CN108062369B

CN108062369B - Situation-integrated polymorphic ubiquitous learning resource aggregation method and system

Info

Publication number: CN108062369B
Application number: CN201711298864.6A
Authority: CN
Inventors: 陈敏
Original assignee: Central China Normal University
Current assignee: Central China Normal University
Priority date: 2017-12-08
Filing date: 2017-12-08
Publication date: 2020-08-11
Anticipated expiration: 2037-12-08
Also published as: CN108062369A

Abstract

The invention discloses a situation-integrated polymorphism ubiquitous learning resource aggregation method, which comprises the following specific steps: creating a learning resource comprising a plurality of internal learning elements; according to the situation that the learning resources can play the utility, carrying out resource situation annotation on each learning element in the resources; sensing the specific learning situation of the learner in the ubiquitous learning environment; matching the learning context with the resource context, thereby obtaining a resource context matched with the current learning context; and dynamically aggregating the learning elements in the resources according to the obtained resource situation. The invention also provides a system for realizing the method. The invention describes key elements related to situation aggregation in learning resources, and specifies a connection mode between the elements, so that the learning resources have polymorphism capability, namely, the elements in the resources can be dynamically aggregated to form different resource forms under different situations, thereby providing the learning resources which are more matched with situation requirements for ubiquitous learners and effectively improving the learning effect.

Description

Situation-integrated polymorphic ubiquitous learning resource aggregation method and system

Technical Field

The invention relates to the technical field of ubiquitous learning, in particular to a situation-integrated polymorphic ubiquitous learning resource aggregation method and system.

Background

The situation cognition theory considers that the situation is the basis of all cognitive activities, and effective learning cannot be separated from the specific situation. Knowledge is contextualized and is continuously developed in activities and applications, and knowledge deviated from the situation makes it difficult for learners to apply the knowledge in specific situations and realize meaningful learning. On the contrary, when knowledge information related to the situation is provided for the learner, the default knowledge inside the learner can promote the learner to establish the association with the previous similar situation, so that similar behaviors are adopted when the problem is solved, and the application of the knowledge in a specific scene, the cognitive development of the learner and the effective occurrence of learning are further promoted.

As one of the core elements of learning, learning resources play an important role in the efficient occurrence of learning. The situation of the extensive learning emphasizes the solution of the "situation problem", and the extensive learner learns to acquire knowledge to solve the specific situation problem, only knows objective knowledge, but does not know how to apply the knowledge in different situations, so that the knowledge has no practical significance to the learner. Improving the matching degree of the learning resources and the situation requirements is beneficial for the learners to obtain the method and the ability of solving the actual problems.

However, due to the different knowledge requirements of learners for the same learning object, under certain circumstances, it is highly likely that the same learning resource will have both learner-required content and undesired content. In order to provide learning resources matching with the situation requirements to the learner, the current system extracts the learning resources integrally related to the learning situation from the existing resource library by matching the learning situation with the resource characteristics (single situation matching), and presents the whole learning resources to the learner. Currently, the matching degree of the learning resources and the situation needs to be improved in this way. On one hand, the method needs to convert the learning situation into the requirement on the characteristics of the target learning resource, and then searches resources meeting the characteristic requirement from the resource library, and the matching accuracy and efficiency are limited, on the other hand, the method only focuses on the correlation degree of the whole learning resource and the situation requirement, always presents the whole learning resource to the learner, and ignores the matching degree of the learning elements and the situation contained in the learning resource.

In order to provide a learning resource more matched with the situation requirement to the extensive learner, the learning resource is required to be attached with resource situation information to support the double situation matching on one hand, and the learning resource is required to have a dynamic structure to support the dynamic aggregation of the learning elements in the resource on the other hand. However, the current learning resources adopt static resource descriptions and static resource structures which lack resource context information, and the requirements are difficult to meet.

Disclosure of Invention

In view of the above drawbacks or improvement needs of the prior art, the present invention provides a method and system for aggregating situation-integrated polymorphic ubiquitous learning resources, which aims to provide a ubiquitous learner with learning resources more matched with situation needs, thereby effectively improving learning effects.

A method for polymorphic ubiquitous learning resource aggregation with respect to integrated context, comprising the steps of:

(1) creating a learning resource comprising at least a plurality of internal learning elements of learning content, associated learners, learning activities;

(2) according to the situation that the learning resources can play the utility, carrying out resource situation annotation on each learning element in the resources;

(3) sensing the specific learning situation of the learner in the ubiquitous learning environment;

(4) matching the learning context with the resource context, thereby obtaining a resource context matched with the current learning context;

(5) and aggregating the learning elements in the learning resources, which are associated with the matched resource context.

Further, the specific process of step (1) creating a learning resource including at least learning content, relevant learner, and a plurality of internal learning elements of learning activity is:

the components of the learning resources comprise learning content, learning activities, relevant learners, resource situations, associated information and situation interfaces; wherein, the learning content, the learning activities and the related learners can directly provide information and support for learning, which are collectively called learning elements and are aggregation objects of resource aggregation; the resource situation, the associated information and the situation interface are important conditions for supporting resource aggregation and belong to supportability elements; when a resource creator creates learning resources, two main learning elements, namely learning content and learning activity, are created, and corresponding association between the learning activity and the learning content is established; the resource creator automatically becomes one of the learners related to the resource; after the resource is created, learners, subscribers, editors and domain experts related to the resource in the system become relevant learners of the resource.

