Patents by Inventor Xiaolu Zhang
Xiaolu Zhang 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).
-
Publication number: 20240145616Abstract: The technical solution discloses a preparation method for a solar cell and a silicon film. The preparation method comprises: forming a dielectric layer on a first main surface of a silicon substrate; forming a silicon film having a first conductive characteristic on the dielectric layer, the silicon film including a first region and a second region located outside the first region; and transforming the conductive characteristic of the first region from the first conductive characteristic to a second conductive characteristic, the first conductive characteristic being opposite to the second conductive characteristic. The preparation method simplifies a solar cell manufacturing process.Type: ApplicationFiled: October 25, 2021Publication date: May 2, 2024Inventors: Wenshuai TANG, Junbing ZHANG, Xiaolu SUN
-
Publication number: 20240119653Abstract: Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled, at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor.Type: ApplicationFiled: December 19, 2023Publication date: April 11, 2024Applicant: Tahoe Research, Ltd.Inventors: Minje PARK, Tae-Hoon KIM, Myung-Ho JU, Jihyeon YI, Xiaolu SHEN, Lidan ZHANG, Qiang LI
-
Publication number: 20240093142Abstract: The present invention relates to the fields of microorgan-isms, feed, food and ecological restoration, in particular to a strain for degrading deoxynivalenol (DON) and the use thereof. The strain has the deposit number CCTCC No. M 2020565. The strain can grow by means of taking the toxic compound DON as a sole carbon source, and convert the DON into chemical components for itself. The reaction process is irreversible, the reaction conditions are moderate, and secondary pollu-tion cannot be caused. The strain provided in the present invention can be used for preparing a biological detoxification preparation for DON. The strain provided in the present invention can be used for degrading DON in feed and food raw materials, primary processing products, deep processing products and related processing byproducts. The strain provided in the present invention can be applied to various ecosystems such as soil or bodies of water polluted by DON to achieve the purposes of DON degradation and ecological restoration.Type: ApplicationFiled: November 11, 2021Publication date: March 21, 2024Inventors: Huiying LUO, Honghai ZHANG, Bin YAO, Huoqing HUANG, Yaru WANG, Yingguo BAI, Xiaoyun SU, Yuan WANG, Tao TU, Jie ZHANG, Huimin YU, Xing QIN, Xiaolu WANG
-
Publication number: 20240062531Abstract: A computer-implemented method for image processing includes obtaining, based on a source image including a first biological object, an identity feature and attribute feature used to represent identity information and attribute information of the first biological object. Based on a target image including a second biological object, a context feature used to represent context information of the second biological object is obtained. Based on the identity feature, a fused image of the source image and the target image, the attribute feature, and the context feature is generated, where the fused image includes a fused biological object of a first biological object and the second biological object, identity information and attribute information of the fused biological object is identical to the identity information and the attribute information of the first biological object, and context information of the fused biological object is identical to the context information of the second biological object.Type: ApplicationFiled: August 22, 2023Publication date: February 22, 2024Applicant: Alipay (Hangzhou) Information Technology Co., Ltd.Inventors: Ang Li, Jun Zhou, Chilin Fu, Xiaolu Zhang
-
Patent number: 11276164Abstract: A computer implemented method, computer system and computer program product are provided for data classification. According to the method, an original data is received by one or more processing units. A classification of the original data with a trained classifier is determined by one or more processing units, wherein the classifier is trained by a labeled data of different granularity, and the labeled data include at least one defect object.Type: GrantFiled: August 21, 2018Date of Patent: March 15, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Shiwan Zhao, Xiaolu Zhang, Yong Qin
-
Patent number: 11205123Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.Type: GrantFiled: January 27, 2020Date of Patent: December 21, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Peng Gao, Xiu Li Li, Yong Qin, Shi Lei Zhang, Xiaolu Zhang, Xin Zhang, Shi Wan Zhao
-
Patent number: 10902298Abstract: This disclosure is related to determining an item push list for a user based on a reinforcement learning model. In one aspect, a method includes obtaining M first item lists that have been predetermined for a first user. Each first item list includes i?1 items. For each first item list, an ith state feature vector is obtained. The ith state feature vector includes a static feature and a dynamic feature. The ith state feature vector is provided as input to the reinforcement machine learning model. The reinforcement model outputs a weight vector including weights of sorting features. A sorting feature vector of each item in a candidate item set corresponding to the first item list is obtained. The sorting feature vector includes feature values of sorting features. M updated item lists are determined for the first item lists based on a score for each item in M candidate item sets.Type: GrantFiled: March 9, 2020Date of Patent: January 26, 2021Assignee: Alibaba Group Holding LimitedInventors: Cen Chen, Xu Hu, Chilin Fu, Xiaolu Zhang
