-
公开(公告)号：US10863137B2
公开(公告)日：2020-12-08
申请号：US16710597
申请日：2019-12-11
Inventor： Jiamei Kang , Xingbiao Li , Wanqi Tang , Hanyao Shao , Yijing Zhou
Abstract: Embodiments of the present disclosure provide a method and apparatus for controlling an audio-video conference, a device and a storage medium. The method may include: establishing, according to a conference preparation request of an inviting party, a communication connection between a target basic audio-video device of an associated conference room and the inviting party, and enabling the inviting party to select at least one invited party; constructing a conference join request according to an invited party included in a conference initiation request of the inviting party, and sending the conference join request to the invited party; and establishing, based on a confirmation response fed back for the conference join request by the invited party, a communication connection between the invited party and the target basic audio-video device.
-
2.发明申请公开(公告)号：US20200334682A1
公开(公告)日：2020-10-22
申请号：US16851726
申请日：2020-04-17
Inventor： Jiamei Kang
Abstract: Embodiments of the present disclosure provide a face payment device, a face payment method, a face payment system and a machine-readable storage medium. The face payment device includes a first facial information recognition unit, a second facial information recognition unit, and a payment unit. The second facial information recognition unit is configured to receive first facial information of one or more persons in a place, and compare the first facial information with a pre-stored public database to obtain first identity information that matches the first facial information. The second facial information recognition unit is configured to receive second facial information of persons waiting for payment at a payment spot, and compare the second facial information with the first identity information to obtain second identity information that matches the second facial information. The payment unit is configured to perform a transaction based on the second identity information and a payment instruction.
-
公开(公告)号：US11488603B2
公开(公告)日：2022-11-01
申请号：US16711310
申请日：2019-12-11
Inventor： Wanqi Tang , Jiamei Kang , Lixia Zeng , Yijing Zhou , Hanmei Xie , Lina Zhu
Abstract: Embodiments of the present disclosure provide a method and apparatus for processing a speech. The method may include: acquiring an original speech; performing speech recognition on the original speech, to obtain an original text corresponding to the original speech; associating a speech segment in the original speech with a text segment in the original text; recognizing an abnormal segment in the original speech and/or the original text; and processing a text segment indicated by the abnormal segment in the original text and/or the speech segment indicated by the abnormal segment in the original speech, to generate a final speech. A speech segment in the original speech is associated with a text segment in the original text to realize visual processing of the speech.
-
-
Search Results
3
records
(took 0.016 seconds)
