• Title/Summary/Keyword: 인공지능프레임워크

Search Result 119, Processing Time 0.025 seconds

Attentive Knowledge Selection Model for Knowledge-Grounded Multi-turn Dialogue System (지식 기반 다중 대화 시스템을 위한 주의 집중 지식 선택 모델)

  • Lee, Dohaeng;Jang, Youngjin;Huang, Jin-Xia;Kwon, Oh-Woog;Kim, Harksoo
    • Annual Conference on Human and Language Technology
    • /
    • 2021.10a
    • /
    • pp.361-364
    • /
    • 2021
  • 지식 기반 다중 대화 시스템은 지식 정보를 포함한 응답을 생성하는 대화 시스템이다. 이 시스템은 응답 생성에 필요한 지식 정보를 찾아내는 지식 선택 작업과 찾아낸 지식 정보를 바탕으로 문맥을 고려한 응답을 생성하는 응답 생성 작업으로 구성된다. 본 논문에서는 지식 선택 작업을 기계독해 프레임워크에 적용하여 해결하는 방법을 제안한다. 지식 선택 작업은 여러 개의 발화로 이루어진 대화 기록을 바탕으로 지식 문서 내에 존재하는 지식을 찾아내는 작업이다. 본 논문에서는 대화 기록 모델링 계층을 활용해 마지막 발화와 관련 있는 대화 기록을 찾아내고, 주의 집중 풀링 계층을 활용해 긴 길이의 지식을 효과적으로 추출하는 방법을 제안한다. 실험 결과, 목적지향 지식 문서 기반 대화 데이터 셋인 Doc2dial 데이터의 지식 선택 작업에서 F1 점수 기준 76.52%, EM 점수 기준 66.21%의 성능을 기록해 비교 모델 보다 높은 성능을 기록하는 것을 확인할 수 있었다.

  • PDF

KBO Win/Lose Predict Using Innings Data in AI Environments (인공지능 환경에서 이닝별 데이터를 이용한 KBO 승패 예측)

  • Kim, Tae-Hun;Lim, Seong-Won;Koh, Jin-Gwang
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2020.11a
    • /
    • pp.1028-1030
    • /
    • 2020
  • 과거 몇 년간의 데이터를 기반으로 현재 KBO 승패를 예측하고자 하는 것으로, 경기 초반 페이스가 얼마나 승패에 영향을 미치는지 파악하고자 한다. 경기의 이닝별 데이터로 딥러닝·머신러닝을 이용해 승리 팀을 예측하여 리그 순위를 예측하고, Flask 웹 프레임워크를 통해 입력값을 받아 예측해 주는 웹사이트를 구축하였다.

A Study on the Suitability of Scripting Language in Metaverse Development (메타버스 개발과 스크립팅 언어 적합성에 관한 연구)

  • Hwa-Seon Choi
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2023.01a
    • /
    • pp.299-300
    • /
    • 2023
  • 최근 인공지능의 현실화와 더불어 프로그래밍 언어인 Python의 독주가 한창이다. 그렇다면 과연 메타버스 시대가 현실화 된다면 어떤 프로그래밍 언어가 대세가 될 것인가. 현재 메타버스 플랫폼인 로블록스에서 사용되고 있는 루아스크립트, 제페토 월드에서 사용되고 있는 Typescript에서 착안해서 미래의 메타버스 개발에 공용으로 사용될 효율적인 언어를 살펴보았다.

  • PDF

The Improvement Plan for Personal Information Protection for Artificial Intelligence(AI) Service in South Korea (우리나라의 인공지능(AI)서비스를 위한 개인정보보호 개선방안)

  • Shin, Young-Jin
    • Journal of Convergence for Information Technology
    • /
    • v.11 no.3
    • /
    • pp.20-33
    • /
    • 2021
  • This study is to suggest improvements of personal information protection in South Korea, according to requiring the safety of process and protection of personal information. Accordingly, based on data collection and analysis through literature research, this study derived the issues and suitable standards of personal information for major artificial intelligence services. In addition, this cases studies were reviewed, focusing on the legal compliance and porcessing compliance for personal information proection in major countries. And it suggested the improvement plan applied in South Korea. As the results, in legal compliance, it is required reorganization of related laws, responsibility and compliance to develop and provide AI, and operation of risk management for personal information protection laws in AI services. In terms of processing compliance, first, in pre-processing and refining, it is necessary to standardize data set reference models, control data set quality, and voluntarily label AI applications. Second, in development and utilization of algorithm, it is need to establish and apply a clear regulation of the algorithm. As such, South Korea should apply suitable improvement tasks for personal information protection of safe AI service.