-
Patent number: 10892050Abstract: Methods, systems, and storage components for utilizing a deep neural network(s) for classifying at least one medical image. A deep neural network (DNN) can be configured by an image processing component to contain at least one revived neuron, where the revived neuron has an adjusted value based on a focus-learning function that is transferred to the DNN by the image processing component, where the focus-learning function provides the adjustment by updating the DNN with data that contains a corrected classification with respect to at least one normal image sample derived from a medical image, and where the correction is based on the focus-learning function comparing an annotation associated with an abnormal image sample derived from the medical image to another annotation associated with the at least one normal image.Type: GrantFiled: April 13, 2018Date of Patent: January 12, 2021Assignee: International Business Machines CorporationInventors: Xin Zhang, Guo Tong Xie, Xiaolu Zhang, Xiu Li Li, Peng Gao
-
Patent number: 10878461Abstract: Embodiments of the present disclosure disclose a method and an apparatus. The apparatus includes interface circuitry and processing circuitry. The processing circuitry obtains attribute information of multimedia information associated with a multimedia provider. The attribute information includes website information of a website used to display the multimedia information and identifier (ID) information associated with the multimedia information. The processing circuitry generates a machine-readable identification code to be scanned by a user device of a user based on at least the website information. Based on the ID information, the processing circuitry obtains a first image corresponding to the multimedia information. The processing circuitry determines an image area in the first image in which the machine-readable identification code is to be inserted. The processing circuitry inserts the machine-readable identification code into the image area to generate a second image.Type: GrantFiled: January 4, 2019Date of Patent: December 29, 2020Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Qian Wang, Qi Jin, Chenjun Yang, Zhengyun Chen, Can Zheng, Junliang Chen, Wenji Li, Xiaolu Zhang, Shaogang Tang, Huijuan Li, Yikun Li
-
Patent number: 10832458Abstract: A method, system, and computer program product, include receiving a first input at a first element among a plurality of elements associated with at least one electronic document, determining a second element associated with the first element from the plurality of elements based on predetermined relations of the plurality of elements, and causing a view to be displayed together with an electronic document including the first element, the view at least including the second element.Type: GrantFiled: February 8, 2019Date of Patent: November 10, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Keke Cai, Dongxu Duan, Zhong Su, Li Zhang, Xiaolu Zhang, Shiwan Zhao
-
Publication number: 20200342268Abstract: This disclosure is related to determining an item push list for a user based on a reinforcement learning model. In one aspect, a method includes obtaining M first item lists that have been predetermined for a first user. Each first item list includes i-1 items. For each first item list, an ith state feature vector is obtained. The ith state feature vector includes a static feature and a dynamic feature. The ith state feature vector is provided as input to the reinforcement machine learning model. The reinforcement model outputs a weight vector including weights of sorting features. A sorting feature vector of each item in a candidate item set corresponding to the first item list is obtained. The sorting feature vector includes feature values of sorting features. M updated item lists are determined for the first item lists based on a score for each item in M candidate item sets.Type: ApplicationFiled: March 9, 2020Publication date: October 29, 2020Applicant: Alibaba Group Holding LimitedInventors: Cen Chen, Xu Hu, Chilin Fu, Xiaolu Zhang
-
Patent number: 10750013Abstract: A method, system, and computer program product, include receiving a request for registration from a service provider, upon the service receiver having authorized the request for registration, registering characteristic information of the service call in a user device of a service receiver, and upon a lapse of time, deregistering the characteristic information from the user device.Type: GrantFiled: January 2, 2019Date of Patent: August 18, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Keke Cai, Bai Chen Deng, Dongxu Duan, Zhong Su, Li Zhang, Xiaolu Zhang, Shiwan Zhao
-
Patent number: 10748281Abstract: A method and system of detecting abnormalities captured in a medical image are provided. A medical image is received having one or more lesions and one or more interferences. One or more convolution layers are applied to the medical image to create one or more feature maps, respectively. A region proposal network (RPN) is applied to each of the one or more feature maps to create a bounding box around each lesion and interference. For each bounding box, an object in the bounding box is classified as a lesion, an interference, or a background. Each object that is incorrectly classified as a lesion but determined to be an interference, is stored as a hard-negative example to be part of a training set for a next application of the RPN.Type: GrantFiled: July 21, 2018Date of Patent: August 18, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Xiaolu Zhang, Xin Zhang, Dingli Gao, Peng Gao, Xiu Li Li, Shiwan Zhao
