Semantically-aware Networks and Services for Training and Knowledge Management in Organizations.
Download as PPT, PDF0 likes451 views
This document discusses semantically-aware networks and services for training and knowledge management. It describes software developed at CICE/LICEF for building ontologies and semantically referencing resources to enable semantic search and personalized recommendations. The TELOS system uses competency descriptors and comparison methods to power rules-based recommender agents that are integrated into learning scenarios to provide adaptive assistance to users. Future work is aimed at experimental validation, improving group recommendations, automation, and integrating other recommendation methods.
Semantically-aware Networks and Services for Training and Knowledge Management in Organizations.
- 1. NGNS ’ 12 – Faro, Portugal – DecembrerNetworks and Services Semantically-aware Networks and Services for Training and Knowledge Management in Organizations Dr. Gilbert Paquette www.licef.ca/cice Canada Research Chair in Instructional and Cognitive Enginerring (CICE) LICEF Research Center Télé-université
- 2. Software Developments at CICE/LICEF Virtual Campus Virtual Campus AGD AGD Model Model MOT 2.0 MOT 2.0 MISA 2.0 MISA 2.0 Explor@ Explor@ MISA 3.0 MISA 3.0 ADISA ADISA Paloma Paloma MOT MOT ++ MISA 4.0 MISA 4.0 Concept@ Concept@ MISA LD MISA LD MOT+LD MOT+LD MOT+OWL PalomaWeb PalomaWeb MOT+OWL TELOS TELOS G-MOT G-MOT Scénario Ed.. Scénario Ed.. COMÈTE COMÈTE Ontology Ed. Ontology Ed. Competency Ed. Competency Ed. Competences ++ Competences Semantic Ref Semantic Ref Reccomenders Reccomenders
- 3. Why Semantics ? 1. Inform users (students, workers) during the execution of task or learning activity of the content of the resources that they use. 2. Assist users and designers in the selection of resources appropriate to their knowledge and competencies. 3. Create well-balanced learning of work scenarios, locally and globally. 4. Build user models for the personalization of learning or work environments. 5. Provide an execution semantic for resources and scenarios.
- 4. The Web of Data (Web 3.0) Web of documents Web of linked data Relational DB RDF graphs . . URIs to identify all kinds of rssources . Subject/relation/Object triples Graphs to relate Normalized syntax ( XML)
- 7. Semantic Question Answering “Give me all the resources of a certain author?” “Give me all the resources of an organization of a certain author?” “Give me all the resources from authors who have published with a certain list of authors?” “Give me all the exercises references under “Atomic Physics” in the Dewey classification and under the equivalent classifications in my University’s classifications?” “Give me all the Geometry tutorials , excluding Euclidian Geometry ?” “Give me all the Reports on open source tools that could replace a certain tool ?””
- 8. The Adaptive Semantic Web Add semantic references to scenario components: actors, tasks and resources within educational modeling languages such as IMS-LD (2003) – Paquette and Marino, 2005 “Include the improved modeling of users and items, and contextual information into the recommendation process” – Adomavicus and Tuzhilin (2005) The “Adaptive Semantic Web” opens new approaches for recommenders systems: use of folksonomies and ontological filtering of resources – Jannach et al, 2011
- 9. The PRIOWS Project Data Documents Processes Experts Integrating data bases Knowledge Modeling Methods Ontology Ontology Modeling Work Scenario Query Assistance Federated Search
- 10. TELOS LORNET (2003-2008): A hundred researchers, assistants, graduate students 17 organizations, NSERC support Semantic WEB research TELOS Specialized TEL op. system Resource aggregation: …in multi-actor scenarios Service-oriented system on NGN Ontology-driven system Produces semanticallly aware Web environment 10
- 11. TELOS Architecture Server Technical KB KB Ontology Man Man KB KB TCP/IP .. Rel. Rel. BD BD
- 12. Execution Semantic (based on the technical ontology)
- 13. Recommendation (assistance) Principles Epiphyte – grafted on the scenario process but external to it; no scenario modification Multi-agent system: agents are associated to tasks at different levels in the scenario Flexible association: one, some or all of the tasks are assisted. Delegation between a task agent towards its super tasks agents; tree topology
- 14. Insertion of recommenders (assistance agents): an example
