Patents by Inventor Wenbin Jiang

Wenbin Jiang 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: 12236361
    Abstract: The present disclosure discloses a question analysis method, a device, a knowledge base question answering system and an electronic equipment. The method includes: analyzing a question to obtain N linearized sequences, N being an integer greater than 1; converting the N linearized sequences into N network topology maps; separately calculating a semantic matching degree of each of the N network topology maps to the question; and selecting a network topology map having a highest semantic matching degree to the question as a query graph of the question from the N network topology maps. According to the technology of the present disclosure, the query graph of the question can be obtained more accurately, and the accuracy of the question to the query graph is improved, thereby improving the accuracy of question analysis.
    Type: Grant
    Filed: September 29, 2020
    Date of Patent: February 25, 2025
    Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd
    Inventors: Wenbin Jiang, Huanyu Zhou, Meng Tian, Ying Li, Xinwei Feng, Xunchao Song, Pengcheng Yuan, Yajuan Lyu, Yong Zhu
  • Patent number: 12210982
    Abstract: The present disclosure provides a method for processing intelligent question-answering, an intelligent question-answering system, an electronic device and a storage medium, and relates to the field of artificial intelligence technologies, such as machine learning technologies, natural language processing technologies, or the like. An implementation includes: acquiring an input question and input data information; and based on the question, the data information and a plurality of knowledge bases, deciding an answer to the question by multilayer appreciation using a plurality of understanding module layers.
    Type: Grant
    Filed: July 25, 2022
    Date of Patent: January 28, 2025
    Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Wenbin Jiang, Yajuan Lyu, Yong Zhu, Hua Wu, Haifeng Wang
  • Patent number: 12175379
    Abstract: The present disclosure discloses a method, apparatus, device, and storage medium for training a model, relates to the technical fields of knowledge graph, natural language processing, and deep learning. The method may include: acquiring a first annotation data set, the first annotation data set including sample data and a annotation classification result corresponding to the sample data; training a preset initial classification model based on the first annotation data set to obtain an intermediate model; performing prediction on the sample data in the first annotation data set using the intermediate model to obtain a prediction classification result corresponding to the sample data; generating a second annotation data set based on the sample data, the corresponding annotation classification result, and the corresponding prediction classification result; and training the intermediate model based on the second annotation data set to obtain a classification model.
    Type: Grant
    Filed: December 11, 2020
    Date of Patent: December 24, 2024
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Hongjian Shi, Wenbin Jiang, Xinwei Feng, Miao Yu, Huanyu Zhou, Meng Tian, Xueqian Wu, Xunchao Song
  • Patent number: 12165072
    Abstract: A method, apparatus, device, and storage medium for expanding data are disclosed. The method includes: acquiring a triplet from a knowledge graph; mining a relationship path equivalent to a relationship in the triplet from the knowledge graph, a subject in the triplet being used as a start point of the relationship path, and an object in the triplet being used as an end point of the relationship path; and expanding the triplet based on the relationship path to generate an expanded triplet. This implementation expands the triplet in the knowledge graph, and strengthens the association between the subject and the object in the triplet in a larger context, such that the association between the subject and the object in the triplet is more global.
    Type: Grant
    Filed: March 26, 2021
    Date of Patent: December 10, 2024
    Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.
    Inventors: Pingping Huang, Quan Wang, Wenbin Jiang, Pengcheng Yuan
  • Patent number: 12019990
    Abstract: The present application discloses a text processing method and device based on natural language processing and a knowledge graph, and relates to the in-depth field of artificial intelligence technology. A specific implementation is: an electronic device uses a joint learning model to obtain a semantic representation, which is obtained by the joint learning model by combining knowledge graph representation learning and natural language representation learning, it combines a knowledge graph representation learning and a natural language representation learning, compared to using only the knowledge graph representation learning or the natural language representation learning to learn semantic representation of a prediction object, factors considered by the joint learning model are more in quantity and comprehensiveness, so accuracy of semantic representation can be improved, and thus accuracy of text processing can be improved.
