Patents by Inventor SHENGYU FU
SHENGYU FU 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).
-
Publication number: 20240076586Abstract: The present disclosure provides a formula of a remover reagent for a cured silicone sealant and a method using the same. The remover reagent is prepared from an acid catalyst and a solvent each having a high boiling point and a high flash point. The acid catalyst is benzenesulfonic acid or alkylbenzenesulfonic acid. The solvent is mineral oil and/or silicone oil. The cured silicone sealant is first soaked with the remover reagent for 30 to 120 min, and then baked at a high temperature of 80 to 120° C. for 10 min or above into debris or powder, whereby the cured silicone sealant with a thickness of 10 mm or above can be removed. Moreover, the remover reagent has the advantages of readily available raw materials, high safety, environmentally friendliness, convenient preparation and good sealant removal effect, and thus, has good application prospects.Type: ApplicationFiled: September 1, 2023Publication date: March 7, 2024Inventors: Cheng FU, Shengyu GE, Huijun GUO, Liang ZHAO
-
Publication number: 20240028306Abstract: A code completion tool uses a neural transformer model to generate candidate sequences to complete a line of source code. The neural transformer model is trained using a conditional language modeling objective on a large unsupervised dataset that includes source code programs written in several different programming languages. The neural transformer model is used within a beam search that predicts the most likely candidate sequences for a code snippet under development.Type: ApplicationFiled: August 9, 2023Publication date: January 25, 2024Inventors: ALEXEY SVYATKOVSKIY, SHENGYU FU, NEELAKANTAN SUNDARESAN, SHAO KUN DENG
-
Publication number: 20230376685Abstract: Edit automation enhancements may be implemented in source code editors and other text editors. Provisional selections that indicate user intentions are submitted to a suggestion generator with other edit context information, to improve the quality of generated text suggestions and reduce the cognitive load on users. A provisional selection may include a highlighted completion list entry, or document text targeted by a hovering cursor, or metainformation text targeted by the hovering cursor, for example. An inline grey text suggestion driven by provisional selection may be displayed simultaneously with completion list suggestions that were created without regard to provisional selection. Suggestions driven by provisional selection may be interleaved with existing document text. Suggestions may be accepted fully in one gesture, or in parts. Suggestions may be edited by a user before being accepted, driving further suggestion refinement.Type: ApplicationFiled: August 2, 2023Publication date: November 23, 2023Inventors: Mark Alistair WILSON-THOMAS, Jonathan Keith SIMMONS, David Ellis PUGH, Vivian Julia LIM, Anqi LI, Shwetha SRINATH, German David OBANDO CHACON, Jin Woo JANG, Shengyu FU, Shao Kun DENG
-
Patent number: 11809842Abstract: A code completion tool uses a neural transformer model to generate candidate sequences to complete a line of source code. The neural transformer model is trained using a conditional language modeling objective on a large unsupervised dataset that includes source code programs written in several different programming languages. The neural transformer model is used within a beam search that predicts the most likely candidate sequences for a code snippet under development.Type: GrantFiled: January 20, 2022Date of Patent: November 7, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Alexey Svyatkovskiy, Shengyu Fu, Neelakantan Sundaresan, Shao Kun Deng
-
Publication number: 20230305824Abstract: A code adaptation mechanism automatically integrates the variable names of a pasted source code snippet into variable names defined in a pre-existing partial source code program. The variable names from the pasted source code snippet are replaced with anonymized values. A deep learning model predicts the most likely variable name from the pre-existing partial source code program to replace each anonymized value. The deep learning model is trained on numerous variable usage patterns from various source code programs to learn to predict the most likely mapping of an undefined variable name from the pasted source code snippet to a variable name in the pre-existing partial source code program thereby generating a syntactically and semantically correct program.Type: ApplicationFiled: March 24, 2022Publication date: September 28, 2023Inventors: MILTIADIS ALLAMANIS, SHENGYU FU, XIAOYU LIU, NEELAKANTAN SUNDARESAN, ALEXEY SVYATKOVSKIY
-
Patent number: 11763078Abstract: Edit automation enhancements may be implemented in source code editors and other text editors. Provisional selections that indicate user intentions are submitted to a suggestion generator with other edit context information, to improve the quality of generated text suggestions and reduce the cognitive load on users. A provisional selection may include a highlighted completion list entry, or document text targeted by a hovering cursor, or metainformation text targeted by the hovering cursor, for example. An inline grey text suggestion driven by provisional selection may be displayed simultaneously with completion list suggestions that were created without regard to provisional selection. Suggestions driven by provisional selection may be interleaved with existing document text. Suggestions may be accepted fully in one gesture, or in parts. Suggestions may be edited by a user before being accepted, driving further suggestion refinement.Type: GrantFiled: April 22, 2021Date of Patent: September 19, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Mark Alistair Wilson-Thomas, Jonathan Keith Simmons, David Ellis Pugh, Vivian Julia Lim, Anqi Li, Shwetha Srinath, German David Obando Chacon, Jin Woo Jang, Shengyu Fu, Shao Kun Deng