Multi-source information integration framework using self-supervised learning-based language model (자기 지도 학습 기반의 언어 모델을 활용한 다출처 정보 통합 프레임워크)

  • Kim, Hanmin;Lee, Jeongbin;Park, Gyudong;Sohn, Mye
    • Journal of Internet Computing and Services
    • /
    • v.22 no.6
    • /
    • pp.141-150
    • /
    • 2021
  • Based on Artificial Intelligence technology, AI-enabled warfare is expected to become the main issue in the future warfare. Natural language processing technology is a core technology of AI technology, and it can significantly contribute to reducing the information burden of underrstanidng reports, information objects and intelligences written in natural language by commanders and staff. In this paper, we propose a Language model-based Multi-source Information Integration (LAMII) framework to reduce the information overload of commanders and support rapid decision-making. The proposed LAMII framework consists of the key steps of representation learning based on language models in self-supervsied way and document integration using autoencoders. In the first step, representation learning that can identify the similar relationship between two heterogeneous sentences is performed using the self-supervised learning technique. In the second step, using the learned model, documents that implies similar contents or topics from multiple sources are found and integrated. At this time, the autoencoder is used to measure the information redundancy of the sentences in order to remove the duplicate sentences. In order to prove the superiority of this paper, we conducted comparison experiments using the language models and the benchmark sets used to evaluate their performance. As a result of the experiment, it was demonstrated that the proposed LAMII framework can effectively predict the similar relationship between heterogeneous sentence compared to other language models.

Network Security Modeling and Simulation Using the SES/MB Framework (SES/MB 프레임워크를 이용한 네트워크 보안 모델링 및 시뮬레이션)

  • 지승도;박종서;이장세;김환국;정기찬;정정례
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.11 no.2
    • /
    • pp.13-26
    • /
    • 2001
  • This paper presents the network security modeling methodology and simulation using the hierarchical and modular modeling and simulation framework. Recently, Howard and Amoroso developed the cause-effect model of the cyber attack, defense, and consequences, Cohen has been proposed the simplified network security simulation methodology using the cause-effect model, however, it is not clear that it can support more complex network security model and also the model-based cyber attack simulation. To deal with this problem, we have adopted the hierarchical and modular modeling and simulation environment so called the System Entity Structure/Model Base (SES/MB) framework which integrates the dynamic-based formalism of simulation with the symbolic formalism of AI. Several simulation tests performed on sample network system verify the soundness of our method.

A Development of Intelligent Simulation Tools based on Multi-agent (멀티 에이전트 기반의 지능형 시뮬레이션 도구의 개발)

  • Woo, Chong-Woo;Kim, Dae-Ryung
    • Journal of the Korea Society of Computer and Information
    • /
    • v.12 no.6
    • /
    • pp.21-30
    • /
    • 2007
  • Simulation means modeling structures or behaviors of the various objects, and experimenting them on the computer system. And the major approaches are DEVS(Discrete Event Systems Specification). Petri-net or Automata and so on. But, the simulation problems are getting more complex or complicated these days, so that an intelligent agent-based is being studied. In this paper, we are describing an intelligent agent-based simulation tool, which can supports the simulation experiment more efficiently. The significances of our system can be described as follows. First, the system can provide some AI algorithms through the system libraries. Second, the system supports simple method of designing the simulation model, since it's been built under the Finite State Machine (FSM) structure. And finally, the system acts as a simulation framework by supporting user not only the simulation engine, but also user-friendly tools, such as modeler scriptor and simulator. The system mainly consists of main simulation engine, utility tools, and some other assist tools, and it is tested and showed some efficient results in the three different problems.

