Patents by Inventor Liang Gou
Liang Gou 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: 11978246Abstract: Provided is a method for implementing reinforcement learning by a neural network. The method may include performing, for each epoch of a first predetermined number of epochs, a second predetermined number of training iterations and a third predetermined number of testing iterations using a first neural network. The first neural network may include a first set of parameters, the training iterations may include a first set of hyperparameters, and the testing iterations may include a second set of hyperparameters. The testing iterations may be divided into segments, and each segment may include a fourth predetermined number of testing iterations. A first pattern may be determined based on at least one of the segments. At least one of the first set of hyperparameters or the second set of hyperparameters may be adjusted based on the pattern. A system and computer program product are also disclosed.Type: GrantFiled: January 3, 2023Date of Patent: May 7, 2024Assignee: Visa International Service AssociationInventors: Liang Gou, Hao Yang, Wei Zhang
-
Publication number: 20240135160Abstract: A computer-implemented method for a machine-learning network that includes receiving an input dataset, sending the input dataset to a first machine-learning model to output predictions associated with the input data, identifying one or more slices associated with the input dataset and a first machine learning model in a first iteration, wherein each of the one or more slices include input data from the input dataset and common attributes associated with each slice; upon selecting one or more slices of the input dataset, training a shallow regressor model configured to predict residuals associated with the model, create a representation associated with a ground-truth label and a second representation associated with a model prediction associated with each sample associated with each of the one or more slices, determine residuals associated with every prediction of the first machine learning model, training the shallow regressor to compute one or more predicted residuals of the selected slices, generate an optiType: ApplicationFiled: October 15, 2022Publication date: April 25, 2024Inventors: Jorge Henrique Piazentin Ono, Xiaoyu Zhang, Liang Gou, Liu Ren
-
Publication number: 20240135159Abstract: A computer-implemented method for a machine-learning network includes receiving an input dataset, wherein the input dataset is indicative of image information, tabular information, radar information, sonar information, or sound information, sending the input dataset to the machine-learning model to output predictions associated with the input data, identifying one or more slices associated with the input dataset and the machine learning model in a first iteration, wherein each of the one or more slices include input data from the input dataset and common attributes associated with each slice, outputting an interface that includes information associated with the one or more slices and performance measurements of the one or more slices of the first iteration and subsequent iterations identifying subsequent slices, wherein the performance measurements relate to the predictions associated with the first iteration and subsequent iterations.Type: ApplicationFiled: October 15, 2022Publication date: April 25, 2024Inventors: Jorge Henrique Piazentin Ono, Xiaoyu Zhang, Huan Song, Liang Gou, Liu Ren
-
Publication number: 20240125963Abstract: The present disclosure provides a method and a system for acquiring seismic data of a four-component ocean bottom node (OBN). The method is implemented by the system, comprising controlling installations of a plurality of ocean bottom submerged buoys and a plurality of four-component OBN seismic data acquisition instruments and sending positioning signals and timing signals to the plurality of ocean bottom submerged buoys through armored opto-electronic composite cables. The method also includes obtaining real-time and uninterrupted water temperature data, pressure data, density data, and salt saturation data along the armored opto-electronic composite cables from the ocean surface to locations of the plurality of ocean bottom submerged buoys, and calculating real-time and three-dimensional data of waters of a whole measurement work area through interpolation.Type: ApplicationFiled: December 25, 2023Publication date: April 18, 2024Applicants: BGP INC., CHINA NATIONAL PETROLEUM CORPORATION, OPTICAL SCIENCE AND TECHNOLOGY (CHENGDU) LTD.Inventors: Liang GOU, Gang YU, Haibo LIU, Zhaohong XU, Ximing WANG, Shujun XIA, Shujie AN, Mengxiong XIAO
-
