SmartCOPI Smart Consolidation of Product Information

Maintaining the quality of detailed product data, ranging from data about required raw materials to detailed specifications of tools and spare parts, is of vital importance in many industries. Ordering or using wrong spare parts (based on wrong or incomplete information) may result in significant production loss or even impact health and safety. The web provides a wealth of information on products provided in various formats, detail levels, targeted at at a variety of audiences. Semiautomatically locating, extracting and consolidating this information would be a “killer app” for enriching and improving product data quality with a significant impact on production cost and quality. The new to COMMIT/ industry partner Mydatafactory is interested in both the web harvesting and data cleansing technologies developed in COMMIT/-projects P1/Infiniti and P19/TimeTrails for this potential and for improving Mydatafactory’s data cleansing services. The ICT science questions behind data cleansing and web harvesting are how noise can be detected and reduced in discrete structured data, and how human cognitive skills in information navigation and extraction can be mimicked. Research results on these questions may benefit a wide range of applications from various domains such as fraud detection and forensics, creating a common operational picture, and safety in food and pharmaceuticals. Three partners and their status The new to COMMIT/ industry partner Mydatafactory provides product data cleansing solutions to global and regional companies. Mydatafactory focuses on one thing: fixing product data quality problems by delivering customers the best software to cleanse, update, structure, standardize and enrich their product data. In an industrial setting product data is used throughout the production chain: it ranges from data about required raw materials, and specifications of tools and spare parts needed in the production process, to detailed information about the delivered products. The number of items involved in the process may easily grow to several hundreds of thousands. The Mydatafactory software is intelligent; it improves and adapts itself depending on the usage. Where others work with rule-based functions, Mydatafactory works with machine learning, language processing and dictionary-driven technologies. In this way, product data cleansing processes can be shortened from weeks/months to hours/days, costs reduced to 20%, and errors reduced from over 50% to less than 1% of the products. People involved in this Zwaluw project will be Arjan Herskamp (director), Dolf Trieschnigg (data scientist, previously a PostDoc researcher at the University of Twente, not involved in COMMIT/), as well as software engineers from Mydatafactory and sister-company Calago. The Old to COMMIT/ academic are project leader Maurice van Keulen and Software Engineer Jan Flokstra from the University of Twente both involved in COMMIT/-projects P1/Infiniti and P19/TimeTrails. Data enrichment and cleansing are important drivers in smart industry. Mydatafactory has the ambition to be the best in what they do by staying on the forefront of technology, and is as such an attractive partner for the upcoming COMMIT2DATA program. The New to COMMIT/ academic is Brend Wanders, currently finishing his PhD at the University of Twente. Brend worked on probabilistic data integration and cleansing technology for bioinformatics. His cooperation with the FedSS project (ITEA2) has led to a promising approach for data cleansing based on his open source probabilistic datalog engine. Mydatafactory is interested in both the web harvesting and data cleansing technologies developed in COMMIT/-projects P1/Infiniti and P19/TimeTrails and by Brend himself, for their potential for enriching product data from web sources and for improving Mydatafactory’s data cleansing capabilities.