-
公开(公告)号：US20230101388A1
公开(公告)日：2023-03-30
申请号：US18076230
申请日：2022-12-06
Inventor： Bin WU , Kai ZHONG , Jianzhong YANG , Tongbin ZHANG , Zhen LU
Abstract: A method for detecting a road change is provided. The method includes: obtaining a road image comprising a road to be detected; extracting a road region in the road image as a target region, wherein the road region corresponds to where the road to be detected is located; obtaining a target geographical location of the target region; determining a reference region for the target region from pre-stored road regions based on the target geographical location; calculating a similarity between the target region and the reference region; and determining, based on the similarity, whether a passability of the road to be detected is changed. By applying the solution provided by the embodiments of the present disclosure, efficiency of road change detection can be improved.
-
152.发明申请公开(公告)号：US20230094377A1
公开(公告)日：2023-03-30
申请号：US17735373
申请日：2022-05-03
Inventor： Qi LI , Hailu JIA , Xiaotong LIU
IPC: G06N5/04
Abstract: The present disclosure provides a subway operating state prediction method and apparatus, an electronic device and a storage medium, and relates to technical fields such as intelligent transportation and artificial intelligence. A specific implementation solution involves: acquiring air pressure information of a mobile terminal used by a user on a subway at respective moments in a time window; and predicting an operating state of the subway in the time window based on the air pressure information at the moments in the time window.
-
公开(公告)号：US20230092978A1
公开(公告)日：2023-03-23
申请号：US17992550
申请日：2022-11-22
Inventor： Xiaoming CHEN , Yongfeng JI , Zhe LI
IPC: G06F9/50 , G06F1/28 , G06F1/3206 , H05K5/02
Abstract: This disclosure provides a resource tapping method, a resource tapping apparatus and an electronic device, and relates to the field of computer technology, in particular to the technical field of artificial intelligence, such as deep learning and machine learning. A specific implementation is as follows: obtaining operation data in M resource dimensions of a target cabinet, the M resource dimensions including a power resource, where M is a positive integer; determining a target power over-allocation value of the target cabinet based on the operation data, the target power over-allocation value being used for indicating an allowable power increment on the basis of a power rating of the target cabinet; and determining, based on the target power over-allocation value, a first quantity of additional servers deployable in the target cabinet.
-
公开(公告)号：US20230089268A1
公开(公告)日：2023-03-23
申请号：US18060692
申请日：2022-12-01
Inventor： Hao Li , Zhenyu Jiao , Shuqi Sun , Yue Chang , Tingting Li
IPC: G06F40/56 , G06F40/35 , G06F16/332
Abstract: A semantic understanding method, includes: acquiring a query statement and a preceding dialogue; rewriting the query statement based on a preset rule to generate a target query statement if it is recognized that the query statement meets a rule rewriting condition according to the query statement and the preceding dialogue; rewriting the query statement based on a rewriting model to generate the target query statement if it is recognized that the query statement does not meet the rule rewriting condition according to the query statement and the preceding dialogue; and performing intention recognition according to the target query statement to generate an intention recognition result.
-
公开(公告)号：US20230084438A1
公开(公告)日：2023-03-16
申请号：US17992436
申请日：2022-11-22
Inventor： Zhe Hu , Jiachen Liu , Xinyan Xiao
Abstract: A method of generating a text, a method of training a text generation model, an electronic device, and a storage medium, which relate to a field of a computer technology, in particular to fields of deep learning and natural language processing technologies. A specific implementation solution includes: determining a reference feature representation of a target semantic information; determining, based on the reference feature representation and at least one predetermined logical character, at least one sentence latent representation respectively corresponding to the at least one predetermined logical character; and generating a target text content based on the at least one sentence latent representation.
