Patents by Inventor Dandan Tu
Dandan Tu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 12211257Abstract: This application relates to the artificial intelligence field, and provides an image processing method, an apparatus, and a system. The image processing method includes: obtaining a plurality of image blocks by segmenting a to-be-analyzed pathological image; inputting the plurality of image blocks to a first analysis model to obtain a first analysis result, where the first analysis model classifies each of the plurality of image blocks based on a quantity or an area of suspicious lesion components; inputting at least one second-type image block in the first analysis result to a second analysis model to obtain a second analysis result, where the second analysis model analyzes a location of a suspicious lesion component of each input second-type image block; and obtaining a final analysis result of the pathological image based on the first analysis result and the second analysis result.Type: GrantFiled: February 1, 2022Date of Patent: January 28, 2025Assignee: HUAWEI CLOUD COMPUTING TECHNOLOGIES CO., LTD.Inventors: Yaoxin Li, Changzheng Zhang, Xiaoshi Chen, Dandan Tu
-
Publication number: 20240339202Abstract: The method includes: obtaining medical detection data to be interpreted, where the medical detection data to be interpreted includes a detection image and indicator data; performing image recognition on the detection image, to obtain image recognition data; and interpreting, by using a rule library, the indicator data and the image recognition data, to obtain an interpretation result, where an interpretation rule in the rule library is obtained by mining and analyzing a plurality of pieces of interpreted data based on a data mining algorithm, and the rule library is dynamically updated with an interpretation process. Because the interpretation rule in the rule library is obtained by mining and analyzing the plurality of pieces of interpreted data based on the data mining algorithm, a potential data law that is difficult to be discovered by human can be mined, and a more accurate interpretation rule can be extracted.Type: ApplicationFiled: June 17, 2024Publication date: October 10, 2024Inventors: Yimin Wang, Changzheng Zhang, Dandan Tu, Yi Gao, Jinping Zheng, Xiaoshi Chen
-
Patent number: 12100209Abstract: An image analysis method, including: obtaining influencing factors of t frames of images, where the influencing factors include self-owned features of h target subjects in each of the t frames of images and relational vector features between the h target subjects in each of the t frames of images, self-owned features of each target subject include a location feature, an attribute feature, and a posture feature, and t and h are natural numbers greater than 1; and obtaining a panoramic semantic description based on the influencing factors, where the panoramic semantic description includes a description of relationships between target subjects, relationships between actions of the target subjects and the target subjects, and relationships between the actions of the target subjects.Type: GrantFiled: July 1, 2021Date of Patent: September 24, 2024Assignee: HUAWEI CLOUD COMPUTING TECHNOLOGIES CO., LTD.Inventors: Pengpeng Zheng, Jiahao Li, Xin Jin, Dandan Tu
-
Publication number: 20240104904Abstract: In a fault image generation method, a processing device obtains a non-fault image and a first fault image, where the non-fault image records a first object that is not faulty, the first fault image records a second object that is faulty, and a type of the first object is different from a type of the second object. The processing device then migrates a fault pattern of the second object in the first fault image to the first object in the non-fault image, to obtain a second fault image, where the second fault image presents the first object in a faulty state.Type: ApplicationFiled: October 8, 2023Publication date: March 28, 2024Applicant: Huawei Cloud Computing Technologies Co., Ltd.Inventors: Changde Du, Xin Jin, Huajie Jiang, Dandan Tu
-
Publication number: 20240013098Abstract: Embodiments of the present invention disclose a data processing apparatus. The apparatus is configured to: after calculating a set of gradient information of each parameter by using a sample data subset, delete the sample data subset, read a next sample data subset, calculate another set of gradient information of each parameter by using the next sample data subset, and accumulate a plurality of sets of calculated gradient information of each parameter, to obtain an update gradient of each parameter.Type: ApplicationFiled: September 20, 2023Publication date: January 11, 2024Inventors: Changzheng ZHANG, Xiaolong BAI, Dandan TU
-
Publication number: 20230376674Abstract: A page layout method includes obtaining page information, element information of at least one page element to be laid out, and a layout rule; obtaining at least one candidate page layout policy based on the page information, the element information, and the layout rule using a reinforcement learning algorithm; and determining a target page layout policy from the at least one candidate page layout policy using an imitation learning algorithm.Type: ApplicationFiled: July 27, 2023Publication date: November 23, 2023Inventors: Jia He, Feiyang Pan, Xin Jin, Dandan Tu
-
Publication number: 20230368467Abstract: This application provides a remote reproduction method, applied to a remote reproduction system, where the system includes a first terminal worn by a first user and a second terminal worn by a second user, and the first user and the second user are located in different geographical scenarios. The method includes: The second terminal obtains an action image of the first user, where the action image of the first user includes a sequence of at least one action formed by a pre-constructed human body model of the first user, and then the second terminal reproduces, for the second user, the action image of the first user to a geographical scenario in which the second user is located.Type: ApplicationFiled: July 25, 2023Publication date: November 16, 2023Applicant: Huawei Cloud Computing Technologies Co., Ltd.Inventors: Weimeng GONG, Jun LI, Dandan TU
