Patents by Inventor Zhipeng CHEN

Zhipeng CHEN 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: 11029172
    Abstract: The present disclosure provides a real scenario navigation method and apparatus, a device and a computer readable storage medium. In the embodiments of the present disclosure, it is feasible to obtain the travel manner, the query starting point, the query finishing point and the destination provided by the user, and then perform navigation map-based first travel manner path planning, according to the travel manner, the query starting point and the query finishing point so that it is feasible to perform real-scenario image-based second travel manner path planning, according to the query finishing point and the destination, if the user reaches the query finishing point and a distance between the query finishing point and the destination is smaller than or equal to a preset distance threshold.
    Type: Grant
    Filed: December 27, 2017
    Date of Patent: June 8, 2021
    Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Xintao Chen, Zhipeng Zhou
  • Publication number: 20210133396
    Abstract: This application discloses a prosodic pause prediction method, a prosodic pause prediction device and an electronic device. The specific implementation scheme includes: obtaining a first matrix by mapping a to-be-tested text sequence through a trained embedding layer, where the to-be-tested text sequence includes a to-be-tested input text and an identity of a to-be-tested speaker; inputting the first matrix into a trained attention model, and determining a semantic representation matrix by the trained attention model; and, performing prosodic pause prediction based on the semantic representation matrix and outputting a prosodic pause prediction result of each word in the to-be-tested input text.
    Type: Application
    Filed: May 8, 2020
    Publication date: May 6, 2021
    Applicant: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Zhipeng Nie, Yanyao Bian, Zhanjie Gao, Changbin Chen
  • Publication number: 20210097974
    Abstract: The present application discloses a training method and an apparatus for a speech synthesis model, electronic device, and storage medium. The method includes: taking a syllable input sequence, a phoneme input sequence and a Chinese character input sequence of a current sample as inputs of an encoder of a model to be trained, to obtain encoded representations of these three sequences at an output end of the encoder; fusing the encoded representations of these three sequences, to obtain a weighted combination of these three sequences; taking the weighted combination as an input of an attention module, to obtain a weighted average of the weighted combination at each moment at an output end of the attention module; taking the weighted average as an input of a decoder of the model to be trained, to obtain a speech Mel spectrum of the current sample at an output end of the decoder.
    Type: Application
    Filed: June 19, 2020
    Publication date: April 1, 2021
    Inventors: Zhipeng CHEN, Jinfeng BAI, Lei JIA
  • Publication number: 20210090270
    Abstract: A method for detecting a flow velocity of a high-temperature molten fluid can include: collecting a video stream of a high-temperature high-velocity molten fluid, decomposing the video stream into a frame image sequence sorted by time, and extracting a molten fluid Region Of Interest (ROI) from the frame image sequence, extracting a molten fluid outline of the molten fluid ROI, and extracting a characteristic block of the molten fluid outline, and obtaining the flow velocity of the molten fluid based on the characteristic block. A flow velocity detection accuracy can be improved for a molten fluid with a high temperature, a high velocity and a high glossiness.
    Type: Application
    Filed: July 16, 2019
    Publication date: March 25, 2021
    Applicant: CENTRAL SOUTH UNIVERSITY
    Inventors: Zhaohui JIANG, Lei HE, Zhipeng CHEN, Weihua GUI, Dong PAN, Chunhua YANG, Yongfang XIE, Haifeng ZHANG
  • Patent number: 10931871
    Abstract: A method including: putting a pre-set detection apparatus in a pipeline to be detected, collecting, every pre-set time, movement information about and pipeline image thereof; at each collection moment, calculating, according to movement information collected, first position where detection apparatus is located; calculating, according to pipeline image photographed, second position where detection apparatus is located; determining, according to first position and second position, position where detection apparatus is located so as to position pipeline according to position at each collection moment. By performing position information extraction by means of inertial navigation and video combined positioning algorithm, accurate positioning of pipeline position is realized, so as to accurately position crack inside pipeline according to photographed image and positioned pipeline position.
    Type: Grant
    Filed: November 3, 2017
    Date of Patent: February 23, 2021
    Assignee: SHENZHEN UNIVERSITY
    Inventors: Qingquan Li, Jiasong Zhu, Chisheng Wang, Zhipeng Chen
  • Publication number: 20210045749
    Abstract: In some examples, an embolization device includes multiple sections with three-dimensional non-helical structures when deployed at a vascular site. The multiple sections include a first section and one or more second sections that are smaller than the first section. The first section may have a deployed structure configured to anchor the device at a vascular site (e.g., a blood vessel) of a patient while each of the one or more second sections may be formed from loops that configured to pack and obstruct the vascular site. In some cases, the embolization device also includes a third section having a deployed configuration with multiple helical windings or loops is configured to anchor the embolization device at the vascular site.
    Type: Application
    Filed: August 13, 2019
    Publication date: February 18, 2021
    Inventors: Yihan Wang, Victoria Schuman, Zhimin Fang, Yapeng Xu, Haitao Cao, Zhipeng Chen, Xiaojing Guo, Shichang Wen
  • Publication number: 20210011275
    Abstract: A true-seeing infrared industrial endoscope endoscope includes an external shell protective unit including a housing and an electrical appliance component box connected to a rear end of the housing. A cavity of the housing is provided with a dual capturing-imaging unit including at least two capturing-imaging subunits. Each of the capturing-imaging subunits includes a light splitter, an image capturing lens, an infrared imaging tube, and a visible light imaging tube. The electrical appliance component box is provided with a communication module and a power supply electrically connected to the dual capturing-imaging unit and the communication module. The communication module is communicatively connected to the dual capturing-imaging unit and an upper computer via a communication bus, and the power supply is electrically connected to the dual capturing-imaging unit via a power bus.
    Type: Application
    Filed: November 16, 2018
    Publication date: January 14, 2021
    Applicant: CENTRAL SOUTH UNIVERSITY
    Inventors: Zhaohui JIANG, Jilin ZHU, Zhipeng CHEN, Weihua GUI, Yongfang XIE, Chunhua YANG, Haifeng ZHANG
  • Publication number: 20200400419
    Abstract: A pipeline three-dimensional curve measuring robot and implementation method therefor. The measuring robot includes an electronic bin, sliding rods, wheel bracket, walking wheels arranged on wheel bracket, odometer wheels arranged on sliding rod on one side and encoders; the electronic bin is internally provided with an inertia measurement unit, collection control module and power supply module; when measuring, the measuring robot is controlled to move back and forth in a pipeline collecting measuring data; comparing measured data with three-dimensional curve data at pipeline reference moment to obtain deformation quantity of pipeline three-dimensional curve.
    Type: Application
    Filed: November 28, 2019
    Publication date: December 24, 2020
    Applicant: SHENZHEN UNIVERSITY
    Inventors: Qingquan LI, Zhipeng CHEN, Yu YIN, Xiang CHENG, Jiasong ZHU
  • Publication number: 20200177805
    Abstract: A method including: putting a pre-set detection apparatus in a pipeline to be detected, collecting, every pre-set time, movement information about and pipeline image thereof; at each collection moment, calculating, according to movement information collected, first position where detection apparatus is located; calculating, according to pipeline image photographed, second position where detection apparatus is located; determining, according to first position and second position, position where detection apparatus is located so as to position pipeline according to position at each collection moment. By performing position information extraction by means of inertial navigation and video combined positioning algorithm, accurate positioning of pipeline position is realized, so as to accurately position crack inside pipeline according to photographed image and positioned pipeline position.
    Type: Application
    Filed: November 3, 2017
    Publication date: June 4, 2020
    Applicant: SHENZHEN UNIVERSITY
    Inventors: Qingquan LI, Jiasong ZHU, Chisheng WANG, Zhipeng CHEN