-
81.发明公开公开(公告)号：US20240070454A1
公开(公告)日：2024-02-29
申请号：US18108956
申请日：2023-02-13
Inventor： Ruoyu GUO , Yuning DU , Chenxia LI , Baohua LAI , Yanjun MA
Abstract: Provided is a lightweight model training method, an image processing method, a device and a medium. The lightweight model training method includes: acquiring first and second augmentation probabilities and a target weight adopted in an e-th iteration; performing data augmentation on a data set based on the first and second augmentation probabilities respectively, to obtain first and second data sets; obtaining a first output value of a student model and a second output value of a teacher model based on the first data set; obtaining a third output value and a fourth output value based on the second data set; determining a distillation loss function, a truth-value loss function and a target loss function; training the student model based on the target loss function; and determining a first augmentation probability or target weight to be adopted in an (e+1)-th iteration in a case of e is less than E.
-
公开(公告)号：US20240062654A1
公开(公告)日：2024-02-22
申请号：US17753817
申请日：2021-11-17
Inventor： Jizhou Huang , Deguo Xia , Haifeng Wang
IPC: G08G1/0968 , G08G1/01 , G08G1/0967 , G08G1/052
CPC classification number: G08G1/0968 , G08G1/0145 , G08G1/0112 , G08G1/096725 , G08G1/052
Abstract: The present disclosure discloses a vehicle control method and apparatus, a device and a computer storage medium, and relates to the technical fields of autonomous driving and intelligent transportation. A specific implementation solution involves: determining vehicles in a preset geo-fencing region; determining a vehicle weight of each said vehicles according to a vehicle type and a waiting duration of each said vehicles; estimating, according to the vehicle weights of the vehicles in each of lanes in the geo-fencing region and positions of the vehicles in each said lanes, a duration to be waited in each said lanes; and generating a control instruction for each said vehicles according to the respective durations to be waited in each said lanes and the respective positions of the vehicles in each said lanes, the control instruction including a state instruction and/or a target speed instruction. According to the present disclosure, global scheduling decisions can be performed on vehicles in a geo-fencing region, so as to alleviate traffic congestion.
-
公开(公告)号：US20240062351A1
公开(公告)日：2024-02-22
申请号：US18113860
申请日：2023-02-24
Inventor： Wei WANG , Yizhuo LIU
CPC classification number: G06T7/0002 , G06V20/49 , H04N9/64 , G06T7/90 , G06T2207/10024 , G06T2207/10016 , G06T2207/20021 , G06T2207/30168
Abstract: Provided is a method for evaluating video quality, an electronic device and a storage medium, relating to the field of computer technology, and in particular, to the field of artificial intelligence, cloud computing, computer vision and deep learning technologies. The method includes: determining a plurality of video frames containing a target object in a target video; obtaining HSL data of an image area corresponding to the target object in the plurality of video frames; and evaluating a quality of the target video according to the HSL data.
-
公开(公告)号：US11907668B2
公开(公告)日：2024-02-20
申请号：US18148904
申请日：2022-12-30
Inventor： Minlong Peng , Mingming Sun , Ping Li
Abstract: The present disclosure provides a method for selecting an annotated sample. The method includes: determining a first attribute and a second attribute of a sample characteristic; in which the first attribute is a characteristic attribute of the sample characteristic in a source field sample set, and the second attribute is a characteristic attribute of the sample characteristic in a target field sample set; and determining a target annotated sample from a plurality of candidate annotated samples of the source field sample set according to the first attribute and the second attribute; in which the target annotated sample is configured to train a classification model, the classification model includes a model for determining an emotion polarity by analyzing an input sample to be classified.
-
公开(公告)号：US11900918B2
公开(公告)日：2024-02-13
申请号：US17451380
申请日：2021-10-19
Inventor： Liao Zhang , Zhengxiang Jiang , Xiaoyin Fu
IPC: G10L15/06 , G06F40/253 , G06F40/30
CPC classification number: G10L15/063 , G06F40/253 , G06F40/30
Abstract: The present disclosure provides a method for training a linguistic model, related to fields of speech, natural language processing, deep learning technologies. A method includes: obtaining grammars corresponding to a plurality of sample texts and a slot value of a slot in each grammar by using semantic analysis; generating a grammar graph corresponding to each grammar based on the corresponding grammar and the slot value of the slot in the corresponding grammar; obtaining a weight of each grammar, a weight of each slot, and a weight of each slot value in each grammar graph based on the sample texts; determining at least one grammar frequency of each order based on the weight of each grammar, the weight of each slot, and the weight of each slot value in each grammar graph; and training the linguistic model based on the at least one grammar frequency of each order.
