KR20200066418A - Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation - Google Patents

Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation Download PDF

Info

Publication number
KR20200066418A
KR20200066418A KR1020180152042A KR20180152042A KR20200066418A KR 20200066418 A KR20200066418 A KR 20200066418A KR 1020180152042 A KR1020180152042 A KR 1020180152042A KR 20180152042 A KR20180152042 A KR 20180152042A KR 20200066418 A KR20200066418 A KR 20200066418A
Authority
KR
South Korea
Prior art keywords
platform
llvm
deep learning
user
code
Prior art date
Application number
KR1020180152042A
Other languages
Korean (ko)
Inventor
주해종
박민규
Original Assignee
동국대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 동국대학교 산학협력단 filed Critical 동국대학교 산학협력단
Priority to KR1020180152042A priority Critical patent/KR20200066418A/en
Publication of KR20200066418A publication Critical patent/KR20200066418A/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/451Execution arrangements for user interfaces
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/20Education

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Educational Administration (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Educational Technology (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Human Computer Interaction (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention relates to a deep-learning application technology of a virtual reality/augmented reality (VR/AR) education platform using low level virtual machine-intermediate representation (LLVM-IR). An implementation system of the VR/AR education platform comprises: a connection means which can be connected with a deep-learning platform; a platform generating an asm.js code which can be used by a user through LLVM-IR connection to use the connected code for AR/VR content production; and a user interface analyzing a pattern drawn by the user to automatically extract and express the pattern.

Description

LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용에 대한 방법 및 시스템{Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation}Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation}

본 발명은 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥 러닝 적용 시스템에 관한 것으로, VR/AR 환경에서 다양한 교육환경을 학습함으로써 효율적인 교육용 콘텐츠 제작에 필요한 플랫폼 제공을 위해 VR/AR 개발환경에서 LLVM IR(Low Level Virtual Machine Intermediate Representation) 기반으로 프레임워크 연결(Bridge) 모델 및 딥 러닝 개발자들이 최적의 프레임워크의 조합을 선택할 수 있는 플랫폼에 관한 것이다.The present invention relates to a deep learning application system of a VR/AR educational platform using an LLVM intermediate language, and by learning various educational environments in a VR/AR environment, LLVM in a VR/AR development environment to provide a platform necessary for efficient educational content production. It is based on a low level virtual machine intermediate representation (IR) framework and a platform that allows deep learning developers to choose the optimal combination of frameworks.

가상현실(Virtual Reality, VR)은 컴퓨터 등을 사용한 인공지능 기술로 만들어낸 실제와 유사하지만 실제가 아닌 어떤 특정한 환경이나 상황 혹은 그 기술 자체를 의미한다. VR은 청각, 촉각 및 시각과 같은 인간의 감각을 소프트웨어 및 하드웨어와 결합하여 몰입형 가상현실을 만드는 것을 목표로 한다. 최근에는 인공지능 기술의 비약적인 발전으로 VR/AR 환경에도 인공지능 특히 딥러닝 기술들이 활용되고 있으며 그 조합은 다양한 교육 환경을 제공하고 있다. 몰입형 교육에 있어서 조력자의 도움이 없이 교육의 질을 높일 수 있고 실무적인 특정 업무에 대한 반복적인 결과(성공/실패)를 학습함으로써 자원 효율 측면과 시간 단축 측면에서 향후 발전할 분야라 할 수 있다.Virtual Reality (VR) refers to a certain environment or situation, or the technology itself, which is similar to reality created by artificial intelligence technology using a computer, but not real. VR aims to create an immersive virtual reality by combining human senses such as hearing, touch, and vision with software and hardware. Recently, with the rapid development of artificial intelligence technology, artificial intelligence, especially deep learning technologies, are used in VR/AR environments, and the combination provides various educational environments. In immersive education, the quality of education can be improved without the help of an assistant, and by learning repetitive results (success/failure) for specific practical tasks, it can be said to be a future development area in terms of resource efficiency and time reduction. .

VR/AR 환경에서 딥러닝 기술이 활용되는 분야는, 첫째, 손 추적 및 제스처 인식(Hand-Tracking Gestures), 둘째, 자연언어처리(Natural Language Processing), 셋째, 비디오 게임에서 강화학습(Reinforcement Learning in Video Games) 등이 있다. The areas where deep learning technology is used in VR/AR environments are: first, hand-tracking gestures, second, natural language processing, and third, reinforcement learning in video games. Video Games).