-
Patent number: 11715006Abstract: A natural language code search service provides idioms or frequently-occurring code patterns for a code fragment based on similar type usage and method/API invocation usage. The search service uses a data mining technique that mines code snippets found from various websites and code snippets generated from a neural model to detect idioms in the code snippets that were previously unknown and which can be reused. A search is initiated through a natural language query within a code development tool or application thereby avoiding the need to switch out of the current application to perform the search.Type: GrantFiled: March 31, 2020Date of Patent: August 1, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Christian Alma Bird, Shengyu Fu, Zhongyan Guan, Neelakantan Sundaresan, Mark Alistair Wilson-Thomas, Shuo Zhang
-
Patent number: 11662984Abstract: A data mining technique is used to find large frequently-occurring source code patterns from methods/APIs that can be used in code development. Simplified trees that represent the syntactic structure and type and method usage of a source code fragment, such as a method, are mined to find closed and maximal frequent subtrees which represent the largest frequently-occurring source code patterns or idioms associated with a particular type and method usage. These idioms are then used in an idiom web service and/or a code completion system to assist users in the development of source code programs.Type: GrantFiled: June 28, 2022Date of Patent: May 30, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Christian Alma Bird, Shengyu Fu, Neelakantan Sundaresan, Nina Wang, Shuo Zhang
-
Patent number: 11645576Abstract: A code completion system predicts candidates to complete a code fragment with a tag name and/or an attribute name in source code written in a hierarchically-structured language. Candidates for predicting a tag name are based on a first-order tag Markov chain model generated from usage patterns of relationships of tag names found in a training dataset. Candidates for predicting an attribute name are based on a second-order attribute Markov chain model generated from usage patterns of sequences of attribute names associated with each tag name found in the training dataset.Type: GrantFiled: April 22, 2019Date of Patent: May 9, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Shengyu Fu, Neelakantan Sundaresan, Ying Zhao
-
Patent number: 11586839Abstract: A code completion tool uses machine learning models to more precisely predict the likelihood of the parameters of a method invocation. A score is computed for each candidate variable that is used to rank the viability of a variable as the intended parameter. The score is a weighted sum of a scope factor, an edit distance factor and a declaration proximity factor. The factors are based on a scope model, a method overload model, and a weight file trained offline on a training set of source code programs utilizing various method invocations.Type: GrantFiled: December 3, 2018Date of Patent: February 21, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Shengyu Fu, David Poeschl, Neelakantan Sundaresan, Shuo Zhang, Ying Zhao
-
Publication number: 20220358286Abstract: Edit automation enhancements may be implemented in source code editors and other text editors. Provisional selections that indicate user intentions are submitted to a suggestion generator with other edit context information, to improve the quality of generated text suggestions and reduce the cognitive load on users. A provisional selection may include a highlighted completion list entry, or document text targeted by a hovering cursor, or metainformation text targeted by the hovering cursor, for example. An inline grey text suggestion driven by provisional selection may be displayed simultaneously with completion list suggestions that were created without regard to provisional selection. Suggestions driven by provisional selection may be interleaved with existing document text. Suggestions may be accepted fully in one gesture, or in parts. Suggestions may be edited by a user before being accepted, driving further suggestion refinement.Type: ApplicationFiled: April 22, 2021Publication date: November 10, 2022Inventors: Mark Alistair WILSON-THOMAS, Jonathan Keith SIMMONS, David Ellis PUGH, Vivian Julia LIM, Anqi LI, Shwetha SRINATH, German David OBANDO CHACON, Jin Woo JANG, Shengyu FU, Shao Kun DENG
-
Publication number: 20220326918Abstract: A data mining technique is used to find large frequently-occurring source code patterns from methods/APIs that can be used in code development. Simplified trees that represent the syntactic structure and type and method usage of a source code fragment, such as a method, are mined to find closed and maximal frequent subtrees which represent the largest frequently-occurring source code patterns or idioms associated with a particular type and method usage. These idioms are then used in an idiom web service and/or a code completion system to assist users in the development of source code programs.Type: ApplicationFiled: June 28, 2022Publication date: October 13, 2022Inventors: CHRISTIAN ALMA BIRD, SHENGYU FU, NEELAKANTAN SUNDARESAN, NINA WANG, SHUO ZHANG
-
Patent number: 11392354Abstract: A data mining technique is used to find large frequently-occurring source code patterns from methods/APIs that can be used in code development. Simplified trees that represent the syntactic structure and type and method usage of a source code fragment, such as a method, are mined to find closed and maximal frequent subtrees which represent the largest frequently-occurring source code patterns or idioms associated with a particular type and method usage. These idioms are then used in an idiom web service and/or a code completion system to assist users in the development of source code programs.Type: GrantFiled: March 31, 2020Date of Patent: July 19, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Christian Alma Bird, Shengyu Fu, Neelakantan Sundaresan, Nina Wang, Shuo Zhang
-
Patent number: 11379190Abstract: A code completion tool uses a deep learning model to predict the likelihood of a method completing a method invocation. In one aspect, the deep learning model is a LSTM trained on features that represent the syntactic context of a method invocation derived from an abstract tree representation of the code fragment.Type: GrantFiled: April 18, 2021Date of Patent: July 5, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING LLC.Inventors: Alexey Svyatkovskiy, Shengyu Fu, Neelakantan Sundaresan, Ying Zhao
-
Publication number: 20220147321Abstract: A code completion tool uses a neural transformer model to generate candidate sequences to complete a line of source code. The neural transformer model is trained using a conditional language modeling objective on a large unsupervised dataset that includes source code programs written in several different programming languages. The neural transformer model is used within a beam search that predicts the most likely candidate sequences for a code snippet under development.Type: ApplicationFiled: January 20, 2022Publication date: May 12, 2022Inventors: Alexey SVYATKOVSKIY, Shengyu FU, Neelakantan SUNDARESAN, Shao Kun DENG
-
Patent number: 11307831Abstract: A code completion system uses neural components to rank the unordered list of code completion candidates generated from an existing static analyzer. The candidates represent the next sequence of tokens likely to complete a partially-formed program element as a developer is typing in a software development tool. A re-ranking component generates a ranked order of the candidates based on a context embedding of the code context and candidate embeddings of the candidates, where both embeddings are based a common token encoding.Type: GrantFiled: June 15, 2020Date of Patent: April 19, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Miltiadis Allamanis, Shengyu Fu, Xiaoyu Liu, Neelakantan Sundaresan, Alexey Svyatkovskiy
-
Patent number: 11262984Abstract: A code completion tool uses a neural transformer model to generate candidate sequences to complete a line of source code. The neural transformer model is trained using a conditional language modeling objective on a large unsupervised dataset that includes source code programs written in several different programming languages. The neural transformer model is used within a beam search that predicts the most likely candidate sequences for a code snippet under development.Type: GrantFiled: November 11, 2019Date of Patent: March 1, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Alexey Svyatkovskiy, Shengyu Fu, Neelakantan Sundaresan, Shao Kun Deng
-
Patent number: 11243750Abstract: A code completion tool uses machine learning models to more precisely predict the likelihood of a method invocation completing a code fragment that follows one or more method invocations of different classes in a same document during program development. In one aspect, the machine learning model is a n-order Markov chain model that is trained on features that represent characteristics of the context of method invocations found in commonly-used programs from a sampled population. The machine learning model is implemented as a hash table contained a ranked order of hash values in descending order of probability of completing a partially-formed method invocation.Type: GrantFiled: May 4, 2020Date of Patent: February 8, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING LLCInventors: Shengyu Fu, Xiaoyu Liu, Neelakantan Sundaresan
-
Patent number: 11194825Abstract: A distributed sequential pattern data mining framework mines user data to determine statistically-relevant sequential patterns which are used to correlate the sequential patterns to a particular outcome. The correlation is provided by a statistical model, a binary predictive model and/or a logistic regression model which uses the sequential patterns to learn the behavior of end users during their usage of a software application.Type: GrantFiled: September 23, 2018Date of Patent: December 7, 2021Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Shengyu Fu, Sai Tulasi Neppali, Neelakantan Sundaresan, Siyu Yang
-
Publication number: 20210357193Abstract: A code completion tool uses machine learning models to more precisely predict the likelihood of a method invocation completing a code fragment that follows one or more method invocations of different classes in a same document during program development. In one aspect, the machine learning model is a n-order Markov chain model that is trained on features that represent characteristics of the context of method invocations found in commonly-used programs from a sampled population. The machine learning model is implemented as a hash table contained a ranked order of hash values in descending order of probability of completing a partially-formed method invocation.Type: ApplicationFiled: May 4, 2020Publication date: November 18, 2021Inventors: SHENGYU FU, XIAOYU LIU, NEELAKANTAN SUNDARESAN