    Type: Grant
    Filed: December 16, 2020
    Date of Patent: June 25, 2024
    Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Haifeng Wang, Wenbin Jiang, Yajuan Lv, Yong Zhu, Hua Wu
  • Patent number: 11995560
    Abstract: The present disclosure discloses a method and an apparatus for generating a vector representation of a knowledge graph, and relates to a field of a field of artificial intelligence technologies. The detailed implementing solution is: obtaining a knowledge graph, the knowledge graph including a plurality of entity nodes; obtaining a context type and context data corresponding to the knowledge graph; and generating vector representations corresponding to the plurality of entity nodes by a context model based on the context data and the context type.
    Type: Grant
    Filed: April 7, 2020
    Date of Patent: May 28, 2024
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Quan Wang, Pingping Huang, Haifeng Wang, Wenbin Jiang, Yajuan Lyu, Yong Zhu, Hua Wu
  • Publication number: 20240151631
    Abstract: A method for a flow cytometer includes generating at least one light output with at least one excitation light source; carrying a bio-sample in a medium to a region of a flow path, wherein the bio-sample in the region is illuminated by the at least one light output of the at least one excitation light source to give off luminescence; spatially dispersing a spectrum of the luminescence across photo detection inputs of a photo-detector array; receiving eight or more analog signals from the photo-detector array and converting them to eight or more digital signals respectively; generating a self trigger signal based on the eight or more digital signals and the luminescence; and causing a digital storage space and a digital processing unit to respectively store and analyze the digital data of the eight or more digital signals based on the self trigger signal.
    Type: Application
    Filed: August 8, 2023
    Publication date: May 9, 2024
    Applicant: Cytek Biosciences, Inc.
    Inventor: Wenbin Jiang
  • Patent number: 11719617
    Abstract: A flow-cytometer has an excitation light source generating an excitation light that excites one or more bio-cells in a bio-sample carried by a flow path to luminesce. The flow-cytometer includes a spectrum dispersive element that disperses the luminescent light generated by the bio-sample into a photo-detector array. The flow-cytometer further includes a digital signal processor (DSP) that receives signals from the photo-detector array and generates a self-triggering signal based on the luminescent light generated by the bio-cells in bio-sample. The self-triggering signal triggers data capture in the DSP to improve synchronization with the data generated from signals received from the photo-detector array.
    Type: Grant
    Filed: November 5, 2021
    Date of Patent: August 8, 2023
    Assignee: Cytek Biosciences, Inc.
    Inventor: Wenbin Jiang
  • Publication number: 20230214688
    Abstract: A method and apparatus for determining an answer to a question are provided.
    Type: Application
    Filed: March 9, 2023
    Publication date: July 6, 2023
    Inventors: Jiyuan ZHANG, Jianguo MAO, Zengfeng ZENG, Weihua PENG, Wenbin JIANG, Yajuan LYU
  • Publication number: 20230153337
    Abstract: A question answering method, a method of training a question answering model, a device, and a medium are provided, which relate to a field of artificial intelligence technology, in particular to fields of natural language processing technology, deep learning technology, and knowledge mapping technology. The question answering method includes: obtaining data to be processed, wherein the data to be processed includes a question and candidate answers; performing general semantic understanding on the data to be processed to obtain a general data feature; selecting a target question answering mode from candidate question answering modes based on the general data feature; and processing the general data feature by using the target question answering mode, to obtain a target answer for the question from the candidate answers.
    Type: Application
    Filed: January 20, 2023
    Publication date: May 18, 2023
    Inventors: Wenbin JIANG, Yajuan LV, Chunguang CHAI, Yong ZHU
  • Publication number: 20230103430
    Abstract: The present disclosure discloses a method and an apparatus for generating a vector representation of a knowledge graph, and relates to a field of a field of artificial intelligence technologies. The detailed implementing solution is: obtaining a knowledge graph, the knowledge graph including a plurality of entity nodes; obtaining a context type and context data corresponding to the knowledge graph; and generating vector representations corresponding to the plurality of entity nodes by a context model based on the context data and the context type.