이러한 결합을 효율적으로 적용하기 위해서는 많은 문제점을 가지고 있으며, 이를 해결하기 위해 컴파일러 기술을 통해 해결하기 위해 많은 연구를 하고 있다.To apply this combination efficiently, there are many problems, and many studies are being conducted to solve it through compiler technology.

"증강현실 기술을 활용한 융합형 교육 콘텐츠 설계 및 구현", 정효남, 상명대학교, 2013년"Design and Implementation of Convergence Education Contents Using Augmented Reality Technology", Hyo-Nam Jeong, Sangmyung University, 2013

종래에는 VR/AR 교육용 콘텐츠를 제작하기 위해서는 Unity 및 Unreal과 같은 개발 플랫폼을 이용하여 제작하였으나, 딥러닝을 적용하기 위한 구조를 지원하는데는 어려움이 있으며, 특히 VR/AR과 결합한 인공지능 개발환경을 제작하는 수단은 상호 독립적으로 동작하게 되어 있다는 문제점이 존재하였다. 또한, 딥 러닝 기술을 이용하여 VR/AR 콘텐츠를 제작할 수 있도록 별도의 연구들이 진행하고 있으나 많은 어려움을 가지고 있다.In the past, in order to produce VR/AR educational contents, it was produced using development platforms such as Unity and Unreal, but it is difficult to support the structure for applying deep learning, and in particular, the AI development environment combined with VR/AR There was a problem in that the means of manufacturing were to operate independently of each other. In addition, separate studies are being conducted to produce VR/AR content using deep learning technology, but they have many difficulties.

본 발명이 해결하고자 하는 기술적 과제는, LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 제공하여 VR/AR 콘텐츠 제작에 딥 러닝을 적용하여 사용자가 제작하는 형태에 따라 Object 및 Asset 등을 자동으로 제시할 수 있는 플랫폼을 제공하는 것을 목적으로 한다.The technical problem to be solved by the present invention is to provide a deep learning application platform of VR/AR education platform using LLVM intermediate language, apply deep learning to VR/AR content production, and create objects and assets according to the type of user's production. It is an object of the present invention to provide a platform that can be automatically presented.

본 발명은 Unreal과 Unity로 대표되는 플랫폼에 대한 관련기술과 딥러닝 기술에 플랫폼 통합 기술에 대한 정리와 VR/AR 개발환경에서 LLVM IR기반으로 프레임워크 연결(Bridge) 모델 및 딥 러닝 개발자들이 최적의 프레임워크의 조합을 선택할 수 있는 플랫폼을 제공하고자 한다.According to the present invention, the platform integration technology and deep learning technology for platforms represented by Unreal and Unity are summarized, and the framework model (Bridge) and deep learning developers are optimized based on LLVM IR in VR/AR development environment. We want to provide a platform to choose a combination of frameworks.

상기 기술적 과제를 해결하기 위하여, 본 발명의 일 실시예에 따른 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 구현하는 시스템은, LLVM 기술을 이용하여 IR간의 연결방법을 제공하기 위해 LLVM IR로 변환하는 변환 부, 코드의 최적화를 위한 최적화 부, 프로그램 변환 및 정적 분석을 제공하는 프로그램 변환부를 포함하는 플랫폼을 포함한다.In order to solve the above technical problem, a system for implementing a deep learning application platform of a VR/AR education platform using an LLVM intermediate language according to an embodiment of the present invention, to provide a connection method between IRs using LLVM technology It includes a platform including a conversion unit to convert to LLVM IR, an optimization unit to optimize code, and a program conversion unit to provide program conversion and static analysis.

또한, 일 실시예에 따른 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 구현하는 시스템에서, VR 제작 및 편집부는 웹 인터페이스를 통해 객체행위 편집 및 3D Scene 등 저작 및 편집을 할 수 있는 화면을 더 포함할 수 있다.In addition, in a system implementing a deep learning application platform of a VR/AR educational platform using an LLVM intermediate language according to an embodiment, the VR production and editing department can edit and edit object behaviors and 3D scenes through a web interface. It may further include a screen.

또한, 일 실시예에 따른 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 구현하는 시스템에서, 딥러닝 개발환경과 같은 다양한 프런트엔드 프레임워크와 연결하기 위한 NNVM 컴파일러 연결부를 더 포함할 수 있다.In addition, in a system implementing a deep learning application platform of a VR/AR educational platform using an LLVM intermediate language according to an embodiment, the NNVM compiler connection for connecting with various front-end frameworks such as a deep learning development environment may be further included. You can.