Publication number: 20240112455Abstract: A method for training a machine learning model. The method comprises receiving a training dataset that includes a plurality of images. The method also includes identifying, by a machine learning model, at least one portion of at least one image of the plurality of images in the training dataset associated with a first object type. The method further includes identifying other images having at least one portion that includes the first object type. The method also includes grouping the identified other images into a first image group. The method also includes generating for display a first user interface, that at least includes a rank matrix, wherein a first row of the rank matrix represents the images of the first image object. The user may provide feedback for the visualization using the first interface. The method may also include training the machine learning model based on the user feedback.Type: ApplicationFiled: September 26, 2022Publication date: April 4, 2024Inventors: Wenbin He, Md Naimul Hoque, Liang Gou, Liu Ren
-
Publication number: 20240085581Abstract: The present disclosure provides a device for full-wave field seismic source based on a gas explosion technology and a method for acquiring seismic data. The device includes a cylindrical explosion-proof metal outer barrel, and four sides of the explosion-proof metal outer barrel are fixedly connected to four high-strength steel plates. The device also includes a cylindrical explosion-proof metal gas explosion inner barrel and pipelines for injecting high-pressure air and high-pressure gas into the gas explosion inner barrel. A center of the gas explosion inner barrel is installed with an electronic ignition gun, which is connected to a GPS timing module connected to the electronic ignition gun. The device further includes a controller configured to control a seismic source of a gas explosion full-wave field.Type: ApplicationFiled: November 6, 2023Publication date: March 14, 2024Applicants: BGP INC., CHINA NATIONAL PETROLEUM CORPORATION, OPTICAL SCIENCE AND TECHNOLOGY (CHENGDU) LTD.Inventors: Liang GOU, Gang YU, Maojun YANG, Ximing WANG
-
Publication number: 20240086422Abstract: Provided are systems for analyzing a relational database using embedding learning that may include at least one processor programmed or configured to generate one or more entity-relation matrices from a relational database and perform, for each entity-relation matrix of the one or more entity-relation matrices, an embedding learning process on an embedding associated with an entity. When performing the embedding learning process on the embedding associated with the entity, the at least one processor is programmed or configured to generate an updated embedding associated with the entity. Computer-implemented methods and computer program products are also provided.Type: ApplicationFiled: November 15, 2023Publication date: March 14, 2024Inventors: Michael Yeh, Liang Gou, Wei Zhang, Dhruv Gelda, Zhongfang Zhuang, Yan Zheng
-
Patent number: 11836159Abstract: Provided are systems for analyzing a relational database using embedding learning that may include at least one processor programmed or configured to generate one or more entity-relation matrices from a relational database and perform, for each entity-relation matrix of the one or more entity-relation matrices, an embedding learning process on an embedding associated with an entity. When performing the embedding learning process on the embedding associated with the entity, the at least one processor is programmed or configured to generate an updated embedding associated with the entity. Computer implemented methods and computer-program products are also provided.Type: GrantFiled: October 9, 2020Date of Patent: December 5, 2023Assignee: Visa International Service AssociationInventors: Michael Yeh, Liang Gou, Wei Zhang, Dhruv Gelda, Zhongfang Zhuang, Yan Zheng
-
Patent number: 11803616Abstract: Methods and systems for performing function testing for moveable objects. One system includes an electronic processor configured to access a driving scene including a moveable object. The electronic processor is also configured to perform spatial representation learning on the driving scene. The electronic processor is also configured to generate an adversarial example based on the learned spatial representation. The electronic processor is also configured to retrain the deep learning model using the adversarial example and the driving scene.Type: GrantFiled: March 1, 2021Date of Patent: October 31, 2023Assignee: Robert Bosch GmbHInventors: Wenbin He, Liang Gou, Lincan Zou, Liu Ren
-
Publication number: 20230303084Abstract: A method for performing at least one perception task associated with autonomous vehicle control includes receiving a first dataset and identifying a first object category of objects associated with the plurality of images, the first object category including a plurality of object types. The method also includes identifying a current statistical distribution of a first object type of the plurality of object types and determining a first distribution difference between the current statistical distribution of the first object type and a standard statistical distribution associated with the first object category. The method also includes, in response to a determination that the first distribution difference is greater than a threshold, generating first object type data corresponding to the first object type, configuring at least one attribute of the first object type data, and generating a second dataset by augmenting the first dataset using the first object type data.Type: ApplicationFiled: March 23, 2022Publication date: September 28, 2023Inventors: Yiqi Zhong, Xinyu Huang, Yuliang Guo, Liang Gou, Liu Ren
