Patents by Inventor Yongjian Wu

Yongjian Wu 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: 10699699
    Abstract: The embodiments of the present disclosure disclose a method for constructing a speech decoding network in digital speech recognition. The method comprises acquiring training data obtained by digital speech recording, the training data comprising a plurality of speech segments, and each speech segment comprising a plurality of digital speeches; performing acoustic feature extraction on the training data to obtain a feature sequence corresponding to each speech segment; performing progressive training starting from a mono-phoneme acoustic model to obtain an acoustic model; acquiring a language model, and constructing a speech decoding network by the language model and the acoustic model obtained by training.
    Type: Grant
    Filed: May 30, 2018
    Date of Patent: June 30, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Fuzhang Wu, Binghua Qian, Wei Li, Ke Li, Yongjian Wu, Feiyue Huang
  • Publication number: 20200205061
    Abstract: An implantable medical device (IMD) that includes a transceiver configured to broadcast an advertising data packet that includes a unique identifier, and to receive a scan request data packet from an external device. A memory stores program instructions, and stores an approved device list, and one or more processors are configured to execute the program instructions to identify a device identifier (ID) from the scan request data packet received, apply an advertising filter to determine if the scan request data packet is from an authorized external device based on the device ID and the approved device list, based on the determination by the advertising filter, deny transmission of a scan response data packet from the transceiver when the advertising filter determines that the scan request data packet is from an unauthorized external device, and establish a communication session with an authorized external device independent of the scan request data packet.
    Type: Application
    Filed: December 3, 2019
    Publication date: June 25, 2020
    Inventors: Chaowen Young, Yongjian Wu, Jyoti Bhayana, Samir Shah, Reza Shahandeh
  • Patent number: 10692503
    Abstract: A voice data processing method and apparatus are provided. The method includes obtaining an I-Vector vector of each of voice samples, and determining a target seed sample in the voice samples. A first cosine distance is calculated between an I-Vector vector of the target seed sample and an I-Vector vector of a target remaining voice sample, where the target remaining voice sample is a voice sample other than the target seed sample in the voice samples. A target voice sample is filtered from the voice samples or the target remaining voice sample according to the first cosine distance, to obtain a target voice sample whose first cosine distance is greater than a first threshold.
    Type: Grant
    Filed: March 3, 2017
    Date of Patent: June 23, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Xingming Jin, Wei Li, Fangmai Zheng, Fuzhang Wu, Bilei Zhu, Binghua Qian, Ke Li, Yongjian Wu, Feiyue Huang
  • Patent number: 10686878
    Abstract: Methods and systems are provided to manage display of cardiac signals. The methods and systems receive a first data steam along a first communications path conveyed with first throughput and receiving a second data stream along a second communications path transmitted with second throughput. The first and second throughputs are asynchronous with respect to one another. The first and second data streams carry cardiac signals sensed by external and implanted electrodes, respectively, for one or more common events. The methods and systems store data from the first and second data streams in first and second memory buffers. The methods and systems synchronize the data stored in the first and second memory buffers with one another by performing at least one of: temporally offsetting activation of the storing operation for the first and second data streams with respect to one another; or managing an amount of the data maintained in at least one of the first memory buffer or the second memory buffer.
    Type: Grant
    Filed: March 30, 2017
    Date of Patent: June 16, 2020
    Assignee: Pacesetter, Inc.
    Inventors: Muthuvale Shanmugam, Pulkit Bisen, Chao-Wen Young, Yongjian Wu, Lisbet Miller, Xing Pei, Reza Shahandeh
  • Publication number: 20200187272
    Abstract: A method, system and external instrument are provided. The method initiates a communication link between an external instrument (EI) and an implantable medical device (IMD), established a first connection interval for conveying data packets between the EI and IMD and monitors a connection criteria that includes at least one of a data throughput requirement. A battery indicator or link condition of the communications link is between the IMD and EI. The method further changes from the first connection interval to a second connection interval based on the connection criteria.
