-
公开(公告)号：US11436540B2
公开(公告)日：2022-09-06
申请号：US16722649
申请日：2019-12-20
Inventor： Guangyao Han , Xingbo Chen , Guobin Xie , Yanjiang Liu , Fu Qu , Liqiang Xue , Jin Zhang , Wenjing Qin , Xiaolan Luo , Hongjiang Du , Zeqing Jiang
Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating information. The method may include: receiving a modeling request; determining a target number of initial machine learning pipelines according to a type of training data and a model type; and executing following model generation steps using the target number of initial machine learning pipelines: generating a target number of new machine learning pipelines based on the target number of initial machine learning pipelines; performing model training based on the training data, the target number of initial machine learning pipelines, and the target number of new machine learning pipelines, to generate trained models; evaluating the obtained trained models respectively according to the evaluation indicator; determining whether a preset training termination condition is reached; and determining, in response to determining the preset training termination condition being reached, a target trained model from the obtained trained models according to evaluation results.
-
92.发明授权公开(公告)号：US11436409B2
公开(公告)日：2022-09-06
申请号：US16458427
申请日：2019-07-01
Inventor： Zhipeng Wu , Zhihua Wang , Tianxing Yang
IPC: G06F40/253 , G06F40/295 , G06F40/232 , G06F40/30
Abstract: Embodiments disclose a method and apparatus for updating subject name information of a target information source. A specific embodiment of the method includes: acquiring at least one subject name from to-be-processed information; matching, for a subject name in the at least one subject name, the subject name with pre-acquired at least one initial information source subject name, and setting a weight for the subject name based on a matching result; and sorting the subject name in the at least one subject name and an initial information source subject name in the at least one initial information source subject name according to the weight to obtain updated at least one initial information source subject name.
-
公开(公告)号：US11429680B2
公开(公告)日：2022-08-30
申请号：US16234337
申请日：2018-12-27
Inventor： Hao Tian , Daren Li , Bo Huang , Dai Dai , Chengxiang Liu , Anjun Wei , Kexin Ren , Haiguang Yuan
IPC: G06F16/00 , G06F16/953 , G06F16/33 , G06F16/31 , G06F16/174
Abstract: Embodiments of the present disclosure disclose a method and apparatus for subscribing to a topic. The method includes: matching a persistent topic for a retrieval keyword based on the retrieval keyword of a user combined with at least one of historical behavior or a subscription record of the user; returning the persistent topic to a client for display, so that the user performs subscription; and saving the persistent topic subscribed to by the user, and when a matching resource corresponding to the persistent topic subscribed to by the user is updated, recommending the updated matching resource to the user. Since a recommendation strategy can be timely adjusted according to real-time behavior of a user combined with historical behavior, the probability of hitting a topic of interest to the user is increased.
-
公开(公告)号：US20220270289A1
公开(公告)日：2022-08-25
申请号：US17743402
申请日：2022-05-12
Inventor： Wei Zhang , Xiaoqing Ye , Xiao Tan , Hao Sun , Shilei Wen , Hongwu Zhang , Errui Ding
IPC: G06T7/73 , G06T7/194 , G06T7/593 , H04N13/128
Abstract: A method and device for detecting a vehicle pose, relating to the fields of computer vision and automatic driving. The specific implementation solution comprises: inputting a vehicle left view point image and a vehicle right view point image into a part prediction and mask segmentation network model, and determining foreground pixel points and part coordinates thereof in a reference image; converting coordinates of the foreground pixels in the reference image into coordinates of the foreground pixels in a camera coordinate system so as to obtain a pseudo-point cloud, and fusing part coordinate of the foreground pixels and the pseudo-point cloud to obtain fused pseudo-point cloud; and inputting the fused pseudo-point cloud into a pre-trained pose prediction model to obtain a pose information of the vehicle to be detected.
-
公开(公告)号：US11416967B2
公开(公告)日：2022-08-16
申请号：US17024253
申请日：2020-09-17
Inventor： Chao Li , Shilei Wen , Errui Ding
Abstract: Embodiments of the present disclosure provide a video processing method, a video processing device and a related non-transitory computer readable storage medium. The method includes the following. Frame sequence data of a low-resolution video to be converted is obtained. Pixel tensors of each frame in the frame sequence data are inputted into a pre-trained neural network model to obtain high-resolution video frame sequence data corresponding to the video to be converted output by the neural network model. The neural network model obtains the high-resolution video frame sequence data based on high-order pixel information of each frame in the frame sequence data.
