-
公开(公告)号：US11646016B2
公开(公告)日：2023-05-09
申请号：US17024668
申请日：2020-09-17
发明人： Zhouwei Zhai , Rongsheng Huang , Ben Xu , Fei You , Ning Li , Wensong He
CPC分类号： G10L15/1822 , G06F40/216 , G06F40/35 , G06N5/04 , G06N20/00 , G10L15/063
摘要： A method and apparatus for recognizing a user intention, a device, and a readable storage medium are disclosed. A specific implementation of the method includes: acquiring a plurality of rounds of dialogue data and a satisfaction degree of each round of dialogue data, selecting target dialogue data having a satisfaction degree meeting a set satisfaction condition; labeling input data in the target dialogue data with an intention label; and training the intention recognition model based on the input data in the target dialogue data and the intention label of the input data, so that the trained intention recognition model performs intention recognition on new input data.
-
公开(公告)号：US11140462B2
公开(公告)日：2021-10-05
申请号：US16517876
申请日：2019-07-22
发明人： Yaqiong Zhou , Xi Zhang , Zhouwei Zhai , Xiangtao Jiang , Ben Xu , Fei Wang , Yue Liu , Zhaoji Xu , Wenlin Dong , Xinjie Wang
IPC分类号： H04N21/8405 , H04N21/472 , H04N21/845
摘要： The present disclosure provides a method, an apparatus, and a device for generating an essence video, and a storage medium. The method includes: acquiring a plot keyword in a plot introduction of a movie and a television play; acquiring a first plot fragment corresponding to the plot keyword according to the plot keyword; acquiring a second plot fragment with a heat meeting a preset condition, the second plot fragment being different from the first plot fragment; and generating an essence video according to the first plot fragment and the second plot fragment. The present disclosure can acquire an essence video which is stitched naturally, developed logically and includes a plot fragment with higher heat.
-
公开(公告)号：US11153651B2
公开(公告)日：2021-10-19
申请号：US16454176
申请日：2019-06-27
发明人： Zhike Zhang , Fei Wang , Jiaguang Lu , Zhouwei Zhai , Wenlin Dong , Hongwei Ma , Zhaoji Xu , Sheng Chen , Weiwen Gao , Ning Li
IPC分类号： H04N21/462 , H04N21/239 , H04N21/431 , H04N21/437 , H04N21/472 , H04N21/482
摘要： The present disclosure provides a methods, an apparatus and a device for obtaining play data, and a storage medium, including: receiving request information sent by a user, and transmitting the request information to a server, so that the server searches VOD data and EPG data simultaneously according to the request information, where the EPG data includes live broadcast data and live broadcast playback data; receiving the VOD data and the EPG data sent by the server; displaying the VOD data and the EPG data simultaneously, when the VOD data and the EPG data are determined to have been received. Therefore, the VOD data and the EPG data may be searched simultaneously, and the terminal device may simultaneously obtain the VOD data and the EPG data, allowing the user to obtain the VOD data and the EPG data simultaneously, so as to facilitate the user to watch the data in time.
-
公开(公告)号：US20210256969A1
公开(公告)日：2021-08-19
申请号：US17024668
申请日：2020-09-17
发明人： Zhouwei Zhai , Rongsheng Huang , Ben Xu , Fei You , Ning Li , Wensong He
摘要： A method and apparatus for recognizing a user intention, a device, and a readable storage medium are disclosed. A specific implementation of the method includes: acquiring a plurality of rounds of dialogue data and a satisfaction degree of each round of dialogue data, selecting target dialogue data having a satisfaction degree meeting a set satisfaction condition; labeling input data in the target dialogue data with an intention label; and training the intention recognition model based on the input data in the target dialogue data and the intention label of the input data, so that the trained intention recognition model performs intention recognition on new input data.
-
-
-
搜索结果
4 条记录 (耗时 0.016 秒)
