Research is the core task of STI Innsbruck. Our motto is "Enabling Semantics". Find out more about our current research directions!

Projects

This page lists the current projects with STI Innsbruck. Please see the archive and the historical projects for more on completed projects.

Bausteine für KI-basierte Optimierungen in der industriellen Fertigung (KI-Net)

Contact:

Der Interreg Programmraum Österreich-Bayern ist eine Region mit einer hohen Anzahl von (kleinen und mittelständischen) Unternehmen (KMU), die der Produktion und Fertigung von Produktionsanlagen zugeordnet werden können. Künstliche Intelligenz (KI) ist eine Schlüsseltechnologie der industriellen Digitalisierung. Sie bietet großes Potential im Bereich der Optimierung verschiedenster Aspekte von Produktionsprozessen (z.B. Ressourcenverbrauch, Energieverbrauch, Emissionsreduktion, Qualitätsverbesserungen, Predictive Maintenance). Jedoch umfasst das Thema KI so viele Bausteine/Methoden (siehe Auflistung unten), dass Unternehmen - insbesondere KMU - damit überfordert sind und diese Potentiale nicht ausschöpfen können. Gründe sind zum einen fehlende Fachexpertise und zum anderen eine derzeit für die Unternehmen unwägbare Komplexität und Risiken in der Anwendung. Das vorliegende Projekt entwickelt ein grenzübergreifendes Kompetenznetzwerk, das grundlegende Bausteine für KI-basierte Optimierungen in der industriellen Fertigung untersucht, erforscht und entwickelt, präsentiert und damit für KMU den Zugang zum gezielten Einsatz von KI in Produktions- und Instandhaltungs-Prozessen erleichtert. Dabei wird klar herausgearbeitet, welche KI-Bausteine/Methoden für welche industriellen Fertigungsaufgaben die passendsten sind. Zu den KI-Bausteinen/Methoden zählen 1) Digital Twins, Robotik & KI-gestützte Modellbildung, 2) Systems-Engineering Prozesse, 3) Wissensrepräsentation, 4) Datenanalyse- sowie Optimierungs- & Lernverfahren, 5) Anwendungsleitfaden für den Einsatz von KI in der Fertigung. Die Projektteilnehmer bündeln das notwendige Know-how, um eine für Europa als vorteilhaft erachtete Reindustrialisierung basierend auf neuesten Technologien, hier vorranging der Nutzbarmachung von KI in industriellen Produktions- und Instandhaltungsprozessen durch KMU, voranzutreiben.


Digital Innovation Hub West, FFG

Contact:

The aim of DIH West is to help SMEs in Western Austria to transform, digitally support their innovation potential by giving them the institutionalized access to the know-how of research institutions through various activities is possible. According to the needs of SMEs in Salzburg, Tyrol and Vorarlberg, the content of the DIH West focuses on the areas of application Industry 4.0, for manufacturing companies, and eServices, for companies from tourism, commerce and trade.
The main objective of the STI WP is to develop a semi‐automatic annotation editor to help SMEs to annotate their web content.


DTE

Contact:

Der Innovationslehrgang zielt darauf ab, die digitale Kompetenz im Tourismus zu erhöhen. Zielgruppe sind IT-Verantwortliche in Tourismusunternehmen. Hierzu zählen bspw. Tour Operator, die Hotellerie, aber auch Beratungsunternehmen im Tourismus. Zudem werden auch Tourismusverbände und Landestourismusorganisationen angesprochen, ihre IT-Verantwortlichen weiterzubilden. Die Weiterbildungsinhalte richten sich nach aktuellen Forschungsinitiativen an den beteiligten Universitäten und Fachhochschulen und decken hierbei Themen wie Semantische Technologien im Web, Usability von Assistenzsystemen, Konsumentenverhalten im Buchungsprozess, Big Data Management oder Strategien zur Cyber-Sicherheit ab. Derzeit sind 15 Module zwischen 2-4 Lehrtagen eingeplant. Diese Lehrtage werden branchenspezifisch in Nebensaisonen und an Randzeiten der Arbeitswoche angeboten. Als LektorInnen stehen ForscherInnen aus (derzeit) acht Universitäten und Fachhochschulen zur Verfügung. Die angebotenen Inhalte werden in einigen Themenbereichen auf Einstiegs- und Aufbauniveau angeboten. Somit können sehr erfahrene MitarbeiterInnen, wenn gewünscht, direkt im Aufbauniveau einsteigen. Das Resultat wird zu einer erhöhten Professionalisierung des eTourismus in Österreich führen.


