公开(公告)号：US11126930B2

公开(公告)日：2021-09-21

申请号：US16396686

申请日：2019-04-27

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Shengyu Fu ,  Neelakantan Sundaresan ,  Jason Wang ,  Ying Zhao

IPC: G06F8/30 ,  G06N20/00

Abstract: A code completion system predicts candidates to complete a method invocation in a source code program written in a dynamically-typed programming language. A pseudo type is generated for each variable in the source code program to approximate the runtime type of the variable. The pseudo type is then used to group a set of method invocations into a classification that can be modeled by an n-order Markov chain model. The n-order Markov chain model is used to predict candidate methods more likely to complete a method invocation in a dynamically-typed programming language.

公开(公告)号：US10983761B2

公开(公告)日：2021-04-20

申请号：US16377789

申请日：2019-04-08

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Alexey Svyatkovskiy ,  Shengyu Fu ,  Neelakantan Sundaresan ,  Ying Zhao

IPC: G06F9/44 ,  G06F8/33 ,  G06N3/08 ,  G06F16/901 ,  G06F17/18 ,  G06F8/41 ,  G06N3/04

Abstract: 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.

公开(公告)号：US11645576B2

公开(公告)日：2023-05-09

申请号：US16391284

申请日：2019-04-22

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Shengyu Fu ,  Neelakantan Sundaresan ,  Ying Zhao

IPC: G06F9/44 ,  G06F9/455 ,  G06F9/445 ,  G06N20/00 ,  G06F8/30 ,  G06F8/33

CPC classification number: G06N20/00 ,  G06F8/30 ,  G06F8/33

Abstract: 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.

公开(公告)号：US10990358B2

公开(公告)日：2021-04-27

申请号：US16360008

申请日：2019-03-21

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Shengyu Fu ,  Neelakantan Sundaresan ,  Ying Zhao

IPC: G06F8/33 ,  G06N20/00 ,  G06F17/18 ,  G06F8/41 ,  G06K9/62

Abstract: A code completion tool uses machine learning models to more precisely predict the likelihood of an invocation of a particular overloaded method completing a code fragment that follows one or more method invocations of a same class 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 the method signatures of overloaded methods in order to generate ordered sequences of method signatures of overloaded method invocations.

公开(公告)号：US11379190B2

公开(公告)日：2022-07-05

申请号：US17233527

申请日：2021-04-18

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Alexey Svyatkovskiy ,  Shengyu Fu ,  Neelakantan Sundaresan ,  Ying Zhao

IPC: G06F9/44 ,  G06F8/33 ,  G06N3/08 ,  G06F16/901 ,  G06F17/18 ,  G06F8/41 ,  G06N3/04

Abstract: 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.

公开(公告)号：US11586839B2

公开(公告)日：2023-02-21

申请号：US16208455

申请日：2018-12-03

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Shengyu Fu ,  David Poeschl ,  Neelakantan Sundaresan ,  Shuo Zhang ,  Ying Zhao

IPC: G06F9/44 ,  G06K9/62 ,  G06N20/00 ,  G06F8/70 ,  G06F8/33

Abstract: 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.

公开(公告)号：US10671355B2

公开(公告)日：2020-06-02

申请号：US15939742

申请日：2018-03-29

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： Jorge Banuelos ,  Shengyu Fu ,  Roshanak Zilouchian Moghaddam ,  Neelakantan Sundaresan ,  Siyu Yang ,  Ying Zhao

IPC: G06F9/44 ,  G06F8/33 ,  G06N7/00 ,  G06N20/00 ,  G06F8/35 ,  G06F8/36 ,  G06N5/02

Abstract: 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 a same class 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 of a class in commonly-used programs from a sampled population.