-
21.发明申请公开(公告)号：US20250077780A1
公开(公告)日：2025-03-06
申请号：US18748642
申请日：2024-06-20
Inventor： Yongkang Xie , Guming Gao , Penghao Zhao , Xue Xiong , Qian Wang , Dongze Xu , En Shi , Yuxuan Li , Sheng Zhou , Shupeng Li , Yao Wang , Zhou Xin
Abstract: A method for invoking a plugin of a large language model includes: acquiring natural language content; performing semantic understanding on the natural language content and detecting whether the natural language content hits a plugin to obtain a first plugin pointed to by the plugin hit result; comparing the first plugin with a second plugin corresponding to the current session understanding task to determine a to-be-executed session understanding task and a third plugin corresponding to the to-be-executed session understanding task; acquiring the language understanding content of the to-be-executed session understanding task and sending the language understanding content to the large language model to obtain the input parameter of the third plugin; and calling the third plugin according to the input parameter of the third plugin to obtain the calling result of the to-be-executed session understanding task.
-
公开(公告)号：US20250069345A1
公开(公告)日：2025-02-27
申请号：US17917518
申请日：2022-04-21
Inventor： Bo JU , Xiaoqing YE , Xiao TAN , Hao SUN
Abstract: Disclosed are a method for generating point cloud data, an electronic device and a storage medium. The method includes: acquiring a set of real point clouds for a target object based on a LiDAR; performing image acquisition on the target object, and generating a set of pseudo point clouds based on an acquired image; and generating the set of target point clouds for model training by fusing the set of real point clouds and the set of pseudo point clouds.
-
23.发明申请公开(公告)号：US20250054272A1
公开(公告)日：2025-02-13
申请号：US18749546
申请日：2024-06-20
Inventor： Xu ZHANG
IPC: G06V10/44 , G06V20/70 , H04N19/176
Abstract: The present disclosure provides a method and apparatus for training a reference frame screening model, a method and apparatus for screening a reference frame, an electronic device, a storage medium, and a computer program product, relates to the field of artificial intelligence. An implementation scheme is: acquiring a training sample set, where training samples in the training sample set include a sequence of video frames and labels corresponding to video frames in the sequence of video frames, and the labels are used to represent whether the video frames corresponding to the labels are reference frames of other video frames in the sequence of video frames; and training, using a machine learning method, using the sequence of video frames as input, using the labels corresponding to the input sequence of video frames as desired output, to obtain a reference frame screening model.
-
公开(公告)号：US20250053605A1
公开(公告)日：2025-02-13
申请号：US18720621
申请日：2022-09-26
Inventor： Gonghui LI , Lunan ZHAO , Shouke QIN , Xiaolong MA , Kun LI
IPC: G06F16/954 , G06F16/906
Abstract: A method is provided that includes: obtaining a list of browsed information of each of a plurality of first users and a first vector corresponding to each list of browsed information; clustering the first vectors to obtain one or more vector clusters and a center vector of each vector cluster; determining one or more information clusters respectively corresponding to the one or more vector clusters; obtaining a list of browsed information of a second user in response to a browsing request of the second user; determining, in response to determining that the list of browsed information of the second user is not void, a second vector corresponding to the list of browsed information of the second user; calculating a similarity between the second vector and each center vector, to determine an information cluster matched with the second vector; and providing recommendations for the second user based on the information cluster.
-
25.发明申请公开(公告)号：US20250036920A1
公开(公告)日：2025-01-30
申请号：US18026140
申请日：2022-09-20
Inventor： Liang SHEN , Haifeng WANG , Huachao WU , Weibao GONG , Zhihua WU , Dianhai YU
IPC: G06N3/045 , G06N3/0495
Abstract: The present disclosure provides a mixture-of-experts (MoE) model implementation method and system, an electronic device, and a storage medium, and relates to the field of artificial intelligence (AI) such as deep learning and distributed storage. The method includes: constructing a communication group, the communication group including a tensor-parallelism communication group, the tensor-parallelism communication group including at least two computing devices, tensor-parallelism segmentation being adopted for sparse parameters of each of the computing devices in a same tensor-parallelism communication group; and training an MoE model based on the communication group. By use of the solutions of the present disclosure, normal operation of model training can be guaranteed.
