利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

172 条记录 (耗时 0.047 秒)

    RETRIEVING AND DISPLAYING KEY WORDS FROM PRIOR CONVERSATIONS
    73.
    发明申请
    RETRIEVING AND DISPLAYING KEY WORDS FROM PRIOR CONVERSATIONS 审中-公开

    公开(公告)号：US20200050862A1

    公开(公告)日：2020-02-13

    申请号：US16659163

    申请日：2019-10-21

    申请人： OrCam Technologies Ltd.

    发明人： Yonatan Wexler ,  Amnon Shashua

    IPC分类号： G06K9/00 ,  G06F1/16 ,  H04N5/225 ,  G10L15/30 ,  G10L15/08 ,  G10L15/22

    摘要： A wearable apparatus is provided. The wearable apparatus may include: a wearable image sensor configured to capture a plurality of images from an environment of a user; and at least one processor programmed to: receive, from the wearable image sensor, a facial image of an individual with whom a user interacted in a first interaction during a time window; receive sound data captured in a vicinity of the image sensor during a part of the time window; process the sound data to identify a key word; store an association between the key word and the facial image; receive another facial image of the individual during a second interaction; determine that the individual is the individual in the second interaction; access the memory to locate the key word from the first interaction; and cause a display of the key word on a display visible to the user.

    Wearable Apparatus for Name Tagging
    74.
    发明申请
    Wearable Apparatus for Name Tagging 审中-公开

    公开(公告)号：US20200050861A1

    公开(公告)日：2020-02-13

    申请号：US16658438

    申请日：2019-10-21

    申请人： ORCAM TECHNOLOGIES LTD.

    发明人： Yonatan Wexler ,  Amnon Shashua

    IPC分类号： G06K9/00 ,  G06F1/16 ,  H04N5/225 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30

    摘要： A wearable apparatus and methods may analyze images. In one implementation, the wearable apparatus may comprise a wearable image sensor and at least one processor. The at least one processor may be programmed to: receive, from the wearable image sensor, a facial image of an individual with whom a user of the wearable apparatus is interacting; receive sound data captured during the interacting; process at least a portion of the sound data to determine a spoken name of the individual; convert the spoken name to text; store, in memory, text associated with the spoken name in a manner associating the text with the facial image; after a subsequent encounter with the individual, receive, from the wearable image sensor, a subsequent facial image of the individual; perform a look-up of an identity of the individual based on the subsequent facial image; receive, from the memory the text of the spoken name of the individual; and cause a display in text of the name of the individual on a device paired with the wearable apparatus.