    Type: Application
    Filed: February 14, 2020
    Publication date: June 11, 2020
    Inventors: Yongjian Wu, Chao-Wen Young, Jun Yang, Xing Pei, Reza Shahandeh
  • Patent number: 10664580
    Abstract: A sign-in method and server based on facial recognition are provided. The method includes: receiving a face image of a sign-in user from a sign-in terminal. According to the face image of the sign-in user, whether a target registration user matching the sign-in user exists in a pre-stored registration set is detected. The registration set includes a face image of at least one registration user. Further, the target registration user is confirmed as signed in successfully if the target registration user exists in the registration set.
    Type: Grant
    Filed: August 10, 2018
    Date of Patent: May 26, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Feiyue Huang, Yongjian Wu, Guofu Tan, Jilin Li, Zhibo Chen, Xiaoqing Liang, Zhiwei Tao, Kejing Zhou, Ke Mei
  • Patent number: 10650830
    Abstract: Processing circuitry of an information processing apparatus obtains a set of identity vectors that are calculated according to voice samples from speakers. The identity vectors are classified into speaker classes respectively corresponding to the speakers. The processing circuitry selects, from the identity vectors, first subsets of interclass neighboring identity vectors respectively corresponding to the identity vectors and second subsets of intraclass neighboring identity vectors respectively corresponding to the identity vectors. The processing circuitry determines an interclass difference based on the first subsets of interclass neighboring identity vectors and the corresponding identity vectors; and determines an intraclass difference based on the second subsets of intraclass neighboring identify vectors and the corresponding identity vectors.
    Type: Grant
    Filed: April 16, 2018
    Date of Patent: May 12, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Wei Li, Binghua Qian, Xingming Jin, Ke Li, Fuzhang Wu, Yongjian Wu, Feiyue Huang
  • Patent number: 10650259
    Abstract: The embodiment of the present invention provides a human face recognition method and recognition system. The method includes that: a human face recognition request is acquired, and a statement is randomly generated according to the human face recognition request; audio data and video data returned by a user in response to the statement are acquired; corresponding voice information is acquired according to the audio data; corresponding lip movement information is acquired according to the video data; and when the lip movement information and the voice information satisfy a preset rule, the human face recognition request is permitted. By performing fit goodness matching between the lip movement information and voice information in a video for dynamic human face recognition, an attack by human face recognition with a real photo may be effectively avoided, and higher security is achieved.
    Type: Grant
    Filed: July 7, 2017
    Date of Patent: May 12, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Chengjie Wang, Jilin Li, Hui Ni, Yongjian Wu, Feiyue Huang
  • Patent number: 10639482
    Abstract: A method and device for managing establishment of a communications link between an external instrument (EI) and an implantable medical device (IMD) are provided. The method stores, in a memory in at least one of the IMD or the EI, a base scanning schedule that defines a pattern for scanning windows over a scanning state. The method enters the scanning state during which a receiver scans for advertisement notices during the scanning windows. At least a portion of the scanning windows are grouped in a first segment of the scanning state. The method stores, in the memory, a scan reset pattern for restarting the scanning state. Further, the method automatically restarts the scanning state based on the scan reset pattern to form a pseudo-scanning schedule that differs from the base scanning schedule and establishes a communication session between the IMD and the EI.
    Type: Grant
    Filed: September 18, 2017
    Date of Patent: May 5, 2020
    Assignee: PACESETTER, INC.
    Inventors: Yongjian Wu, Jyoti Bhayana, Chao-Wen Young, Tejpal Singh, Samir Shah
  • Patent number: 10623933
    Abstract: Example electronic devices, including but not limited to implantable medical devices, and methods employing dynamic announcing for creation of wireless communication connections are disclosed herein. In an example, an electronic device includes a wireless communication interface to transmit announcement signals for creating a wireless communication connection with the external device. The electronic device also includes a sensor to detect a characteristic of an environment external to the electronic device, and a control circuit including an announcement timing control module to dynamically control timing of the announcement signals based on the detected characteristic.