-
Patent Agency Ranking
公开(公告)号：US11416283B2
公开(公告)日：2022-08-16
申请号：US16503145
申请日：2019-07-03
Inventor： Weikang Gao , Yanlin Wang , Yue Xing , Jianwei Zhang , Yi Cheng
IPC: G06F9/48 , G06F9/50 , G06F9/54 , G06F9/4401 , G06F9/455
Abstract: A method and apparatus for processing stream data are provided. The method may include: acquiring a to-be-adjusted number of target execution units, the target execution unit referring to a unit executing a target program segment in a stream computing system; adjusting a number of the target execution units in the stream computing system based on the to-be-adjusted number; determining, for a target execution unit in at least one target execution unit after the adjustment, an identifier set corresponding to the target execution unit, an identifier in the identifier set being used to indicate to-be-processed data; and processing, through the target execution unit, the to-be-processed data indicated by the identifier in the corresponding identifier set.
-
公开(公告)号：US11412024B2
公开(公告)日：2022-08-09
申请号：US16675810
申请日：2019-11-06
Inventor： Yongqiang Wu , Yixing Sun , Tai Wang
IPC: H04L65/80 , H04L47/125 , H04L47/24 , H04L65/61 , H04L67/1008 , H04L67/101 , H04L67/141 , H04L67/5681 , H04L69/40
Abstract: Embodiments of the present disclosure relate to a method, apparatus, electronic device for determining an access path of a content delivery network, and a computer readable medium. A method may include: acquiring, in response to determining that an edge node receiving a user request fails to cache a requested resource, access performance information of each node in the content delivery network, and determining a target path from the edge node receiving the user request via a preset node corresponding to a requested target source station in the content delivery network to the target source station based on the access performance information of the each node in the content delivery network, where the preset node pre-establishes a connection with the requested target source station, and a distance between the preset node and the target source station meets a preset distance condition.
-
公开(公告)号：US11380104B2
公开(公告)日：2022-07-05
申请号：US16798162
申请日：2020-02-21
Inventor： Guanhao Wang , Zhi Ye
Abstract: The present disclosure provides a method for detecting illegal parking. The method includes: obtaining a detection frame having a category of vehicle from an image acquired by an acquisition module through a first neural network to determine coordinate information of the detection frame; determining whether an area corresponding to the detection frame in the image is an illegal parking area through a second neural network; and when determining that the area is the illegal parking area, determining whether the coordinate information of the detection frame is changed within a preset period of time to determine whether the vehicle is parked illegally.
-
公开(公告)号：US11378957B1
公开(公告)日：2022-07-05
申请号：US16677321
申请日：2019-11-07
Inventor： Xinjing Cheng , Ruigang Yang , Yajue Yang , Feixiang Lu , Hao Xu
Abstract: Embodiments of the present disclosure relate to a method and apparatus for controlling vehicle driving. The method includes: generating a global path of a driving site of a vehicle; executing following controlling: generating a local path of a site in front of a current position of the vehicle based on the global path, the local path following a direction of the global path, controlling the vehicle to drive along the local path until reaching an end point of the local path, determining whether the vehicle reaches an end point of the global path, and terminating the controlling if the vehicle reaches the endpoint of the global path; and continuing, in response to determining the vehicle failing to reach the end point of the global path, executing the controlling.
-
公开(公告)号：US11372594B2
公开(公告)日：2022-06-28
申请号：US17209914
申请日：2021-03-23
Inventor： Yu Hou , Shiyong Li , Junfang Zhao , Yueji Liu
IPC: G06F3/06
Abstract: The present disclosure provides a method and apparatus for scheduling a memory access request, an electronic device and a storage medium. The method may include: acquiring monitoring data of at least one service module; determining a target service module from the at least one service module based on the monitoring data; determining a target NUMA node matching the target service module from a preset NUMA node set, based on the monitoring data; and sending a memory access request of the target service module to the target NUMA node.
-
-
-
-
-
-
-
-
-
Search Results
1660
records
(took 0.078 seconds)
