-
公开(公告)号：US20210319795A1
公开(公告)日：2021-10-14
申请号：US17357598
申请日：2021-06-24
Inventor： Song YANG , Saisai ZOU , Jieyi CAO , Junyao SHAO
IPC: G10L15/22 , G10L15/05 , G06F16/635
Abstract: The disclosure provides a speech control method, a speech control apparatus, an electronic device, and a storage medium. The method includes: acquiring target audio data sent by a client, the target audio data including audio data collected by the client within a target duration before wake-up and audio data collected by the client after wake-up; performing speech recognition on the target audio data; and controlling the client based on an instruction recognized from a second audio segment of the target audio data in response to recognizing a wake-up word from a first audio segment at beginning of the target audio data; in which, the second audio segment is later than the first audio segment or has an overlapping portion with the first audio segment.
-
公开(公告)号：US20210319241A1
公开(公告)日：2021-10-14
申请号：US17354734
申请日：2021-06-22
Inventor： Pengyuan LYU , Chengquan ZHANG
Abstract: A method, an apparatus, a device and a storage medium for processing an image are provided. The method may include: acquiring a target image; determining at least one stamp image included in the target image; determining position information of a character in the at least one stamp image; and determining a text in the at least one stamp image based on the position information.
-
公开(公告)号：US20210319231A1
公开(公告)日：2021-10-14
申请号：US17355137
申请日：2021-06-22
Inventor： Yuchen Yuan
Abstract: Embodiments of the present disclosure provide a method and apparatus for detecting a target object, an electronic device, and a computer readable storage medium. The method may include: acquiring a to-be-detected image; processing the to-be-detected image using an object detection model including a deformable convolutional layer to obtain an offset prediction result of the deformable convolutional layer; and adjusting a size of an anchor point using the offset prediction result, and determining position information of the target object in the to-be-detected image using the anchor point of the adjusted size.
-
公开(公告)号：US20210318907A1
公开(公告)日：2021-10-14
申请号：US17355134
申请日：2021-06-22
Inventor： Ji Liu , Dejing Dou , Jizhou Huang , Qingyang Li
Abstract: A data management method, apparatus, a computing device, a storage medium, and a cloud platform are provided. The data management method includes: obtaining a task request, the task request indicating to retrieve stored data to execute a task; updating execution information for the data, the execution information for the data describing one or more tasks that need retrieval of the data and the execution frequency of each of the tasks; calculating, based on the updated execution information for the data and for each of a plurality of electronic storage locations, a storage-location-specific cost value of the data; and determining a target electronic storage location of the data according to the calculated cost value.
-
585.发明申请公开(公告)号：US20210318883A1
公开(公告)日：2021-10-14
申请号：US17343139
申请日：2021-06-09
Inventor： Yingnan XU , Xueliang DU
Abstract: The invention discloses an apparatus and method for writing back an instruction execution result. The apparatus for writing back the instruction execution result includes: a first writing port, coupled between a first execution unit with a first execution delay and a register file, and configured to receive a first execution result from the first execution unit, and to write the first execution result back to a first register unit in the register file based on a first writing address; and a second writing port, coupled between a second execution unit with a second execution delay different from the first execution delay and the register file, and configured to receive a second execution result from the second execution unit, and to write the second execution result back to a second register unit in the register file based on a second writing address.
-
Patent Agency Ranking
公开(公告)号：US20210312264A1
公开(公告)日：2021-10-07
申请号：US17354430
申请日：2021-06-22
Inventor： Fukui YANG , Shengzhao WEN , Junyu HAN
Abstract: A method, and an apparatus for model distillation are provided. The method may include: obtaining a batch of teacher features corresponding to a teacher model and a batch of student features corresponding to a student model; determining a set of teacher similarities corresponding to the batch of teacher features and a set of student similarities corresponding to the batch of student features; determining weights of loss values of features of images based on difference values corresponding to the images; and weighting a loss value of a feature of each image in a batch of images, training the student model by using a weighting result. The present disclosure may use the difference values between the feature similarities of the student model and the feature similarities of the teacher model to determine the weights of the loss values.
-
587.发明申请公开(公告)号：US20210306428A1
公开(公告)日：2021-09-30
申请号：US17347288
申请日：2021-06-14
Inventor： Jinshuai LIU , Siyuan LEI , Lei ZHOU , Lianlian CHEN
Abstract: A method, apparatus, electronic device, and computer readable storage medium for communication between private networks are provided. An embodiment of the method may include: receiving a communication request sent by a first sub-instance provided in a first private network, the first sub-instance being created based on that the first private network initiates a network registration request to a master instance; determining a second private network as a destination based on the communication request; and sending the communication request to the second private network through a second sub-instance provided in the second private network, the second sub-instance being created based on that the second private network initiates a network registration request to the master instance, wherein the first private network, the second private network, and a cloud enterprise network provided with the master instance forms a star topology centered on the cloud enterprise network.
-
公开(公告)号：US20210304413A1
公开(公告)日：2021-09-30
申请号：US17344917
申请日：2021-06-10
Inventor： Hao SUN , Fu LI , Tianwei LIN , Dongliang HE
Abstract: An image processing method, an image processing device and an electronic device, all relate to computer vision and deep learning. The image processing method includes: acquiring a first image and a second image; performing semantic region segmentation on the first image and the second image to acquire a first segmentation image and a second segmentation image respectively; determining an association matrix between the first segmentation image and the second segmentation image; and processing the first image in accordance with the association matrix to acquire a target image.
-
公开(公告)号：US11132387B2
公开(公告)日：2021-09-28
申请号：US16255359
申请日：2019-01-23
IPC: G06F16/28 , G06F16/2457
Abstract: An event display method and an event display device are provided. The method includes: acquiring types of events; setting colors for the events based on the types of the events; grouping the events based on starting times and ending times of the respective events; and displaying the events based on the grouping and colors of the events. According to the embodiments, the event type, event distribution and event duration can be intuitively displayed, the user can quickly screen out valid events and quickly acquire valid information of the events, thereby quickly positioning a fault and determining a cause for the fault.
-
590.发明申请公开(公告)号：US20210295857A1
公开(公告)日：2021-09-23
申请号：US17035548
申请日：2020-09-28
Inventor： Nengjun OUYANG , Junhua XU , Zhengbin SONG , Danqing YANG , Gang XU
IPC: G10L21/0216 , B60R16/037 , G10L15/20
Abstract: This application discloses a voice recognition method, a voice recognition apparatus, an electronic device and a computer readable storage medium, and relates to the field of voice recognition technology. A specific implementation is: performing a latency estimation according to a first microphone signal and a first reference signal in a preset time period to obtain a latency value; acquiring a system audio signal, and processing the system audio signal by using the latency value to obtain a second reference signal; performing de-noising processing on a collected second microphone signal according to the second reference signal, to obtain a to-be-recognized voice signal; and performing recognition on the to-be-recognized voice signal.
-
-
-
-
-
-
-
-
-
Search Results
1986
records
(took 0.032 seconds)
