-
公开(公告)号：US12175198B2
公开(公告)日：2024-12-24
申请号：US17952103
申请日：2022-09-23
Inventor： Yingqi Sun
IPC: G06F40/30 , G06F40/103 , G06F40/279 , G06V30/19 , G06V30/412
Abstract: A method of document processing is provided. An implementation solution is: obtaining target text information and target layout information of a target document, the target text information includes target text included in the target document and character position information of the target text, and the target layout information is used to characterize the region where text in the target document is located; fusing the target text information and the target layout information to obtain first multimodal information of the target document; and inputting the first multimodal information into an intelligent document comprehension model, and obtaining at least one target word in the target document and at least one feature vector corresponding to the at least one target word output by the intelligent document comprehension model, each target word is related to semantics of the target document.
-
公开(公告)号：US12174824B2
公开(公告)日：2024-12-24
申请号：US18147823
申请日：2022-12-29
Inventor： Wei Xu , Xiaoling Xia , Junxiang Jiang , Chengtai Cao , Bolei He , Kunbin Chen , Wei He
IPC: G06F16/23 , G06F9/451 , G06F16/906 , G06F18/10 , G06F18/213 , G06F18/241 , G06F18/2415
Abstract: A method for denoising click data includes: acquiring a set of click data including pieces of first click data and a real label corresponding to each piece of first click data; extracting feature vectors of each piece of first click data with a graph model; dividing the feature vectors into sets of feature vectors; obtaining trained binary classification models by training binary classification models with the sets of feature vectors; for each of the feature vectors, obtaining prediction values corresponding to the feature vector by predicting the feature vector with the trained binary classification models, and calculating a prediction label of the feature vector based on the prediction values of the feature vector; and removing noise data in the pieces of first click data, based on the pieces of first click data, the real label and the prediction label of each piece of first click data.
-
613.发明授权公开(公告)号：US12169942B2
公开(公告)日：2024-12-17
申请号：US17324174
申请日：2021-05-19
Inventor： Minyue Jiang , Xipeng Yang , Xiao Tan , Hao Sun
Abstract: A method for training an image depth estimation model. A sample environmental image, sample environmental point cloud data and sample edge information of the sample environmental image are input into a to-be-trained model; initial depth information of each of pixel points in the sample environmental image and a feature relationship between each of the pixel points and a corresponding neighboring pixel point of each of the pixel points are determined through the to-be-trained model, the initial depth information of each of the pixel points is optimized according to the feature relationship to obtain optimized depth information of each of the pixel points, and a parameter of the to-be-trained model is adjusted according to the optimized depth information to obtain the image depth estimation model.
-
公开(公告)号：US20240411616A1
公开(公告)日：2024-12-12
申请号：US18748075
申请日：2024-06-19
Inventor： Yao LIN
IPC: G06F9/50
Abstract: A resource eviction method, an electronic device and a readable storage medium, which relate to the field of artificial intelligence technologies, such as cloud service technologies, big data technologies, or the like, are disclosed. The resource eviction method includes: acquiring an access day number of at least one target resource in a current cache period, and acquiring an access frequency of the at least one target resource according to the access day number and a preset time interval; acquiring a time heat factor corresponding to the current cache period, and acquiring resource heat of the at least one target resource according to the access frequency and the time heat factor; acquiring target heat according to the time heat factor; and evicting the target resource with the resource heat smaller than or equal to the target heat, updating the time heat factor according to a preset update value, and taking the updated time heat factor as a time heat factor corresponding to a next cache period.
-
公开(公告)号：US20240394190A1
公开(公告)日：2024-11-28
申请号：US18696757
申请日：2022-09-27
Inventor： Minxu ZHANG , Haifeng WANG , Fan ZHANG , Xinxuan WU , Xuefeng YAO , Danlei FENG , Zhihua WU , Zhipeng TAN , Jie DING , Dianhai YU
IPC: G06F12/0873 , G06F12/0815 , G06F15/80
Abstract: The present application provides a method of training a deep learning model. A specific implementation solution of the method of training the deep learning model includes: determining, according to first training data for a current training round, a first target parameter required to be written into a target memory in a first network parameter required by an embedding of the first training data, wherein the target memory is a memory contained in a target processor; determining a remaining storage slot in the target memory according to a first mapping relationship between a storage slot of the target memory and a network parameter; and writing, in response to the remaining storage slot meeting a storage requirement of the first target parameter, the first target parameter into the target memory so that a computing core contained in the target processor adjusts the first network parameter according to the first training data.
