CN107391883A - A kind of intelligent instruction system perceived based on context and its implementation - Google Patents
A kind of intelligent instruction system perceived based on context and its implementation Download PDFInfo
- Publication number
- CN107391883A CN107391883A CN201710754170.2A CN201710754170A CN107391883A CN 107391883 A CN107391883 A CN 107391883A CN 201710754170 A CN201710754170 A CN 201710754170A CN 107391883 A CN107391883 A CN 107391883A
- Authority
- CN
- China
- Prior art keywords
- context
- data
- learning
- leads
- lead
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 241000270281 Coluber constrictor Species 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- OQZCSNDVOWYALR-UHFFFAOYSA-N flurochloridone Chemical compound FC(F)(F)C1=CC=CC(N2C(C(Cl)C(CCl)C2)=O)=C1 OQZCSNDVOWYALR-UHFFFAOYSA-N 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The present invention discloses a kind of intelligent instruction system perceived based on context, context information acquisition module is learned including leading, lead context semantic model and establish module, context leads rule generation module, lead and learn context semantic data Fusion Module, context leads resource recommendation module and context leads execution module, context native data is led by leading context information acquisition module collection, foundation, which is led, learns context semantic model, learnt by gauge, generation context leads rule, fusion, which is led, learns field semanteme related data, release context and lead optimal resource, receive semantic service match selection and recommendation service, operation intelligence leads engine, service is led to provide intelligence.The invention also discloses a kind of implementation method of the intelligent instruction system perceived based on context.The present invention provides for MOOC education resource platforms and leads service more with personalized autonomous learning.
Description
Technical field
The present invention relates to instructional technology field, more particularly to a kind of intelligent instruction system perceived based on context and its realization
Method.
Background technology
Under Internet education environment, various MOOC education resource platforms emerge in an endless stream, the MOOC teaching moneys of opening and shares
Source is enriched constantly, and technology constantly breaks through with education depth integration so that MOOC platforms are more open, and MOOC platforms just turn into study
Type social construction and the effective way of life-long education system structure, this will need MOOC platforms more open, be also required to simultaneously
The offer of MOOC platforms is more personalized to lead service.Then existing MOOC platforms pay attention to the design and fabrication of MOOC resources, weight
Depending on the design and innovation of teaching pattern, it is difficult to adapt to the demand of personalized autonomous learning.Based on above-mentioned background, clothes are intelligently being led
The personalized service of leading of study context progress how is combined in business framework just turns into current urgent problem.
The defects of conventional method and deficiency:Learner's context is not designed, merged and applied from Ontology layer,
It is difficult to meet the needs of MOOC platform learners user individual experience.On the other hand, it is not based on the change of learner's context situation
Change, there is provided realize the flexible customization of the flexible configuration and learning method of education resource.Such case is obviously not suitable with MOOC platforms
The megatrend that deeply develops and learner's life-long education it is inherently required.
The content of the invention
The main object of the present invention is to propose a kind of intelligent instruction system perceived based on context, it is intended to can be learnt
Context Intelligent Recognition realizes that context scene carries out intelligence and leads with merging.
To achieve the above object, the intelligent instruction system proposed by the present invention perceived based on context, including lead and learn context letter
Breath acquisition module, lead and learn that context semantic model establishes module, context is led and learns rule generation module, leads and learn the fusion of context semantic data
Module, context lead resource recommendation module and context leads execution module, wherein:
Lead and learn context information acquisition module, learn context native data for gathering to lead from study context information, and upload
Intelligence, which is perceived, to context leads platform service end;
Lead context semantic model and establish module, lead for being established by ontology modeling tool using ontology description language
Context semantic model;
Context leads rule generation module, for according to learning situation rule and knowledge connection relation, using SWRL language
SWRL rules are formulated, using SWRL rule design learning Knowledge routes and alternative learning method, context is thus generated and leads rule;
Lead and learn context semantic data Fusion Module, context knowledge is learned for merging study context data and leading, and based on this
Body access element, and ontology inference engine service is utilized, carry out leading the converged services for learning context data knowledge in ontology knowledge layer,
Complete consistency detection and the scene convergence of context data;
Context, which is led, learns resource recommendation module, for leading rule using above-mentioned generated context, is taken based on education resource
Business specification, service quality and service price, are calculated by education resource semantic dependency and learning objective degree of reaching, and are led for intelligence
Learn engine and semantic service match selection and recommendation service are provided;
Context leads execution module, and for receiving semantic service match selection and recommendation service, operation intelligence leads engine,
Service is led to provide intelligence.
Preferably, described lead learns context information acquisition module including leading context information collecting unit and leading context information
Conversion unit, wherein:
Lead and learn context information collecting unit, for learning Platform Server and the study context of learning terminal institute arrangement by leading
In information extract Agent periodically or gathered in a manner of event response lead learn context native data;
Lead and learn context information conversion unit, for the context native data of leading gathered to be converted into object model table
Context mark data is learned in leading for the unified form shown.
Preferably, the context leads rule generation module and leads the single nothing of rule generation including pretreatment unit and context,
Wherein:
Pretreatment unit, for carrying out leading context actively classification knowledge to leading context mark data in context native data
Not and the representation for learning context semantic data is led, pre-processed to leading context native data, generation study context data;
Context leads rule generating unit, by by lead learn context native data lead learn context semantic model in based on
Device learns, and generation context leads rule.
Preferably, in addition to context is led and learns situation feedback module, and the context, which is led, learns situation feedback module in context
Lead during learning execution module execution, customization intelligence leads the feedback data for the Semantic Aware for learning each stage, is intelligently led for next stage
Learn and semantic feedback data is provided.
Preferably, in addition to context data enquiry module, the context data enquiry module, for being inquired about with ontology knowledge
Engine connects, to provide context data inquiry service.
The present invention also proposes a kind of implementation method of the intelligent instruction system perceived based on context, comprises the following steps:
S10 collections from study context information, which are led, learns context native data, and is uploaded to context perception intelligence and leads platform
Service end;
S20 establishes to lead by ontology modeling tool using ontology description language learns context semantic model;
S30 uses SWRL language for SWRL rules, to advise learning situation rule and knowledge connection transformation using SWRL
Then design learning Knowledge route and alternative learning method, thus generate context and lead rule;
S40 fusions learn context data and led to learn context knowledge, and are based on body access element, and utilize ontology inference
Engine service, carry out leading the converged services for learning context data knowledge in ontology knowledge layer, complete the consistency detection of context data
Converged with scene;
S50 leads rule using above-mentioned generated context, based on education resource service profiles, service quality and service
Price, calculated by education resource semantic dependency and learning objective degree of reaching, leading engine for intelligence provides semantic service
With selection and recommendation service;
S60 receives semantic service match selection and recommendation service, and operation intelligence leads engine, and clothes are led to provide intelligence
Business.
Preferably, the S10 steps include:
S101 learns Platform Server and extraction Agent in the study context information of learning terminal institute arrangement is regular by leading
Or gather to lead in a manner of event response and learn context native data;
S102 leads field by what leading of being gathered learned that context native data is converted into the unified form that is represented with object model
Border mark data
Preferably, the S30 steps include:
S301 lead context active Classification and Identification and lead learning field to leading context mark data in context native data
The representation of border semantic data, pre-processed to leading context native data, generation study context data;
S302 leads by leading the gauge study for learning context native data in context semantic model is being led, generation context
Regular technical solution of the present invention can carry out learning context Intelligent Recognition with merging by developing one kind, realize context scene
Carry out system and its implementation that intelligence leads.This technology can be widely applied to MOOC teaching platforms and motion education net
In network environment.
Preferably, in addition to:For S70 during context is led and learns execution module execution, customization intelligence leads the semanteme for learning each stage
The feedback data of perception, intelligently lead for next stage and semantic feedback data is provided.
Preferably, also include after the S40:S80 is connected with ontology knowledge query engine, is looked into providing context data
Ask service.