  • PDF

Framework for Image Understanding System using Ontology (온톨로지를 이용한 영상이해 시스템의 설계)

  • Lee, In-Geun;Seo, Seok-Tae;Jeong, Hye-Cheon;Son, Se-Ho;Gwon, Sun-Hak
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2006.11a
    • /
    • pp.33-38
    • /
    • 2006
  • 인공지능 분야에서는 합의된 개념을 정의하고, 개념과 개념사이의 관계를 표현하여 인간과 시스템이 지식을 공유하는 것으로 온톨로지를 정의하고 있다. 현재까지 영상이해를 위해 온톨로지를 설계하고 이용하는 연구가 진행되어 왔다. 그러나 기존의 영상이해에 관한 연구는 개념적인 연구에 그칠 뿐 구체적인 방법을 제시하지는 못하고 있다. 본 논문에서는 온톨로지로 표현한 지식에 근거하여 영상의 처리, 분석 해석 과정을 통해 영상을 이해하는 영상이해 시스템의 프레임워크를 제안한다. 영상이해 과정은 i)특정 부야의 지식을 온톨로지로 표현하고, ii)영상 처리 및 분석 과정을 통해 영상을 구성하는 객체들의 속성을 추출하며, iii)온톨로지 추론을 통해 객체의 속성으로부터 객체를 정의하여 영상을 해석한다. 그리고 제안한 프로세스에 기반 하여 영상이해 시스템을 구축하고 특정 분야에서의 실험을 통하여 제안된 시스템의 효용성을 확인한다.

  • PDF

Trend of Paradigm for integrating Blockchain, Artificial Intelligence, Quantum Computing, and Internet of Things

  • Rini Wisnu Wardhani;Dedy Septono Catur Putranto;Thi-Thu-Huong Le;Yustus Eko Oktian;Uk Jo;Aji Teguh Prihatno;Naufal Suryanto;Howon Kim
    • Smart Media Journal
    • /
    • v.12 no.2
    • /
    • pp.42-55
    • /
    • 2023
  • The combination of blockchain (BC), artificial Intelligence (AI), quantum computing (QC), and the Internet of Things (IoT) can potentially transform various industries and domains, including healthcare, logistics, and finance. In this paper, we look at the trends and developments in integrating these emerging technologies and the potential benefits and challenges that come with them. We present a conceptual framework for integrating BC, AI, QC, and IoT and discuss the framework's key characteristics and challenges. We also look at the most recent cutting-edge research and developments in integrating these technologies, as well as the key challenges and opportunities that come with them. Our analysis highlights the potential benefits of integrating the technologies and looks to increased security, privacy, and efficiency to provide insights into the future of these technologies.

Framework Design for Malware Dataset Extraction Using Code Patches in a Hybrid Analysis Environment (코드패치 및 하이브리드 분석 환경을 활용한 악성코드 데이터셋 추출 프레임워크 설계)

  • Ki-Sang Choi;Sang-Hoon Choi;Ki-Woong Park
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.34 no.3
    • /
    • pp.403-416
    • /
    • 2024
  • Malware is being commercialized and sold on the black market, primarily driven by financial incentives. With the increasing demand driven by these sales, the scope of attacks via malware has expanded. In response, there has been a surge in research efforts leveraging artificial intelligence for detection and classification. However, adversaries are integrating various anti-analysis techniques into their malware to thwart analytical efforts. In this study, we introduce the "Malware Analysis with Dynamic Extraction (MADE)" framework, a hybrid binary analysis tool devised to procure datasets from advanced malware incorporating Anti-Analysis techniques. The MADE framework has the proficiency to autonomously execute dynamic analysis on binaries, encompassing those laden with Anti-VM and Anti-Debugging defenses. Experimental results substantiate that the MADE framework can effectively circumvent over 90% of diverse malware implementations using Anti-Analysis techniques and can adeptly extract relevant datasets.