Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020117538 - CODE COMPLETION OF METHOD PARAMETERS WITH MACHINE LEARNING

Publication Number WO/2020/117538
Publication Date 11.06.2020
International Application No. PCT/US2019/063126
International Filing Date 26.11.2019
IPC
G06F 8/33 2018.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
8Arrangements for software engineering
30Creation or generation of source code
33Intelligent editors
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06F 8/33
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
8Arrangements for software engineering
30Creation or generation of source code
33Intelligent editors
G06F 8/70
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
8Arrangements for software engineering
70Software maintenance or management
G06K 9/6215
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6201Matching; Proximity measures
6215Proximity measures, i.e. similarity or distance measures
G06K 9/6228
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6228Selecting the most significant subset of features
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 5/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
Applicants
  • MICROSOFT TECHNOLOGY LICENSING, LLC [US]/[US]
Inventors
  • FU, Shengyu
  • POESCHL, David
  • SUNDARESAN, Neelakantan
  • ZHANG, Shuo
  • ZHAO, Ying
Agents
  • MINHAS, Sandip S.
  • ADJEMIAN, Monica
  • BARKER, Doug
  • CHATTERJEE, Aaron C.
  • CHEN, Wei-Chen Nicholas
  • CHOI, Daniel
  • CHURNA, Timothy
  • DINH, Phong
  • EVANS, Patrick
  • GABRYJELSKI, Henry
  • GOLDSMITH, Micah P.
  • GUPTA, Anand
  • HINOJOSA-SMITH, Brianna L.
  • HWANG, William C.
  • JARDINE, John S.
  • LEE, Sunah
  • LEMMON, Marcus
  • MARQUIS, Thomas
  • MEYERS, Jessica
  • ROPER, Brandon
  • SPELLMAN, Steven
  • SULLIVAN, Kevin
  • SWAIN, Cassandra T.
  • TABOR, Ben
  • WALKER, Matt
  • WIGHT, Stephen A.
  • WISDOM, Gregg
  • WONG, Ellen
  • WONG, Thomas S.
  • ZHANG, Hannah
  • TRAN, Kimberly
Priority Data
16/208,45503.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) CODE COMPLETION OF METHOD PARAMETERS WITH MACHINE LEARNING
(FR) COMPLÉTION DE CODE DE PARAMÈTRES DE PROCÉDÉ AVEC UN APPRENTISSAGE AUTOMATIQUE
Abstract
(EN)
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.
(FR)
Un outil de complétion de code utilise des modèles d'apprentissage automatique pour prédire de manière plus précise la probabilité des paramètres d'une invocation de procédé. Un score est calculé pour chaque variable candidate qui est utilisée pour classer la viabilité d'une variable en tant que paramètre prévu. Le score est une somme pondérée d'un facteur de portée, d'un facteur de distance d'édition et d'un facteur de proximité de déclaration. Les facteurs sont basés sur un modèle de portée, un modèle de surcharge de procédé et un fichier de poids appris hors ligne sur un ensemble d'apprentissage de programmes de code source utilisant diverses invocations de procédé.
Also published as
Latest bibliographic data on file with the International Bureau