-
公开(公告)号：US20240028909A1
公开(公告)日：2024-01-25
申请号：US18478833
申请日：2023-09-29
IPC: G06N3/096
CPC classification number: G06N3/096
Abstract: A data generation method based on a deep learning model and a training method is provided. The data generation method includes: determining an initial input of the deep learning model based on input data; obtaining a first output of the model, where in response to the model determining that generating a reply based on the initial input requires calling a first functional component different from the deep learning model, the first output includes a first token for calling the first functional component and a first intermediate inquiry determined based on the initial input and recognizable by the first functional component; obtaining a first intermediate result determined by the first functional component based on the first intermediate inquiry; determining a second input for the model based on the initial input and the first intermediate result; and obtaining a second output of the model for generating a reply to the initial input.
-
公开(公告)号：US20230215203A1
公开(公告)日：2023-07-06
申请号：US18168759
申请日：2023-02-14
Inventor： Pengyuan LV , Chengquan ZHANG , Shanshan LIU , Meina QIAO , Yangliu XU , Liang WU , Xiaoyan WANG , Kun YAO , Junyu Han , Errui DING , Jingdong WANG , Tian WU , Haifeng WANG
IPC: G06V30/19
CPC classification number: G06V30/19147 , G06V30/19167
Abstract: The present disclosure provides a character recognition model training method and apparatus, a character recognition method and apparatus, a device and a medium, relating to the technical field of artificial intelligence, and specifically to the technical fields of deep learning, image processing and computer vision, which can be applied to scenarios such as character detection and recognition technology. The specific implementing solution is: partitioning an untagged training sample into at least two sub-sample images; dividing the at least two sub-sample images into a first training set and a second training set; where the first training set includes a first sub-sample image with a visible attribute, and the second training set includes a second sub-sample image with an invisible attribute; performing self-supervised training on a to-be-trained encoder by taking the second training set as a tag of the first training set, to obtain a target encoder.
-
公开(公告)号：US20220215899A1
公开(公告)日：2022-07-07
申请号：US17557691
申请日：2021-12-21
Inventor： Fan WANG , Jingzhou HE , Xiaomin FANG , Xiaonan ZHANG , Hua WU , Tian WU , Haifeng WANG
Abstract: The present disclosure discloses an affinity prediction method and apparatus, a method and apparatus for training an affinity prediction model, a device and a medium, and relates to the field of artificial intelligence technologies, such as machine learning technologies, smart medical technologies, or the like. An implementation includes: collecting a plurality of training samples, each training sample including information of a training target, information of a training drug and a test data set corresponding to the training target; and training an affinity prediction model using the plurality of training samples. In addition, there is further disclosed the affinity prediction method. The technology in the present disclosure may effectively improve accuracy and a training effect of the trained affinity prediction model. During an affinity prediction, accuracy of a predicted affinity of a target to be detected with a drug to be detected may be higher by acquiring a test data set corresponding to the target to be detected to participate in the prediction.
-
公开(公告)号：US20220058490A1
公开(公告)日：2022-02-24
申请号：US17519815
申请日：2021-11-05
Inventor： Haifeng WANG , Xiaoguang HU , Hongyu LIU , Dianhai YU , Yanjun MA , Tian WU
Abstract: A method and apparatus of constructing a network model for deep learning, a device, and a storage medium, which relate to artificial intelligence, and in particular to a field of deep learning. The method of constructing the network model for deep learning includes: determining an execution mode for executing codes, based on a mode parameter; executing the codes by using a first component, which is executable in a first execution mode, through a syntax element in the codes, in response to determining that the execution mode is the first execution mode; and executing the codes by using a second component, which is executable in a second execution mode, through the syntax element, in response to determining that the execution mode is the second execution mode; wherein the first component and the second component have the same component interface, and the syntax element corresponds to the component interface.
-
公开(公告)号：US20230214423A1
公开(公告)日：2023-07-06
申请号：US18174481
申请日：2023-02-24
Inventor： Haifeng WANG , Hao TIAN , Xinyan XIAO , Xing LI , Tian WU
IPC: G06F16/783 , G06F16/73 , G06N3/0895 , G06F40/30 , G06F40/40 , G06F40/295 , G10L15/22 , G10L15/18 , G10L15/16 , G10L25/57
CPC classification number: G06F16/7844 , G06F16/73 , G06F40/30 , G06F40/40 , G06F40/295 , G06N3/0895 , G10L15/16 , G10L15/22 , G10L15/1815 , G10L25/57
Abstract: A video generation method is provided. The video generation method includes: obtaining global semantic information and local semantic information of a text, where the local semantic information corresponds to a text fragment in the text, searching, based on the global semantic information, a database to obtain at least one first data corresponding to the global semantic information; searching, based on the local semantic information, the database to obtain at least one second data corresponding to the local semantic information; obtaining, based on the at least one first data and the at least one second data, a candidate data set; matching, based on a relevancy between each of at least one text fragment and corresponding candidate data in the candidate data set, target data for the at least one text fragment; and generating, based on the target data matched with each of the at least one text fragment, a video.