Further, the specific process of performing resource context labeling on each learning element in the resource according to the context in which the learning resource can exert utility in the step (2) is as follows:

(21) resource context initialization: when a resource is created, after a creator creates certain learning content, manually marking partial attribute values of a resource context related to the learning content according to a resource context marking support, wherein the partial attribute values comprise learner context attributes, teaching context attributes, equipment context attributes and space-time context attributes, and providing some auxiliary information to support automatic marking of a system; according to the auxiliary information provided by the creator, automatically marking the rest attribute values of the resource situation by combining with a preset recommendation rule, thereby completing the initialization of the resource situation and storing the resource situation information into a resource situation library; the resource context of the learning content also automatically becomes the resource context of the learning activity associated with the learning content; (22) and (3) dynamically updating the resource context: after the learning element is used in a certain situation, judging whether the situation exists in the resource situation library of the learning resource, if not, considering the situation as a new application situation of the learning resource, and storing the new application situation into the resource situation library, thereby realizing the dynamic update of the resource situation.

Further, the specific process of the step (3) of sensing the specific learning context in which the learner is located in the ubiquitous learning environment is as follows:

(31) defining the situation elements of the ubiquitous learning, and dividing the situation elements of the ubiquitous learning into: learning needs, learner context, learning environment context, learning device context, and spatiotemporal context.

(32) Acquiring ubiquitous learning context information, acquiring learner context information, learning demand information, time context information, space context information, learning environment context information and learning equipment context information.

Further, the step (4) of matching the learning context with the resource context, so as to obtain the resource context matched with the current learning context comprises the following specific processes:

(41) combining the resource situation body frame and the learning situation body frame to form a situation body tree Q with uniform form in the system;

(42) establishing node mappings of a resource context tree and a learning context tree by using a unified context ontology tree Q;

(43) the system senses the current learning context tree CL of the learner and extracts a resource context tree CR from the resource context library to be matched;

(44) calculating the similarity between corresponding leaf nodes of CL and CR according to the node mapping relation;

(45) the similarity between the resource context tree CR and the learning context tree CL is obtained through the similarity accumulation or weighted summation between the leaf nodes;

(46) if the resource situation which is not matched exists in the resource situation library, repeating the steps (43) to (45), otherwise, entering the step (47);

(47) matching degree sequencing is carried out on the plurality of resource situations by utilizing a preset situation inference rule and combining the similarity between the plurality of resource situation trees CR and the learning situation tree CL;

(48) and determining the resource context which is most matched with the current learning context tree CL according to the matching degree sorting result.

Further, the situation inference rules are divided into three types of filtering rules, user preference rules and optimization selection rules, and the filtering rules, the user preference rules and the optimization selection rules are sequentially arranged from high priority to low priority;

the specific implementation process of the step (47) is as follows:

(721) filtering the resource situation which is not matched with the current situation in the resource situation library according to the filtering rule;

(722) arranging the user preference rules and the preference rules from high to low and from left to right according to the priority, and forming a two-dimensional matrix with the rest resource situations, wherein the inference rules are used as columns of the matrix, and the resource situations are used as rows of the matrix;

(723) matrix filling is carried out on the meeting condition of the rule according to the resource situation, if the resource situation tree CR meets a certain rule R, the element of the intersection of the CR and the R is marked as flag;

(724) grading the resource situation by using a flag in the two-dimensional matrix, and taking the number of columns of the element with the flag appearing first in the row of the resource situation tree CR as the number of stages of the resource situation tree CR;

(725) sequencing the resource situations according to the progression, wherein the lower the progression, the higher the matching degree of the resource situations and the learning situations;

(726) for the resource situations with the same level, the resource situations with the same level are sequentially compared with the conditions respectively satisfied by the rule with the highest priority, namely the similarity specified in the specific rule is compared, and the resource with the high similarity is arranged in the front;

(727) and taking the resource context ranked at the first position as the resource context which is matched with the current context most.

A system for polymorphic ubiquitous learning resource aggregation with respect to integrated context, comprising the following modules:

a first module for creating a learning resource comprising at least a learning content, a relevant learner, a plurality of internal learning elements of a learning activity; (ii) a

The second module is used for carrying out resource situation annotation on each learning element in the resource according to the situation that the learning resource can exert the effect;

the fourth module is used for perceiving the concrete learning situation of the learner in the ubiquitous learning environment;

a fifth module for matching the learning context with the resource context, thereby obtaining a resource context matching the current learning context;

and the sixth module is used for aggregating the learning elements in the learning resources, which are associated with the resource context obtained by matching.

Further, the first module is used for creating the components of the learning resource, including learning content, learning activities, related learners, resource context, associated information and context interface; wherein, the learning content, the learning activities and the related learners can directly provide information and support for learning, which are collectively called learning elements and are aggregation objects of resource aggregation; the resource situation, the associated information and the situation interface are important conditions for supporting resource aggregation and belong to supportability elements; when a resource creator creates learning resources, two main learning elements, namely learning content and learning activity, are created, and corresponding association between the learning activity and the learning content is established; the resource creator automatically becomes one of the learners related to the resource; after the resource is created, learners, subscribers, editors and domain experts related to the resource in the system become relevant learners of the resource.

