Patents by Inventor Bing Xiang

Bing Xiang 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: 12189638
    Abstract: The described system provides a dual-model framework for data retrieval from complex data environments such as webpages on the internet. It combines a traditional similarity model that identifies relevant data from vast amounts of data and a large language model that delves deeper into the relevant data to uncover specifics. The models, in conjunction, provide a method for providing responses to structured queries about an entity. A source investigator receives a request for information about an entity alongside a set of keywords. A source datastore is identified for the entity and a similarity model is applied to the datastore to determine relevancy scores for data within. Data and/or nodes above a relevancy threshold are stored as relevant data. Then, using the large language model, the investigator generates responses to the structured queries based on the relevant data and provides responses to the user system.
    Type: Grant
    Filed: April 25, 2024
    Date of Patent: January 7, 2025
    Assignee: Goldman Sachs & Co. LLC
    Inventors: Konstantin Kuchenmeister, Alysa V Shcherbakova, Demetrius Rowland, Bing Xiang
  • Patent number: 12141553
    Abstract: Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.
    Type: Grant
    Filed: June 22, 2022
    Date of Patent: November 12, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Praphruetpong Athiwaratkun, Zixuan Lin, Ramana Keerthi, Zijian Wang, Yuchen Tian, Hantian Ding, Sri Ranga Akhilesh Bontala, Matthew Lee, Yanitsa Donchev, Ramesh M Nallapati, Parminder Bhatia, Andrew Oliver Arnold, Bing Xiang, Sudipta Sengupta, Rama Krishna Sandeep Pokkunuri, Srinivas Iragavarapu, Atul Deo, Ankur Deepak Desai
  • Publication number: 20240302262
    Abstract: A method and a system for identifying a glacial lake outburst debris flow (GLODF) are provided. The method is obtained based on considering induced influences of slopes of channels and particle sizes of source particles on the GLODF. The method not only compensates for deficiencies in identifying the GLODF, but also realizes determination of the GLODF, which provides data basis for disaster prevention and control layout such as monitoring and early warning on a glacial lake and assists preventing and managing disasters caused by the GLODF. Meanwhile, multiple parameters used in the method are easy and convenient to obtain, and the parameters can be directly used on site, which saves engineering cost, improves working efficiency, and has high practical and promotional value in environmental protection and disaster prevention and mitigation.
    Type: Application
    Filed: March 8, 2024
    Publication date: September 12, 2024
    Inventors: Zhi-quan Yang, Zi-xu Zhang, Wen-qi Jiao, Ying-yan Zhu, Muhammad Asif Khan, Yong-shun Han, Li-ping Liao, Jie Zhang, Wen-fei Xi, Han-hua Xu, Tian-bing Xiang, Xin Zhao, Bi-hua Zhang, Shen-zhang Liu, Cheng-yin Ye
  • Patent number: 12014155
    Abstract: Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.
    Type: Grant
    Filed: June 22, 2022
    Date of Patent: June 18, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Praphruetpong Athiwaratkun, Yuchen Tian, Mingyue Shang, Zijian Wang, Ramesh M Nallapati, Parminder Bhatia, Andrew Oliver Arnold, Bing Xiang, Sudipta Sengupta, Yanitsa Donchev, Srinivas Iragavarapu, Matthew Lee, Vamshidhar Krishnamurthy Dantu, Atul Deo, Ankur Deepak Desai
  • Patent number: 12007988
    Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.
    Type: Grant
    Filed: March 10, 2023
    Date of Patent: June 11, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Ramesh M Nallapati, Zhiguo Wang, Bing Xiang, Patrick Ng, Yung Haw Wang, Mukul Karnik, Nanyan Li, Sharanabasappa Parashuram Revadigar, Timothy Jones, Stephen Michael Ash, Sudipta Sengupta, Gregory David Adams, Deepak Shantha Murthy, Douglas Scott Cerny, Stephanie Weeks, Hanbo Li
  • Patent number: 11958789
    Abstract: A method for determining a consistency coefficient of a power-law cement grout includes: determining a water-cement ratio of the power-law cement grout; according to engineering practice requirements, determining a time required to determine the consistency coefficient of the power-law cement grout; and obtaining the consistency coefficient of the power-law cement grout. The method is accurate and reliable, requires less calculation, etc.; and has very high practical value and popularization value in environmental protection and ecological restoration.
    Type: Grant
    Filed: December 12, 2023
    Date of Patent: April 16, 2024
    Assignee: KUNMING UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Zhi-quan Yang, Jun-fan Xiong, Ying-yan Zhu, Yi Yang, Yong-shun Han, Muhammad Asif Khan, Jian-bin Xie, Tian-bing Xiang, Bi-hua Zhang, Han-hua Xu, Jie Zhang, Shen-zhang Liu, Qi-jun Jia, Cheng-yin Ye, Gang Li
  • Patent number: 11946845
    Abstract: A method for determining a three-dimensional tortuosity of a loose and broken rock-soil mass, includes the following steps: a particle grading curve of the loose and broken rock-soil mass is obtained by utilizing a particle size analysis, and followed by calculating an equivalent particle size and an average particle size; a porosity of the loose and broken rock-soil mass is obtained by utilizing a moisture content test, a density test, and a specific gravity test; the three-dimensional tortuosity of the loose and broken rock-soil mass is obtained by utilizing the equivalent particle size, the average particle size and the porosity of the loose and broken rock-soil mass. The method has the advantages of simple logic, accuracy and reliability, simple and fast parameter determination, and has high practical value and promotion value in the field of environmental protection and ecological restoration technology.
    Type: Grant
    Filed: November 1, 2023
    Date of Patent: April 2, 2024
    Assignee: KUNMING UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Zhi-quan Yang, Jia-jun Zhang, Jun-fan Xiong, Ying-yan Zhu, Yi Yang, Muhammad Asif Khan, Tian-bing Xiang, Bi-hua Zhang, Han-hua Xu, Jie Zhang, Shen-zhang Liu
  • Publication number: 20230418566
    Abstract: Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.
    Type: Application
    Filed: June 22, 2022
    Publication date: December 28, 2023
    Applicant: Amazon Technologies, Inc.
    Inventors: Praphruetpong Athiwaratkun, Zixuan Lin, Ramana Keerthi, Zijian Wang, Yuchen Tian, Hantian Ding, Sri Ranga Akhilesh Bontala, Matthew Lee, Yanitsa Donchev, Ramesh M Nallapati, Parminder Bhatia, Andrew Oliver Arnold, Bing Xiang, Sudipta Sengupta, Rama Krishna Sandeep Pokkunuri, Srinivas Iragavarapu, Atul Deo, Ankur Deepak Desai
  • Publication number: 20230418565
    Abstract: Code completion suggestions may be proactively obtained and validated. An event that triggers obtaining a code completion suggestion for inclusion in a code file being edited using an integrated development environment may be detected. The code completion suggestion may be obtained. The characters of the code completion suggestion may be compared with characters added to the code file after the detection of the event that triggered obtaining the code completion suggestion to determine whether the code completion suggestion is valid. A valid code completion suggestion may then be displayed.
    Type: Application
    Filed: June 22, 2022
    Publication date: December 28, 2023
    Applicant: Amazon Technologies, Inc.
    Inventors: Sathish Arumugam Selvaraj, Qiang Yu, Venkat Rakshith Reddy Swamireddy, Matthew Lee, Lei Gao, Wei Fang, Rama Krishna Sandeep Pokkunuri, Ramesh M Nallapati, Srinivas Iragavarapu, Alexander Johannes Smola, Sudipta Sengupta, Wasi Uddin Ahmad, Parminder Bhatia, Atul Deo, Ankur Deepak Desai, Bing Xiang, Andrew Oliver Arnold
  • Publication number: 20230418567
    Abstract: Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.
    Type: Application
    Filed: June 22, 2022
    Publication date: December 28, 2023
    Applicant: Amazon Technologies, Inc.
    Inventors: Praphruetpong Athiwaratkun, Yuchen Tian, Mingyue Shang, Zijian Wang, Ramesh M. Nallapati, Parminder Bhatia, Andrew Oliver Arnold, Bing Xiang, Sudipta Sengupta, Yanitsa Donchev, Srinivas Iragavarapu, Matthew Lee, Vamshidhar Krishnamurthy Dantu, Atul Deo, Ankur Deepak Desai
  • Publication number: 20230419036
    Abstract: Random token segmentation may be implemented for next token prediction. Text data may be received for training a machine learning model to predict a next token given input text tokens. Multiple tokens may be determined from the text data. Different ones of the multiple token may be randomly segmented in to sub-tokens. The machine learning model may then be trained using the multiple tokens including the respective sub-tokens as a training data set.
    Type: Application
    Filed: June 22, 2022
    Publication date: December 28, 2023
    Applicant: Amazon Technologies, Inc.
    Inventors: Zijian Wang, Yuchen Tian, Mingyue Shang, Praphruetpong Athiwaratkun, Ming Tan, Parminder Bhatia, Andrew Oliver Arnold, Ramesh M Nallapati, Sudipta Sengupta, Bing Xiang, Atul Deo, Ankur Deepak Desai
  • Publication number: 20230325384
    Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.
    Type: Application
    Filed: March 10, 2023
    Publication date: October 12, 2023
    Applicant: Amazon Technologies, Inc.
    Inventors: Ramesh M Nallapati, Zhiguo Wang, Bing Xiang, Patrick Ng, Yung Haw Wang, Mukul Karnik, Nanyan Li, Sharanabasappa Parashuram Revadigar, Timothy Jones, Stephen Michael Ash, Sudipta Sengupta, Gregory David Adams, Deepak Shantha Murthy, Douglas Scott Cerny, Stephanie Weeks, Hanbo Li
  • Patent number: 11726994
    Abstract: Query restatements may be provided for explaining natural language query results. A natural language query is received at a natural language query processing system. An intermediate representation of the natural language query is generated for executing the natural language query. The intermediate representation is translated into a natural language restatement of the natural language query. The natural language restatement is provided with a result of the natural language query via an interface of the natural language query processing system.
    Type: Grant
    Filed: March 31, 2021
    Date of Patent: August 15, 2023
    Assignee: Amazon Technologies, Inc.
    Inventors: Jun Wang, Zhiguo Wang, Sharanabasappa Parashuram Revadigar, Ramesh M Nallapati, Bing Xiang, Sudipta Sengupta, Yung Haw Wang
  • Patent number: 11726997
    Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.
    Type: Grant
    Filed: November 14, 2022
    Date of Patent: August 15, 2023
    Assignee: Amazon Technologies, Inc.
    Inventors: Jun Wang, Zhiguo Wang, Sharanabasappa Parashuram Revadigar, Ramesh M Nallapati, Bing Xiang, Stephen Michael Ash, Timothy Jones, Sudipta Sengupta, Rishav Chakravarti, Patrick Ng, Jiarong Jiang, Hanbo Li, Donald Harold Rivers Weidner
  • Publication number: 20230078177
    Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.
    Type: Application
    Filed: November 14, 2022
    Publication date: March 16, 2023
    Applicant: Amazon Technologies, Inc.
    Inventors: Jun Wang, Zhiguo Wang, Sharanabasappa Parashuram Revadigar, Ramesh M Nallapati, Bing Xiang, Stephen Michael Ash, Timothy Jones, Sudipta Sengupta, Rishav Chakravarti, Patrick Ng, Jiarong Jiang, Hanbo Li, Donald Harold Rivers Weidner
  • Patent number: 11604794
    Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.
    Type: Grant
    Filed: March 31, 2021
    Date of Patent: March 14, 2023
    Assignee: Amazon Technologies, Inc.
    Inventors: Ramesh M Nallapati, Zhiguo Wang, Bing Xiang, Patrick Ng, Yung Haw Wang, Mukul Karnik, Nanyan Li, Sharanabasappa Parashuram Revadigar, Timothy Jones, Stephen Michael Ash, Sudipta Sengupta, Gregory David Adams, Deepak Shantha Murthy, Douglas Scott Cerny, Stephanie Weeks, Hanbo Li
  • Patent number: 11526557
    Abstract: Techniques for displaying a search are described. An exemplary method includes receiving a search query, performing the search query on a plurality of documents, the documents including text passages, to generate a search query result, determining an aspect of the search query result that has a confidence value that exceeds a first confidence threshold with respect to its relevance to the search query; and, displaying the search result including an emphasis on the aspect of the result exceeds the first confidence threshold.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: December 13, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Zhiguo Wang, Zhiheng Huang, Ramesh M. Nallapati, Bing Xiang
  • Patent number: 11500865
    Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.
    Type: Grant
    Filed: March 31, 2021
    Date of Patent: November 15, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Jun Wang, Zhiguo Wang, Sharanabasappa Parashuram Revadigar, Ramesh M Nallapati, Bing Xiang, Stephen Michael Ash, Timothy Jones, Sudipta Sengupta, Rishav Chakravarti, Patrick Ng, Jiarong Jiang, Hanbo Li, Donald Harold Rivers Weidner
  • Patent number: 11475067
    Abstract: Techniques for generation of synthetic queries from customer data for training of document querying machine learning (ML) models as a service are described. A service may receive one or more documents from a user, generate a set of question and answer pairs from the one or more documents from the user using a machine learning model trained to predict a question from an answer, and store the set of question and answer pairs generated from the one or more documents from the user. The question and answer pairs may be used to train another machine learning model, for example, a document ranking model, a passage ranking model, a question/answer model, or a frequently asked question (FAQ) model.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: October 18, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Cicero Nogueira Dos Santos, Xiaofei Ma, Peng Xu, Ramesh M. Nallapati, Bing Xiang, Sudipta Sengupta, Zhiguo Wang, Patrick Ng
  • Patent number: 11397647
    Abstract: Embodiments of the present disclosure provide a hot backup system, a hot backup method, and a computer device. The hot backup system includes a centralized management module, a master server, a slave server and a delay server. The master server is configured to receive a write instruction sent by the centralized management module, and write first data to a database of the master server based on the write instruction. The slave server is configured to perform data synchronization with the master server in real time, receive a read instruction sent by the centralized management module, and send second data read based on the read instruction to the centralized management module to cause the centralized management module to send the second data to the service server.
    Type: Grant
    Filed: August 28, 2019
    Date of Patent: July 26, 2022
    Assignee: Apollo Intelligent Driving Technology (Beijing) Co., Ltd.
    Inventors: Bing Xiang, Xiaoliang Cong