Iskanje po katalogu digitalne knjižnice

Opis: Knowledge Graphs (KGs) describe objective facts in the form of RDF triples, each triple contains sufficient semantic information and triple structure information. Knowledge Graph Completion (KGC) is to acquire new knowledge by predicting hidden relationships between entities and adding the new knowledge to the KG. At present, the mainstream KGC approaches only applied the triple structure information or only utilized the semantic information of the text. This paper proposes an approach (TSTR) using BERT and deep neural networks to fully extract the semantic information of knowledge, and designs an aggregated re-ranking scheme that incorporates existing graph embedding approach to learn the structural information of triples. In experiments, the approach achieves state-of-the-art performance on three benchmark datasets, and outperforms recent KGC approaches on sparsely connected datasets.
Ključne besede: knowledge graph completion, BERT, deep convolutional architecture, re-ranking
Objavljeno v DKUM: 19.02.2024; Ogledov: 229; Prenosov: 18
Celotno besedilo (1,03 MB)
Gradivo ima več datotek! Več...

Opis: In this bachelor thesis, the different types of innovation within a company are studied and analysed. The companies studied are SMEs i.e. from 10 to 250 employees. Smaller companies are mainly confronted with the problem of resources and larger companies with their strategic orientation. We have studied the ten types of innovations according to Doblin (Doblin 2014), and we realise that they have a rather marketing-oriented focus, so we analyse five groups of innovations that we consider to be the key (marketing, product, organisational, business model and technological innovation). Five groups of innovations have been weighed on a scale from 0 to 100 % according to their importance to contribute to the economic success of the company. All groups have been weighted and ranked in order of priority to initiate the innovation process in the SME, starting with marketing, followed by product, technological, organisational and business model innovations. We found innovation process needs to be implemented as a continuous cyclical process. If the company wants to be successful, it is a continuous cycle model, which should never stop. Once a particular innovation is chosen, it will be studied and tested whether the investment can be successful. If so investment process will be executed, if not, the cycling process will start again until gives a positive result. This way one of the innovation is recognized as most important according to circumstances in SME involved at a certain moment.
Ključne besede: Innovation model, types of innovation, pondering of innovations, cycling innovation process, innovation in SMEs, ten types of innovation by Doblin, ranking of innovations, marketing innovations, product innovations.
Objavljeno v DKUM: 07.07.2021; Ogledov: 968; Prenosov: 33
Celotno besedilo (1,56 MB)

Opis: The paper deals with the importance of web page optimization. Internet and its characteristics are shown in the beginning of this paper, as the main source of obtaining information. Web pages should have all the necessary information that people are seeking and should also be ranged as high as possible in the search engines. The fact is that almost every search begins through a search engine. The basic tool that is used here are words that describe your search area and are called keywords. Examples are showing us the differences between optimized and not-optimized pages. Article deals with the basic examples of a page optimization (on-page optimization) and also web page optimization outside the page (off-page optimization). Further on we can know about the recommended techniques and possibility how to use them in online optimization to increase your competitiveness in search marketing which leads to more web page visitors. It also shows the advantages of optimized web pages and its trends that are shown in the area of search marketing.
Ključne besede: optimization, search engine optimization, internet marketing, page ranking
Objavljeno v DKUM: 03.11.2017; Ogledov: 1437; Prenosov: 460
Celotno besedilo (160,45 KB)
Gradivo ima več datotek! Več...

Opis: In the growing need for information we have come to rely on search engines. The use of large scale search engines, such as Google, is as common as surfingthe World Wide Web. We are impressed with the capabilities of these search engines but still there is a need for improvment. A common problem withsearching is the ambiguity of words. Their meaning often depends on the context in which they are used or varies across specific domains. To resolve this we propose a domain specific search engine that is globally oriented. We intend to provide content classification according to the target domain concepts, access to privileged information, personalization and custom rankingfunctions. Domain specific concepts have been formalized in the form ofontology. The paper describes our approach to a centralized search service for domain specific content. The approach uses automated indexing for various content sources that can be found in the form of a relational database, we! b service, web portal or page, various document formats and other structured or unstructured data. The gathered data is tagged with various approaches and classified against the domain classification. The indexed data is accessible through a highly optimized and personalized search service.
Ključne besede: information search, personalization, indexes, crawling, domain specific crawling, natural language processing, content tagging, distributed data sources, ranking functions
Objavljeno v DKUM: 31.05.2012; Ogledov: 2151; Prenosov: 37
Povezava na celotno besedilo