Further, the second module comprises:

a 21 st sub-module for resource context initialization: when a resource is created, after a creator creates certain learning content, manually marking partial attribute values of a resource context related to the learning content according to a resource context marking support, wherein the partial attribute values comprise learner context attributes, teaching context attributes, equipment context attributes and space-time context attributes, and providing some auxiliary information to support automatic marking of a system; according to the auxiliary information provided by the creator, automatically labeling the rest attribute values of the resource situation by combining with the recommendation rule, thereby completing the initialization of the resource situation and storing the resource situation information into a resource situation library; the resource context of the learning content also automatically becomes the resource context of the learning activity associated with the learning content;

a 22 nd sub-module for dynamically updating the resource context: after the learning element is used in a certain situation, judging whether the situation exists in the resource situation library of the learning resource, if not, considering the situation as a new application situation of the learning resource, and storing the new application situation into the resource situation library, thereby realizing the dynamic update of the resource situation.

Further, the fifth module comprises:

a 41 th sub-module, configured to combine the resource context ontology framework and the learning context ontology framework to form a context ontology tree Q with a uniform form in the system;

a 42 th sub-module, configured to establish node mappings of a resource context tree and a learning context tree by using the unified context ontology tree Q;

a 43 th sub-module, configured to systematically perceive a current learning context tree CL of the learner, and extract a resource context tree CR from the resource context library to be matched;

the 44 th sub-module is used for calculating the similarity between the leaf nodes corresponding to the CL and the CR according to the node mapping relation;

a 45 th sub-module, configured to obtain a similarity between the resource context tree CR and the learning context tree CL by accumulating or performing weighted summation on the similarities between the leaf nodes;

a 46 th sub-module, configured to repeat the 43 th sub-module to the 45 th sub-module if there is no matched resource context in the resource context library, otherwise, enter the 47 th sub-module;

a 47 th sub-module, configured to perform matching degree sorting on the multiple resource contexts by using a preset context inference rule and combining similarities between the multiple resource context trees CR and the learning context tree CL;

and a 48 th sub-module, configured to determine, according to the matching degree sorting result, a resource context that best matches the current learning context tree CL.

Generally, compared with the prior art, the technical scheme provided by the invention describes key elements related to situation aggregation in the learning resources, and specifies the connection mode between the elements, so that the learning resources have polymorphism capability, that is, the elements in the resources can be dynamically aggregated to form different resource forms in different situations, the learning resources which are more matched with situation requirements are provided for ubiquitous learners, and the learning effect is effectively improved.

Drawings

FIG. 1 is a general flowchart of the method for aggregating polymorphism ubiquitous learning resources for context integration according to the present invention;

FIG. 2 is a diagram of the present invention creating a resource aggregation model of resources;

FIG. 3 is a resource context framework diagram of the present invention;

FIG. 4 is a flow chart of the resource context annotation of the present invention;

FIG. 5 is a resource context tree of the present invention;

FIG. 6 is a context element of the ubiquitous learning environment of the present invention;

FIG. 7 is a flow chart of the dual context matching of the present invention;

FIG. 8 is a general thread diagram of the resource aggregation of the present invention;

FIG. 9 is a flow chart of resource aggregation of the present invention;

FIG. 10 is a resource aggregation chart of Murraya koenigii according to an experimental example of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are intended to be illustrative only and are not intended to be limiting. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

The general idea of adopting dual-scenario matching to realize the learning resource aggregation matched with the scenario requirements is as follows: and then, the association between the resource context and the learning elements in the resource aggregation model is utilized to aggregate all the learning elements associated with the resource context, thereby forming the learning resource which is highly matched with the requirement of the current learning context.

FIG. 1 is a flow chart of the method for aggregating polymorphism ubiquitous learning resources according to the context-integrated method of the present invention, comprising the following steps:

(1) a learning resource is created that includes at least a plurality of internal learning elements of learning content, associated learners, learning activities, and the like.

As shown in fig. 2, the key components of the resource creation include learning content, learning activities, people, resource context, associated information, and contextual interfaces. The learning content, the learning activities and the people can directly provide information and support for learning, which are collectively called as learning elements and are aggregation objects of resource aggregation; the resource context, the associated information and the context interface are important conditions for supporting resource aggregation, and belong to supportive elements. When creating learning resources, the resource creator creates two main learning elements, namely learning content and learning activity, and establishes corresponding association between the learning activity and the learning content. The resource creator automatically becomes one of the learners associated with the resource. After the resource is created, the person (e.g., learner, subscriber, editor, domain expert, etc.) associated with the resource in the system will become the associated learner for the resource.

Learning content: is a must-select object for aggregation. The learning content in one learning resource is dynamically composed of one or more content segments, different learning content segments may be associated with a plurality of different resource contexts, and a learning content segment may not be associated with any resource context. Learning content that is not associated with any resource context means that the content is applicable to, and presented in, any context. Under certain circumstances, aggregation of a plurality of learning content segments can transfer knowledge of different sides of a certain learning object.

