12/03/ Second International Workshop on New Generation Enterprise and Business Innovation NGEBIS 2013 Cross Domain Crawling for Innovation Pieruigi Assogna, Francesco Taglino CNR-IASI (Italy)
12/03/ Outline Motivations & Objectives Methodological approach Technological approach Conclusions
12/03/ Motivations and Objectives In any kind of organization, creativity and innovation come from people Tools aiming at supporting creativity need to be based on the most accredited theories related to how people use their knowledge to act on the environment, adapt to new situations, invent. The method proposed here aims at providing knowledge “raw material”, capable of triggering out-of-the-box ideas
12/03/ Constructivism According to Constructivism a person’s culture is an integrated network of concepts and models This guides the person’s activity, and is consolidated, enriched, modified by each new experience Apart from pathological situations (schizophrenia) each person’s structure is anyway connected
12/03/ New Paths The connections between concepts create paths that, with time, our mind travels more or less automatically In new situations we have to “take the lead” and try new paths, possibly linking different and distant clusters This is for instance what is favored by “lateral thinking” methods
12/03/ Knowledge Base In general a domain Knowledge Base (KB) is a tool for maintaining and enriching its users’ focused knowledge In particular the KB’s ontology mimics their focused conceptual structure When the users are confronted by new issues, a search on the KB or on the Net (on the base of the domain ontology) typically keeps them within this focused ground
12/03/ The Methodology We propose a way to extend a focused knowledge domain to support diversions from usual thinking paths We use the domain ontology to search the Net for documents that address key topics of the domain together with topics belonging to different ones These documents have good probability of containing considerations, theories, metaphors that link the person’s knowledge clusters with “exotic” ones, able to trigger ideas out-of-the- box
12/03/ Semantics-based cross-domains crawling
12/03/ Documental Resources Space where we search for interesting documents websites (e.g., MIT website on innovations), RSS feeds, and public documents repositories (e.g., BBC news) In our example we focus on Robotics and Machine Vision (R&MV) domain
12/03/ Linked Data A set of principles to allow Standard description of data (RDF-based) Standard way of accessing data (HTTP) Linking resources/data among them Linking Open Data as a project for publishing datasets (e.g., Dbpedia) in a Linked Data fashion
12/03/ The Linking Open Data cloud DBpedia
12/03/ Reference ontology and bridge to the LOD cloud Within the BIVEE project we have built a glossary of 600 concepts on R&MV We enriched such concepts with DBpedia entries (owl:sameAs) Photodiodes R&MV reference ontology DBpedia Photodiode owl:sameAs Camera owl:sameAs
12/03/ Terms extraction from analyzed document Extracted terms/concepts are representative and somehow synthesize the document’s content We analyzed different tools for extracting knowledge from documents Zemanta, Alchemy, OpenCalais, FISE AlchemyAPI: extract concepts from a text relevance value link to DBpedia and other LOD dataset
12/03/ Semantic Filter over a doc Two steps Identify the extracted concepts related to our domain of interest Identify good candidate and discarding not interesting documents
12/03/ Semantic Filter over a doc: step 1 Identify the extracted concepts related to our domain of interest (e.g., R&MV) Given an extracted concept ec, it exists at least one reference concept rc, such that Extracted Concept (ec) (r 1 = ref. to Dbpedia entry) Reference Ontology Concept (rc) (r 2 = ref. to Dbpedia entry) (r 1 dc:subject) r AND (r 2 dc:subject r) where r is a resources r 1 = r 2 OR
12/03/ Semantic Filter over a doc: step 2 Let be S1 the set of extracted concepts related to our domain Let be S2 the set of extracted concepts NOT related to our domain A document is a good candidate if (a) t1<Sum(relVal(S1))<t2 AND t 1 =0.1, t 2 =0.4 (b) Sum(relVal(S2))>t3t 3 =0.4 (a) ensures that the analyzed document deals with our reference domain, but in a small manner, (b) second constraint ensures that the analyzed document deals with other topics in a considerable measure.
12/03/ Filtering: example 1 Extracted Concepts and Relevance The document is about extracting energy from insects SUGGESTED AS INTERESTING
12/03/ Filtering: example 2 Extracted Concepts and Relevance The document is about supporting shoppers get the right fit when buying clothes online SUGGESTED AS INTERESTING
12/03/ Filtering: example 3 Extracted Concepts and Relevance The document does not consider Robotics and Machine Vision at all NOT INTERESTING document
12/03/ Filtering: example 4 Extracted Concepts and Relevance The document is too much Robotics oriented, so it can be surely useful for experts in the Robotics field, but it does not appear inspiring for lateral thinking NOT INTERESTING document
12/03/ Conclusions and Outlook Very preliminary work on supporting lateral thinking activities More experimentation Using the LOD cloud as much as possible
12/03/ Questions & Answers