Patents by Inventor Leyi Wang
Leyi Wang 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: 11926877Abstract: A saliva-based testing method that bypasses the need for RNA isolation/purification is described herein. In experiments with inactivated SARS-CoV-2 virus spiked into saliva, this method has a limit of detection of 500-1000 viral particles per mL, rivalling the standard NP swab method. Initial studies showed excellent performance with 100 clinical samples. This saliva-based process is operationally simple, utilizes readily available materials, and can be easily implemented by existing testing sites thus allowing for high-throughput, rapid, and repeat testing of large populations.Type: GrantFiled: June 17, 2021Date of Patent: March 12, 2024Assignee: The Board of Trustees of the University of IllinoisInventors: Diana Rose Ranoa, Robin L. Holland, Fadi G. Alnaji, Kelsie J. Green, Leyi Wang, Christopher B. Brooke, Martin D. Burke, Timothy M. Fan, Paul J. Hergenrother
-
Publication number: 20230351241Abstract: The present application discloses a model training method, a short message auditing method and apparatuses, a device, and a storage medium, and relates to the field of artificial intelligence. A specific implementation solution of model training is: performing a sample reduction on first unlabeled samples to obtain second unlabeled samples; inputting the second unlabeled samples to a machine learning model for prediction, to obtain a probability corresponding to a result of predicting the second unlabeled samples; selecting a third unlabeled sample from the second unlabeled samples according to the probability; and training the machine learning model by using a third unlabeled sample after labeling. In embodiments of the present application, redundant samples are removed through a sample reduction, such that the selected samples have a certain degree of representativeness.Type: ApplicationFiled: April 12, 2021Publication date: November 2, 2023Inventors: Huihui He, Leyi Wang, Minghao Liu, Jiangliang Guo
-
Patent number: 11681875Abstract: The present application discloses a method for image text recognition, an apparatus, a device, and a storage medium, and relates to image processing technologies in the field of cloud computing. A specific implementation is: acquiring an image to be processed, where at least one text line exists in the image to be processed; processing each text line in the image to be processed to obtain a composite encoded vector corresponding to each word in each text line, where the composite encoded vector carries semantic information and position information; and determining a text recognition result of the image to be processed according to the semantic information and the position information carried in the composite encoded vector corresponding to each word in each text line. This technical solution can accurately distinguish adjacent fields with small pixel spacing in the image and improve the accuracy of text recognition in the image.Type: GrantFiled: August 4, 2020Date of Patent: June 20, 2023Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.Inventors: Xiangkai Huang, Leyi Wang, Lei Nie, Siyu An, Minghao Liu, Jiangliang Guo
-
Publication number: 20230142217Abstract: The present disclosure provides a model training method and apparatus, an electronic device, and a storage medium, and relates to the field of artificial intelligence, in particular, to the field of natural language processing and deep learning. A specific implementation solution includes: constructing initial training corpora; performing data enhancement on the initial training corpora based on an algorithm contained in a target algorithm set to obtain target training corpora, wherein the target algorithm set is determined from multiple algorithm sets, and different algorithm sets are used for performing data enhancement on corpora with different granularity in the initial training corpora; and performing training on a language model based on the target training corpora to obtain a sequence labeling model, herein the language model is pre-trained based on text corpora.Type: ApplicationFiled: August 26, 2022Publication date: May 11, 2023Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.Inventors: Huihui HE, Leyi WANG, Duohao QIN, Minghao LIU
-
Patent number: 11530457Abstract: A saliva-based testing method that bypasses the need for RNA isolation/purification is described herein. In experiments with inactivated SARS-CoV-2 virus spiked into saliva, this method has a limit of detection of 500-1000 viral particles per mL, rivalling the standard NP swab method. Initial studies showed excellent performance with 100 clinical samples. This saliva-based process is operationally simple, utilizes readily available materials, and can be easily implemented by existing testing sites thus allowing for high-throughput, rapid, and repeat testing of large populations.Type: GrantFiled: June 17, 2021Date of Patent: December 20, 2022Assignee: The Board of Trustees of the University of IllinoisInventors: Diana Rose Ranoa, Robin L. Holland, Fadi G. Alnaji, Kelsie J. Green, Leyi Wang, Christopher B. Brooke, Martin D. Burke, Timothy M. Fan, Paul J. Hergenrother
-