- 15. The implemented recommender model Recommender = {rules} Rule = <targetActor, event, condition, action > Event = – Activity transition (started, terminated, revisited,…) – Time spent (activity, global …) – Resources opened, reopened,… Condition = boolean expression comparing: – Target actor progress in the scenario + knowledge and competencies acquired + evidence => User persistent model – Resources: prerequisite and target competencies – Activities: prerequisite and target competencies Action = advice, notification, model update
- 16. Knowledge Descriptors Classes and instances (From OWL-DL domain ontologies) General properties: Domain – Data Properties / Domain – ObjectProperty – Range Instanciated properties (facts): Instance – Property / Instance – Property – Value
- 17. Competency Descriptors (K, S, P) triples K: Knowledge descriptor K=Planet K=Planet – From a OWL domain ontology S: S=Apply S=Apply Generic Skill – From a 10-level taxonomy (Paquette, 2007) P=Expert P=Expert P: Performance level – A combination of P-values (Paquette, 2007)
- 18. Referencing Process in the TELOS Implementation Ontology Resource Semantic 1 1 contruction 2 2 selection 3 3 Referencing or import Of resources … and/or competencies
- 19. Semantic Search Methods Type of Search Type of Result Simple Ressources with an Using key words from the ontology exact match Advanced Exact match OR Using knowledge and competency Semantically boolean query near match Exact match OR Resource Pairing Semantically Using semantic comparison between queried ressource and other resources near match → Rests on knowledge and competency comparison
- 20. Knowledge Comparison (K1 et K2) Based on the structure of the ontology where the knowledge descriptors are stored Compare the neighbourhoods of K1 and K2 Possible results – K2 near and more specialized / general than K1
- 21. Competency Comparison C1=(K1, S1, P1) et C2=(K2, S2, P2) Based on knowledge comparison (K) Base on the distance between skills’ levels (H) and performance levels distances(P) Possible results C2 veryNear / Near C1 C2 stronger / weaker than C1 C2 more specialized / general than C1
- 23. Competency comparison within rule conditions A competency-based condition is a triple: – ObjectCompetencyList is the list of prerequisite or target competencies of another actor, a task or a resource to be compared with user’s actual competency list – Relation is one of the comparison relations : Identical, Near, VeryNear, MoreGeneric, MoreSpecific, Stronger, Weaker, or any combination of these. – Quantification takes two values: HasOne or HasAll EX: HasAll /NearMoreSpecific / Target competencies for Essay EX: HasOne/Weaker/Target competency for Build Table activity
- 27. Achievements in PRIOWS Extension of the TELOS Technical Ontology for semantic referencing of resources, search and recommendation Definition of a Typology of semantic descriptors (ontology descriptors and competenciers) Search methods for resources ‘identical’ ou ‘near’ sémantically Recommendation Model: based on competency comparison between actors, tasks and resources New integrated suite of tools: Semantic referencer, Semantic search tools, Competency and Ontology editors, to Recommander Integration in scenarios, Recomenders’ rule editor.
- 28. Future Research More experimental validation to refine the semantic relations between OWL-DL references, i.e adding weights to the various comparison cases Investigate recommendation methods for groups in collaborative scenarios (permitted by our model of multi-actor learning scenarios) Improve the practical use of the approach, partly automate tasks, improve the ergonomics Investigate the integration of other recommendation methods (e.g. user analytics) “Free” the suite of tools from TELOS to extend its usability on the Web of data.
- 29. NGNS ’ 12 – Faro, Portugal – Decembrer 2, 2012 4th International Conference on Next Generation Networks and Services Questions, Comments ? www.licef.ca/gp www.licef.ca/cice www.cogigraph.com
Editor's Notes
- #2: Abstract: The presentation will summarize the results of the PRIOWS research program on Ontological Engineering and Semantic Web applications, a three-year program that ended on September 2012. The program achieved an innovation project for technical information management at Hydro-Quebec, plus four related research project on the modeling of target knowledge and competencies, the modeling of work and training multi-actor scenarios, the semantic referencing of actors, tasks and documents, and the assistance to network-distributed user according to their knowledge and competencies. An ontology-driven software framework integrating these various components will be presented, together with an implemented system, TELOS, enabling designers to build and deploy work or training environments on the Web.
- #20: Donner des exemples (à l ’oral) pour chaque type de recherche.
- #21: Voisinage ‘proche’ au sens qu’on ne descend pas la hiérarchie des classes, propriétés, etc.…