    Type: Grant
    Filed: May 1, 2019
    Date of Patent: April 14, 2020
    Assignee: PACESETTER, INC.
    Inventors: Timothy Pflugh, Fujian Qu, Benjamin Coppola, Edward Karst, Lisa P. Weinberg, Xing Pei, Yongjian Wu
  • Patent number: 10607066
    Abstract: The present disclosure discloses a living body identification method, an information generation method, and a terminal, and belongs to the field of biometric feature recognition. The method includes: providing lip language prompt information, the lip language prompt information including at least two target characters, and the at least two target characters being at least one of: characters of a same lip shape, characters of opposite lip shapes, or characters whose lip shape similarity is in a preset range; collecting at least two frame pictures; detecting whether lip changes of a to-be-identified object in the at least two frame pictures meet a preset condition, when the to-be-identified object reads the at least two target characters; and determining that the to-be-identified object is a living body, if the preset condition is met.
    Type: Grant
    Filed: March 17, 2017
    Date of Patent: March 31, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Jilin Li, Chengjie Wang, Feiyue Huang, Yongjian Wu, Hui Ni, Ruixin Zhang, Guofu Tan
  • Patent number: 10599913
    Abstract: Face model matrix training method, apparatus, and storage medium are provided. The method includes: obtaining a face image library, the face image library including k groups of face images, and each group of face images including at least one face image of at least one person, k>2, and k being an integer; separately parsing each group of the k groups of face images, and calculating a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images; and training face model matrices according to the first matrix and the second matrix.
    Type: Grant
    Filed: July 11, 2019
    Date of Patent: March 24, 2020
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Shouhong Ding, Jilin Li, Chengjie Wang, Feiyue Huang, Yongjian Wu, Guofu Tan
  • Patent number: 10582444
    Abstract: An implantable medical device (IMD) that includes a transceiver configured to broadcast an advertising data packet that includes a unique identifier, and to receive a scan request data packet from an external device. A memory stores program instructions, and stores an approved device list, and one or more processors are configured to execute the program instructions to identify a device identifier (ID) from the scan request data packet received, apply an advertising filter to determine if the scan request data packet is from an authorized external device based on the device ID and the approved device list, based on the determination by the advertising filter, deny transmission of a scan response data packet from the transceiver when the advertising filter determines that the scan request data packet is from an unauthorized external device, and establish a communication session with an authorized external device independent of the scan request data packet.
    Type: Grant
    Filed: December 20, 2018
    Date of Patent: March 3, 2020
    Assignee: PACESETTER, INC.
    Inventors: Chaowen Young, Yongjian Wu, Jyoti Bhayana, Samir Shah, Reza Shahandeh
  • Patent number: 10575346
    Abstract: A method, system and external instrument are provided. The method initiates a communication link between an external instrument (EI) and an implantable medical device (MD), established a first connection interval for conveying data packets between the EI and IMD and monitors a connection criteria that includes at least one of a data throughput requirement. A battery indicator or link condition of the communications link is between the IMD and EI. The method further changes from the first connection interval to a second connection interval based on the connection criteria.
    Type: Grant
    Filed: February 11, 2019
    Date of Patent: February 25, 2020
    Assignee: PACESETTER, INC.
    Inventors: Yongjian Wu, Chao-Wen Young, Jun Yang, Xing Pei, Reza Shahandeh
  • Patent number: 10541977
    Abstract: Methods and devices for establishing secure communications with an implantable medical device (IMD) are provided. The method and devices receive a credential from an external instrument (EI). The credential is signed utilizing a private key, and the credential includes at least two of a credential time to live (TTL) indicator, an IMD Identifier (ID), and an EI ID. The method and device authenticate the credential using a public key and verify the at least two of the TTL indicator, the IMD ID, and the EI ID. The method and device establish a secure communications session with the EI based on the verification and authentication.
    Type: Grant
    Filed: July 25, 2017
    Date of Patent: January 21, 2020
    Assignee: PACESETTER, INC.
