Patents by Inventor Yao Zhang

Yao Zhang 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: 20220121908
    Abstract: Embodiments of the present disclosure relate to a method and an apparatus for processing data, and related products. The embodiments of the present disclosure relate to a board card including a storage component, an interface apparatus, a control component, and an artificial intelligence chip, where the artificial intelligence chip is connected to the storage component, the control component and the interface apparatus respectively. The storage component is used to store data; the interface apparatus is used to realize data transmission between the artificial intelligence chip and the external device. The control component is used to monitor a state of the artificial intelligence chip. The board card may be used to perform artificial intelligence computations.
    Type: Application
    Filed: December 29, 2021
    Publication date: April 21, 2022
    Applicant: Shanghai Cambricon Information Technology Co., Ltd
    Inventors: Yao ZHANG, Guang JIANG, Xishan ZHANG, Shiyi ZHOU, Di HUANG, Chang LIU, Jiaming GUO
  • Publication number: 20220121601
    Abstract: The present application relates to a network-on-chip data processing method. The method is applied to a network-on-chip processing system, the network-on-chip processing system is used for executing machine learning calculation, and the network-on-chip processing system comprises a storage device and a calculation device. The method comprises: accessing the storage device in the network-on-chip processing system by means of a first calculation device in the network-on-chip processing system and obtaining first operation data; performing an operation on the first operation data by means of the first calculation device to obtain a first operation result; and sending the first operation result to a second calculation device in the network-on-chip processing system. According to the method, operation overhead can be reduced and data read/write efficiency can be improved.
    Type: Application
    Filed: December 29, 2021
    Publication date: April 21, 2022
    Inventors: Shaoli LIU, Zhen LI, Yao ZHANG
  • Publication number: 20220121604
    Abstract: The present application relates to a network-on-chip data processing method. The method is applied to a network-on-chip processing system, the network-on-chip processing system is used for executing machine learning calculation, and the network-on-chip processing system comprises a storage device and a calculation device. The method comprises: accessing the storage device in the network-on-chip processing system by means of a first calculation device in the network-on-chip processing system, and obtaining first operation data; performing an operation on the first operation data by means of the first calculation device to obtain a first operation result; and sending the first operation result to a second calculation device in the network-on-chip processing system. According to the method, operation overhead can be reduced and data read/write efficiency can be improved.
    Type: Application
    Filed: December 29, 2021
    Publication date: April 21, 2022
    Inventors: Shaoli LIU, Zhen LI, Yao ZHANG
  • Patent number: 11308389
    Abstract: Provided are an integrated circuit chip apparatus and a related product, the integrated circuit chip apparatus being used for executing a multiplication operation, a convolution operation or a training operation of a neural network. The present technical solution has the advantages of a small amount of calculation and low power consumption.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: April 19, 2022
    Assignee: CAMBRICON TECHNOLOGIES CORPORATION LIMITED
    Inventors: Shaoli Liu, Xinkai Song, Bingrui Wang, Yao Zhang, Shuai Hu
  • Publication number: 20220108150
    Abstract: Embodiments of the present disclosure relate to a method and an apparatus for processing data, and related products. The embodiments of the present disclosure provide a board card including a storage component, an interface device, a control component, and an artificial intelligence chip. The artificial intelligence chip is connected to the storage component, the control component, and the interface device, respectively; the storage component is configured to store data; the interface device is configured to implement data transfer between the artificial intelligence chip and external equipment; and the control component is configured to monitor a state of the artificial intelligence chip. The board card is configured to perform artificial intelligence operations.
    Type: Application
    Filed: December 17, 2021
    Publication date: April 7, 2022
    Applicant: Shanghai Cambricon Information Technology Co., Ltd
    Inventors: Yao ZHANG, Guang JIANG, Xishan ZHANG, Shiyi ZHOU, Di HUANG, Chang LIU, Jiaming GUO
  • Patent number: 11296418
    Abstract: The invention discloses a dual-polarized filtering magneto-electric dipole antenna, which comprises an upper dielectric substrate and a lower dielectric substrate. The upper surface of the upper dielectric substrate is printed with a radiator structure, and the lower dielectric substrate is printed with a slot coupling feed network; the radiator structure comprises four parasitic patches loaded with symmetrical slots. The parasitic patches are loaded with short-circuit probes, and the slot coupling feed network comprises two orthogonal sets of Y-shaped feeders and cross-shaped slots, and the cross-shaped slots are printed on a metal floor. The new parasitic slot structures on the radiator structure increases the bandwidth while introducing a high roll-off band edge filtering effect, and combined with the slot coupling feed network with filtering function to achieve good band-pass filtering characteristics and hardly introduce additional insertion loss.
    Type: Grant
    Filed: October 25, 2019
    Date of Patent: April 5, 2022
    Assignee: SOUTH CHINA UNIVERSITY OF TECHNOLOGY
    Inventors: Xiuyin Zhang, Shengjie Yang, Zhijie Zhang, Yongmei Pan, Yunfei Cao, Yao Zhang
  • Patent number: 11296425
    Abstract: A dual-polarized duplex antenna includes a top-layer dielectric substrate; a metal reflective ground plate below the top-layer dielectric substrate; vertically-placed duplex baluns for duplexing operation between the top-layer dielectric substrate and the metal reflective ground plate; and four dipole arms horizontally printed on an upper surface of the top-layer dielectric substrate. Each of the duplex balun includes a vertical dielectric substrate, a balun feedline printed on a front side of the vertical dielectric substrate, and a ground plane with a printed slot line printed on a reverse side of the vertical dielectric substrate. The balun feedline includes a low-pass filter, a high-pass filter and a microstrip feeding structure serving as a connection. The low-pass filter and the high-pass filter are located on two sides of the slot line, and are connected together by the microstrip feeding structure.
    Type: Grant
    Filed: October 18, 2018
    Date of Patent: April 5, 2022
    Inventors: Xiuyin Zhang, Yufeng Wu, Yunfei Cao, Wen Duan, Yao Zhang
  • Publication number: 20220096543
    Abstract: Described herein are modified cells and compositions thereof, wherein the cells can have reduced or eliminated Tollip gene and/or protein expression. In some embodiments, the modified cells can be neutrophils. Also described herein are methods of making and using the modified cells and compositions thereof. In some embodiments, the modified cells having reduced or eliminated Tollip gene and/or protein expression can be administered to a subject in need thereof.
    Type: Application
    Filed: December 23, 2019
    Publication date: March 31, 2022
    Inventors: Liwu LI, Yao ZHANG, Christina LEE
  • Publication number: 20220098183
    Abstract: Provided herein are compounds of Formula (I), methods of using the compounds as immunomodulators, and pharmaceutical compositions comprising such compounds. The compounds are useful in treating, preventing or ameliorating diseases or disorders such as cancer or infections.
    Type: Application
    Filed: January 20, 2020
    Publication date: March 31, 2022
    Inventors: Yiqian WANG, Yao ZHANG, Bang FU, Jiabing WANG, Lieming DING
  • Publication number: 20220091849
    Abstract: There is provides an operation module, which includes a memory, a register unit, a dependency relationship processing unit, an operation unit, and a control unit. The memory is configured to store a vector, the register unit is configured to store an extension instruction, and the control unit is configured to acquire and parse the extension instruction, so as to obtain a first operation instruction and a second operation instruction. An execution sequence of the first operation instruction and the second operation instruction can be determined according to the first operation instruction and the second operation instruction, and an input vector of the first operation instruction can be read from the memory. An index processing unit is configured to proceed an indexing transformation, and to screen data according to an index, and so on.
    Type: Application
    Filed: July 23, 2018
    Publication date: March 24, 2022
    Inventors: Bingrui WANG, Shengyuan ZHOU, Yao ZHANG
  • Publication number: 20220083909
    Abstract: The present disclosure relates to a method, a device, and related products for processing data. In an embodiment of the present disclosure, when processing data related to a neural network, an optimal truncation threshold value for a plurality of pieces of data is determined. The data is truncated through the truncation data threshold, and the plurality of pieces of data is quantized from a high-precision format to a low-precision format. The method in the present disclosure can ensure the precision of data processing as high as possible while reducing the amount of data processing. In addition, the method also helps to significantly reduce the amount of data transmission, thereby greatly accelerating the data exchange among a plurality of computing devices.
    Type: Application
    Filed: June 29, 2021
    Publication date: March 17, 2022
    Inventors: Yao ZHANG, Guang JIANG, Xishan ZHANG, Shiyi ZHOU, Di HUANG, Chang LIU, Jiaming GUO
  • Publication number: 20220053221
    Abstract: A method for managing a live-streaming room comprises displaying a first live-streaming interface of a live-streaming room by a first terminal; detecting a first operation through the first live-streaming interface; and sending a first instruction to a live-streaming server in response to the first operation, wherein the live-streaming server is configured to send the first instruction to a second terminal, the first instruction instructs the second terminal to perform a synchronization operation with the first terminal.
    Type: Application
    Filed: August 3, 2021
    Publication date: February 17, 2022
    Inventor: Yao ZHANG
  • Publication number: 20220041583
    Abstract: Provided herein is compounds of Formula I, methods of using the compounds as immunomodulators, and pharmaceutical compositions comprising such compounds. The compounds are useful in treating, preventing or ameliorating diseases or disorders such as cancer or infections.
    Type: Application
    Filed: September 12, 2019
    Publication date: February 10, 2022
    Applicant: BETTA PHARMACEUTICALS CO., LTD
    Inventors: Yiqian WANG, Yao ZHANG, Bang FU, Jiabing WANG
  • Publication number: 20220035762
    Abstract: The present application relates to a network-on-chip data processing method. The method is applied to a network-on-chip processing system, the network-on-chip processing system is used for executing machine learning calculation, and the network-on-chip processing system comprises a storage device and a calculation device. The method comprises: accessing the storage device in the network-on-chip processing system by means of a first calculation device in the network-on-chip processing system, and obtaining first operation data; performing an operation on the first operation data by means of the first calculation device to obtain a first operation result; and sending the first operation result to a second calculation device in the network-on-chip processing system. According to the method, operation overhead can be reduced and data read/write efficiency can be improved.
