Sökning: "Domän driven"

Visar resultat 1 - 5 av 10 uppsatser innehållade orden Domän driven.

  1. 1. Exploring Knowledge Vaults with ChatGPT : A Domain-Driven Natural Language Approach to Document-Based Answer Retrieval

    Kandidat-uppsats, Mittuniversitetet/Institutionen för data- och elektroteknik (2023-)

    Författare :Mathias Hammarström; [2023]
    Nyckelord :Human-computer-interaction; NLP; LLM; ChatGPT; Question-Answering; Information-Retrieval.; Människa-dator interaktion; NLP; LLM; ChatGPT; Question-Answering; Information-Retrieval.;

    Sammanfattning : Problemlösning är en viktig aspekt i många yrken. Inklusive fabriksmiljöer, där problem kan leda till minskad produktion eller till och med produktionsstopp. Denna studie fokuserar på en specifik domän: en massafabrik i samarbete med SCA Massa. LÄS MER

  3. 2. Study of AI Service Providers in IT Consulting, Marketing, and Law

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Aren Hovsepyan; Kevin Johansson; [2023]
    Nyckelord :Artificial Intelligence; AI; professional service firms PSFs ; AI services; IT consulting; marketing; legal services; Gioia analysis; sector-specific analysis of AI services; automation; augmentation; intermediaries; Artificiell intelligens; AI; professionella tjänsteföretag PSFs ; AI-tjänster; IT-rådgivning; marknadsföring; juridiska tjänster; Gioia analys; sektorspecifik analys av AI-tjänster; automatisering; augmentation; mellanhänder;

    Sammanfattning : This study employs a Gioia analysis to investigate the AI services offered within three distinct professional service sectors in Sweden: IT consulting, marketing, and legal services. Utilizing a list of companies from a prior KTH project and publicly accessible information, we applied a cross-sectoral Gioia analysis to systematically categorize, compare, and understand the types of AI services provided and how these offerings differ between sectors. LÄS MER

  4. 3. ElektroCHAT: A Knowledge Base-Driven Dialogue System for Electrical Engineering Students : A Proposal for Interactive Tutoring

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Fredrik Gölman; [2023]
    Nyckelord :Knowledge base; Knowledge graph; Dialogue system; Chatbot; Electrical engineering; Education; Kunskapsbas; Kunskapsgraf; Dialogsystem; Chatbot; Elektroteknik; Utbildning;

    Sammanfattning : Universities worldwide face challenges both with students dropping out of educational programmes and repetitive questions directed toward teaching staff which both consume resources and result in delays. Recent progress in natural language processing (NLP) introduces the possibility of more sophisticated dialogue systems that could help alleviate the situation. LÄS MER

  5. 4. Migrating monolithic system to domain-driven microservices : Developing a generalized migration strategy for an architecture built on microservices

    M1-uppsats, KTH/Hälsoinformatik och logistik

    Författare :Milan Languric; Leo Zaki; [2022]
    Nyckelord :Domain-Driven Design; monolithic architecture; microservices; serverless; cloud; Domän driven; monolitisk arkitektur; mikrotjänster; serverlös; moln;

    Sammanfattning : As monolithic software grows in complexity, they tend to reach a point where further improvements and maintenance become a significant burden. Therefore, Many organizations consider moving components of their systems into separate microservices. LÄS MER

  7. 5. A study of transfer learning on data-driven motion synthesis frameworks

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Nuo Chen; [2022]
    Nyckelord :Transfer learning; data-driven motion synthesis; objective-driven motion generation; rig-agnostic encoding; deep learning-based clustering model; procedural animation; Kunskapsöverföring; data-driven rörelsesyntetisering; procedurell animation; mål-driven animation-genereringsmodel; rig-agnostisk-kodning; djupinlärningsbaserad klusteringsmodel;

    Sammanfattning : Various research has shown the potential and robustness of deep learning-based approaches to synthesise novel motions of 3D characters in virtual environments, such as video games and films. The models are trained with the motion data that is bound to the respective character skeleton (rig). LÄS MER