The present invention develops one kind and can carry out learning context Intelligent Recognition and merging, and realizes that context scene carries out intelligence
Instruction system and its implementation, provided for MOOC education resource platforms and lead clothes more with personalized autonomous learning
Business.The present invention establishes individual learners context, position ability context information, education resource knowledge and study context historical feedback etc.
Native data is unified in context Ontology data describing framework resource, is realized that intelligence is led and is learned the fusion of context semantic data, is
Calculated based on Ontology reasoning and semantic dependency and individualized learning offer semantic data is provided;Based on study context scene rule
Then establish intelligence and lead engine, realize education resource and Learning Service semantic matches.Will be to learning context feelings based on SWRL language
Scape is modeled to be designed with inference rule, and is provided the other reasoning principle of optimality of different priorities and provided personalization to learner
Education resource;The system uses learner according to the requirement of position ability intension and all critical learning path of acquisition position ability
Context Ontology relatedness computation realizes that position capability factor matches, and handy learner's procedural semantics data, study context
Semantic data, study examination semantic data etc., carry out position capability maturity appraisal service, examine with improving learning process with learning
Practise effect.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Structure according to these accompanying drawings obtains other accompanying drawings.
Fig. 1 is a kind of functional block diagram of an embodiment of the intelligent instruction system perceived based on context in the present invention;
Fig. 2 is the heretofore described functional module refinement figure led and learn context information acquisition module;
Fig. 3 is that heretofore described context leads the functional module refinement figure for learning rule generation module;
Fig. 4 is a kind of functional block diagram of the another embodiment of the intelligent instruction system perceived based on context in the present invention;
Fig. 5 is a kind of functional block diagram of another embodiment of the intelligent instruction system perceived based on context in the present invention;
Fig. 6 is a kind of method of an embodiment of the implementation method of the intelligent instruction system perceived based on context in the present invention
Flow chart;
Fig. 7 is heretofore described S10 method flow diagram;
Fig. 8 is S30 of the present invention method flow diagram;
Fig. 9 is a kind of side of the another embodiment of the implementation method of the intelligent instruction system perceived based on context in the present invention
Method flow chart;
Figure 10 is a kind of another embodiment of the implementation method of the intelligent instruction system perceived based on context in the present invention
Method flow diagram;
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only the part of the embodiment of the present invention, rather than whole embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of creative work is not made it is all its
His embodiment, belongs to the scope of protection of the invention.
If it is to be appreciated that related in the embodiment of the present invention directionality instruction (such as up, down, left, right, before and after ...),
Then directionality instruction be only used for explaining relative position relation under a certain particular pose (as shown in drawings) between each part,
Motion conditions etc., if the particular pose changes, directionality instruction also correspondingly changes therewith.
If in addition, relating to the description of " first ", " second " etc. in the embodiment of the present invention, " first ", " second " etc. are somebody's turn to do
Description be only used for describing purpose, and it is not intended that instruction or implying its relative importance or implicit indicating indicated skill
The quantity of art feature.Thus, " first " is defined, the feature of " second " can be expressed or implicitly includes at least one spy
Sign.In addition, the technical scheme between each embodiment can be combined with each other, but must be with those of ordinary skill in the art's energy
Based on enough realizations, the knot of this technical scheme is will be understood that when the combination appearance of technical scheme is conflicting or can not realize
Conjunction is not present, also not within the protection domain of application claims.
As Figure 1-10 shows, the present invention proposes a kind of intelligent instruction system perceived based on context, including leads and learn context letter
Breath acquisition module 10, lead learn context semantic model establish module 20, context lead learn rule generation module 30, lead learn context semanteme number
Resource recommendation module 50 is led according to Fusion Module 40, context and context is led and learns execution module 60, wherein:
Lead and learn context information acquisition module 10, context native data is learned for gathering to lead from study context information, and on
Reach context perception intelligence and lead platform service end;
Lead context semantic model and establish module 20, led for being established by ontology modeling tool using ontology description language
Learn context semantic model;
Context, which is led, learns rule generation module 30, for being turned learning situation rule and knowledge connection relation using SWRL language
SWRL rules are turned to, using SWRL rule design learning Knowledge routes and alternative learning method, context is thus generated and leads rule;
Lead and learn context semantic data Fusion Module 40, learn context knowledge for merging study context data and leading, and be based on
Body access element, and ontology inference engine service is utilized, carry out leading the fusion clothes for learning context data knowledge in ontology knowledge layer
Business, complete consistency detection and the scene convergence of context data;
Context, which is led, learns resource recommendation module 50, for leading rule using above-mentioned generated context, based on education resource
Service profiles, service quality and service price, calculated by education resource semantic dependency and learning objective degree of reaching, for intelligence
Lead and engine offer semantic service match selection and recommendation service are provided;
Context, which is led, learns execution module 60, and for receiving semantic service match selection and recommendation service, operation intelligence is led and drawn
Hold up, service is led to provide intelligence.
In the present embodiment, heretofore described context information acquisition module 10 of leading leads similar to the intelligence of isomerous multi-source
Data acquisition unit, led by the collection of intelligent instruction system, conversion and generation and learn context semantic data, the module passes through data grabber
Agent is captured periodically or in a manner of event response to lead and is learned context native data, it is described lead to learn context native data and include study lead
Body context data, learning process data, education resource context relation data, position ability intension require data, learn context
Assessment and feedback data etc..
The context semantic model of leading establishes module 20, and by Prot é g é, (Prot é g é are by Stanford University
The ontology editor of one open source code of Stanford Medical Informatics exploitations, it is with written in Java)
Ontology modeling tool, structure lead the semantic data model for learning context, are led based on the generation of RDF/OWL ontology description languages and learn context number
According to model, and by Racer (Racer is the dial-up program of the client of Netcom) and Jena (Jena is java API,
For supporting the relevant application of semantic net) etc. ontology inference machine carry out context lead learn semantic model uniformity and redundancy detection,
Formation, which is led, learns context semantic data ontology model.
The context, which is led, learns rule generation module 30, and various fields will be combined by perceiving intelligent platform service end of leading by context
Border knowledge data and episode rule, learning agent environment context Rule Builder is run, position ability context Rule Builder, is learned
Resources and knowledge context Rule Builder etc. is practised, is produced based on episode rule, rule is led using what SWRL rule languages represented,
The ability for learning engine identification learning high level situation is led with enhancing.Requiring supplementation with is explanatorily, the learning situation rule and knowledge
Incidence relation is the learning situation rule and knowledge connection relation provided by expert of the art, by the knowledge for learning high-rise scene
Not, learning demand and identification learning resource are extracted.SWRL (semantic WEB rule languages, Semantic Web Rule
Language), it is that World Wide Web Consortium (W3C) proposed in 2004, for describing inference rule.It is with OWL sublanguages OWL
Regular description language based on DL, OWL Lite and RuleML.Its purpose is to allow rule to produce combination with OWL, from
And improve the inferential capability of body.Body be between the related notion in some field (resource) and concept relation it is accurate
Description.OWL is a kind of ontology description language, is to carry out formalized description to body so that computer is it will be appreciated that ontology describing
Knowledge.Body is the knowledge that can be formalized, and is clearly stating for generalities.Body has stronger knowledge representation ability, but
Ability of the body in terms of knowledge reasoning is weaker, it has also become the main bottleneck of OWL Technique Popularizings application, SWRL is incorporated into this
In body, the inferential capability of body can be substantially improved, so as to excavate many new tacit knowledges.
Described lead learns context semantic data Fusion Module 40, by context perceive intelligence lead learn platform service end will identify and
The study context data of expression and lead and learn context knowledge, using based on body access element, and utilize ontology inference engine service
(such as Jena, Racer) carries out leading the converged services for learning context data knowledge in ontology knowledge layer, completes the consistent of context data
Property detection and scene convergence.
The context, which is led, learns resource recommendation module 50, is perceived by context and leads service-Engine, using filterability rule and
Optimum choice rule, learning tasks are completed in selection from learning object repository needs Optimal Learning resource and education resource step, hands over
Enforcement engine execution is led by context and leads service.
The context leads execution module 60, for according to leading, context to be regular and context is led resource recommendation module and pushed away
The Optimal Learning resource recommended, receives semantic service match selection and recommendation service, and operation intelligence is led engine, provided for learner
Personalized intelligence leads service, and realizes and continue to optimize and adjustment target in service process.
The present invention establishes individual learners context, position ability context information, education resource knowledge and study context history
The native datas such as feedback are unified in context Ontology data describing framework resource, realize that intelligence is led context semantic data and melted
Close, semantic data is provided to calculate progress individualized learning based on Ontology reasoning and semantic dependency;Based on study context
Episode rule establishes intelligence and leads engine, realizes education resource and Learning Service semantic matches.Will be to study based on SWRL language
Context scene is modeled to be designed with inference rule, and provides the other reasoning principle of optimality of different priorities to learner's offer
The education resource of property;The system uses according to the requirement of position ability intension and all critical learning path of acquisition position ability
Learner's context Ontology relatedness computation realizes that position capability factor matches, and handy learner's procedural semantics data,
Context semantic data, study examination semantic data etc. are practised, position capability maturity appraisal service is carried out, examines and learnt with improvement
Journey and results of learning.
Preferably, described lead learns context information acquisition module 10 including leading context information collecting unit 101 and leading field
Environment information conversion unit 102, wherein:
Lead and learn context information collecting unit 101, for learning Platform Server and the study of learning terminal institute arrangement by leading
In context information extract Agent periodically or gathered in a manner of event response lead learn context native data;
Lead and learn context information conversion unit 102, for the context native data of leading gathered to be converted into object mould
Context mark data is learned in leading for the unified form that type represents.
In the present embodiment, the present invention learns Platform Server and the study context information extraction of learning terminal arrangement by leading
Agent is regular or study context native data is obtained in a manner of event response, and context native data is converted into object mould
The unified form (such as JSON or XML) that type represents, upload to context perception intelligence and lead platform service end, be next step field
Border data fusion prepares basic data.
Preferably, the context leads rule generation module 30 and leads rule generation including pretreatment unit 301 and context
Unit 302, wherein:
Pretreatment unit 301, for according to learning situation rule and knowledge connection Relation acquisition context mark data, to field
Border mark data carries out learning context active Classification and Identification and learns the representation of context semantic data, and it is former that context is led in completion
The pretreatment of raw data, and generate study context data;
Context, which is led, learns rule generating unit 302, for learning context native data in context semantic model is led by leading
Gauge study, generation context lead learning rule.
In the present embodiment, context perceives intelligence and leads platform service end on the one hand by context mark data
Practise context active Classification and Identification and learn the pretreatment of the primary context data of representation completion of context semantic data, generated
Study context data include context concept, context relation, context function, context axiom and context example;On the other hand pass through
Primary context data carries out leading the semantics recognition for learning basic context and complicated context correlation analysis using machine learning method, meter
Calculate adaptable lead and learn context episode rule set (SWRL expressions), Studying Situntion is expressed as to the collection of different entities state
Close, the expression of situation rule may decide that to lead the context of context and how to be deduced based on context learned.
Preferably, in addition to context is led and learns situation feedback module 70, and the context, which is led, learns situation feedback module 70, for
Context is led during learning execution module execution, and customization intelligence leads the feedback data for the Semantic Aware for learning each stage, is next stage intelligence
It can lead and semantic feedback data is provided.
In the present embodiment, the present invention is perceived by context and leads service-Engine, using filterability rule and optimum choice
Rule, learning tasks are completed in selection from learning object repository needs Optimal Learning resource and education resource step, transfers to context to lead
Learn enforcement engine to carry out leading service, and learning process and the feedback of learning quality are realized by visual means, by learning field
Environment information extracts AGENT and further carries out context data feedback, intelligently leads for next stage and provides semantic feedback data.
Preferably, in addition to context data enquiry module 80, the context data enquiry module 80, it is used for and ontology knowledge
Query engine connects, to provide context data inquiry service.
In the present embodiment, the present invention provides context data unified query by ontology knowledge query engine (such as SPARQL)
Service, lead the learning rules inquiry service that regulation engine supports ASK and TELL modes of learning.
The present invention also proposes a kind of implementation method of the intelligent instruction system perceived based on context, should be perceived based on context
The implementation method of intelligent instruction system is to realize the above-mentioned intelligent instruction system perceived based on context, due to described based on field
The implementation method for the intelligent instruction system that border perceives employs whole technical schemes of above-mentioned all embodiments, therefore at least has
All beneficial effects caused by the technical scheme of above-described embodiment, this is no longer going to repeat them.The present invention also proposes a kind of base
In the implementation method for the intelligent instruction system that context perceives, comprise the following steps:
S10 collections from study context information, which are led, learns context native data, and is uploaded to context perception intelligence and leads platform
Service end;
S20 establishes to lead by ontology modeling tool using ontology description language learns context semantic model;
S30 uses SWRL language for SWRL rules, to advise learning situation rule and knowledge connection transformation using SWRL
Then design learning Knowledge route and alternative learning method, thus generate context and lead rule;
S40 fusions learn context data and led to learn context knowledge, and are based on body access element, and utilize ontology inference
Engine service, carry out leading the converged services for learning context data knowledge in ontology knowledge layer, complete the consistency detection of context data
Converged with scene;
S50 leads rule using above-mentioned generated context, based on education resource service profiles, service quality and service
Price, calculated by education resource semantic dependency and learning objective degree of reaching, leading engine for intelligence provides semantic service
With selection and recommendation service;
S60 receives semantic service match selection and recommendation service, and operation intelligence leads engine, and clothes are led to provide intelligence
Business.
Preferably, the S10 steps include:
S101 learns Platform Server and extraction Agent in the study context information of learning terminal institute arrangement is regular by leading
Or gather to lead in a manner of event response and learn context native data;
S102 leads field by what leading of being gathered learned that context native data is converted into the unified form that is represented with object model
Border mark data
Preferably, the S30 steps include:
S301 lead context active Classification and Identification and lead learning field to leading context mark data in context native data
The representation of border semantic data, pre-processed to leading context native data, generation study context data;
S302 leads by leading the gauge study for learning context native data in context semantic model is being led, generation context
Regular technical solution of the present invention can carry out learning context Intelligent Recognition with merging by developing one kind, realize context scene
Carry out system and its implementation that intelligence leads.This technology can be widely applied to MOOC teaching platforms and motion education net
In network environment.
Preferably, in addition to:For S70 during context is led and learns execution module execution, customization intelligence leads the semanteme for learning each stage
The feedback data of perception, intelligently lead for next stage and semantic feedback data is provided.
Preferably, also include after the S4:S80 is connected with ontology knowledge query engine, is looked into providing context data
Ask service.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the scope of the invention, it is every at this
Under the inventive concept of invention, the equivalent structure transformation made using description of the invention and accompanying drawing content, or directly/use indirectly
It is included in other related technical areas in the scope of patent protection of the present invention.
Claims (10)
1. a kind of intelligent instruction system perceived based on context, it is characterised in that including leading context information acquisition module, leading
Context semantic model establishes module, context leads rule generation module, lead context semantic data Fusion Module, context leads money
Source recommending module and context lead execution module, wherein:
Lead and learn context information acquisition module, learn context native data for gathering to lead from study context information, and be uploaded to field
Border perceives intelligence and leads platform service end;
Lead context semantic model and establish module, context is led for being established by ontology modeling tool using ontology description language
Semantic model;
Context leads rule generation module, for use SWRL language by learning situation rule and knowledge connection transformation for
SWRL rules, using SWRL rule design learning Knowledge routes and alternative learning method, thus generate context and lead rule;
Lead and learn context semantic data Fusion Module, learn context knowledge for merging study context data and leading, and deposit based on body
Component is taken, and utilizes ontology inference engine service, carries out leading the converged services for learning context data knowledge in ontology knowledge layer, completes
Consistency detection and the scene convergence of context data;
Context, which is led, learns resource recommendation module, for leading rule using above-mentioned generated context, is advised based on education resource service
Lattice, service quality and service price, calculated by education resource semantic dependency and learning objective degree of reaching, lead for intelligence and draw
Hold up and semantic service match selection and recommendation service are provided;
Context leads execution module, and for receiving semantic service match selection and recommendation service, operation intelligence leads engine, to carry
Service is led for intelligence.