    Inventors: Yongjian Wu, Mostafa Sadeghi, Chao-Wen Young, Jun Yang, Samir Shah, Simon Skup
  • Publication number: 20190381326
    Abstract: A method is provided for establishing a communication session with an implantable medical device (“IMD”). The method includes configuring an IMD and an external device to communicate with one another through a protocol that utilizes a dedicated advertisement channel. The advertisement period and the scan period of the protocol are independent of one another such that the advertisement and scan periods at least partially overlap intermittently after a number of cycles. When the external device detects one of the advertisement notices, the method includes establishing a communications link between the external device and the IMD.
    Type: Application
    Filed: January 2, 2018
    Publication date: December 19, 2019
    Inventors: Reza Shahandeh, Richard Williamson, Gabriel A. Mouchawar, Brent Croft, William Winstrom, Robert McCormick, Jorge N. Amely-Velez, Thanh Tieu, Ali Dianaty, Samir Shah, Yongjian Wu
  • Publication number: 20190332847
    Abstract: Face model matrix training method, apparatus, and storage medium are provided. The method includes: obtaining a face image library, the face image library including k groups of face images, and each group of face images including at least one face image of at least one person, k>2, and k being an integer; separately parsing each group of the k groups of face images, and calculating a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images; and training face model matrices according to the first matrix and the second matrix.
    Type: Application
    Filed: July 11, 2019
    Publication date: October 31, 2019
    Inventors: Shouhong DING, Jilin LI, Chengjie WANG, Feiyue HUANG, Yongjian WU, Guofu TAN
  • Publication number: 20190321646
    Abstract: Methods and devices for managing establishment of a communications link between an external instrument (EI) and an implantable medical device (IMD) are provided. The methods and devices comprise storing, in memory in at least one of the IMD or the EI an advertising schedule defining a pattern for advertisement notices. The advertisement notices are distributed un-evenly and separated by unequal advertisement intervals. The method transmits, from a transmitter in at least one of the IMD or the EI the advertisement notices. The advertisement notices are distributed as defined by the advertising schedule. The method establishes a communication session between the IMD and the EI.
    Type: Application
    Filed: July 3, 2019
    Publication date: October 24, 2019
    Inventors: Yongjian Wu, Samir Shah, Heidi Hellman, Reza Shahandeh, Tejpal Singh, Youjing Huang, Chao-Wen Young
  • Patent number: 10449372
    Abstract: Methods and devices for managing establishment of a communications link between an external instrument (EI) and an implantable medical device (IMD) are provided. The methods and devices comprise storing, in memory in at least one of the IMD or the EI an advertising schedule defining a pattern for advertisement notices. The advertisement notices are distributed un-evenly and separated by unequal advertisement intervals. The method transmits, from a transmitter in at least one of the IMD or the EI the advertisement notices. The advertisement notices are distributed as defined by the advertising schedule. The method establishes a communication session between the IMD and the EI.
    Type: Grant
    Filed: July 21, 2016
    Date of Patent: October 22, 2019
    Assignee: Pacesetter, Inc.
    Inventors: Yongjian Wu, Samir Shah, Heidi Hellman, Reza Shahandeh, Tejpal Singh, Youjing Huang, Chao-Wen Young
  • Patent number: 10438077
    Abstract: A face liveness detection method includes outputting a prompt to complete one or more specified actions in sequence within a specified time period, obtaining a face video, detecting a reference face image frame in the face video using a face detection method, locating a facial keypoint in the reference face image frame, tracking the facial keypoint in one or more subsequent face image frames, determining a state parameter of one of the one or more specified actions using a continuity analysis method according to the facial keypoint, and determining whether the one of the one or more specified actions is completed according to a continuity of the state parameter.
    Type: Grant
    Filed: October 9, 2017
    Date of Patent: October 8, 2019
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Chengjie Wang, Jilin Li, Feiyue Huang, Yongjian Wu