-
Patent Agency Ranking
86.发明公开公开(公告)号：US20240037436A1
公开(公告)日：2024-02-01
申请号：US18483184
申请日：2023-10-09
Inventor： Zelin MENG , Shusen LIU , Xueyi GUO , Zixian YAN , Wenxue ZHANG , Yang HE
CPC classification number: G06N10/20 , G06F9/5027
Abstract: A system for processing a quantum task, a method, a device and a storage medium are provided. The system includes: a user terminal, configured to acquire basic measurement and control parameters of a superconducting quantum computer, generate a quantum task consisting of a quantum pulse and a quantum pulse gate based on the basic measurement and control parameters and an intended task purpose, and send the quantum task to a quantum hardware client; the quantum hardware client, configured to parse the quantum task into a queue of quantum pulses arranged in a time sequence, and send the queue of quantum pulses to the superconducting quantum computer; and the superconducting quantum computer, configured to execute quantum pulse instructions in the queue of quantum pulses in the time sequence, and return an obtained task result to the user terminal.
-
公开(公告)号：US11849164B2
公开(公告)日：2023-12-19
申请号：US17820207
申请日：2022-08-16
Inventor： Tengfei Shan , Xiaoen Zhu
IPC: H04N21/24 , H04N21/2187
CPC classification number: H04N21/2402 , H04N21/2187
Abstract: Provided is a method for detecting live streaming jitter, a device, and a medium. An implementation is: calculating, for a live stream transmitted by an edge content delivery network (CDN) node in a CDN, quality information of the live stream based on a transmission frame rate and a viewer count of the live stream; calculating quality information of the edge CDN node based on the quality information of the live stream; and determining, based on the quality information of the edge CDN node, whether jitter occurs at the edge CDN node.
-
公开(公告)号：US20230376726A1
公开(公告)日：2023-11-23
申请号：US17980204
申请日：2022-11-03
Inventor： Zhengxiong YUAN , Zhenfang CHU , Jinqi LI , Mingren HU , Guobin WANG , Yang LUO , Yue HUANG , Zhengyu QIAN , En SHI
IPC: G06N3/04
CPC classification number: G06N3/04
Abstract: Provided are an inference service deployment method, a device and a storage medium, relating to the field of artificial intelligence technology, and in particular to the field of machine learning and inference service technology. The inference service deployment method includes: obtaining performance information of a runtime environment of a deployment end; selecting a target version of an inference service from a plurality of candidate versions of the inference service of a model according to the performance information of the runtime environment of the deployment end; and deploying the target version of the inference service to the deployment end.
-
公开(公告)号：US11823494B2
公开(公告)日：2023-11-21
申请号：US17494724
申请日：2021-10-05
Inventor： Tao Hu , Xiangbo Su
CPC classification number: G06V40/20 , G06V10/40 , G06V10/751 , G06V20/52
Abstract: A human behavior recognition method, a device, and a storage medium are provided, which are related to the field of artificial intelligence, specifically to computer vision and deep learning technologies, and applicable to smart city scenarios. The method includes: obtaining attribute information of a target object and N pieces of candidate behavior-related information of a target human from a target image, wherein N is an integer greater than or equal to 1; determining target behavior-related information based on comparison results between the N pieces of candidate behavior-related information and the attribute information of the target object; and determining a behavior recognition result of the target human based on the target behavior-related information.
-
公开(公告)号：US11822568B2
公开(公告)日：2023-11-21
申请号：US17577668
申请日：2022-01-18
Inventor： Zhen Wang
CPC classification number: G06F16/254 , G06F16/215 , G06F16/219 , G06F16/2237 , G06F16/2365
Abstract: A data processing method, an electronic equipment, and a storage medium. The method includes: acquiring target data; performing a data segmentation on the target data by using a first micro-service to obtain a plurality of types of sub-data; using a plurality of second micro-services to process the plurality of types of sub-data to obtain a plurality of data processing results respectively corresponding to the plurality of second micro-services, in which each second micro-service corresponds to one type of sub-data; combining the plurality of data processing results to obtain a target data processing result.
-
-
-
-
-
-
-
-
-
Search Results
1511
records
(took 0.039 seconds)