2. the intelligent instruction system perceived as claimed in claim 1 based on context, it is characterised in that described to lead context information
Acquisition module, which includes leading learning context information collecting unit and leading, learns context information conversion unit, wherein:
Lead and learn context information collecting unit, for learning Platform Server and the study context information of learning terminal institute arrangement by leading
Middle extraction Agent periodically or gathered in a manner of event response lead learn context native data;
Lead and learn context information conversion unit, for the context native data of leading gathered to be converted into what is represented with object model
Context mark data is learned in leading for unified form.
3. the intelligent instruction system perceived as claimed in claim 1 based on context, it is characterised in that the context leads rule
Generation module includes pretreatment unit and context leads rule and generates single nothing, wherein:
Pretreatment unit, for lead learn context mark data in context native data lead learn context active Classification and Identification and
The representation for learning context semantic data is led, is pre-processed to leading context native data, generation study context data;
Context leads rule generating unit, for by leading the gauge for learning context native data in context semantic model is being led
Practise, generation context leads rule.
4. the intelligent instruction system perceived as claimed in claim 1 based on context, it is characterised in that also lead feelings including context
Border feedback module, the context, which is led, learns situation feedback module, for during context is led and learns execution module execution, customization intelligence to be led
The feedback data of the Semantic Aware in each stage is learned, intelligently leads for next stage and semantic feedback data is provided.
5. the intelligent instruction system perceived based on context as described in claim any one of 1-4, it is characterised in that also including field
Border data inquiry module, the context data enquiry module, for being connected with ontology knowledge query engine, to provide context data
Inquiry service.
6. a kind of implementation method of the intelligent instruction system perceived based on context, it is characterised in that comprise the following steps:
S10 collections from study context information, which are led, learns context native data, and is uploaded to context perception intelligence and leads platform service
End;
S20 establishes to lead by ontology modeling tool using ontology description language learns context semantic model;
S30 uses SWRL language for SWRL rules, to set learning situation rule and knowledge connection transformation using SWRL rules
Learning knowledge path and alternative learning method are counted, context is thus generated and leads rule;
S40 fusions learn context data and led to learn context knowledge, and are based on body access element, and utilize ontology inference engine clothes
Business, carry out leading the converged services for learning context data knowledge in ontology knowledge layer, complete the consistency detection and scene of context data
Convergence;
S50 leads rule using above-mentioned generated context, based on education resource service profiles, service quality and service price,
Calculated by education resource semantic dependency and learning objective degree of reaching, leading engine for intelligence provides semantic service match selection
With recommendation service;
S60 receives semantic service match selection and recommendation service, and operation intelligence leads engine, and service is led to provide intelligence.
7. the implementation method of the intelligent instruction system perceived as claimed in claim 6 based on context, it is characterised in that described
S10 steps include:
S101 learns Platform Server with extracting Agent in the study context information of learning terminal institute arrangement periodically or with thing by leading
The collection of part response mode, which is led, learns context native data;
S102 leads context mark by what leading of being gathered learned that context native data is converted into the unified form that is represented with object model
Know data.
8. the implementation method of the intelligent instruction system perceived as claimed in claim 6 based on context, it is characterised in that described
S30 steps include:
S301 lead context active Classification and Identification and lead learning context language to leading context mark data in context native data
The representation of adopted data, pre-processed to leading context native data, generation study context data;
S302 leads rule by leading the gauge study for learning context native data in context semantic model is being led, generation context.
9. the implementation method of the intelligent instruction system perceived as claimed in claim 6 based on context, it is characterised in that also wrap
Include:
S70 is during context is led and learns execution module execution, and customization intelligence leads the feedback data for the Semantic Aware for learning each stage, under
One stage intelligently led and provides semantic feedback data.