-
Patent Agency Ranking
公开(公告)号：US12155500B2
公开(公告)日：2024-11-26
申请号：US18099458
申请日：2023-01-20
Inventor： Zhiyu Liu
Abstract: Provided are a remote control method and apparatus, an electronic device and a medium, which relate to the field of communications and in particular, to the fields of smart home, smart life, Internet of things and cloud service. The specific implementation is as follows: acquiring a remote control instruction from a first smart device, wherein the remote control instruction is generated according to a control operation on a second remote controller and transmitted to the first smart device through a second smart device, and the first smart device is connected to a first remote controller; and controlling a control object of the first remote controller according to the remote control instruction.
-
公开(公告)号：US12148295B2
公开(公告)日：2024-11-19
申请号：US17824966
申请日：2022-05-26
Inventor： Xinjiang Lu , Dejing Dou
IPC: G08G1/01
Abstract: A method of predicting traffic volume, an electronic device, and a storage medium are provided, which relate to a field of artificial intelligence technology, in particular to big data and deep learning technologies The method includes: generating, for a plurality of traffic regions, a function relation graph and a volume relation graph; generating a volume feature of a target traffic region among the plurality of traffic regions, according to a historical volume information of the target traffic region; generating a volume and function relation feature for the target traffic region, based on the function relation graph and the volume relation graph; and predicting a volume of the target traffic region according to the volume feature and the volume and function relation feature.
-
618.发明公开公开(公告)号：US20240354658A1
公开(公告)日：2024-10-24
申请号：US18745529
申请日：2024-06-17
Inventor： Feng HE , Jianhua WANG , Junjie OU , Pingxuan HUANG , Zhifan FENG , Xiaopeng CUI , Qiaoqiao SHE , Hua WU
Abstract: A method and apparatus for training a question solving model, a question solving method and apparatus, an electronic device and a readable storage medium are disclosed. The method for training a question solving model includes: acquiring a first sample question; inputting the first sample question and a solving step grabbing template into a large language model to obtain a first sample solving step; inputting the first sample question, the first sample solving step and an answer grabbing template into the large language model to obtain a first sample answer; pre-training a step planning model according to the first sample question and the first sample solving step; pre-training the large language model according to the first sample question, the first sample solving step and the first sample answer; and acquiring the question solving model according to the step planning model and the large language model obtained by pre-training. The question solving method includes: acquiring a to-be-solved question; inputting the to-be-solved question into a step planning model to obtain a solving step; and inputting the to-be-solved question and the solving step into a large language model to obtain an answer.
-
公开(公告)号：US12118578B2
公开(公告)日：2024-10-15
申请号：US17822507
申请日：2022-08-26
Inventor： Jing Qu , Mengbo Liu , Zhi Feng
IPC: G06F16/245 , G06F16/901 , G06Q30/0207
CPC classification number: G06Q30/0207 , G06F16/245 , G06F16/9027
Abstract: A method for processing commodity information includes: obtaining commodity information of a commodity, in which the commodity information includes a target commodity configuration and a configuration value; obtaining a composite structure of matching conditions associated with the commodity, in which the composite structure is a tree structure of matching conditions with respect to commodity configurations, non-leaf nodes of the tree structure are in an AND-OR relationship, leaf nodes of the tree structure store Boolean expressions, each Boolean expression includes a commodity configuration, a matching value and a matching operator; obtaining a target expression having an AND-OR relationship by traversing the matching conditions in the composite structure; and obtaining a matching result by performing a matching process based on the target expression, the target commodity configuration and the configuration value of the commodity.
-
公开(公告)号：US20240338862A1
公开(公告)日：2024-10-10
申请号：US18749461
申请日：2024-06-20
Inventor： Jiachen LIU , Xinyan XIAO , Hua WU , Guohao LI , Wei LI , Hong ZHU , Qiaoqiao SHE , Yajuan LV
Abstract: A method is provided that includes: obtaining current dialogue data; determining a requirement type of the user in the current round of dialogue based on the current dialogue data; in response to the requirement type being an image processing requirement, determining an action sequence for implementing the image processing requirement; executing the action sequence to generate a target image; and generating response data corresponding to the user input data based on the target image.
-
-
-
-
-
-
-
-
-
Search Results
1526
records
(took 0.038 seconds)
