Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Generativ AI i företagsmiljöer: En jämförelsestudie av olika informationshämtningsmetoder
Dalarna University, School of Information and Engineering.
Dalarna University, School of Information and Engineering.
2024 (Swedish)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Generative AI in Enterprise Environments : A Comparative Study of Various Information Retrieval Methods (English)
Abstract [sv]

Teknologiska innovationer, särskilt inom AI, har förändrat hur företag driver innovation de senaste åren. Denna studie undersöker effektiviteten och tillförlitligheten hos den generativa AI-chattboten Petra, som har tillgång till all information på ett företags intranät. Problemet som studien adresserar är att enligt litteraturgenomgången, har användning av generativa AI-system för informationshämtning från ett företags interna information ännu inte omfattande undersökts. Med hjälp av deltagarna i studiens experiment undersöktes effektiviteten samt tidsåtgången mellan användandet av den traditionella informationshämtningsmetoden då information hämtas från ett intranät med informationshämtning med Petra. Deltagarna som använde Petra visade sig vara i genomsnitt 109% snabbare än de som använde intranätet. Tillförlitligheten undersöktes genom en fallstudie där loggar genererade från tidigare användning av Petra analyserades, här visade boten upp en noggrannhetsgrad på 82% i att leverera korrekta svar. Denna studie bidrar med insikter om potentialen hos generativ AI inom informationshämtning i företagsmiljöer, vilket kan leda till betydande tidsbesparingar och ökad effektivitet. 

Abstract [en]

Technological innovations, especially in AI, have transformed how companies drive innovation in recent years. This study investigates the efficiency and reliability of the generative AI-chatbot Petra, which has access to all information on a company´s intranet. The problem addressed by the study is that, according to the literature review, the use of generative AI systems for information retrieval from a company's internal information has not yet been extensively studied. With the help of participants in the study's experiment, the efficiency and time taken between using the traditional information retrieval method when retrieving information from an intranet and using Petra were examined. The participants who used Petra turned out to be on average 52% faster than those who used the intranet. Reliability was examined through a case study where logs generated from previous use of Petra were analyzed, the bot did reveal an accuracy rate of 82% in delivering correct answers. This study provides insights into the potential of generative AI in information retrieval in corporate environments, which can lead to significant time savings and increased efficiency. 

Place, publisher, year, edition, pages
2024.
Keywords [sv]
AI-chattbot, Generativ AI, Informationshämtning, Innovation, Noggrannhetsgrad, Prestanda, Tidsbesparing
National Category
Information Systems
Identifiers
URN: urn:nbn:se:du-49038OAI: oai:DiVA.org:du-49038DiVA, id: diva2:1883354
Subject / course
Microdata Analysis
Available from: 2024-07-10 Created: 2024-07-10

Open Access in DiVA

fulltext(1517 kB)782 downloads
File information
File name FULLTEXT01.pdfFile size 1517 kBChecksum SHA-512
819a4bec13d8c90a78a07129d9bcbaa529c93a5d592ff0b0d5cc9e3ac75344b79aad1271f5bf74c8cf0e946b5aacf917c0442d6c010ed81d4e25bbe47cf62d3c
Type fulltextMimetype application/pdf

By organisation
School of Information and Engineering
Information Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 783 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1108 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf