Patents by Inventor Yabing Shi

Yabing Shi 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: 12182724
    Abstract: A method and apparatus for generating a temporal knowledge graph, a device and a medium. An embodiment comprises: acquiring corpus including time information; performing multivariate data extraction on the corpus, multivariate data including an entity pair, an entity relationship and a target time interval of the entity relationship, the target time interval being used to indicate a valid period of the entity relationship; and generating a temporal knowledge graph based on the entity pair, the entity relationship and the target time interval of the entity relationship.
    Type: Grant
    Filed: September 18, 2020
    Date of Patent: December 31, 2024
    Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.
    Inventors: Fang Huang, Shuangjie Li, Yabing Shi, Ye Jiang, Yang Zhang, Yong Zhu
  • Publication number: 20240411979
    Abstract: A method, apparatus, device, and medium for determining the similarity of text processing tasks is provided. The method includes: determining a first task, a second task, and a neural network, the neural network includes a plurality of network modules and a plurality of importance coefficients corresponding to the plurality of network modules, and the importance coefficients are used to scale output values of a corresponding network module; respectively performing a target operation using the first task and the second task as a target task to obtain an embedding feature of the first task and an embedding feature of the second task; and determining the task similarity between the first task and the second task based on the embedding features. The target operation includes: training using text samples and obtaining a plurality of trained importance coefficients; and determining an embedding feature of the target task based on trained importance coefficients.
    Type: Application
    Filed: June 20, 2024
    Publication date: December 12, 2024
    Inventors: Minlong PENG, Mingming SUN, Yabing SHI
  • Patent number: 12038982
    Abstract: A method of extracting a table information, an electronic device, and a storage medium are provided, which relate to fields of artificial intelligence and big data, in particular to fields of machine learning, knowledge graph, intelligent search and intelligent recommendation, and may be used for an intelligent extraction of an information in a table and other scenarios. The method includes: performing a clustering based on features of a plurality of rows of cells and/or features of a plurality of columns of cells in a table, so as to determine candidate header cells in the table; and performing an information extraction on the table based on the candidate header cells, so as to extract attribute-attribute value pairs in the table.
    Type: Grant
    Filed: September 30, 2022
    Date of Patent: July 16, 2024
    Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Yue Zhang, Zhou Fang, Yabing Shi, Ye Jiang, Chunguang Chai
  • Patent number: 12008313
    Abstract: The present disclosure provides a medical data verification method, apparatus and an electronic device, related to a field of artificial intelligence technologies, such as AI (artificial intelligence) medical treatment, deep learning, knowledge graphs, natural language processing. A specific implementation is: obtaining medical data to be verified and a candidate document; obtaining feature vectors respectively corresponding to the medical data to be verified and the candidate document by processing the medical data to be verified and the candidate document by using a nature language processing model; obtaining N correlation vectors by calculating correlation between the medical data to be verified and the candidate document based on the feature vectors by using N methods, N being a positive integer greater than 1; and determining a confidence degree of the medical data to be verified to the candidate document by performing fusion calculation on the N correlation vectors.
    Type: Grant
    Filed: September 20, 2021
    Date of Patent: June 11, 2024
    Assignee: BAIDU INTERNATIONAL TECHNOLOGY (SHENZHEN) CO., LTD.
    Inventors: Zhou Fang, Yabing Shi, Ye Jiang, Chunguang Chai
  • Patent number: 11954084
    Abstract: A method and apparatus for processing a table, a device, a storage medium and a product. An implementation of the method comprise: receiving a content query request for a target table; acquiring a target tree structure of the target table according to the content query request; where, the target tree structure is obtained by performing absorbing processing and merging processing on at least one target cell in the target table; acquiring to-be-queried content in the content query request; and querying target content matching the to-be-queried content from the target tree structure.
    Type: Grant
    Filed: July 22, 2022
    Date of Patent: April 9, 2024
    Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.
    Inventors: Yue Zhang, Yabing Shi, Ye Jiang, Chunguang Chai
  • Publication number: 20240090627
    Abstract: A magnetic button with a attraction effect is disclosed. The magnetic button includes an adsorption sub-buckle and an adsorption female buckle. Installation pads are arranged at one end of the adsorption sub-buckle and at one end of the adsorption female buckle. A connection clamping column is arranged on one side of the adsorption sub-buckle. Double locking is performed via clamping between the connection clamping column and a female buckle and adsorption between a common magnet and a strong neodymium iron boron magnet. A male buckle concave clamping groove is formed in the connection clamping column. A clamping ring is arranged on an inner wall of the male buckle concave clamping groove.
    Type: Application
    Filed: September 20, 2022
    Publication date: March 21, 2024
    Applicant: Dongguan YANLI Hardware plastic Co. LTD
    Inventor: Yabing SHI
  • Patent number: 11775776
    Abstract: A method and an apparatus for processing information are provided. The method can include: acquiring a word sequence obtained by performing word segmentation on two paragraphs in a text; inputting the word sequence into a to-be-trained natural language processing model to generate a word vector corresponding to a word in the word sequence; inputting the word vector into a preset processing layer of the to-be-trained natural language processing model; predicting whether the two paragraphs are adjacent, and a replaced word in the two paragraphs; and acquiring reference information of the two paragraphs, and training the to-be-trained natural language processing model to obtain a trained natural language processing model, based on the prediction result and the reference information.
    Type: Grant
    Filed: January 13, 2021
    Date of Patent: October 3, 2023
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Shuangjie Li, Miao Yu, Yabing Shi, Xuefeng Hao, Xunchao Song, Ye Jiang, Yang Zhang, Yong Zhu
  • Patent number: 11755654
    Abstract: Provided by the present disclosure is a new category tag mining method, involving the field of knowledge graph technology, and including: obtaining a plurality of queries during a current preset time period; labeling a category tag on each query of the plurality of queries, by using a pre-trained sequence labeling model, to extract the category tag currently corresponding to the query from the query; and removing a category tag already existing in a preset current category tag library from category tags currently corresponding to all the queries, and determining a remaining category tag as a new category tag. The present disclosure also provides an electronic device and a non-transitory computer-readable storage medium.
    Type: Grant
    Filed: February 11, 2021
    Date of Patent: September 12, 2023
    Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.
    Inventors: Qian Li, Yabing Shi, Ye Jiang, Chunguang Chai, Yong Zhu
  • Publication number: 20230133717
    Abstract: Disclosed are an information extraction method, an electronic device and a readable storage medium, which relate to the field of artificial intelligence technologies, and particularly to the field of knowledge graph technologies. The information extraction method includes: acquiring to-be-processed text to obtain a semantic vector of each token in the to-be-processed text; generating a relationship prediction matrix, an entity prediction matrix and an alignment matrix according to each token in the to-be-processed text and the semantic vector of each token; and extracting a target triplet in the to-be-processed text using the relationship prediction matrix, the entity prediction matrix and the alignment matrix, and taking the target triplet as an information extraction result of the to-be-processed text.
    Type: Application
    Filed: September 28, 2022
    Publication date: May 4, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Jiandong SUN, Yabing SHI, Ye JIANG, Chunguang CHAI
  • Patent number: 11636936
    Abstract: The present disclosure relates to the field of medical data processing based on natural language processing. Embodiments of the present disclosure disclose a method and apparatus for verifying a medical fact. The method may include: acquiring a description text of the medical fact; selecting a relevant paragraph related to the description text of the medical fact from a medical document; and inputting the description text of the medical fact and the corresponding relevant paragraph into a trained discrimination model for authenticity judgment, to obtain a verification result of the medical fact, the discrimination model being pre-trained based on a medical text paragraph pair extracted from the medical document, and being iteratively adjusted using a medical fact sample set including authenticity labeling information after the pre-training.
    Type: Grant
    Filed: September 17, 2020
    Date of Patent: April 25, 2023
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Zhou Fang, Shuangjie Li, Yabing Shi, Ye Jiang
  • Publication number: 20230103728
    Abstract: A computer-implemented method for sample augmentation includes: acquiring a second sample corpus and second triplet information of the second sample corpus by performing data augmentation on a first sample corpus labeled with first triplet information; acquiring third triplet information of a third sample corpus by performing semi-supervised learning on the third sample corpus that is not labeled with triplet information; and generating a set of training corpora for a triplet information extraction network based on the first sample corpus and the first triplet information, the second sample corpus and the second triplet information, and the third sample corpus and the third triplet information.
    Type: Application
    Filed: December 8, 2022
    Publication date: April 6, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Jian Liu, Jiandong Sun, Yabing Shi, Ye Jiang, Chunguang Chai
  • Publication number: 20230038091
    Abstract: A method of extracting a table information, an electronic device, and a storage medium are provided, which relate to fields of artificial intelligence and big data, in particular to fields of machine learning, knowledge graph, intelligent search and intelligent recommendation, and may be used for an intelligent extraction of an information in a table and other scenarios. The method includes: performing a clustering based on features of a plurality of rows of cells and/or features of a plurality of columns of cells in a table, so as to determine candidate header cells in the table; and performing an information extraction on the table based on the candidate header cells, so as to extract attribute-attribute value pairs in the table.
    Type: Application
    Filed: September 30, 2022
    Publication date: February 9, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Yue ZHANG, Zhou FANG, Yabing SHI, Ye JIANG, Chunguang CHAI
  • Publication number: 20230016403
    Abstract: The present disclosure provides a method of processing triple data, a method of training a triple data processing model, an electronic device, and a storage medium. A specific implementation solution includes: performing a triple data extraction on text data to obtain a plurality of field data; normalizing the plurality of field data to determine target triple data, wherein the target triple data contains entity data, entity relationship data, and association entity data; and verifying a confidence level of the target triple data to obtain a verification result.
    Type: Application
    Filed: September 23, 2022
    Publication date: January 19, 2023
    Inventors: Zhaoji WANG, Fang HUANG, Ye JIANG, Yabing SHI, Chunguang CHAI, Yong ZHU
  • Patent number: 11556812
    Abstract: Embodiments of the present disclosure provide to a method and a device for acquiring a data model in a knowledge graph, an apparatus and a storage medium. The method includes: receiving a knowledge entry describing a relationship between an entity and an object; determining a plurality of candidate object types of the object according to at least one of the entity, the relationship and the object; determining an object type for generating a data model that matches the knowledge entry from the plurality of candidate object types based on a preset rule; and generating the data model based at least on the object type.
    Type: Grant
    Filed: January 22, 2020
    Date of Patent: January 17, 2023
    Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Qian Li, Yabing Shi, Haijin Liang, Yang Zhang, Yong Zhu
  • Publication number: 20220358110
    Abstract: A method and apparatus for processing a table, a device, a storage medium and a product. An implementation of the method comprise: receiving a content query request for a target table; acquiring a target tree structure of the target table according to the content query request; where, the target tree structure is obtained by performing absorbing processing and merging processing on at least one target cell in the target table; acquiring to-be-queried content in the content query request; and querying target content matching the to-be-queried content from the target tree structure.
    Type: Application
    Filed: July 22, 2022
    Publication date: November 10, 2022
    Inventors: Yue ZHANG, Yabing SHI, Ye JIANG, Chunguang CHAI
  • Patent number: 11361002
    Abstract: The disclosure discloses a method and an apparatus for recognizing an entity word. The method includes: obtaining an entity word category and a document to be recognized; generating an entity word question based on the entity word category; segmenting the document to be recognized to generate a plurality of candidate sentences; inputting the entity word question and the plurality of candidate sentences into a question-answer model trained in advance to obtain an entity word recognizing result; and obtaining an entity word set corresponding to the entity word question based on the entity word recognizing result.
    Type: Grant
    Filed: February 17, 2021
    Date of Patent: June 14, 2022
    Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Yabing Shi, Shuangjie Li, Ye Jiang, Yang Zhang, Yong Zhu
  • Patent number: 11321421
    Abstract: Embodiments of the present disclosure provide a method, an apparatus and a device for generating entity relationship data, and a storage medium. The method includes: obtaining webpage source data corresponding to a target webpage; identifying at least one key value block from the webpage source data, wherein the key value block comprises at least one key value pair; identifying body values corresponding to the at least one key value block from the webpage source data; and generating entity relationship data corresponding to the target webpage according to the key value blocks and the body values corresponding to the key value blocks. With the technical solution the present disclosure, the webpage universality may be improved, labor cost may be reduced, and output quantity of the entity relationship data may be increased.
    Type: Grant
    Filed: August 13, 2019
    Date of Patent: May 3, 2022
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventors: Fang Huang, Shuangjie Li, Bingyang Yu, Yabing Shi, Haijin Liang, Yang Zhang, Yong Zhu
  • Publication number: 20220027766
    Abstract: A method for an industry text increment, as well as an electronic device and a computer readable storage medium for the same are provided. The method may include: acquiring an original industry text in a target industry field, an order of magnitude of a number of the original industry text being smaller than a preset first order of magnitude; and performing a sample incremental processing on the original industry text by using a distant supervision method, to obtain increased industry texts, an order of magnitude of a number of the increased industry texts is greater than a preset second order of magnitude, wherein the preset second order of magnitude is not smaller than the preset first order of magnitude.
    Type: Application
    Filed: October 4, 2021
    Publication date: January 27, 2022
    Inventors: Zhou FANG, Yabing SHI, Ye JIANG, Chunguang CHAI
  • Publication number: 20220004706
    Abstract: The present disclosure provides a medical data verification method, apparatus and an electronic device, related to a field of artificial intelligence technologies, such as AI (artificial intelligence) medical treatment, deep learning, knowledge graphs, natural language processing. A specific implementation is: obtaining medical data to be verified and a candidate document; obtaining feature vectors respectively corresponding to the medical data to be verified and the candidate document by processing the medical data to be verified and the candidate document by using a nature language processing model; obtaining N correlation vectors by calculating correlation between the medical data to be verified and the candidate document based on the feature vectors by using N methods, N being a positive integer greater than 1; and determining a confidence degree of the medical data to be verified to the candidate document by performing fusion calculation on the N correlation vectors.
    Type: Application
    Filed: September 20, 2021
    Publication date: January 6, 2022
    Applicant: BAIDU INTERNATIONAL TECHNOLOGY (SHENZHEN) CO., LTD
    Inventors: Zhou FANG, Yabing SHI, Ye JIANG, Chunguang CHAI
  • Publication number: 20210374576
    Abstract: A medical fact verification method and apparatus, an electronic device, and a storage medium are provided. The medical fact verification method comprises: acquiring a medical fact to be verified and candidate evidence, wherein the medical fact to be verified includes a target entity, a target attribute and a target attribute value; inputting the target entity, the target attribute value and the candidate evidence into an attribute decision model to obtain a decision attribute; inputting the target entity, the target attribute value and the candidate evidence into a relevancy decision model to obtain a relevancy of the candidate evidence in a case that the target attribute and the decision attribute are the same; and determining that the medical fact to be verified is correct in a case that the relevancy of the candidate evidence accords with a preset condition.
    Type: Application
    Filed: December 23, 2020
    Publication date: December 2, 2021
    Inventors: Zhou Fang, Yabing Shi, Ye Jiang, Chunguang Chai