본 발명의 실시예들은, LLVM IR 기법을 이용한 WebAssembly 코드 생성 기술과 딥러닝 통합 분야의 새로운 컴파일러인 NNVM 컴파일러를 통해 효과적으로 사용자가 콘텐트를 제작하는 형태를 빠르게 판단하여 작성할 수 있도록 한다.Embodiments of the present invention, through the NNVM compiler, a new compiler in the field of deep learning integration and WebAssembly code generation technology using the LLVM IR technique, allows the user to quickly determine and create a form of content creation.

도 1은 본 발명의 실시예에 따른 따라 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 나타낸 블록 구성도이다.
도 2는 도 1에 도시된 NNVM-TVM(200)과 LLVM-IR(100)의 내부 구성 요소에 대한 예를 나타내는 블록도이다.
도 3은 딥러닝을 이용하여 그리는 과정에서 자동 에셋 인식 후 선택하는 과정을 나타내는 사용자 인터페이스의 예이다.
1 is a block diagram illustrating a deep learning application platform of a VR/AR education platform using an LLVM intermediate language according to an embodiment of the present invention.
FIG. 2 is a block diagram showing an example of internal components of the NNVM-TVM 200 and the LLVM-IR 100 shown in FIG. 1.
3 is an example of a user interface showing a process of selecting after automatic asset recognition in a drawing process using deep learning.

이하에는 첨부한 도면을 참조하여 본 발명의 실시예들에 따라 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼에 대해서 상세하게 설명한다.Hereinafter, a deep learning application platform of a VR/AR education platform using an LLVM intermediate language according to embodiments of the present invention will be described in detail with reference to the accompanying drawings.

도 1은 본 발명의 실시예에 따른 따라 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 나타낸 블록 구성도이다.1 is a block diagram illustrating a deep learning application platform of a VR/AR education platform using an LLVM intermediate language according to an embodiment of the present invention.

도 1에 도시된 바와 같이, 본 발명의 실시예에 따른 원시 소스코드(300), 딥러닝 적용을 위한 플랫폼(400), 상위 데이터를 최적화하기 위한 NNVM-TVM모듈(200), 원시 소스 코드와 딥러닝 데이터를 최적화하여 컴파일을 제공하기 위한 LLVM-IR(100) 컴파일러, 컴파일된 데이터를 JavaScript로 제공하기 위한 asm.js 모듈(500)을 포함한다.As shown in FIG. 1, the source code 300 according to an embodiment of the present invention, the platform 400 for deep learning application, the NNVM-TVM module 200 for optimizing upper data, the source code and LLVM-IR (100) compiler for optimizing deep learning data and providing compilation, and asm.js module (500) for providing compiled data in JavaScript.

도 2는 도1에 도시된 NNVM-TVM(200)과 LLVM-IR(100)의 내부 구성 요소에 대한 예를 나타내는 블록도이다.FIG. 2 is a block diagram showing an example of internal components of the NNVM-TVM 200 and the LLVM-IR 100 shown in FIG. 1.

보다 구체적으로, 다양한 딥러닝 적용을 위한 플랫폼(400) 연동을 통해 상위수준 최적화 분석을 위한 최적화 딥러닝 컴파일 플랫폼인 NNVM(210)으로 최적화된 컴파일 과정을 수행하고, TVM(220)을 통해 연산 및 병렬처리를 할 수 있도록 제공한다.More specifically, through the platform 400 for various deep learning applications, the optimized deep learning compilation platform NNVM 210, which is optimized for high-level optimization analysis, performs an optimized compilation process, and computes and calculates it through TVM 220. Provided for parallel processing.

또한, TVM Primitive(230)을 통해 코드에 대한 최적화를 절차를 포함하고 있다.In addition, the process of optimizing the code through the TVM Primitive 230 is included.

최적화된 코드는 LLVM-IR 과정을 통해 원 소스코드를 연계하기 위한 Frontend(110)을 통해 LLVM-IR로 변환하고, Optimizer(130)을 통해 코드를 최적화한다. 또한 Backend(150)을 통해 AR/VR 콘텐츠 제작을 위해 asm.js(500) 코드로 컴파일 하여 제공한다.The optimized code is converted to LLVM-IR through the Frontend 110 for linking the original source code through the LLVM-IR process, and the code is optimized through the Optimizer 130. Also, it compiles and provides asm.js(500) code to produce AR/VR contents through Backend(150).

도 3은 딥러닝을 이용하여 그리는 과정에서 자동 에셋 인식후 선택하는 과정을 나타내는 사용자 인터페이스의 예이다.3 is an example of a user interface showing a process of selecting after automatic asset recognition in a drawing process using deep learning.

이상에서와 같이 본 발명에 따른 LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼은 상기한 바와 같이 설명된 실시예들의 구성과 방법이 한정되게 적용될 수 있는 것이 아니라, 상기 실시예들은 다양한 변형이 이루어질 수 있도록 각 실시예들의 전부 또는 일부가 선택적으로 조합되어 구성될 수도 있다. As described above, the deep learning application platform of the VR/AR educational platform using the LLVM intermediate language according to the present invention is not limited to the configuration and method of the embodiments described as described above, and the embodiments are various All or part of each of the embodiments may be selectively combined to constitute a modification.

한편, 본 발명의 실시예들은 컴퓨터로 읽을 수 있는 기록 매체에 컴퓨터가 읽을 수 있는 코드로 구현하는 것이 가능하다. 컴퓨터가 읽을 수 있는 기록 매체는 컴퓨터 시스템에 의하여 읽혀질 수 있는 데이터가 저장되는 모든 종류의 기록 장치를 포함한다.On the other hand, embodiments of the present invention can be implemented in computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data readable by a computer system are stored.

컴퓨터가 읽을 수 있는 기록 매체의 예로는 ROM, RAM, CD-ROM, 자기 테이프, 플로피디스크, 광 데이터 저장장치 등을 포함한다. 또한, 컴퓨터가 읽을 수 있는 기록 매체는 네트워크로 연결된 컴퓨터 시스템에 분산되어, 분산 방식으로 컴퓨터가 읽을 수 있는 코드가 저장되고 실행될 수 있다. 그리고 본 발명을 구현하기 위한 기능적인(functional) 프로그램, 코드 및 코드 세그먼트들은 본 발명이 속하는 기술 분야의 프로그래머들에 의하여 용이하게 추론될 수 있다.Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, optical data storage devices, and the like. In addition, the computer-readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers in the technical field to which the present invention pertains.

이상에서 본 발명에 대하여 그 다양한 실시예들을 중심으로 살펴보았다. 본 발명에 속하는 기술 분야에서 통상의 지식을 가진 자는 본 발명이 본 발명의 본질적인 특성에서 벗어나지 않는 범위에서 변형된 형태로 구현될 수 있음을 이해할 수 있을 것이다. 그러므로 개시된 실시예들은 한정적인 관점이 아니라 설명적인 관점에서 고려되어야 한다. 본 발명의 범위는 전술한 설명이 아니라 특허청구범위에 나타나 있으며, 그와 동등한 범위 내에 있는 모든 차이점은 본 발명에 포함된 것으로 해석되어야 할 것이다.In the above, the present invention has been mainly focused on the various embodiments. Those skilled in the art to which the present invention pertains will appreciate that the present invention may be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered in terms of explanation, not limitation. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the equivalent range should be interpreted as being included in the present invention.

100: LLVM-IR 저레벨 언어 변환 모델
200: NNVM-TVM 딥러닝 플랫폼 연계 모델
300: 원시 소스 코드
400: 딥러닝 플랫폼
100: LLVM-IR low-level language conversion model
200: NNVM-TVM deep learning platform linkage model
300: raw source code
400: deep learning platform

Claims (4)

LLVM 중간언어를 이용한 VR/AR 교육 플랫폼의 딥러닝 적용 플랫폼을 구현하는 시스템에 있어서,
딥러닝 플랫폼과 연계할 수 있는 연계 수단;
연계된 코드를 AR/VR 콘텐츠 제작에 사용하기 위한 LLVM-IR 연계를 통해 사용자가 사용할 수 있는 asm.js 코드를 생성하는 플랫폼; 및
사용자가 그리는 패턴을 분석하여 자동으로 추출하여 표현해 주는 사용자 인터페이스;를 포함하는, VR/AR 교육 플랫폼의 구현 시스템.
In the system that implements the deep learning application platform of VR/AR education platform using LLVM intermediate language,
A linking means capable of linking with a deep learning platform;
A platform for generating asm.js code that can be used by a user through LLVM-IR linkage for using the linked code for AR/VR content production; And
A user interface that automatically extracts and expresses the patterns drawn by the user; and includes, a VR/AR educational platform implementation system.
제 1 항에 있어서,
다양한 딥러닝 플랫폼과 연계한 후, 저 레벨 언어(LLVM)에서 인식할 수 있도록 제공하는 연계 수단에 관한 NNVM 컴파일 환경;을 더 포함하는, VR/AR 교육 플랫폼의 구현 시스템.
According to claim 1,
After linking with various deep learning platforms, the NNVM compilation environment for linkage means provided to be recognized by a low level language (LLVM); further comprising a VR/AR educational platform implementation system.
제 1 항에 있어서,
딥러닝 플랫폼에서 연계된 최적화 코드를 사용자가 사용할 수 있도록 컴파일 하는 LLVM-IR 연계 수단에 관한 코드변환 플랫폼;을 더 포함하는, VR/AR 교육 플랫폼의 구현 시스템.
According to claim 1,
A system for implementing a VR/AR educational platform further comprising: a code conversion platform for LLVM-IR linking means that compiles optimized code linked in a deep learning platform for use by a user.
제 1 항에 있어서,
산출된 출력 코드를 이용하여 사용자가 그리는 과정에서 자동으로 에셋을 인식한 후, 사용자 화면에 표출해 주는 수단;을 더 포함하는 VR/AR 교육 플랫폼의 구현 시스템.
According to claim 1,
A system for realizing a VR/AR educational platform further comprising: means for automatically recognizing an asset in the process of drawing by the user using the calculated output code and then displaying it on the user screen.
KR1020180152042A 2018-11-30 2018-11-30 Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation KR20200066418A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020180152042A KR20200066418A (en) 2018-11-30 2018-11-30 Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020180152042A KR20200066418A (en) 2018-11-30 2018-11-30 Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation

Publications (1)

Publication Number Publication Date
KR20200066418A true KR20200066418A (en) 2020-06-10

Family

ID=71087268

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020180152042A KR20200066418A (en) 2018-11-30 2018-11-30 Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation

Country Status (1)

Country Link
KR (1) KR20200066418A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113254002A (en) * 2021-07-08 2021-08-13 企查查科技有限公司 Component, medium and equipment for improving webpage performance and supporting cross-platform calling

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"증강현실 기술을 활용한 융합형 교육 콘텐츠 설계 및 구현", 정효남, 상명대학교, 2013년

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113254002A (en) * 2021-07-08 2021-08-13 企查查科技有限公司 Component, medium and equipment for improving webpage performance and supporting cross-platform calling

Similar Documents

Publication Publication Date Title
KR101940720B1 (en) Contents authoring tool for augmented reality based on space and thereof method
EP2087424A2 (en) A system and method for automated re-architectureing of legacy systems using object-oriented language
CN102262534A (en) System and method for developing computer online games based on Internet browser/server (B/S) structure
CN104777911A (en) Intelligent interaction method based on holographic technique
Coronado et al. Towards a modular and distributed end-user development framework for human-robot interaction
CN117032453A (en) Virtual reality interaction system for realizing mutual recognition function
US7480642B2 (en) Automatic knowledge creating system
CN102789450A (en) Definable semantic analysis system and method on basis of rules
US20230162736A1 (en) Training, education and/or advertising system for complex machinery in mixed reality using metaverse platform
KR20200066418A (en) Method and system for deep-learning application of virtual reality/augmented reality education platform using low level virtual machine intermediate representation
CN116188618B (en) Image generation method and device based on structured semantic graph
Saleme et al. MulseOnto: a Reference Ontology to Support the Design of Mulsemedia Systems.
Wang et al. Research on consistency maintenance of the real-time image editing system based on bitmap
Son et al. MOF based code generation method for android platform
CN115081488A (en) Scene control method based on holographic projection technology
KR20240013613A (en) Method for generating AI human 3D motion only with video and its recording medium
KR20240013610A (en) Method and device for providing image-based ai human and motion generation sevice
Mokhov et al. Agile forward-reverse requirements elicitation as a creative design process: A case study of Illimitable Space System v2
KR101965732B1 (en) the method for controling motion platform using the authoring tool
Cantrell et al. Coding landscape
Chang et al. Usability framework for the design and evaluation of multimodal interaction
CN117437366B (en) Method for constructing multi-mode large-scale scene data set
CN117649461B (en) Interactive image generation method and system based on space layout and use method thereof
Wang et al. Research on 3D Animation Technology of Human and Scene Based on Virtual Reality
Franco et al. Paper and Pencil Interactive Storytelling Based on Generic Hand-drawn Sketches