    Type: Application
    Filed: October 18, 2019
    Publication date: February 3, 2022
    Inventors: Yao ZHANG, Shaoli LIU, Jun LIANG, Yu CHEN
  • Publication number: 20220036693
    Abstract: The present disclosure relates to an image processing method and apparatus, an electronic device, and a storage medium. The method includes: obtaining video streams of a game tabletop; detecting target objects in a plurality of image frames included in the video streams; determining a current game stage based on the target objects; and determining game detecting results according to the target objects and the determined game stage.
    Type: Application
    Filed: December 31, 2020
    Publication date: February 3, 2022
    Inventors: Yao ZHANG, Wenbin ZHANG, Shuai ZHANG
  • Publication number: 20220013442
    Abstract: A pin map covers a surface area of a layer of a printed circuit board (PCB). The pin map includes a plurality of electrical designations for each pin in the pin map and a plurality of empty spaces within the pin map. Each electrical designation may be assigned to a pin on the pin map. Each electrical designation includes a positive polarity (P+) pin, a negative polarity (P?) pin, or an electrical ground (G) pin. If a space in the pin map does not have an electrical designation, then it may include an empty space/plain portion of the printed circuit board (PCB). The pin map may include a plurality of rows and a first repeating pin polarity pattern. The first repeating pin polarity pattern may include a lane unit tile. The pin map may help couple two circuit elements together that are attached to one layer of a PCB.
    Type: Application
    Filed: June 30, 2021
    Publication date: January 13, 2022
    Inventors: Nelly CHEN, Gary Yao ZHANG, Michael Randy MAY, Shrinivas GOPALAN UPPILI, Varin SRIBOONLUE
  • Publication number: 20210406649
    Abstract: The present disclosure provides a computation device. The computation device is configured to perform a machine learning computation, and includes an operation unit, a controller unit, and a conversion unit. The storage unit is configured to obtain input data and a computation instruction. The controller unit is configured to extract and parse the computation instruction from the storage unit to obtain one or more operation instructions, and to send the one or more operation instructions and the input data to the operation unit. The operation unit is configured to perform operations on the input data according to one or more operation instructions to obtain a computation result of the computation instruction. In the examples of the present disclosure, the input data involved in machine learning computations is represented by fixed-point data, thereby improving the processing speed and efficiency of training operations.
    Type: Application
    Filed: September 3, 2018
    Publication date: December 30, 2021
    Inventors: Yao ZHANG, Bingrui WANG
  • Publication number: 20210374510
    Abstract: The present disclosure provides a data processing method, a board card device, computer equipment, and a storage medium for data quantization. The board card provided in the present disclosure includes a storage device, an interface apparatus, a control device, and an artificial intelligence chip of a data processing device, where the artificial intelligence chip is connected to the storage device, the control device, and the interface apparatus, respectively. The storage device is configured to store data; the interface apparatus is configured to implement data transmission between the artificial intelligence chip and an external apparatus; and the control device is configured to monitor the state of the artificial intelligence chip. The data to be quantized is quantized according to corresponding quantization parameters, which reduce the storage space of data while ensuring precision, accuracy and reliability of the operation result, and improving the operation efficiency.
    Type: Application
    Filed: August 20, 2020
    Publication date: December 2, 2021
    Inventors: Shaoli LIU, Di HUANG, Xishan ZHANG, Yao ZHANG
  • Publication number: 20210356457
    Abstract: Embodiments herein relate to chemical sensors, devices and systems including the same, and related methods. In an embodiment, a medical device is included. The medical device can include a graphene varactor. The graphene varactor can include a graphene layer and a self-assembled monolayer disposed on an outer surface of the graphene layer through ?-? stacking interactions. The self-assembled monolayer can provide a Langmuir theta value of at least 0.9. The self-assembled monolayer can include polycyclic aromatic hydrocarbons, tetraphenylporphyrins or derivatives thereof, metallotetraphenylporphyrins, or aromatic cyclodextrins. Other embodiments are also included herein.
    Type: Application
    Filed: July 28, 2021
    Publication date: November 18, 2021
    Inventors: Xue Zhen, Philippe Pierre Joseph Buhlmann, Steven Koester, Yao Zhang, Justin Theodore Nelson
  • Patent number: 11169803
    Abstract: The present disclosure provides a computation device. The computation device is configured to perform a machine learning computation, and includes an operation unit, a controller unit, and a conversion unit. The storage unit is configured to obtain input data and a computation instruction. The controller unit is configured to extract and parse the computation instruction from the storage unit to obtain one or more operation instructions, and to send the one or more operation instructions and the input data to the operation unit. The operation unit is configured to perform operations on the input data according to one or more operation instructions to obtain a computation result of the computation instruction. In the examples of the present disclosure, the input data involved in machine learning computations is represented by fixed-point data, thereby improving the processing speed and efficiency of training operations.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: November 9, 2021
    Assignee: Shanghai Cambricon Information Technology Co., Ltd.
    Inventors: Yao Zhang, Bingrui Wang