MindLab

Contact:

MindLab is a cooperative research project with the goal to develop methods and software tools for modeling and implementing scalability for knowledge graphs.

Feratel and Onlim provide dialogue-based access to touristic information, products, and services. But meaningful dialogues require large amounts of knowledge to be available in a machine-processable way. For this purpose, the Mindlab project develops knowledge graph technologies. In MindLab, we will develop methods and tools that allow information providers to construct a Knowledge Graph relevant to their content. In detail:

Semantic annotations: Methods and tools for the manual, semi-automatic and automated generation of semantic annotations and their integration into a knowledge graph.
Quality control of Knowledge Graphs: Methods and tools for semi-automated and automated quality control and improvement of knowledge graphs.
Connecting Knowledge Graphs: Methods and tools for semi-automated and automated extension of a knowledge graph with other heterogeneous and dynamic information sources and knowledge graphs.
Life cycle of knowledge graphs: Methods and tools for the manual, semi-automatic and automated generation of semantic annotations and their integration into a knowledge graph.
Mapping: Methods and tools for manual, semi-automatic and automatic mapping of unstructured data into machine processable form.

Talking Knowledge Graphs:

Presentation:Talking Knowledge Graphs, MindLab New York, 2019

Additional link:https://sps.columbia.edu/academics/executive-education/programs-individuals/knowledge-graph-conference/speakers

Talk's video link:https://www.youtube.com/watch?v=Xrp-ET5GUL4

 


Ontology-driven data documentation for Industry Commons (OntoCommons)

Contact:

The OntoCommons project's overall objective is to bring together and coordinate activities of the most relevant EU stakeholders for the development of an Ontology Commons EcoSystem (OCES), consisting of ontologies and tools following specific standardization rules, that can be effectively used as foundation for data documentation in the industrial domain, in order to facilitate data sharing and valorisation and overcome the existing interoperability bottlenecks.


Platform for Real-time Vehicle Data Campaigns (CampaNeo)

Contact:

In the CampaNeo project, an open platform will be developed on which private and public institutions can create campaigns and collect and analyze vehicle data in real-time. The goal is to set up a prototype platform for secure campaign-based data collection in Hanover, Wolfsburg and in cross-regional scenarios, as well as the implementation of the first smart use cases based on the campaign data. The focus is in particular on the data ownerships of vehicle owners and the traceability of data processing. The analysis of vehicle sensor data (e.g. for the detection of driving behavior, finding of driver efficiency scores, anomaly detection, etc.) requires the creation and use of models of machine learning (ML). Among others, the CampaNeo project aims to address issues related to the efficient use of ML models, taking into account data quality and data protection aspects for real-time vehicle data. The results of the CampaNeo project include technologies and analysis techniques that are useful for many user groups such as municipalities, fleet management providers, insurance companies and service providers in the fields of data science and mobility. These results are validated together with business users in selected application scenarios and economically and scientifically exploited by the consortium and associated partners.


Semantic Direct Booking Bot (SDB2)

Contact:

Subtitle: dynamic on-the-fly access to (new) data sources and web services by chatbots

The Web is facing a major paradigm shift. Over the next few years it will transform from a human readable platform to a platform for bots. Therefore, the prerequisite for content, data, and service providers to be visible in this "new" web, is the proper structuring and the semantic annotation of their data and services. Semantic technologies will be the backbone infrastructure enabling this paradigm shift.