-
Patent Agency Ranking
公开(公告)号：US20230147798A1
公开(公告)日：2023-05-11
申请号：US18052143
申请日：2022-11-02
Inventor： Haifeng WANG , Hao TIAN , Jing LIU , Hua WU , Tian WU , Yu SUN , Qiaoqiao SHE
CPC classification number: G06F16/3347 , G06F40/30
Abstract: A method is provided. The method includes converting a search request of a user into a first request semantic vector. The method further includes searching a search resource database for at least one first data semantic vector matched with the first request semantic vector, wherein the search resource database is constructed as a semantic vector space in which different types of data are converted into corresponding data semantic vectors, and the different types of data include at least texts, pictures and videos. The method further includes generating, based on the at least one first data semantic vector, a search result.
-
7.发明申请公开(公告)号：US20230120253A1
公开(公告)日：2023-04-20
申请号：US18082997
申请日：2022-12-16
Inventor： Jie Li , Haojie LIU , Yan ZHANG , Xuecen SHEN , Ruizhi CHEN , Chen ZHAO , Yuqiao TENG , Errui DING , Tian WU , Haifeng WANG
Abstract: A method and apparatus for generating a virtual character, an electronic device and a computer readable storage medium are provided. The method includes: performing mesh simplification on an initial model of a virtual character to obtain a mesh-simplified model; obtaining a first target model by performing white model mapping rendering on an area of each material type on the mesh-simplified model, and obtaining a second target model by performing hyper-realistic rendering on the area of each material type on the mesh-simplified model; and establishing a bidirectional mapping between the first target model and the second target model, and obtaining a target virtual character through iterative updating of the bidirectional mapping.
-
公开(公告)号：US20220222111A1
公开(公告)日：2022-07-14
申请号：US17707895
申请日：2022-03-29
Inventor： Haifeng Wang , Xiaoguang HU , Dianhai YU , Yanjun MA , Tian WU
Abstract: A scheduling method for a deep learning framework, a scheduling apparatus, an electronic device, a storage medium, and a program product is provided, and can be used in the field of artificial intelligence, especially in the fields of machine learning, deep learning, etc. The method includes: receiving a processing request for processing a plurality of tasks by using a dedicated processing unit, the processing request including scheduling requirements for the plurality of tasks, and each of the plurality of tasks being associated with execution of multi-batch data processing; and scheduling, based on the scheduling requirements for the plurality of tasks in batches of data, the dedicated processing unit to process the plurality of tasks.
-
9.发明申请公开(公告)号：US20220004930A1
公开(公告)日：2022-01-06
申请号：US17480292
申请日：2021-09-21
Inventor： Qingqing DANG , Kaipeng DENG , Lielin JIANG , Sheng GUO , Xiaoguang HU , Chunyu ZHANG , Yanjun MA , Tian WU , Haifeng WANG
Abstract: Embodiments of the present disclosure provide a method and apparatus of training a model, an electronic device, a storage medium and a development system, which relate to a field of deep learning. The method may include calling a training preparation component to set at least a loss function and an optimization function for training the model, in response to determining that a training preparation instruction is received. The method further includes calling a training component to set a first data reading component, in response to determining that a training instruction is received. The first data reading component is configured to load a training data set for training the model. In addition, the method may further include training the model based on the training data set from the first data reading component, by using the loss function and the optimization function through the training component.
-
10.发明公开公开(公告)号：US20240338564A1
公开(公告)日：2024-10-10
申请号：US18744501
申请日：2024-06-14
Inventor： Zhifan FENG , Hua WU , Qiaoqiao SHE , Tian WU
IPC: G06N3/08
CPC classification number: G06N3/08
Abstract: A large model optimization training method in the artificial intelligence fields, such as large models, deep learning, natural language processing, may include: taking, as candidate queries, queries collected from a predetermined data source and capable of serving as input to a large model in response to determining that an optimization triggering condition is met; screening out target queries from the candidate queries, the target queries being queries which cannot be correctly processed by the large model; and constructing respectively corresponding training samples according to the target queries, the training samples being used for carrying out optimization training on the large model.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.025 seconds)
