semantically-aware networks and services for training and knowledge management in organizations
DESCRIPTION
My presentation at NGNS-2012 Conference, Faro Portugal, 2 décembre 2012TRANSCRIPT
Semantically-aware Networks and Services for Training and Knowledge
Management in Organizations
Dr. Gilbert PaquetteDr. Gilbert Paquettewww.licef.ca/cice
Canada Research Chair in Instructional and Canada Research Chair in Instructional and Cognitive Enginerring (CICE)Cognitive Enginerring (CICE)
LICEF Research CenterLICEF Research Center
Télé-universitéTélé-université
NGNS’12 – Faro, Portugal – DecembrerNetworks and NGNS’12 – Faro, Portugal – DecembrerNetworks and ServicesServices
Software Developments at CICE/LICEF
MOT+LDMOT+LD
MOT +MOT +
MOT 2.0MOT 2.0
AGDAGD
MOT+OWLMOT+OWL
MISA 2.0MISA 2.0
MISA 4.0MISA 4.0
MISA LDMISA LD
ADISAADISA
MISA 3.0MISA 3.0
G-MOTG-MOT
PalomaPaloma
PalomaWebPalomaWeb
Competences +Competences +COMÈTECOMÈTE
TELOSScénario Ed.. Ontology Ed.
Competency Ed.Semantic Ref
Reccomenders
TELOSScénario Ed.. Ontology Ed.
Competency Ed.Semantic Ref
Reccomenders
Explor@Explor@
Concept@Concept@
Virtual CampusModel
Virtual CampusModel
Why Semantics ?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.
The Web of Data (Web 3.0)The Web of Data (Web 3.0)
URIs to identify all kinds of rssources Subject/relation/Object triples Graphs to relate Normalized syntax ( XML)
Web of documentsRelational DB
.
.
.
Web of linked dataRDF graphs
COMÈTECOMÈTE ArchitectureArchitecture
COMÈTE InterfaceCOMÈTE Interface
Semantic Question Semantic Question AnsweringAnswering
““Give me all the resources of a certain author?”Give me all the resources of a certain author?” ““Give me all the resources of an organization of a certain Give me all the resources of an organization of a certain
author?”author?” ““Give me all the resources from authors who have published Give me all the resources from authors who have published
with a certain list of authors?”with a certain list of authors?” ““Give me all the exercises references under “Atomic Give me all the exercises references under “Atomic
Physics” in the Dewey classification and under the Physics” in the Dewey classification and under the equivalent classifications in my University’s classifications?”equivalent classifications in my University’s classifications?”
““Give me all the Geometry tutorials , excluding Euclidian Give me all the Geometry tutorials , excluding Euclidian Geometry ?” Geometry ?”
““Give me all the Reports on open source tools that could Give me all the Reports on open source tools that could replace a certain tool ?””replace a certain tool ?””
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
The PRIOWS ProjectThe PRIOWS Project
Integrating data basesIntegrating data basesKnowledge ModelingKnowledge ModelingOntology ModelingOntology ModelingWork ScenarioWork ScenarioAssistanceAssistance
Ontology
Query
Experts
Documents
Data
Processes
Methods
Federated
Search
TELOSTELOS
Specialized TEL op. systemSpecialized TEL op. system Resource aggregation:Resource aggregation: ……in multi-actor scenarios in multi-actor scenarios Service-oriented system on NGNService-oriented system on NGN Ontology-driven systemOntology-driven system Produces semanticallly aware Web environmentProduces semanticallly aware Web environment
1010
LORNET (2003-2008):
A hundred researchers, A hundred researchers, assistants, graduate studentsassistants, graduate students
17 organizations, NSERC 17 organizations, NSERC support Semantic WEB support Semantic WEB researchresearch
TELOS
TELOS ArchitectureTELOS Architecture
Server
TechnicalOntologyTCP/IP
KBMan.
KBMan.
KBKB
Rel.BDRel.BD
Execution Semantic(based on the technical ontology)
Recommendation (assistance) Recommendation (assistance) PrinciplesPrinciples
Epiphyte – grafted on the scenario process Epiphyte – grafted on the scenario process
but external to it; no scenario modificationbut external to it; no scenario modification
Multi-agent system: agents are associated to Multi-agent system: agents are associated to
tasks at different levels in the scenariotasks at different levels in the scenario
Flexible association: one, some or all of the Flexible association: one, some or all of the
tasks are assisted.tasks are assisted.
