BigDataGrapes (Big Data to Enable Global Disruption of the Grapevine-powered Industries) aims to help European companies in the wine and natural cosmetics industries become more competitive in the international markets. More specifically, it tries to help companies from this sector seize the opportunities that big data creates, supporting business decisions with real time and cross-stream analysis of very large, diverse and multimodal data sources.
The project is driven by the need to meet generic data challenges that are applicable to other sectors and geographical regions. It focuses on three critical big data problems: handling of missing, corrupted or inconsistent data; scalability & resource optimization on complex systems analysis; and handling uncertainty & building trust in visual analytics. For each of these problems, the project strives to provide concrete, applicable and measurable solutions, based on solid scientific and technical hypotheses, to be tested under a clearly defined application setting.
BigDataGrapest involves wine producers, bottlers and distributors; producers and packagers of food and wine products; and natural cosmetic companies. It also aims to improve the competitive positioning of enterprises in the European IT sector that are serving companies and organizations with software applications such as farm management and precision agriculture systems, quality control and compliance software for the beauty and cosmetics sector, etc.
Big data is becoming a hype that is redefining industries within very traditional sectors like agriculture, food and beauty. BigDataGrapes wants to make a difference by building upon the rich historical, cultural and artisan heritage of Europe. It aims to support European companies in the wine and natural cosmetics industries and help them respond to the significant opportunity that big data is creating in their relevant markets.
To achieve that, BigDataGrapes has set two goals: one is to develop and demonstrate powerful, rigorously tested, cross-sector data processing technologies in order to increase company efficiency when taking business decisions. The other is to create a large-scale, multifaceted marketplace for grapevine-related data assets.
BigDataGrapes targets some of the big technology challenges of the grapevine-powered economy. Its business problems and decisions require processing, analysis and visualization of data with rapidly increasing volume, velocity and variety (satellite and weather data, environmental and geological data, phenotypic and genetic plant data, food supply chain data, economic and financial data, etc.). As such, it makes a great cross-sector and cross-country combination of industries that are of high European significance and value.
Ontotext is leading the Data & Semantic Layer Work Package and taking the responsibility for the development of the Semantic Modelling and Semantic Enrichment of the BigDataGrapes components. The core activities of the Semantic Enrichment task are to design and develop advanced text analytics pipelines aiming to extract and semantically annotate information from unstructured data included in the BigDataGrapes data pool.
The extracted entities refer instances from the conceptual BigDataGrapes model and thus further extend the knowledge graph both with new facts and new provenance sources. Ontotext’s semantic graph database Graph DB™ is used as the triplestore in the BigDataGrapes project.
In addition to leading the Semantic Layer activities, Ontotext is playing an important role in two other Work Packages. The company delivers the components for the Distributed Semantic Inference for the Analytics and Processing Layer and contributes to the integration and operation of the BigDataGrapes platform for the Integration & Deployment. Ontotext also supports the activities of the Grapevine-powered Industry Big Data Challenges and Cross-sector Rigorous Experimental Testing Work Packages.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 780751.