-
Patent number: 10740895Abstract: A computer implemented method, computer system and computer program product are provided for data classification. The method includes receiving original data, wherein the original data includes at least one object in a first condition. The method also includes receiving generated data from a generator based on the original data, wherein the generated data includes the at least one object in a second condition, the generator trained by training data of the first condition and training data of the second condition. The method further includes determining a classification of the at least one object with a classifier based on the original data and the generated data, the classifier trained by labeled data of the first condition and more training data of the second condition that is generated based on the labeled data by the trained generator, wherein the labeled data includes the at least one object.Type: GrantFiled: June 25, 2018Date of Patent: August 11, 2020Assignee: International Business Machines CorporationInventors: Shiwan Zhao, Xiaolu Zhang, Shi Lei Zhang, Bingzhe Wu
-
Patent number: 10671918Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.Type: GrantFiled: October 24, 2017Date of Patent: June 2, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Peng Gao, Xiu Li Li, Yong Qin, Shi Lei Zhang, Xiaolu Zhang, Xin Zhang, Shi Wan Zhao
-
Publication number: 20200160183Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.Type: ApplicationFiled: January 27, 2020Publication date: May 21, 2020Inventors: Peng Gao, Xiu Li Li, Yong Qin, Shi Lei Zhang, Xiaolu Zhang, Xin Zhang, Shi Wan Zhao
-
Publication number: 20200065961Abstract: A computer implemented method, computer system and computer program product are provided for data classification. According to the method, an original data is received by one or more processing units. A classification of the original data with a trained classifier is determined by one or more processing units, wherein the classifier is trained by a labeled data of different granularity, and the labeled data include at least one defect object.Type: ApplicationFiled: August 21, 2018Publication date: February 27, 2020Inventors: Shiwan Zhao, Xiaolu Zhang, Yong Qin
-
Publication number: 20200027207Abstract: A method and system of detecting abnormalities captured in a medical image are provided. A medical image is received having one or more lesions and one or more interferences. One or more convolution layers are applied to the medical image to create one or more feature maps, respectively. A region proposal network (RPN) is applied to each of the one or more feature maps to create a bounding box around each lesion and interference. For each bounding box, an object in the bounding box is classified as a lesion, an interference, or a background. Each object that is incorrectly classified as a lesion but determined to be an interference, is stored as a hard-negative example to be part of a training set for a next application of the RPN.Type: ApplicationFiled: July 21, 2018Publication date: January 23, 2020Inventors: Xiaolu Zhang, Xin Zhang, Dingli Gao, Peng Gao, Xiu Li Li, Shiwan Zhao
-
Publication number: 20190392576Abstract: A computer implemented method, computer system and computer program product are provided for data classification. The method includes receiving original data, wherein the original data includes at least one object in a first condition. The method also includes receiving generated data from a generator based on the original data, wherein the generated data includes the at least one object in a second condition, the generator trained by training data of the first condition and training data of the second condition. The method further includes determining a classification of the at least one object with a classifier based on the original data and the generated data, the classifier trained by labeled data of the first condition and more training data of the second condition that is generated based on the labeled data by the trained generator, wherein the labeled data includes the at least one object.Type: ApplicationFiled: June 25, 2018Publication date: December 26, 2019Inventors: Shiwan Zhao, Xiaolu Zhang, Shi Lei Zhang, Bingzhe Wu
-
Publication number: 20190318822Abstract: Methods, systems, and storage components for utilizing a deep neural network(s) for classifying at least one medical image. A deep neural network (DNN) can be configured by an image processing component to contain at least one revived neuron, where the revived neuron has an adjusted value based on a focus-learning function that is transferred to the DNN by the image processing component, where the focus-learning function provides the adjustment by updating the DNN with data that contains a corrected classification with respect to at least one normal image sample derived from a medical image, and where the correction is based on the focus-learning function comparing an annotation associated with an abnormal image sample derived from the medical image to another annotation associated with the at least one normal image.Type: ApplicationFiled: April 13, 2018Publication date: October 17, 2019Inventors: Xin ZHANG, Guo Tong XIE, Xiaolu ZHANG, Xiu Li LI, Peng GAO