Delegation between a task agent towards its Delegation between a task agent towards its
super tasks agents; tree topologysuper tasks agents; tree topology
InsertionInsertion of recommenders of recommenders (assistance agents): an example(assistance agents): an example
The implemented recommender The implemented recommender modelmodel
Recommender = {rules}Recommender = {rules} Rule = <targetActor, event, condition, action >Rule = <targetActor, event, condition, action > Event = Event =
– Activity transition Activity transition (started, terminated, revisited,…)(started, terminated, revisited,…)– Time spent (activity, global …) Time spent (activity, global …) – Resources opened, reopened,…Resources opened, reopened,…
Condition = boolean expression comparing: Condition = boolean expression comparing: – Target actor progress in the scenario + Target actor progress in the scenario + knowledge and knowledge and
competencies acquired + evidence => competencies acquired + evidence => User persistent modelUser persistent model
– Resources: prerequisite and target competenciesResources: prerequisite and target competencies
– Activities: prerequisite and target competenciesActivities: prerequisite and target competencies
Action = advice, notification, model updateAction = advice, notification, model update
Knowledge Descriptors
Classes and instances (From OWL-DL domain ontologies)General properties:
Domain – Data Properties / Domain – ObjectProperty – RangeInstanciated properties (facts):
Instance – Property / Instance – Property – Value
Competency Descriptors
(K, S, P) triples(K, S, P) triples
K: Knowledge descriptorK: Knowledge descriptor– From a OWL domain ontologyFrom a OWL domain ontology
S: Generic SkillS: Generic Skill– From a 10-level taxonomy From a 10-level taxonomy
(Paquette, 2007)(Paquette, 2007)
P: Performance levelP: Performance level– A combination of P-values A combination of P-values
(Paquette, 2007) (Paquette, 2007)
S=ApplyS=ApplyS=ApplyS=Apply
P=ExpertP=ExpertP=ExpertP=Expert
K=PlanetK=PlanetK=PlanetK=Planet
Referencing Process in the TELOS Implementation
OntologyOntologycontructioncontructionor importor import
… and/or competencies
ResourceResourceselectionselection1111 2222
SemanticSemanticReferencingReferencingOf resourcesOf resources
3333
Semantic Search Methods
Type of SearchType of Search Type of ResultType of Result
Simple Using key words from the ontology
AdvancedUsing knowledge and competency Using knowledge and competency boolean queryboolean query
Resource PairingUsing semantic comparison between queried ressource and other resources
→ → Rests on knowledge and competency comparisonRests on knowledge and competency comparison
Ressources with an Ressources with an exact matchexact match
Exact match ORExact match OR
Semanticallynear match
Semanticallynear match
Exact match ORExact match OR
Knowledge Comparison (K1 et K2)
Based on the Based on the structure of the ontology where the of the ontology where the knowledge descriptors are storedknowledge descriptors are stored
Compare the Compare the neighbourhoods of K1 and K2of K1 and K2
Possible resultsPossible results– K2 K2 near and more and more specialized / / general than K1 than K1
Competency Comparison
Based on knowledge Based on knowledge comparison ((KK))
Base on Base on the distance between skills’ levels (between skills’ levels (HH) ) and and performance levels distances(performance levels distances(PP))
Possible resultsPossible results C2C2 veryNear / Near C1 C1 C2C2 stronger / weaker than C1than C1 C2 more C2 more specialized / general than C1than C1
C1=(K1, S1, P1) et C2=(K2, S2, P2)C1=(K1, S1, P1) et C2=(K2, S2, P2)
Competency ComparisonCompetency Comparison
Competency comparison Competency comparison within rule conditionswithin 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
Recommendation exampleRecommendation example
Notification exampleNotification example
User model updateUser model update
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.
Future ResearchFuture 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.
Questions, Comments ?Questions, Comments ?
www.licef.ca/gp www.licef.ca/cice
www.cogigraph.com
NGNS’12 – Faro, Portugal – Decembrer 2, 2012NGNS’12 – Faro, Portugal – Decembrer 2, 20124th International Conference on Next Generation 4th International Conference on Next Generation
Networks and ServicesNetworks and Services