-
Publication number: 20230281784Abstract: A target region is first extracted from a to-be-recognized image, and then a defect coarse-selection region including an industrial defect is obtained from the target region. Through two times of region extraction, a proportion of a size of the industrial defect to a size of a background is increased, so that a probability of detecting a small-sized industrial defect can be increased. After the defect coarse-selection region including the industrial defect is detected, localization and size estimation are further performed on the industrial defect in the defect coarse-selection region.Type: ApplicationFiled: May 12, 2023Publication date: September 7, 2023Inventors: Xiudong Wang, Xin Jin, Dandan Tu
-
Publication number: 20230153622Abstract: A method includes determining that there is a difference between a data distribution of an inference data set and a data distribution of a training data set, where the training data set is a data set used for training an existing artificial intelligence (AI) model, and updating the existing AI model by using the inference data set to obtain an updated AI model.Type: ApplicationFiled: January 23, 2023Publication date: May 18, 2023Inventors: Shuzhe Wu, Xin Jin, Xincheng Li, Dandan Tu
-
Patent number: 11605211Abstract: An object detection model training method performed by a computing device, includes obtaining a system parameter including at least one of a receptive field of a backbone network, a size of a training image, a size of a to-be-detected object in the training image, a training computing capability, or a complexity of the to-be-detected object, determining a configuration parameter based on the system parameter, establishing a variable convolution network based on the configuration parameter and a feature map of the backbone network, recognizing the to-be-detected object based on a feature of the variable convolution network, and training the backbone network and the variable convolution network, where a convolution core used by any variable convolution layer may be offset in any direction in a process of performing convolution.Type: GrantFiled: September 29, 2020Date of Patent: March 14, 2023Assignee: HUAWEI CLOUD COMPUTING TECHNOLOGIES CO., LTD.Inventors: Changzheng Zhang, Xin Jin, Dandan Tu
-
Patent number: 11461659Abstract: A feature set determining method includes obtaining, according to a received feature set determining request, data used for feature learning. The feature set determining request includes a learning objective of the feature learning. The method includes performing type analysis on the data to divide the data into first-type data and second-type data. The method includes performing semi-supervised learning on the first-type data to extract multiple first-type features. The method includes performing adaptive learning on the second-type data to extract multiple second-type features. The method includes evaluating the first-type features and the second-type features to obtain an optimal feature set.Type: GrantFiled: January 15, 2018Date of Patent: October 4, 2022Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Dandan Tu, Jiajin Zhang
-
Patent number: 11423634Abstract: In an object detection model training method, a classifier that has been trained in a first phase is duplicated to at least two copies, and in a training in a second phase, each classifier obtained through duplication is configured to detect to-be-detected objects with different sizes, and train an object detection model based on a detection result.Type: GrantFiled: September 18, 2020Date of Patent: August 23, 2022Assignee: HUAWEI CLOUD COMPUTING TECHNOLOGIES CO., LTD.Inventors: Changzheng Zhang, Xin Jin, Dandan Tu
-
Publication number: 20220172476Abstract: A video similarity detection method and apparatus are provided. In the method, a detection apparatus receives a first video, determines a key frame of the first video based on the first video, and determines a similar key frame and a second video, the similar key frame being determined based on the key frame. The second video includes a video in which the similar key frame is located. The method inputs the key frame and the similar key frame to an editing type recognition model to obtain an editing type. The editing type indicates an editing type used for editing between the first video and the second video.Type: ApplicationFiled: January 4, 2022Publication date: June 2, 2022Applicant: HUAWEI TECHNOLOGIES CO.,LTD.Inventors: Jun Li, Haomiao Liu, Weimeng Gong, Dandan Tu
-
Publication number: 20220156931Abstract: This application relates to the artificial intelligence field, and provides an image processing method, an apparatus, and a system. The image processing method includes: obtaining a plurality of image blocks by segmenting a to-be-analyzed pathological image; inputting the plurality of image blocks to a first analysis model to obtain a first analysis result, where the first analysis model classifies each of the plurality of image blocks based on a quantity or an area of suspicious lesion components; inputting at least one second-type image block in the first analysis result to a second analysis model to obtain a second analysis result, where the second analysis model analyzes a location of a suspicious lesion component of each input second-type image block; and obtaining a final analysis result of the pathological image based on the first analysis result and the second analysis result.Type: ApplicationFiled: February 1, 2022Publication date: May 19, 2022Inventors: Yaoxin LI, Changzheng ZHANG, Xiaoshi CHEN, Dandan TU