And (3) learning activities: learning activities are important elements that are closely related to the learning process and are also important objects of aggregation. A learning resource may contain multiple learning activities. On one hand, the learning activities are designed to further support the learner's understanding and application of learning content, and are generally associated with specific content segments, and on the other hand, the development of activities requires support of certain external conditions, so that the learning activities may be associated with certain situations. Of course, there are also some learning activities that are not associated with a particular piece of learning content or resource context, such learning activities being by default suitable for development in any context. The learning activities aggregated by the resource aggregation model are learning activities associated with learning content and deployable under the current context.

Human: "people" as the "conduit" of knowledge are also important objects of aggregation. "human" in the resource aggregation model refers to a learner who is associated with a learning resource. Under different situations, the interaction of the learner with the learning content and the learning activity leads to certain association between the learner and the learning content, the activity and the resource situation. The learner can not only obtain learning from learning content and learning activities, but also obtain learning by communicating and interacting with learners who have learned the same resources and have the same or similar learning experiences (situations). Thus, an aggregated "person" is a learner having the same or similar contextual experience as the current learning context. As resources are used by more and more people, so will the "people" in the resource aggregation model.

Resource context: the method is a description of all situations in which learning resources can effectively play a role, and is a key basis for realizing resource aggregation. A learning resource may function in different contexts, i.e., a learning resource may have multiple specific resource contexts. However, not all learning elements in a learning resource are suitable for performing a function in the same context at the same time, and different learning elements may perform different functions in different contexts. Thus, there is an association between learning elements and resource contexts. Through analysis of existing ubiquitous learning research, the core situation of ubiquitous learning comprises four aspects of a learner, equipment, environment and a space-time situation, and the teaching attributes of learning resources are considered, so that the study describes the learning resource situation from five dimensions of the learner situation, the equipment situation, the environment situation, the teaching situation and the space-time situation.

And (4) correlation information: the method is a general term for all the associated information in the resource aggregation model, and is an indispensable element in the resource aggregation model. As mentioned above, there are associations between learning content, learning activities, people, and resource contexts, and therefore, the association information in the resource aggregation model includes associations between learning content and resource context, associations between learning content and learning activities, associations between learning content and people, associations between learning activities and resource context, associations between people and activities, and associations between digital learning resources and entity resources. These associations are the requisite information to achieve context aggregation of resources. Some of the associated information is automatically created at the beginning of the creation of the resource, and some of the associated information is created during the use of the resource.

Context interface: the context interface is an interface for exchanging context information between the resource context and an external system, and is also an indispensable element in the resource aggregation model. The resource aggregation model outputs the resource context information to the external system through the context interface, so that the external system realizes double-context matching by utilizing the resource context information. And meanwhile, the contextual interface is also responsible for receiving matching result information returned by an external system and realizing the aggregation of the learning elements in the resources according to the matching result.

(2) And performing resource context annotation on each learning element in the resource according to the context of the learning resource capable of exerting the utility.

As shown in fig. 3, the resource teaching feature, the learner's personal feature, the learning environment, the learning device, and the space-time are five latitudes describing the context of the resource. The teaching context refers to the teaching attributes of the learning resources, the learner context refers to the personal characteristics of the learner who is suitable for using the learning resources, the environment context refers to the environment in which the learning resources are effectively used, the equipment context refers to the condition of the learning equipment which supports the operation of the learning resources, and the space-time context refers to the optimal time and space in which the learning resources can effectively exert the effectiveness. Attribute value labeling is performed on the resource context ontology attribute in a manual and automatic combination mode, so that dynamic description of the resource context is realized, and a specific idea is shown in fig. 4. The resource context annotation is divided into two stages, resource context initialization and resource context update.

(21) Resource context initialization: when a certain learning content is created by a creator, partial attribute values of a resource context related to the learning content can be manually labeled according to a resource context labeling support provided by the system, wherein the partial attribute values comprise learner context attributes, teaching context attributes, equipment context attributes and space-time context attributes, and auxiliary information is provided to support automatic labeling of the system. The system automatically marks the rest attribute values of the resource situation according to the information provided by the creator and the recommendation rule, thereby completing the initialization of the resource situation and storing the resource situation information into the resource situation library. And the resource context of the learning content automatically becomes the resource context of the learning activity associated with the learning content.

After learning content and activity creation, the creator can annotate the content paragraph context with context annotation functionality. All learning content is defaulted to be applicable to all situations at the beginning of creating, and a creator can label a plurality of situation elements of a content paragraph by using a situation labeling function according to the applicable requirement of the specific content paragraph. The system infers some context information according to the information manually labeled by the creator, so as to automatically fill the remaining resource context element information for the content paragraph. The context of all content paragraphs in a learner may be freely combined into a free context for that learner. One learning content can be associated with a plurality of contexts, and one learning element can also have a plurality of resource contexts.

After the content segment is labeled with context information, the learning activity associated with the content segment is automatically associated with the context. It should be noted that, if the creator does not insert the learning activity into any learning content segment, the learning activity is not associated with the context information, i.e., the system defaults that the learning activity is suitable for any context.

