公开(公告)号：EP4092529A1

公开(公告)日：2022-11-23

申请号：EP20914465.8

申请日：2020-11-02

申请人： Gree Electric Appliances, Inc. of Zhuhai ,  Leayun Technology Co., Ltd. of Zhuhai

发明人： LI, Mingjie ,  SONG, Dechao ,  JIA, Jutao ,  WU, Wei ,  HU, Tianyun

IPC分类号： G06F9/48

摘要： Embodiments of the present disclosure provide a method and an apparatus for scheduling a service, an electronic device, and a storage medium. The method includes: a service scheduling task is acquired, the service scheduling task is composed of a first identifier corresponding to a service request, and a second identifier corresponding to a device receiving the service request; a third identifier corresponding to a service associated with the service scheduling task is searched in a preset service scheduling knowledge graph; at least one service scheduling sequence is generated on the basis of the service scheduling task and the third identifier corresponding to the service; a target service scheduling sequence is determined from the at least one service scheduling sequence; and the device is notified to access a service corresponding to the third identifier in the target service scheduling sequence. By determining a target service scheduling sequence from the at least one service scheduling sequence, and notifying the device to access the service corresponding to the third identifier in the target service scheduling sequence, the optimization of service allocation can be realized, and the high-quality service and experience can be provided for users.

公开(公告)号：EP3923273A1

公开(公告)日：2021-12-15

申请号：EP19915991.4

申请日：2019-10-09

申请人： Gree Electric Appliances, Inc. of Zhuhai

发明人： LI, Mingjie ,  SONG, Dechao ,  JIA, Jutao ,  WU, Wei ,  XIE, Junjie

IPC分类号： G10L15/22

摘要： Provided is a voice recognition method and apparatus, a storage medium, and an air conditioner. The method includes: acquiring first voice data (S110); adjusting, according to the first voice data, a collection state of second voice data to obtain an adjusted collection state, and acquiring the second voice data based on the adjusted collection state (S120); and performing far-field voice recognition on the second voice data using a preset far-field voice recognition model so as to obtain semantic information corresponding to the acquired second voice data (S130). The application can solve the problem in which far-field voice recognition performance is poor when a deep learning method or a microphone array method is used to remove reverberation and noise from far-field voice data, thereby enhancing far-field voice recognition performance.