    Type: Application
    Filed: April 7, 2020
    Publication date: April 6, 2023
    Inventors: Quan WANG, Pingping HUANG, Haifeng WANG, Wenbin JIANG, Yajuan LYU, Yong ZHU, Hua WU
  • Publication number: 20230092736
    Abstract: The present disclosure provides a method for processing intelligent question-answering, an intelligent question-answering system, an electronic device and a storage medium, and relates to the field of artificial intelligence technologies, such as machine learning technologies, natural language processing technologies, or the like. An implementation includes: acquiring an input question and input data information; and based on the question, the data information and a plurality of knowledge bases, deciding an answer to the question by multilayer appreciation using a plurality of understanding module layers.
    Type: Application
    Filed: July 25, 2022
    Publication date: March 23, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Wenbin JIANG, Yajuan LYU, Yong ZHU, Hua WU, Haifeng WANG
  • Publication number: 20230086145
    Abstract: A method of processing data, a device, and a medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, natural language technology, speech technology, deep learning and knowledge graph. The method of processing data includes: generating a video feature, a question feature and an answer feature based on acquired video data, acquired question data and acquired candidate answer data; determining a link relationship between the video feature, the question feature and the answer feature; and determining a matching result for the video data, the question data and the candidate answer data based on the link relationship.
    Type: Application
    Filed: September 29, 2022
    Publication date: March 23, 2023
    Inventors: Wenbin JIANG, Yajuan LV, Yong ZHU, Hua WU, Haifeng WANG
  • Publication number: 20230018489
    Abstract: The present disclosure discloses a method for acquiring a structured question-answering (QA) model, a QA method and corresponding apparatuses, and relates to knowledge graph and deep learning technologies in the field of artificial intelligence technologies. A specific implementation solution involves: acquiring training samples corresponding to N structured QA database types, the training samples including question samples, information of the structured QA database types and query instruction samples used by the question samples to query structured QA databases of the types, N being an integer greater than 1; and training a text generation model by using the training samples to obtain the structured QA model, wherein the question samples and the information of the structured QA database types are taken as input to the text generation model, and the query instruction samples are taken as target output of the text generation model.
    Type: Application
    Filed: July 12, 2022
    Publication date: January 19, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Wenbin JIANG, Yajuan LYU, Yong ZHU, Hua WU, Haifeng WANG
  • Publication number: 20230013796
    Abstract: The present disclosure provides a method and apparatus for acquiring a pre-trained model, an electronic device and a storage medium, and relates to the fields such as deep learning, natural language processing, knowledge graph and intelligent voice. The method may include: acquiring a pre-training task set composed of M pre-training tasks, M being a positive integer greater than 1, the pre-training tasks including: N question-answering tasks corresponding to different question-answering forms, N being a positive integer greater than 1 and less than or equal to M; and jointly pre-training the pre-trained model according to the M pre-training tasks.
    Type: Application
    Filed: July 15, 2022
    Publication date: January 19, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Wenbin JIANG, Zhifan FENG, Xinwei FENG, Yajuan LYU, Yong ZHU
  • Publication number: 20230008897
    Abstract: An information search method includes: obtaining search words at least including a question to be searched and obtaining an initial text vector representation of the search words; obtaining a video corresponding to the search words, and obtaining multi-modality vector representations of the video; starting from the initial text vector representation, performing N rounds of interaction between the video and the search words based on the multi-modality vector representations and a text vector representation of the search words of a current round, to generate a target fusion vector representation, where N is an integer greater than or equal to 1; and obtaining target video frames matching the question to be searched by annotating the video based on the target fusion vector representation.