-
Patent Agency Ranking
公开(公告)号：US20230081957A1
公开(公告)日：2023-03-16
申请号：US17943025
申请日：2022-09-12
Inventor： Xu ZHANG , Wenpeng DING
IPC: H04N19/533 , H04N19/139 , H04N19/513
Abstract: A method includes: performing a first diamond search according to an initial point determined from points in a search window, a search step size being incremented by ith power of 2, i being a natural number, 0≤i≤N; and performing the following first processing: acquiring an updated initial point and an optimization range, the optimization range being less than 2N; performing a second diamond search according to the initial point, wherein, prior to a search with a search step size larger than the optimization range, if it is determined that an ending condition is met, the diamond search is ended and a corresponding second optimal point is determined; and determining a required optimal motion vector according to the second optimal point if the second optimal point meets a predetermined requirement, and otherwise, repeating the first processing.
-
公开(公告)号：US20230079275A1
公开(公告)日：2023-03-16
申请号：US17985000
申请日：2022-11-10
Inventor： Tianyi Wu , Yu Zhu , Guodong Guo
Abstract: The present disclosure provides a method and apparatus for training a semantic segmentation model and a method and apparatus for performing a semantic segmentation on a video. The method comprises: acquiring a training sample set, wherein a training sample in the training sample set comprises at least one sample video stream and a pixel-level annotation result of the sample video stream; modeling a spatiotemporal context between video frames in the sample video stream using an initial semantic segmentation model to obtain a context representation of the sample video stream; calculating a temporal contrastive loss based on the context representation of the sample video stream and the pixel-level annotation result of the sample video stream; and updating a parameter of the initial semantic segmentation model based on the temporal contrastive loss to obtain a trained semantic segmentation model.
-
158.发明申请公开(公告)号：US20230078726A1
公开(公告)日：2023-03-16
申请号：US17932405
申请日：2022-09-15
Inventor： Bo JING
Abstract: Provided are a training method and apparatus for a distributed machine learning model, a device and a medium. The training method includes: acquiring a first homomorphic encryption intermediate parameter and a second homomorphic encryption intermediate parameter; generating a first interference parameter, and forming a first encryption interference parameter by encrypting the first interference parameter by using a second homomorphic public key of a second participant; performing calculation based on the first homomorphic encryption intermediate parameter, the second homomorphic encryption intermediate parameter, the first encryption interference parameter and the homomorphic calculation function of a first submodel to generate a first encryption key parameter.
-
159.发明申请公开(公告)号：US20230077816A1
公开(公告)日：2023-03-16
申请号：US17658513
申请日：2022-04-08
Inventor： Wei Du , Saisai Zou , Tengyu Du
Abstract: The present disclosure provides a method for training sound source localization model and a sound source localization method, and relates to the field of artificial intelligence technologies such as voice processing and deep learning. The method for training sound source localization model method includes: obtaining a sample audio according to an audio signal including a wake-up word; extracting an audio feature of at least one audio frame in the sample audio, and marking a direction label and a mask label of the at least one audio frame; and training a neural network model by using the audio feature of the at least one audio frame and the direction label and the mask label of the at least one audio frame, to obtain a sound source localization model. The sound source localization method includes: acquiring a to-be-processed audio signal, and extracting an audio feature of each audio frame in the to-be-processed audio signal; inputting the audio feature of each audio frame into a sound source localization model, to obtain sound source direction information outputted by the sound source localization model for each audio frame; determining a wake-up word endpoint frame in the to-be-processed audio signal; and obtaining a sound source direction of the to-be-processed audio signal according to sound source direction information corresponding to the wake-up word endpoint frame.
-
公开(公告)号：US20230076471A1
公开(公告)日：2023-03-09
申请号：US17982965
申请日：2022-11-08
Inventor： Xiyang WANG , Ruiqing ZHANG , Zhongjun HE , Zhi LI , Hua WU
Abstract: A training method, a text translation method, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of natural language processing and deep learning technologies. A specific implementation solution includes: performing a feature extraction on source sample text data to obtain a sample feature vector sequence; obtaining a target sample feature vector according to the sample feature vector sequence; performing an autoregressive decoding and a non-autoregressive decoding on the sample feature vector sequence, respectively; performing a length prediction on the target sample feature vector; training a predetermined model by using translation sample data, the autoregressive text translation result, the non-autoregressive text translation result, a true length value of the source sample text, the first predicted length value, a true length value of the translation sample text, and the second predicted length value to obtain the text translation model.
-
-
-
-
-
-
-
-
-
Search Results
1507
records
(took 0.082 seconds)