Chatbots and intelligent personal assistants currently only work with hard wired data sources and services. They can give information about addresses, opening hours, the weather, a recipe and more. They can also use services, like maybe a table reservation or the purchase of a movie ticket. But only under the premise that the data source or services is known and the connection is implemented by the developers (hard wired). What they can not do up to now is accessing Web data sources on the fly or going into interaction with Web services dynamically. If an assistant wants to use data from a web source, it has to understand the structure in which the data is present. And if an assistant wants to use a Web Service, it has to know its address, the input parameters, the expected output and more. If this information is not available in a machine readable way (semantically annotated), the assistant can not interact.

Currently, the main problem is that neither data on the web, nor services on the web offer a machine readable and machine understandable semantics. So to be able to interact with web data sources and web services on the fly, the assistants would need to understand the structure in which the data is present and the protocol in which a service can be accessed or consumed.

Each chatbot or voice assistant needs a lot of service integrations to fulfill requests and tasks. Therefore a scalable methodology for service integration and execution is needed. Semantic technologies will help assistants to perform service calls. The goals of SDB2 are therefore: 1) to annotate touristic service providers' APIs: to make Web Services machine read- and interpretable, they have to be described in a common language or with a common vocabulary. One goal of that project is therefore to annotate touristic service provider's APIs with the vocabulary of schema.org. We will analyze a selection of APIs and develop a best practice for API annotation. And 2) integrate these services into a platform for an easy integration in chatbots and voice assistants. It is expected that the developed methodology of this project leads to a faster scalability of service integrations in chatbots and voice assistants including an automation of the underlying dialogues for the service processing. Existing chat bots will be extended with the ability to read, interpret, understand and execute annotated web services.


Smart Dispatcher for Secure and Controlled Sharing of Distributed Personal and Industrial Data (smashHit)

Contact:

The objective of smashHit is to assure trusted and secure sharing of data streams from both personal and industrial platforms, needed to build sectorial and cross-sectorial services, by establishing a Framework for processing of data owner consent and legal rules and effective contracting, as well as joint security and privacy preserving mechanisms. The vision of smashHit is to overcome obstacles in the rapidly growing Data Economy which is characterized by heterogeneous technical designs and proprietary implementations, locking business opportunities due to the inconsistent consent and legal rules among different data-sharing platforms actors and operators. The Framework will provide methods and tools, such as Smart Data Dispatcher, to assure common consent over data shared using semantic models of consent and legal rules. The new tools include trace-ability of use of data, data fingerprinting and automatic contracting among the data owners, data providers, service providers and users. These tools are specifically critical for enormous volumes on data streaming from the usage of mass products with cyber physical features (e.g. vehicles). These data streams offer new opportunities to build innovative services, but their combination with other personal and industrial data is subject to complex ownership and consent aspects, as the data streaming from these products belong to persons or organizations who are owners or users of the products. The project will be based on the solutions developed or under development in previous and current projects (AutoMat, Cross-CPP, CAMPANEO, DALICC, etc.). smashHit will be driven by 2 industrial Business Cases involving several existing industrial and personal data platforms owned by the leading data providers in three diverse sectors (automotive industry, insurance, smart city), and will provide 3 demonstrators of various applications of the developed solutions.


WordLift New Generation (WordLiftNG)

Contact:

Eurostars funded project WordLift New Generation aims at the construction of the most SEO-friendly structured linked data in a simple way. Its objective is to expand WordLift’s market reach by creating a new platform to deliver the features offered today to WordPress users to any websites regardless of the CMS. We plan to improve the backend's performance enabling enrichment and querying of RDF graphs with semantic similarity indices and full-text search allowing clients of WordLift and Redlink to: implement semantic search and content recommendations on their website; integrate with personal digital assistants such as Amazon Alexa.


We are hiring!

Check out our researcher job positions at https://www.sti-innsbruck.at/about/jobs