    Type: Application
    Filed: September 15, 2022
    Publication date: January 12, 2023
    Inventors: Wenbin JIANG, Yajuan LYU, Yong ZHU, Hua WU, Haifeng WANG
  • Publication number: 20220391426
    Abstract: The present disclosure provides a multi-system-based intelligent question answering method and apparatus, and a device, relating to the field of artificial intelligence, in particular to the field of knowledge graph. The specific implementation solution is: determining a question category of question information in response to a question answering instruction of a user, wherein the question answering instruction is used to indicate the question information; determining a query engine corresponding to the question category, and invoking multiple question analysis systems corresponding to the query engine according to the query engine; and feeding back answer information to the user when the answer information corresponding to the question information is determined according to a current question analysis system in a process of processing the question information by sequentially using the multiple question analysis systems according to system priorities of the question analysis systems.
    Type: Application
    Filed: August 17, 2022
    Publication date: December 8, 2022
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Xinwei FENG, Meng TIAN, Feifei LI, Hongjian SHI, Wenbin JIANG, Xueqian WU, Chenyang GUO, Yu WANG, Yu SUN, Shuaiyu CHEN
  • Publication number: 20220288731
    Abstract: A decoupling control method for linkage turntable in the technical field of associative motion control mechanisms. Steps of the technical solution are as follows: measure a length L of a hypotenuse of a triangular structure; convert A-axis coordinates input to the system into Z0-axis coordinates according to Z0=L*cos ? and input them on Z0-axis; and in the case of a speed control method, convert the A-axis coordinates into a periodic displacement of Z0 according to ?Z0=L*(cos ?1?cos ?2), and input the displacement to Z0-axis. The beneficial effect is that the horizontal displacement generated by the movement of the Z0-axis is directly integrated into the closed loop of the X-axis by means of measurement combination and the displacement directly calculated by grating scale has high precision and no delay, and it is possible to achieve a more effective control level on this mechanical structure.
    Type: Application
    Filed: August 14, 2020
    Publication date: September 15, 2022
    Inventors: Hu CHEN, Huijie LIU, Jingwen LIU, Wenbin JIANG, Yutong HUANG
  • Patent number: 11333597
    Abstract: A system, an apparatus, and a method are provided for a modular flow cytometer with a compact size. In one embodiment, the modular flow cytometry system includes the following: a laser system for emitting laser beams; a flow cell assembly positioned to receive the laser beams at an interrogation region of a fluidics stream where fluoresced cells scatter the laser beams into fluorescent light; a fiber assembly positioned to collect the fluorescent light; and a compact light detection module including a first image array having a transparent block, a plurality of micro-mirrors in a row coupled to a first side of the transparent block, and a plurality of filters in a row coupled to a second side of the transparent block opposite the first side.
    Type: Grant
    Filed: March 30, 2018
    Date of Patent: May 17, 2022
    Assignee: Cytek Biosciences, Inc.
    Inventors: Ming Yan, Yung-Chieh Hsieh, David Vrane, Eric Chase, Wenbin Jiang
  • Publication number: 20220128450
    Abstract: A system, an apparatus, and a method are provided for a modular flow cytometer with a compact size. In one embodiment, the modular flow cytometry system includes the following: a laser system for emitting laser beams; a flow cell assembly positioned to receive the laser beams at an interrogation region of a fluidics stream where fluoresced cells scatter the laser beams into fluorescent light; a fiber assembly positioned to collect the fluorescent light; and a compact light detection module including a first image array having a transparent block, a plurality of micro-mirrors in a row coupled to a first side of the transparent block, and a plurality of filters in a row coupled to a second side of the transparent block opposite the first side.
    Type: Application
    Filed: March 30, 2018
    Publication date: April 28, 2022
    Inventors: Ming Yan, Yung-Chieh Hsieh, David Vrane, Eric Chase, Wenbin Jiang