
    Abstract: The invention discloses a neural network retraining and gradient sparse method based on the aging sensing of memristors. For the accuracy rate of hardware online reasoning decreases after cross-array aging, the extreme values of programmable weights under a current aging condition is calculated by using the known aging information of memristor, and a neural network model is retrained according to this, so as to improve the accuracy rate of the current hardware online reasoning. In the process of retraining, network weights exceeding the extreme values of programmable weights are automatically truncated. For the working life of the memristor, the sparsity of derivatives of the neural network is utilized to discard the derivatives with a small absolute value in hardware adjustment process, so as to ensure that the memristor corresponding to small derivatives would not be applied voltage, prevent the aging process of the memristors and prolong the service life thereof.
    Type: Application
    Filed: April 29, 2022
    Publication date: January 4, 2024
    Applicant: ZHEJIANG UNIVERSITY
    Inventors: Xunzhao YIN, Wenwen YE, Cheng ZHUO
  • Publication number: 20230334113
    Abstract: Embodiments of the present disclosure disclose an image processing method and apparatus, and a computer readable storage medium. The method includes: obtaining at least one page image of a current full-screen page in a webpage application; converting the at least one page image into at least one file object, and creating at least one link path of the at least one file object, each of the at least one file object corresponding to the respective at least one link path; and creating at least one picture object, and associatively saving the at least one picture object and the at least one link path in webpage application cache to complete taking a screenshot of the current full-screen page. Through the embodiments of the present disclosure, the screenshot capturing performance of the webpage application can be improved.
    Type: Application
    Filed: March 29, 2021
    Publication date: October 19, 2023
    Inventors: Linsen LI, Wenwen YE