知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

2946 条记录 (耗时 0.033 秒)

    Ring enabling its wearer to enter control commands
    3.
    发明授权
    Ring enabling its wearer to enter control commands 有权

    公开(公告)号：US12130965B2

    公开(公告)日：2024-10-29

    申请号：US17859747

    申请日：2022-07-07

    申请人： Plume Design, Inc.

    发明人： Zhicheng Qiu ,  William J. McFarland

    IPC分类号： G06F3/01 ,  G06F1/16 ,  G06F3/16 ,  G10L15/06 ,  H04W4/80

    CPC分类号： G06F3/014 ,  G06F1/163 ,  G06F3/016 ,  G06F3/017 ,  G06F3/167 ,  G10L15/063 ,  H04W4/80

    摘要： Control systems and methods are provided that utilize a device, which can be worn by a user, to enable the user to enter control commands for causing a controller to control one or more electronic devices in a local network, such as a Wi-Fi system. A local control system, according to one implementation, includes a smart ring configured to obtain movement information related to one or more movements of the smart ring while a user is wearing the smart ring. The local control system also includes a controller device configured to communicate with the smart ring using Bluetooth or Wi-Fi signals. Characteristics of the movement information can be translated in order to obtain one or more control commands. The controller device is configured to control one or more aspects of one or more electronic devices based on the one or more control commands.

    SPEECH RECOGNITION DEVICE FOR DENTISTRY AND METHOD USING THE SAME
    4.
    发明公开
    SPEECH RECOGNITION DEVICE FOR DENTISTRY AND METHOD USING THE SAME 审中-公开

    公开(公告)号：US20240355330A1

    公开(公告)日：2024-10-24

    申请号：US18226867

    申请日：2023-07-27

    申请人： DenComm Inc.

    发明人： Byung Joon LIM

    IPC分类号： G10L15/26 ,  G10L15/06

    CPC分类号： G10L15/26 ,  G10L15/063

    摘要： A speech recognition device for dentistry includes a processor, and a memory storing one or more instructions. The instructions are executed by the processor to obtain a sound containing noise and speech generated during a dental treatment, perform a noise cancelling on the sound, and run a speech-to-text (STT) model trained using a self-supervised learning method. The STT model executes extracting a feature from each of the sound with the noise cancelling and from the sound without the noise cancelling, obtaining an encoding vector by assigning a weight to each of the features and processing the features, and obtaining a script for the speech by decoding the encoding vector. Further, the self-supervised learning method includes a fine-tuning process in which sounds containing noises and speeches that are generated during the dental treatment and a script for each of the speeches are used as a training data.

    INTELLIGENT VIRTUAL ASSISTANT TRAINING THROUGH PHASED OBSERVATIONAL LEARNING TASKS
    5.
    发明公开
    INTELLIGENT VIRTUAL ASSISTANT TRAINING THROUGH PHASED OBSERVATIONAL LEARNING TASKS 审中-公开

    公开(公告)号：US20240355318A1

    公开(公告)日：2024-10-24

    申请号：US18137995

    申请日：2023-04-21

    申请人： Verint Americas Inc.

    发明人： Ian BEAVER

    IPC分类号： G10L15/01 ,  G10L15/06

    CPC分类号： G10L15/01 ,  G10L15/063

    摘要： Disclosed embodiments pertain to training an intelligent virtual assistant through phased observational learning tasks. A pre-trained language model can be updated offline to produce a second language model with self-supervised learning based on transcripts of historical interactions between one or more customers, one or more customer service agents, and one or more data stores. The second language model can be evaluated and determined to satisfy a predetermined performance threshold. Subsequently, the second language model can be updated online to produce a third language model with reinforcement learning based on received customer input and similarity between a response provided by a customer service agent and a predicted response generated by the second language model. The third language model can then be deployed with an intelligent virtual assistant to respond to received user input.