-
Patent number: 11763135Abstract: Methods and systems for performing concept-based adversarial generation with steerable and diverse semantics. One system includes an electronic processor configured to access an input image. The electronic processor is also configured to perform concept-based semantic image generation based on the input image. The electronic processor is also configured to perform concept-based semantic adversarial learning using a set of semantic latent spaces generated as part of performing the concept-based semantic image generation. The electronic processor is also configured to generate an adversarial image based on the concept-based semantic adversarial learning. The electronic processor is also configured to test a target model using the adversarial image.Type: GrantFiled: March 1, 2021Date of Patent: September 19, 2023Assignee: Robert Bosch GmbHInventors: Zijie Wang, Liang Gou, Wenbin He, Liu Ren
-
Publication number: 20230213669Abstract: The present invention provides an intelligent geophysical data acquisition system and acquisition method for shale oil and gas optical fiber. A pipe string is arranged in a metal casing, and an external armored optical cable is fixed outside the metal casing; an, internal armored optical cable is fixed outside the pipe string; the external armored optical cable comprises a downhole acoustic sensing optical cable, two multi-mode optical fibers, a strain optical cable and a pressure sensor array, and further comprises horizontal ground acoustic sensing optical cables arranged in the shallow part of the ground according to an orthogonal grid, and artificial seismic source excitation points arranged on the ground according to the orthogonal grid.Type: ApplicationFiled: March 10, 2023Publication date: July 6, 2023Applicants: BGP INC., CHINA NATIONAL PETROLEUM CORPORATION, OPTICAL SCIENCE AND TECHNOLOGY (CHENGDU) LTDInventors: Gang Yu, Xing Liang, Liang Gou, Yunjiang Rao, Ximing Wang, Shujun Xia, Shujie An, Junjun Wu, Yuanzhong Chen, Zengling Ran, Renzhi Zhang
-
Patent number: 11694064Abstract: A method for local approximation of a predictive model may include receiving unclassified data associated with a plurality of unclassified data items. The unclassified data may be classified based on a first predictive model to generate classified data. A first data item may be selected from the classified data. A plurality of generated data items associated with the first data item may be generated using a generative model. The plurality of generated data items may be classified based on the first predictive model to generate classified generated data. A second predictive model may be trained with the classified generated data. A system and computer program product are also disclosed.Type: GrantFiled: September 27, 2022Date of Patent: July 4, 2023Assignee: Visa International Service AssociationInventors: Liang Gou, Junpeng Wang, Wei Zhang, Hao Yang
-
Publication number: 20230196755Abstract: A computer-implemented system and method includes generating first pseudo segment data from a first augmented image and generating second pseudo segment data from a second augmented image. The first augmented image and the second augmented image are in a dataset along with other augmented images. A machine learning system is configured to generate pixel embeddings based on the dataset. The first pseudo segment data and the second pseudo segment data are used to identify a first set of segments that a given pixel belongs with respect to the first augmented image and the second augmented image. A second set of segments is identified across the dataset. The second set of segments do not include the given pixel. A local segmentation loss is computed for the given pixel based on the corresponding pixel embedding that involves attracting the first set of segments while repelling the second set of segments.Type: ApplicationFiled: December 22, 2021Publication date: June 22, 2023Inventors: Wenbin He, Liang Gou, Liu Ren
-
Publication number: 20230144690Abstract: Provided is a method for implementing reinforcement learning by a neural network. The method may include performing, for each epoch of a first predetermined number of epochs, a second predetermined number of training iterations and a third predetermined number of testing iterations using a first neural network. The first neural network may include a first set of parameters, the training iterations may include a first set of hyperparameters, and the testing iterations may include a second set of hyperparameters. The testing iterations may be divided into segments, and each segment may include a fourth predetermined number of testing iterations. A first pattern may be determined based on at least one of the segments. At least one of the first set of hyperparameters or the second set of hyperparameters may be adjusted based on the pattern. A system and computer program product are also disclosed.Type: ApplicationFiled: January 3, 2023Publication date: May 11, 2023Inventors: Liang Gou, Hao Yang, Wei Zhang