-
Patent Agency Ranking
公开(公告)号：US12211381B2
公开(公告)日：2025-01-28
申请号：US17727390
申请日：2022-04-22
Inventor： Yuzhe Wang , Jiantao Zhao
IPC: G08G1/123
Abstract: A method and apparatus for prompting navigation information. The method includes: acquiring, when a user is in an underground vehicle area, traffic behavior statuses of an underground vehicle at stops on a preset navigation route; determining, in response to the traffic behavior status of each stop of adjacent stops on the navigation route being consistent with a first preset traffic behavior status, a base station corresponding to a latter stop in the adjacent stops as a reference station; determining a location of a preset stop on the navigation route, based on a location of the reference station and locations of base stations provided at the stops; and outputting, in response to the traffic behavior status of the underground vehicle at the preset stop being consistent with a second preset traffic behavior status, prompt information for getting off.
-
公开(公告)号：US20250029010A1
公开(公告)日：2025-01-23
申请号：US18895264
申请日：2024-09-24
Inventor： Dianhai Yu , Gexiao Tian , Weibao Gong , Haifeng Wang , Yongsheng Xu , Jiabin Yang
IPC: G06N20/00
Abstract: A cluster-based training method includes: in response to a hardware fault in the training node, selecting a target standby node from the plurality of standby nodes, and obtaining a target training snapshot of the model training task in the training node, in which the target training snapshot includes training state data of the model training task; and initializing the target standby node based on a container image of a model training program in the training node and the training state data to replace the training node with the target standby node to continue executing the model training task.
-
28.发明授权公开(公告)号：US12206583B2
公开(公告)日：2025-01-21
申请号：US17902522
申请日：2022-09-02
Inventor： Chenfei Wang
IPC: H04L47/12
Abstract: A data transmission method and apparatus, an electronic device, a computer readable storage medium, and a computer program product are provided. The method includes: receiving to-be-transmitted data currently transmitted from a data source node; determining an average receiving interval and an average transmitting interval based on a historical data receiving interval and a historical data transmitting interval; determining the splitting transmission number based on the average receiving interval and the average transmitting interval; obtaining a plurality of data fragments based on a data size of the to-be-transmitted data and the splitting transmission number; and sequentially and uniformly transmitting the data fragments to a next-level node within a subsequent period with a duration being the average receiving interval.
-
公开(公告)号：US12204851B2
公开(公告)日：2025-01-21
申请号：US17864636
申请日：2022-07-14
Inventor： Tongyang Liu , Shu Wang , Wanli Chang , Wei Zheng , Zhifan Feng , Chunguang Chai , Yong Zhu
IPC: G06F40/211 , G06F40/109 , G06F40/30 , G06N3/08
Abstract: A method for generating a pre-trained language model, includes: obtaining sample files; obtaining typography structure information and text information of the sample files by parsing the sample files; obtaining a plurality of task models of a pre-trained language model; obtaining a trained pre-trained language model by jointly training the pre-trained language model and the plurality of task models according to the typography structure information and the text information; and generating a target pre-trained language model by fine-tuning the trained pre-trained language model according to the typography structure information and the text information.
-
公开(公告)号：US20250023812A1
公开(公告)日：2025-01-16
申请号：US18747058
申请日：2024-06-18
Inventor： Tengfei Shan
IPC: H04L45/122 , H04L45/02 , H04L45/28
Abstract: A method for redirecting an edge node for a client includes: determining a peak bandwidth of a target region based on peak bandwidths of edge nodes in the target region, in which there are at least two edge nodes in the target region; determining a bandwidth ratio of each edge node based on the peak bandwidth of the target region and peak bandwidth of each edge node; obtaining a hash value of a data request address of a client request data by calculating the data request address using a preset algorithm; and determining one target edge node as an edge node of the client request data from the edge nodes of the target region based on the hash value and the bandwidth ratio of each edge node.
-
-
-
-
-
-
-
-
-
Search Results
1526
records
(took 0.032 seconds)