Under different situations, the interaction of the learner with the learning content and the learning activity leads to certain association between the learner and the learning content, the activity and the resource situation. The learner can not only obtain learning from learning content and learning activities, but also obtain learning by communicating and interacting with learners who have learned the same resources and have the same or similar learning experiences (situations).

(22) And (3) dynamically updating the resource context: after the learning elements (learning content, learning activities) are used in a certain scenario, the system automatically determines whether the scenario already exists in the resource scenario library of the learning resource, and if not, the scenario is considered as a new application scenario of the learning resource and is stored in the resource scenario library, thereby implementing dynamic update of the resource scenario, and finally completing the resource scenario tree diagram as shown in fig. 5.

(3) The specific learning context of the learner in the ubiquitous learning environment is sensed. The ubiquitous learning context awareness comprises a ubiquitous learning context element and two parts of ubiquitous learning context information acquisition.

(31) Context elements for ubiquitous learning

As shown in fig. 6, the context elements of the ubiquitous learning are defined and divided into: learning requirement, learner context, learning environment context, learning equipment context, spatiotemporal context.

Learning requirement: the learning method mainly refers to the learning goal of a learner, and uses two elements of knowledge and cognitive behaviors to respectively represent the knowledge which the learner wants to acquire at present and the cognitive degree of the knowledge which the learner wants to achieve. Learner situation: the characteristic information which represents the learner has some influence on the learning effect at present, including basic information such as profession, occupation, learning interest and the like, and also including information such as learning style, cognitive ability and knowledge base and the like. Learning environment situation: refers to elements of the current environment in which a learner is likely to have a greater impact on most learning of most learners, including light, noise, and limited learning behavior. Learning device context: the learning device used by the learner has some elements influencing learning, including the type of the device, the size of the screen, the installed operating system and application software, and the type of the network and the network bandwidth to which the device is connected. Space-time situation: refers to the learner's current learning time and the learner's space. The space information can be represented by the characteristics of buildings in the space, or the address of the place, or the longitude and latitude.

(32) Acquiring ubiquitous learning context information, namely acquiring learner context information, learning demand information, time context information, space context information, learning environment context information and learning equipment context information by utilizing a sensor of a system or mobile equipment and adopting an automatic and manual combined method. Different obtaining modes are adopted for different situation information.

Learner context information: and the system automatically acquires. Since the support system is built on the learning meta platform, various information related to learners is stored in the learning meta platform. The profession, occupation, learning interest and knowledge base in the learner context can be directly obtained from a learner database of the learning meta-platform. Learning demand information: the user manually enters the input. The learning requirement is a learning objective. Temporal context information: and the system automatically acquires. The current time of learner learning can be directly obtained by the system. Spatial context information: i.e. location information. And the system automatically acquires. Environmental context information: the physical environment situation information can be directly acquired through various sensors, and the social environment situation information can be more quickly and accurately input by the learner. Device context information: the system automatic acquisition is combined with the user manual input. Most of the information in the context of the device is directly available to the system, including device type, screen size, networking conditions, operating system, etc., and the installed application information of the device needs to be informed to the system by the learner.

(4) And matching the learning context with the resource context, thereby obtaining the resource context matched with the current learning context.

In order to provide learners with learning resources matching with context requirements, the commonly used idea is to select learning resources related to context requirements from an existing resource library by matching learning context with resource characteristics (single context matching). Due to the heterogeneity and non-uniformity of the learning context and the learning resource information organization, single context matching needs to convert the learning context into target resource features, and resources related to the context are obtained through feature matching among the resources. The process of converting the learning situation into the target resource characteristics depends on the experience of people and set rules, so that not only is all situations difficult to consider, but also partial information is easy to lose in the conversion process, and errors are difficult to avoid. And the feature matching between resources is also often in error due to the limitation of the algorithm. In addition, due to the existence of the conversion link, the effectiveness of resource acquisition is influenced along with the increasing of the number of resources. Therefore, the accuracy and the efficiency of the single-scenario matching method are all limited.

According to a preferred embodiment, the invention provides a dual-scenario matching method, which mainly adopts a method of combining logic reasoning, ontology-based reasoning and ontology matching to realize the dual-scenario matching of resource scenarios and learning scenarios.

Logical reasoning: and triggering the inference rule in the rule base by using the input information so as to realize inference. Ontology-based reasoning: the ontology is utilized to realize reasoning by compiling a certain reasoning rule. Matching the body: whether semantic compatibility or mapping exists between the two ontologies is judged by calculating the similarity between elements contained in the two ontologies.

First, terms related to this step will be explained:

resource context ontology framework (tree structure): the resource context ontology framework is a general framework that describes resource contexts, listing those context elements that in most cases affect the effectiveness of most learning resource applications. The framework has expansibility, can support the expansion of situation categories and attributes, and further can support the description of all resource situations. Some elements of the framework may not be required in all context descriptions of learning resources. That is, not all elements in the framework need to be used for each description of the resource context, but only those context elements that affect the application of the learning resource. The resource situation body frame is composed of a teaching situation body, a learner situation body, a learning equipment situation body, an environment situation body and a space-time situation body.

Learning context ontology framework (tree structure): and the learning situation ontology framework also describes the learning situation by using an OWL language. Compared with the resource situation body frame, the learning situation body frame and the resource situation body frame have the difference that the learning requirement class, the teaching situation class and the learning time class are mainly used. The learning requirement class in the learning context and the teaching context class in the resource context have different concept names but have the same attribute, so that they are actually the same from the perspective of similarity of concept attributes. The learning situation body frame is composed of learning requirements, learning equipment, a space-time situation, learners and a learning environment.

Resource context tree: the tree structure shows the situation information suitable for the resource and consists of five subtrees, including teaching situation tree, learner situation tree, learning equipment situation tree, environment situation tree and space-time situation tree.

Learning a context tree: the tree structure shows the current learning situation information of the learner, and the learning situation tree is also composed of five subtrees, namely a learning requirement tree, a learning equipment tree, a space-time situation tree, a learner characteristic tree and a learning environment tree.

As shown in fig. 7, the specific steps of the dual context matching are as follows:

(48) and determining the resource context which is most matched with the current learning context CL according to the matching degree sorting result.

The specific process of establishing the node mapping of the resource context tree and the learning context tree in the step (42) is as follows:

(421) traversing the situation ontology tree Q, numbering all nodes of the Q according to a traversal sequence, outputting a binary array QAlry of the nodes of the Q, and respectively storing node names and node numbers;

(422) matching one node in the learning context ontology tree CL as CL with the node name in Qarry, finding out the only one node which is matched with CL and exists in Qarry, storing the serial number of the node and the CL node name into a mapping array CLArry of the CL, and circulating all the nodes in the CL to obtain the most CL mapping array CLArry;

(423) processing the resource context ontology tree CR in the same way as the step (22) to obtain a mapping array CRAlry of the CR;

(424) and matching the node numbers in the CLArry array units and the CRAlry array units, and finding two corresponding arrays with the same node numbers to obtain the nodes corresponding to the CL and the CR.

In the step (44), two methods are generally adopted for calculating the node similarity: when the two node concepts are completely consistent, a general attribute similarity calculation method can be adopted, and when the two node concepts have semantic similarity, a semantic similarity calculation method is required. Because the knowledge points and the learning interests are related to certain knowledge concepts and fields, the similarity between three nodes of the knowledge points, the learning interests and the basic knowledge in the resource context tree and the corresponding nodes in the learning context tree needs to be calculated by a method of semantic similarity, and the similarity of other nodes can be calculated by a method of cosine similarity calculation.

In the step (45), since the resource context tree is composed of a plurality of sub-trees (sub-contexts), for example, five top sub-trees including a teaching context tree, a learner context tree, an equipment context tree, an environment context tree and a spatio-temporal context tree, the similarity between each sub-context tree and the corresponding sub-tree in the learning context is calculated to determine the matching degree between each sub-context and the learning context requirement, so as to provide a data basis for the resource context sequencing of the next step. The concrete implementation process of the resource context tree similarity calculation is as follows: the calculation can adopt a bottom-up method, namely on the basis of the similarity of the leaf nodes corresponding to the resource context tree and the learning context tree, the similarity of the corresponding parent node is obtained by calculating the accumulation sum or the weighted accumulation sum of the similarity of the leaf nodes, and by analogy, the similarity of five subtree root nodes in the resource context tree and the nodes in the corresponding learning context tree can be respectively obtained finally, namely the similarity of the resource context tree is used.

The father node with the child node is called a non-leaf node, and the influence of different resource situation elements on effective play of resources is different, so that the similarity of the non-leaf node in the situation tree is calculated by adopting a common weighting accumulation sum mode at present, and a formula is shown as a formula (6):

wherein CR is a non-leaf node in the resource context tree CR, and CR has M child nodes CR₁,cr₂,…,cr_MCL is a non-leaf node in the learning context tree CL, and CL has M child nodes CL₁,cl₂,…,cl_MSim (cr, cl) denotes the similarity of cr and cl,w_irepresents the weight of the ith child node, and

the weight of the usage frequency defines the policy: in the weighted sum-and-accumulate calculation method, the design of the weight often has an important influence on the result, and actually, the influence degree of each situation element on the situation is difficult to know, so the weight of each situation node is difficult to determine. Because the invention screens the resource situation and calculates the similarity of the top subtree of the resource situation tree, the invention calculates the weight of each child node of the resource situation tree to the parent node thereof by using the weight definition strategy based on the use frequency and provided by Guo tree row and the like, and takes the weight as the weight w in the formula_i。

The specific idea of determining the weight of each child node to a parent node in a resource context tree based on the weight definition strategy of the use frequency is as follows:

(451) using frequency calculator U for any node cr in resource context ontology tree_cr；

(452) If cr is a leaf node of the resource context ontology tree, U_crIs 1, and if cr is a non-sub-leaf node, the frequency calculator U_crThe initial value of (a) is the number of non-root nodes N ═ numoftree (cr) -1 of the subtree with cr as the root node;

(453) when a resource creator labels a resource context for a certain learning resource, if the creator labels an attribute value for cr, the U is labeled_crAccumulating for 1;