-
Publication number: 20230085938Abstract: Embodiments of systems and methods for diagnosing an object-detecting machine learning model for autonomous driving are disclosed herein. An input image is received from a camera mounted in or on a vehicle that shows a scene. A spatial distribution of movable objects within the scene is derived using a context-aware spatial representation machine learning model. An unseen object is generated in the scene that is not originally in the input image utilizing a spatial adversarial machine learning model. Via the spatial adversarial machine learning model, the unseen object is moved to different locations to fail the object-detecting machine learning model. An interactive user interface enables a user to analyze performance of the object-detecting machine learning model with respect to the scene without the unseen object and the scene with the unseen object.Type: ApplicationFiled: September 17, 2021Publication date: March 23, 2023Inventors: Wenbin HE, Liang GOU, Lincan ZOU, Liu REN
-
Patent number: 11593659Abstract: Provided is a method for implementing reinforcement learning by a neural network. The method may include performing, for each epoch of a first predetermined number of epochs, a second predetermined number of training iterations and a third predetermined number of testing iterations using a first neural network. The first neural network may include a first set of parameters, the training iterations may include a first set of hyperparameters, and the testing iterations may include a second set of hyperparameters. The testing iterations may be divided into segments, and each segment may include a fourth predetermined number of testing iterations. A first pattern may be determined based on at least one of the segments. At least one of the first set of hyperparameters or the second set of hyperparameters may be adjusted based on the pattern. A system and computer program product are also disclosed.Type: GrantFiled: March 29, 2019Date of Patent: February 28, 2023Assignee: Visa International Service AssociationInventors: Liang Gou, Hao Yang, Wei Zhang
-
Patent number: 11587330Abstract: Visual analytics tool for updating object detection models in autonomous driving applications. In one embodiment, an object detection model analysis system including a computer and an interface device. The interface device includes a display device. The computer includes an electronic processor that is configured to extract object information from image data with a first object detection model, extract characteristics of objects from metadata associated with image data, generate a summary of the object information and the characteristics, generate coordinated visualizations based on the summary and the characteristics, generate a recommendation graphical user interface element based on the coordinated visualizations and a first one or more user inputs, and update the first object detection model based at least in part on a classification of one or more individual objects as an actual weakness in the first object detection model to generate a second object detection model for autonomous driving.Type: GrantFiled: December 31, 2019Date of Patent: February 21, 2023Assignee: Robert Bosch GmbHInventors: Liang Gou, Lincan Zou, Nanxiang Li, Axel Wendt, Liu Ren
-
Patent number: 11487997Abstract: A method for local approximation of a predictive model may include receiving unclassified data associated with a plurality of unclassified data items. The unclassified data may be classified based on a first predictive model to generate classified data. A first data item may be selected from the classified data. A plurality of generated data items associated with the first data item may be generated using a generative model. The plurality of generated data items may be classified based on the first predictive model to generate classified generated data. A second predictive model may be trained with the classified generated data. A system and computer program product are also disclosed.Type: GrantFiled: October 4, 2019Date of Patent: November 1, 2022Assignee: Visa International Service AssociationInventors: Liang Gou, Junpeng Wang, Wei Zhang, Hao Yang
-
Publication number: 20220277187Abstract: Methods and systems for performing concept-based adversarial generation with steerable and diverse semantics. One system includes an electronic processor configured to access an input image. The electronic processor is also configured to perform concept-based semantic image generation based on the input image. The electronic processor is also configured to perform concept-based semantic adversarial learning using a set of semantic latent spaces generated as part of performing the concept-based semantic image generation. The electronic processor is also configured to generate an adversarial image based on the concept-based semantic adversarial learning. The electronic processor is also configured to test a target model using the adversarial image.Type: ApplicationFiled: March 1, 2021Publication date: September 1, 2022Inventors: Zijie Wang, Liang Gou, Wenbin He, Liu Ren