-
Publication number: 20220134340Abstract: In an embodiment, the present disclosure pertains to a microfluidic device composed of a substrate having an inlet region and a first storage region, a fluid transporting channel in fluid communication with the inlet region, an expandable component in fluid communication with the fluid transporting channel and coupled to a movable arm, and a fluid transporting region coupled to the movable arm and operable to be moved in a horizontal direction to the fluid transporting channel to thereby form fluidic contact between the inlet region and the first storage region upon expansion of the expandable component. In an additional embodiment, the present disclosure pertains to a method of fluid flow utilizing a microfluidic device of the present disclosure.Type: ApplicationFiled: October 28, 2021Publication date: May 5, 2022Applicant: The Texas A&M University SystemInventors: Dandan Tu, Gerard L. Coté, Samuel Mabbott, John Dean
-
Publication number: 20220107736Abstract: An adaptive file storage method and apparatus is disclosed. The method includes determining a cold and hot attribute of a file, and performing coding storage processing or transcoding storage processing on the file according to the cold and hot attribute of the file. Therefore, a requirement of the cold and hot attribute of the file for storage overheads and restoration costs can be fully considered. In addition, the used coding technology has high reliability and a high coding speed. Therefore, comprehensive performance in multiple dimensions of storage overheads, restoration costs, reliability, and an coding speed can be improved.Type: ApplicationFiled: October 20, 2021Publication date: April 7, 2022Inventors: Shiyue ZHUANG, Yulei XIAO, Dandan TU
-
Patent number: 11182080Abstract: An adaptive file storage method and apparatus is disclosed. The method includes determining a cold and hot attribute of a file, and performing coding storage processing or transcoding storage processing on the file according to the cold and hot attribute of the file. Therefore, a requirement of the cold and hot attribute of the file for storage overheads and restoration costs can be fully considered. In addition, the used coding technology has high reliability and a high coding speed. Therefore, comprehensive performance in multiple dimensions of storage overheads, restoration costs, reliability, and an coding speed can be improved.Type: GrantFiled: April 23, 2018Date of Patent: November 23, 2021Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Shiyue Zhuang, Yulei Xiao, Dandan Tu
-
Publication number: 20210326634Abstract: An image analysis method, including: obtaining influencing factors of t frames of images, where the influencing factors include self-owned features of h target subjects in each of the t frames of images and relational vector features between the h target subjects in each of the t frames of images, self-owned features of each target subject include a location feature, an attribute feature, and a posture feature, and t and h are natural numbers greater than 1; and obtaining a panoramic semantic description based on the influencing factors, where the panoramic semantic description includes a description of relationships between target subjects, relationships between actions of the target subjects and the target subjects, and relationships between the actions of the target subjects.Type: ApplicationFiled: July 1, 2021Publication date: October 21, 2021Applicant: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Pengpeng ZHENG, Jiahao LI, Xin JIN, Dandan TU
-
Publication number: 20210295114Abstract: A method for extracting structured data from an image is provided. The method includes: obtaining a first information set and a second information set in the image by using an image text extraction model, where the image includes at least one piece of structured data; obtaining at least one text subimage in the image based on at least one piece of first information included in the first information set; identifying text information in the at least one text subimage; and obtaining at least one piece of structured data in the image based on the text information in the at least one text subimage and at least one piece of second information included in the second information set. By using the image text extraction model and a text identification model, structured data extraction efficiency and accuracy are improved.Type: ApplicationFiled: June 1, 2021Publication date: September 23, 2021Applicant: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Yibin YE, Shenggao ZHU, Jing WANG, Qi DU, Hui LIANG, Dandan TU
-
Publication number: 20210012136Abstract: An object detection model training method performed by a computing device, includes obtaining a system parameter including at least one of a receptive field of a backbone network, a size of a training image, a size of a to-be-detected object in the training image, a training computing capability, or a complexity of the to-be-detected object, determining a configuration parameter based on the system parameter, establishing a variable convolution network based on the configuration parameter and a feature map of the backbone network, recognizing the to-be-detected object based on a feature of the variable convolution network, and training the backbone network and the variable convolution network, where a convolution core used by any variable convolution layer may be offset in any direction in a process of performing convolution.Type: ApplicationFiled: September 29, 2020Publication date: January 14, 2021Inventors: Changzheng Zhang, Xin Jin, Dandan Tu