(454) along with the attention of all resource creators to different attribute nodes when marking resource situations in the system, the use frequency of each node in the resource situation body is gradually accumulated, so that the use frequency distribution of the resource situation nodes is gradually formed, the weight of each node in the resource situation tree relative to the parent node thereof can be calculated by utilizing the frequency distribution, and the formula is shown as the formula (7):

wherein, cr_iThe ith child node representing cr,

denotes cr_iFrequency value, cr_jThe jth child node representing cr,

denotes cr_jFrequency value, N denotes the number of child nodes of cr, w_iRepresents the weight of the cr ith child node, and

in the step (47), the concrete implementation process of the resource context ordering based on the context inference rule is as follows:

different sub-contexts in the resource context have different effects on the utility of the learning resource. Some situations relate to whether the learning resources meet the subjective requirements of the learner, such as teaching situations, some situations relate to whether the learning resources meet objective requirements, such as equipment situations and space-time situations, and some situations relate to optimizing the use effects of the learning resources, such as learner situations and environmental situations. Therefore, the judgment of the matching degree between the resource context and the learning context cannot depend only on the similarity between the resource context and the learning context, and needs a certain support of context inference rules.

(471) Context inference rules

The contextual inference rules may be classified into filtering rules, user preference rules, and optimization selection rules. The filtering rule refers to directly eliminating the situation which does not meet a certain condition, the user preference rule represents the subjective intention of the current user on selection, and the optimization selection rule refers to further obtaining the optimal result by meeting a certain condition on the basis of meeting the filtering rule and the user preference rule. According to the action of the three types of rules, the priority of the three types of rules is from high to low, namely the filtering rule, the user preference rule and the optimization selection rule.

In the invention, aiming at the condition that the resource situation is composed of five sub-situations of a teaching situation tree, a learner situation tree, an equipment situation tree, an environment situation tree and a space-time situation tree, the influence of different sub-situations on the resource utility is considered, and a situation inference rule for situation sequencing is set, as shown in table 1:

TABLE 1 reasoning rules for situation ordering

(472) Resource situation ordering method based on situation inference rule

On the basis of the similarity between the top subtree of the resource situation and the subtree corresponding to the learning situation, the resource situations in the resource situation library can be sequenced by using the situation inference rule, so that the resource situation which is most matched with the current situation is obtained. The method for sequencing the resource situations according to the inference rule mainly comprises the following steps:

(5) And dynamically aggregating the learning elements in the resources according to the obtained resource situation.

As shown in fig. 8, two levels of resource aggregation are designed.

(51) Relevant resource sets capable of supporting current situational learning are screened out from a massive learning resource library to help learners to quickly know and acquire resources which are helpful to learners in the environment.

There are three cases of such resource aggregation: first, learners have no specific learning objective, i.e. aggregation is performed without considering teaching situations; secondly, the learner does not care whether the digitalized learning resources are related to the surrounding entity resources, namely, the spatial situation is not considered during aggregation; third, learners have specific learning objectives and need digital learning resources associated with the physical resources available in the surrounding environment, i.e., they need to consider both teaching and spatial contexts in the aggregate, if the learner wishes to learn the relevant knowledge by observing the surrounding physical resources (plants).

(52) And aiming at a single learning resource, dynamically aggregating learning elements in the learning resource according to the current situation, so that the learning resource presents the most appropriate resource form in a self-adaptive manner under different situations.

As shown in fig. 9, the aggregation of the resource internal learning elements is realized by using the resource context and the associated information contained in the resource and the result of the dual-context matching of "resource context-learning context", which specifically includes the following steps:

(521) the context perception module acquires a current ubiquitous learning context C1 and transmits the current ubiquitous learning context C1 to the resource aggregation module;

(522) the resource aggregation module performs double-context matching on the ubiquitous learning context C1 and the resource contexts in the resource context library;

(523) as a result of the two-scenario matching, if the resource scenario that matches best with the ubiquitous learning scenario C1 is C2, the learning elements (learning content, learning activities and relevant learners) associated with C2 in the learning resources are aggregated, and the resource form formed by aggregating these learning elements is presented to the learner, i.e. the resource form that matches best with the current scenario of the learning resources.

Taking the learning resource for introducing the related knowledge of the plant murraya jasminorage as an example, the polymorphism comprehensive learning resource aggregation method for integrating the situations is used for learning.

1. According to the situation that the learning resources can exert the effectiveness, resource situation labeling is carried out on each learning element in the resources, and learner situation attributes, teaching situation attributes, space-time situation attributes and the like which are suitable for different learning content segments in the learning resources are determined. As shown in fig. 10, the learning resources include basic information, morphological characteristics, ecological habits, reproduction methods of murraya paniculata, and prior knowledge (flower structure and leaf structure) required for learning the morphological characteristics of murraya paniculata. In fig. 10, ovals are shown as knowledge points, diamonds are shown as associated learning activities, and smaller circles are shown as associated learners.

2. Sensing the specific learning situation of the learner in the ubiquitous learning environment;

in this example, the learner is divided into three groups, respectively in scenario A, B, C, wherein the three scenarios are consistent in learning context, learning device context, and spatio-temporal context, except for learning requirement and learner context difference.

Situation A: learning the target, learning the appearance characteristics of the murraya paniculata; the learner, had no basic knowledge of the leaves and flowers.