10. the implementation method of the intelligent instruction system perceived based on context as described in claim any one of 6-9, its feature are existed
In also including after the S40:
S80 is connected with ontology knowledge query engine, to provide context data inquiry service.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710754170.2A CN107391883A (en) | 2017-08-29 | 2017-08-29 | A kind of intelligent instruction system perceived based on context and its implementation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710754170.2A CN107391883A (en) | 2017-08-29 | 2017-08-29 | A kind of intelligent instruction system perceived based on context and its implementation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107391883A true CN107391883A (en) | 2017-11-24 |
Family
ID=60347012
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710754170.2A Pending CN107391883A (en) | 2017-08-29 | 2017-08-29 | A kind of intelligent instruction system perceived based on context and its implementation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107391883A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101105853A (en) * | 2007-08-16 | 2008-01-16 | 上海交通大学 | Personalized teaching-guiding system based on non-zero jumping-off point in network teaching |
CN101382950A (en) * | 2008-09-26 | 2009-03-11 | 中山大学 | Body correlation method based on SWRL-Bridge-Peer model |
CN103064945A (en) * | 2012-12-26 | 2013-04-24 | 吉林大学 | Situation searching method based on body |
CN103258027A (en) * | 2013-05-08 | 2013-08-21 | 南京邮电大学 | Context awareness service platform based on intelligent terminal |
CN106447558A (en) * | 2016-06-23 | 2017-02-22 | 温州职业技术学院 | guidance of learning method and learning system combining ontology and clustering analysis technology |
-
2017
- 2017-08-29 CN CN201710754170.2A patent/CN107391883A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101105853A (en) * | 2007-08-16 | 2008-01-16 | 上海交通大学 | Personalized teaching-guiding system based on non-zero jumping-off point in network teaching |
CN101382950A (en) * | 2008-09-26 | 2009-03-11 | 中山大学 | Body correlation method based on SWRL-Bridge-Peer model |
CN103064945A (en) * | 2012-12-26 | 2013-04-24 | 吉林大学 | Situation searching method based on body |
CN103258027A (en) * | 2013-05-08 | 2013-08-21 | 南京邮电大学 | Context awareness service platform based on intelligent terminal |
CN106447558A (en) * | 2016-06-23 | 2017-02-22 | 温州职业技术学院 | guidance of learning method and learning system combining ontology and clustering analysis technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6432859B2 (en) | Service providing system and program | |
CN106529673A (en) | Deep learning network training method and device based on artificial intelligence | |
McNeill | IBM and the visual formation of smart cities | |
Zhang et al. | The application of artificial intelligence technology in the tourism industry of Jinan | |
JP6617263B2 (en) | Learning support system | |
JP6562328B2 (en) | Support system | |
JP7067755B2 (en) | Service provision system and terminal | |
Nguyen et al. | Conflict resolution in group decision making: insights from a simulation study | |
US20220415199A1 (en) | Smart-learning and knowledge concept graphs | |
CN110263183A (en) | Intelligent home decision support system and decision support method | |
Connier et al. | Perception assistance for the visually impaired through smart objects: concept, implementation, and experiment scenario | |
Wilson et al. | A framework for linking distributed simulations using software agents | |
Peiris et al. | A conceptual framework for evolving, recommender online learning systems | |
CN107391883A (en) | A kind of intelligent instruction system perceived based on context and its implementation | |
JP7208603B2 (en) | Service provision system and terminal | |
Axak et al. | The Agent-Based Learning Platform. | |
Ponce et al. | Smart communities and cities as a unified concept | |
Miñón et al. | Supportive adaptive user interfaces inside and outside the home | |
Jara-Roa et al. | An adaptive multi-agent based architecture for engineering education | |
JP7444489B2 (en) | Learning support system and service provision method | |
Cantucci et al. | Human-robot interaction through adjustable social autonomy | |
Cort | Getting Work Done | |
Liebowitz et al. | MACS: multi-agent COTR system for defense contracting | |
Geldof | Con-textual navigation support | |
Cantucci et al. | Investigating Adjustable Social Autonomy in Human Robot Interaction. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |
|
RJ01 | Rejection of invention patent application after publication |