Publication number: 20220383190Abstract: The present disclosure provides a method of training a classification model, which relates to an active learning, neural network and natural language processing technology. A specific implementation scheme includes: selecting, from an original sample set, a plurality of original samples with a class prediction result meeting a preset condition as to-be-labeled samples according to a class prediction result for a plurality of original samples in the original sample set; labeling the to-be-labeled sample as belonging to a class by using the second classification model, so as to obtain a first labeled sample set; and training the first classification model by using the first labeled sample set. The present disclosure further provides a method of classifying a sample, an electronic device, and a storage medium.Type: ApplicationFiled: May 17, 2021Publication date: December 1, 2022Inventors: Huihui HE, Leyi WANG, Minghao LIU, Jiangliang GUO
-
Publication number: 20220277575Abstract: A method and apparatus for detecting a table. The method includes: acquiring a to-be-processed image; inputting the to-be-processed image into a pre-trained deep learning model, and outputting a full table detection branch result, a column detection branch result and a header detection branch result through the deep learning model; where the full table detection branch result represents a detection result for a full table in the to-be-processed image, the column detection branch result represents a detection result for a column in the table in the to-be-processed image, and the header detection branch result represents a detection result for a header in the to-be-processed image; and obtaining a detection result of the table in the to-be-processed image, based on the full table detection branch result, the column detection branch result and the header detection branch result.Type: ApplicationFiled: May 13, 2022Publication date: September 1, 2022Inventors: Xia Zhou, Leyi Wang, Qiaoyi Li, Duohao Qin, Minghao Liu
-
Publication number: 20220275464Abstract: A saliva-based testing method that bypasses the need for RNA isolation/purification is described herein. In experiments with inactivated SARS-CoV-2 virus spiked into saliva, this method has a limit of detection of 500-1000 viral particles per mL, rivalling the standard NP swab method. Initial studies showed excellent performance with 100 clinical samples. This saliva-based process is operationally simple, utilizes readily available materials, and can be easily implemented by existing testing sites thus allowing for high-throughput, rapid, and repeat testing of large populations.Type: ApplicationFiled: June 17, 2021Publication date: September 1, 2022Applicant: The Board of Trustees of the University of IllinoisInventors: Diana Rose RANOA, Robin L. HOLLAND, Fadi G. ALNAJI, Kelsie J. GREEN, Leyi WANG, Christopher B. BROOKE, Martin D. BURKE, Timothy M. FAN, Paul J. HERGENROTHER
-
Publication number: 20210395839Abstract: A saliva-based testing method that bypasses the need for RNA isolation/purification is described herein. In experiments with inactivated SARS-CoV-2 virus spiked into saliva, this method has a limit of detection of 500-1000 viral particles per mL, rivalling the standard NP swab method. Initial studies showed excellent performance with 100 clinical samples. This saliva-based process is operationally simple, utilizes readily available materials, and can be easily implemented by existing testing sites thus allowing for high-throughput, rapid, and repeat testing of large populations.Type: ApplicationFiled: June 17, 2021Publication date: December 23, 2021Applicant: The Board of Trustees of the University of IllinoisInventors: Diana Rose RANOA, Robin L. HOLLAND, Fadi G. ALNAJI, Kelsie J. GREEN, Leyi WANG, Christopher B. BROOKE, Martin D. BURKE, Timothy M. FAN, Paul J. HERGENROTHER
-
Publication number: 20210081729Abstract: The present application discloses a method for image text recognition, an apparatus, a device, and a storage medium, and relates to image processing technologies in the field of cloud computing. A specific implementation is: acquiring an image to be processed, where at least one text line exists in the image to be processed; processing each text line in the image to be processed to obtain a composite encoded vector corresponding to each word in each text line, where the composite encoded vector carries semantic information and position information; and determining a text recognition result of the image to be processed according to the semantic information and the position information carried in the composite encoded vector corresponding to each word in each text line. This technical solution can accurately distinguish adjacent fields with small pixel spacing in the image and improve the accuracy of text recognition in the image.Type: ApplicationFiled: August 4, 2020Publication date: March 18, 2021Inventors: Xiangkai HUANG, Leyi WANG, Lei NIE, Siyu AN, Minghao LIU, Jiangliang GUO
-
Patent number: 9562077Abstract: Genes for proteins which spontaneously form dimers and/or oligomers can be recombinantly linked together, which upon expression in E. coli produces stable dimeric fusion proteins that spontaneously self-assemble into enormous, polyvalent complexes having increased immunogenicity and functionality. Linear, network and agglomerate complexes with enormous sizes and polyvalences are constructed using glutathione S-transferase, Norovirus P domains (NoV P? and NoV+), the protruding (P) domain of hepatitis E virus (HEV P), the astrovirus P domain (AstV), a monomeric peptide epitope (M2e of influenza virus), and/or a protein antigen (VP8* of rotavirus) fused in different combinations. The resulting complexes can contain hundreds to thousands NoV P-protein, HEV, AstV, M2e and/or VP8* copies and exhibit higher immunogenicity than the individual proteins alone.Type: GrantFiled: March 14, 2013Date of Patent: February 7, 2017Assignee: Children's Hospital Medical CenterInventors: Ming Tan, Xi Jiang, Leyi Wang
-
Patent number: 9441263Abstract: The present invention relates to methods to identify molecules that binds in the neomycin binding pocket of a bacterial ribosome using structures of an intact bacterial ribosome that reveal how the ribosome binds tRNA in two functionally distinct states, determined by x-ray crystallography. One state positions tRNA in the peptidyl-tRNA binding site. The second, a fully rotated state, is stabilized by ribosome recycling factor (RRF) and binds tRNA in a highly bent conformation in a hybrid peptidyl/exit (P/E) site. Additionally, the invention relates to various assays, including single-molecule assay for ribosome recycling, and methods to identify compounds that interfere with ribosomal function by detecting newly identified intermediate FRET states using known and novel FRET pairs on the ribosome. The invention also provides vectors and compositions with an N-terminally tagged S13 protein.Type: GrantFiled: April 14, 2012Date of Patent: September 13, 2016Assignees: Cornell University, The Regents of the University of CaliforniaInventors: Scott C. Blanchard, Michael Brian Feldman, Leyi Wang, James H. Doudna Cate, Arto Pulk, Roger B. Altman, Michael R. Wasserman
-
Patent number: 9080979Abstract: This invention relates to a method to rapidly find crystallization conditions for a biomolecule in a desired conformation using single-molecule, fluorescent resonance energy transfer (smFRET) imaging techniques. The method provides significant cost and time advantages over the empricial exploration for crystallization conditions.Type: GrantFiled: April 14, 2012Date of Patent: July 14, 2015Assignee: CORNELL UNIVERSITYInventors: Scott C. Blanchard, Michael Brian Feldman, Leyi Wang, Roger Altman
-
Publication number: 20140127682Abstract: The present invention relates to methods to identify molecules that binds in the neomycin binding pocket of a bacterial ribosome using structures of an intact bacterial ribosome that reveal how the ribosome binds tRNA in two functionally distinct states, determined by x-ray crystallography. One state positions tRNA in the peptidyl-tRNA binding site. The second, a fully rotated state, is stabilized by ribosome recycling factor (RRF) and binds tRNA in a highly bent conformation in a hybrid peptidyl/exit (P/E) site. Additionally, the invention relates to various assays, including single-molecule assay for ribosome recycling, and methods to identify compounds that interfere with ribosomal function by detecting newly identified intermediate FRET states using known and novel FRET pairs on the ribosome.Type: ApplicationFiled: April 14, 2012Publication date: May 8, 2014Applicants: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, CORNELL UNIVERSITYInventors: Scott C. Blanchard, Michael Brian Feldman, Leyi Wang, James H. Doudna Cate, Arto Pulk, Roger B. Altman, Michael R. Wasserman
-
Publication number: 20140093870Abstract: This invention relates to a method to rapidly find crystallization conditions for a biomolecule in a desired conformation using single-molecule, fluorescent resonance energy transfer (smFRET) imaging techniques. The method provides significant cost and time advantages over the empricial exploration for crystallization conditions.Type: ApplicationFiled: April 14, 2012Publication date: April 3, 2014Applicant: CORNELL UNIVERSITYInventors: Scott C. Blanchard, Michael Brian Feldman, Leyi Wang, Roger Altman
-
Publication number: 20140017269Abstract: Genes for proteins which spontaneously form dimers and/or oligomers can be recombinantly linked together, which upon expression in E. coli produces stable dimeric fusion proteins that spontaneously self-assemble into enormous, polyvalent complexes having increased immunogenicity and functionality. Linear, network and agglomerate complexes with enormous sizes and polyvalences are constructed using glutathione S-transferase, Norovirus P domains (NoV P? and NoV+), the protruding (P) domain of hepatitis E virus (HEV P), the astrovirus P domain (AstV), a monomeric peptide epitope (M2e of influenza virus), and/or a protein antigen (VP8* of rotavirus) fused in different combinations. The resulting complexes can contain hundreds to thousands NoV P-protein, HEV, AstV, M2e and/or VP8* copies and exhibit higher immunogenicity than the individual proteins alone.Type: ApplicationFiled: March 14, 2013Publication date: January 16, 2014Inventors: Ming TAN, Xi Jiang, Leyi Wang
-
Patent number: 6188944Abstract: A method and system for controlling torque disturbances in direct injection stratified charge and lean burn port-fuel injection engines (12) through continuously variable transmission (40). The method and system include using the continuously variable transmission (40) to mitigate the effects of torque disturbances due to a lean NOx trap (22) purge cycle (100). The continuously variable transmission (40) is coordinated with other engine variables, such as throttle (36), fueling rate (Wf), injection timing (&ggr;), and spark timing (&dgr;), to keep the operation near the optimal regime. In periods of trap (22) purge, the engine control variables and the continuously variable transmission (40) are coordinated to maximize purge efficiency for a predetermined period of time. In periods of normal operation (102), the engine control variables and the continuously variable transmission (40) are coordinated to minimize fuel consumption subject to emission constraints.Type: GrantFiled: June 1, 1999Date of Patent: February 13, 2001Assignee: Ford Motor CompanyInventors: Llya V. Kolmanovsky, Jing Sun, Leyi Wang