Situation B: learning the target, learning the ecological habit of murraya paniculata; learners have mastered the basic knowledge of leaves and flowers.

Situation C: learning the target, learning the appearance characteristics of the murraya paniculata; learners have mastered the structure of flowers and not mastered the structure of leaves.

3. And matching the learning context with the resource context, thereby obtaining the resource context matched with the current learning context.

For the situation A, a resource situation matched with the situation A is found in a resource situation library, learning contents (basic information, morphological characteristics and flower structures and leaf structures (prerequisite knowledge)) and learning activities matched with the resource situation are presented to the learner, and related learners who have learned the resource under the same or similar situations with the situation A are screened out from the related learners and presented to the learner.

Similarly, for scenario B, the learning content (basic information, ecological habit) and learning activity associated with the resource scenario matching scenario B are presented to the current learner, and meanwhile, relevant learners who have learned the resource under the same or similar scenario as scenario B are screened from relevant learners and presented to the current learner.

For the situation C, the learning content (basic information, morphological characteristics and leaf structure) and learning activity associated with the resource situation matched with the situation C are presented to the learner, and meanwhile, relevant learners who have learned the resource under the same or similar situation with the situation C are screened from the relevant learners and presented to the current learner.

4. And dynamically aggregating the learning elements in the resources according to the obtained resource situation.

The final result from the two-context matching is shown in FIG. 10.

The aggregate resources in situation a are basic information, appearance features, prior knowledge (leaf structure, flower structure) of murraya paniculata, and also contains relevant learners in a similar way to situation a.

The aggregate resource in situation B is the basic information, ecological habit of murraya paniculata, and also includes related learners similar to situation B.

The aggregated resources in situation C are basic information, appearance features, pre-knowledge (leaf structure) of murraya paniculata, and also contains relevant learners in a similar way to situation C.

It will be understood by those skilled in the art that the foregoing is merely a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included within the scope of the present invention.

Claims

1. A polymorphism ubiquitous learning resource aggregation method for integrated situations is characterized by comprising the following steps of:

(5) aggregating learning elements in the learning resources, which are associated with the resource situation obtained by matching;

wherein, the step (4) of matching the learning context with the resource context, so as to obtain the resource context matched with the current learning context comprises the following specific processes:

2. The method of claim 1, wherein the step (1) of creating a learning resource comprising at least learning content, related learners, and a plurality of internal learning elements of learning activities comprises the following steps:

3. The method for aggregating polymorphism ubiquitous learning resources in context integration according to claim 1, wherein the step (2) of performing context labeling of resource for each learning element in the resource according to the context in which the learning resource can exert utility comprises:

(21) resource context initialization: when a resource is created, after a creator creates certain learning content, manually marking partial attribute values of a resource context related to the learning content according to a resource context marking support, wherein the partial attribute values comprise learner context attributes, teaching context attributes, equipment context attributes and space-time context attributes, and providing some auxiliary information to support automatic marking of a system; according to the auxiliary information provided by the creator, automatically marking the rest attribute values of the resource situation by combining with a preset recommendation rule, thereby completing the initialization of the resource situation and storing the resource situation information into a resource situation library; the resource context of the learning content also automatically becomes the resource context of the learning activity associated with the learning content;

(22) and (3) dynamically updating the resource context: after the learning element is used in a certain situation, judging whether the situation exists in the resource situation library of the learning resource, if not, considering the situation as a new application situation of the learning resource, and storing the new application situation into the resource situation library, thereby realizing the dynamic update of the resource situation.

4. The method of claim 1, wherein the step (3) of sensing the specific learning context in which the learner is in the ubiquitous learning environment comprises:

(31) defining the situation elements of the ubiquitous learning, and dividing the situation elements of the ubiquitous learning into: learning needs, learner context, learning environment context, learning equipment context, and spatiotemporal context;

5. The method for aggregating polymorphism ubiquitous learning resources according to claim 1, wherein the context inference rules are classified into filtering rules, user preference rules, and optimal selection rules, and the filtering rules, the user preference rules, and the optimal selection rules are sequentially assigned to the context inference rules from high priority to low priority;

the specific implementation process of the step (47) is as follows:

6. A system for aggregating polymorphic ubiquitous learning resources for integrated context, comprising:

a first module for creating a learning resource comprising at least a learning content, a relevant learner, a plurality of internal learning elements of a learning activity;

a sixth module, configured to aggregate learning elements associated with the resource context obtained by matching in the learning resources;

wherein the fifth module comprises:

7. The system of claim 6, wherein the first module is configured to create learning resources with components including learning content, learning activities, relevant learners, resource context, association information, and context interfaces; wherein, the learning content, the learning activities and the related learners can directly provide information and support for learning, which are collectively called learning elements and are aggregation objects of resource aggregation; the resource situation, the associated information and the situation interface are important conditions for supporting resource aggregation and belong to supportability elements; when a resource creator creates learning resources, two main learning elements, namely learning content and learning activity, are created, and corresponding association between the learning activity and the learning content is established; the resource creator automatically becomes one of the learners related to the resource; after the resource is created, learners, subscribers, editors and domain experts related to the resource in the system become relevant learners of the resource.

8. The system of claim 6, wherein the second module comprises: