Patents by Inventor Miaosen Wang
Miaosen 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: 11842205Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.Type: GrantFiled: August 30, 2022Date of Patent: December 12, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Ahmed Hassan Awadallah, Miaosen Wang, Ryen White, Yu Su
-
Patent number: 11740196Abstract: A new multifunctional biomass suspension deflagration test-bed is provided, which includes a closed combustion chamber. An integrated temperature and pressure sensor is arranged in the combustion chamber, and a high-speed camera and a laser concentration-measuring instrument are arranged outside the combustion chamber, which can monitor suspension deflagration. A bottom of the combustion chamber is provided with a hollow mushroom-shaped dispersion nozzle with a tray. A nozzle body is provided with a gas main-flow channel at a center thereof and gas deflected-flow channels arranged around the gas main-flow channel. A mushroom-shaped baffle plate is arranged above the nozzle body. The gas main-flow channel extends upward to the mushroom-shaped baffle plate. A vent hole is formed in a portion of the mushroom-shaped baffle plate which is corresponding to the gas main-flow channel. Each gas deflected-flow channel is inclined outward from bottom to top and directed to the mushroom-shaped baffle plate.Type: GrantFiled: July 29, 2021Date of Patent: August 29, 2023Assignee: Henan Agricultural UniversityInventors: Shengyong Liu, Jiong Wang, Jie Lu, Xinping Liu, Libin Jie, Dongdong Wei, Hongge Tao, Chunyao Qing, Li Huang, Aili He, Zhenzhong Wang, Changzhong Ren, Haigang Wang, Baoguo Guo, Lei Peng, Miaosen Wang
-
Publication number: 20220413874Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.Type: ApplicationFiled: August 30, 2022Publication date: December 29, 2022Applicant: Microsoft Technology Licensing, LLCInventors: Ahmed Hassan Awadallah, Miaosen Wang, Ryen White, Yu Su
-
Patent number: 11474836Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.Type: GrantFiled: March 13, 2018Date of Patent: October 18, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Ahmed Hassan Awadallah, Miaosen Wang, Ryen White, Yu Su
-
Patent number: 11295090Abstract: A method for applying a trained machine learning model to answer a user query comprises receiving a query text from a user. A previously-trained discriminator is received, the previously-trained discriminator configured to output, for a pair of sentences, a match value indicating a quality of semantic match between the pair of sentences. For each candidate answer text of a plurality of candidate answer texts, the previously-trained discriminator is operated to output a candidate match value for the query text and the candidate answer text based on comparing a first hierarchy of representations of the query text at increasing degrees of semantic compression to a second hierarchy of representations of the candidate answer text at increasing degrees of semantic compression. An answer text is output that is associated with a highest candidate match value among candidate match values.Type: GrantFiled: April 27, 2020Date of Patent: April 5, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Ahmed Hassan Awadallah, Miaosen Wang, Wei Wang, Madian Khabsa, Xiao Yang
-
Publication number: 20220034832Abstract: A new multifunctional biomass suspension deflagration test-bed is provided, which includes a closed combustion chamber. An integrated temperature and pressure sensor is arranged in the combustion chamber, and a high-speed camera and a laser concentration-measuring instrument are arranged outside the combustion chamber, which can monitor suspension deflagration. A bottom of the combustion chamber is provided with a hollow mushroom-shaped dispersion nozzle with a tray. A nozzle body is provided with a gas main-flow channel at a center thereof and gas deflected-flow channels arranged around the gas main-flow channel. A mushroom-shaped baffle plate is arranged above the nozzle body. The gas main-flow channel extends upward to the mushroom-shaped baffle plate. A vent hole is formed in a portion of the mushroom-shaped baffle plate which is corresponding to the gas main-flow channel. Each gas deflected-flow channel is inclined outward from bottom to top and directed to the mushroom-shaped baffle plate.Type: ApplicationFiled: July 29, 2021Publication date: February 3, 2022Applicant: Henan Agricultural UniversityInventors: Shengyong Liu, Jiong Wang, Jie Lu, Xinping Liu, Libin Jie, Dongdong Wei, Hongge Tao, Chunyao Qing, Li Huang, Aili He, Zhenzhong Wang, Changzhong Ren, Haigang Wang, Baoguo Guo, Lei Peng, Miaosen Wang
-
Publication number: 20200257858Abstract: A method for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.Type: ApplicationFiled: April 27, 2020Publication date: August 13, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Ahmed Hassan AWADALLAH, Miaosen WANG, Wei WANG, Madian KHABSA, Xiao YANG
-
Patent number: 10664662Abstract: A method for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.Type: GrantFiled: April 18, 2018Date of Patent: May 26, 2020Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Ahmed Hassan Awadallah, Miaosen Wang, Wei Wang, Madian Khabsa, Xiao Yang
-
Publication number: 20190325023Abstract: A method for estimating a quality of semantic match of a first sentence to a second sentence comprises outputting a first hierarchy of representations of the first sentence at increasing degrees of semantic compression, outputting a second hierarchy of representations of the second sentence at increasing degrees of semantic compression, comparing a selected representation in the first hierarchy to each of a plurality of representations in the second hierarchy, comparing a selected representation in the second hierarchy to each of a plurality of representations in the first hierarchy, and outputting a match value indicating a quality of semantic match between the first sentence and the second sentence, the match value based at least on the comparisons.Type: ApplicationFiled: April 18, 2018Publication date: October 24, 2019Applicant: Microsoft Technology Licensing, LLCInventors: Ahmed Hassan Awadallah, Miaosen Wang, Wei Wang, Madian Khabsa, Xiao Yang
-
Publication number: 20190286451Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.Type: ApplicationFiled: March 13, 2018Publication date: September 19, 2019Inventors: Ahmed Hassan Awadallah, Miaosen Wang, Ryen White, Yu Su
-
Publication number: 20110145733Abstract: A software tool for organizing and manipulating an electronic document comprising at least one group of document pages, comprises a first user interface module configured to present the document pages of the electronic document in a list-like arrangement; a second user interface module configured to present the document pages of each group in a respective panel; and means operable to manipulate a plurality of selected document pages presented in one or more of the panels simultaneously.Type: ApplicationFiled: January 8, 2009Publication date: June 16, 2011Applicant: Smart Technologies UlcInventors: Jonathan Neitz, Miaosen Wang, Giselle Goncalves, Stewart Schneider, Michael Boyle