Interoperation model of intelligent teaching system based on subject knowledge graph

Abstract

The application provides an intelligent teaching system interoperability model based on a subject knowledge graph by extending the SCORM specification, and comprises the following sub-models: sub-model 1, a structure framework of the subject knowledge graph; sub-model 2, a sharable intelligent content object KCO based on the subject knowledge graph; sub-model 3, a KCO runtime environment conforming to the SCORM specification; and sub-model 4, a KCO content packaging model KCOCP conforming to the SCORM specification. The application takes the subject knowledge graph as a knowledge base, and extends the content model of the SCORM specification from a multimedia-based structured courseware to intelligent learning content combined with the subject knowledge graph, so that the overall intelligence of the teaching system conforming to the SCORM specification can be greatly improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of the cross of artificial intelligence and education technology, and particularly relates to an intelligent teaching system interoperation method based on a subject knowledge graph. BACKGROUND

[0002] In recent years, with the continuous online of Google knowledge graph related products, the knowledge graph technology has attracted widespread attention from the industry and academia, has become one of the key technologies for the transformation and upgrading of various industries from network to intelligence, and has also provided a new technical means for the core problem of domain knowledge modeling in the intelligent teaching system. Therefore, constructing the knowledge graph in the education field has become an important research topic for the development of the intelligent teaching system. At present, the most typical international intelligent teaching system technical specification is the SCORM specification included in the ISO standard system, which has obtained the support of many software platforms including Adobe. However, the domain knowledge mode of the SCORM specification only uses a student-oriented structured courseware, and does not introduce a subject expert model based on a domain knowledge graph. Only a self-adaptive teaching expert system based on structured courseware and production rules is realized, which can provide personalized teaching for learners, and the overall intelligence is not high. Therefore, how to integrate the subject knowledge graph into the SCORM specification and construct a more efficient and intelligent intelligent teaching system interoperation model has become one of the key technologies for accelerating the application of the education knowledge graph in the intelligent teaching system.

[0003] The present application proposes a sharable and automatically inferable intelligent content object KCO based on subject knowledge graph on the basis of SCO sharable content object of ADL. The KCO is a special SCO content object, which can communicate with the learning management system (LMS) during the running process and access the subject knowledge graph and its intelligent teaching function in a unified manner, thereby moving and inter-operating among heterogeneous learning management systems. Then, the ADL / SCORM specification is extended to form an inter-operation model KCOIM of the KCO intelligent content object, including: (1) taking the proposed general model of subject knowledge graph as the subject knowledge model in the SCORM specification; (2) extending the API method in the SCORM specification running environment to enable the subject knowledge graph and its intelligent function to be queried; (3) adding a knowledge graph CKG and its associated learner cognitive state LCS two-level data structure in the communication data model of the SCORM specification running environment, which is used to encapsulate the design details of the subject knowledge graph and the learner model; (4) adding a subject graph section in the content aggregation model of the SCORM specification, so that the same intelligent content object KCO can be associated with different subject knowledge graphs. Finally, the content model of the SCORM specification is extended from the multimedia-based structured courseware to the intelligent learning content integrating the subject knowledge graph, which makes it possible to inter-operate the learning content and learning sequence based on the knowledge graph, and greatly improves the overall intelligence of the teaching system conforming to the SCORM specification. SUMMARY

[0004] The present application discloses an intelligent teaching system inter-operation model based on subject knowledge graph, characterized by comprising the following sub-models:

[0005] Sub-model 1. Structure framework of subject knowledge graph: used to support intelligent teaching, which specifically includes: (1) conceptual schema, (2) content schema, (3) knowledge schema, (4) cognitive schema, and (5) structure definition of relationship;

[0006] Sub-model 2. Sharable intelligent content object KCO based on subject knowledge graph: a special SCO sharable content object in the SCORM specification, which can communicate with the learning management system LMS during the running process, and the KCO is extended to access the subject knowledge graph and its intelligent teaching function in a unified manner, thereby being able to design adaptive learning content according to the ability and performance of learners;

[0007] Submodel 3. KCO runtime environment conforming to SCORM specification: including a knowledge map communication data structure encapsulating the design details of the subject knowledge map, a learner cognitive state communication data structure encapsulating the design details of the learner model, and a set of distributed query communication interfaces for the subject knowledge map, which are used by the KCO object to access the subject knowledge map in a unified manner; the learner model is based on the concept schema in the subject knowledge map, and the concepts in the concept schema are used as the examination points of the subject knowledge in the learner model;

[0008] Submodel 4. KCO content packaging model KCOCP conforming to SCORM specification: used to define the KCO object-based, interoperable content structure, and to describe the content list file conforming to SCORM specification using extensible markup language XML, requiring that the KCO does not specify the operated subject knowledge map in the design stage, and postponing the association of the KCO with the subject knowledge map it operates in the content packaging list until the runtime;

[0009] The SCORM specification is the Sharable Content Object Reference Model.

[0010] Further, the specific features of the submodel 1 are:

[0011] (1) The concept schema is used to reflect the concept, concept synonym, and concept classification structure in the subject field, and is composed of the synonym set of the concept and the "is-a" classification graph, which is a constraint model of the subject knowledge map, and can provide concept association for the content schema, knowledge schema, and cognitive schema;

[0012] (2) The content schema is used to reflect multimedia teaching content, which is composed of media relationships, and the media targets include multimedia teaching content units of documents, pictures, animations, videos, and KCO objects, which explain the knowledge of a certain aspect of the concept in the form of documents, animations, and videos;

[0013] (3) The knowledge schema is used to reflect the subject knowledge of the concept, which is composed of semantic relationships and attribute relationships of the concept, wherein the concept semantic relationship is used to reflect the relationship between concepts in the subject field, and the attribute relationship is used to reflect the relationship between the concept and the attribute entity, and the attribute entity refers to data reflecting the characteristics of the concept, including text, time, and numerical value;

[0014] (4) The cognitive schema is used to reflect the learning order relationship between concepts, which is composed of "predecessor" relationship and "successor" relationship;

[0015] (5) The structure definition of the relationship, characterized in that: the relationship in the subject knowledge map is defined as a four-tuple separated by a diagonal slash " / ":

[0016] <relationship>:=<discipline name> / <concept set> / <relationship name> / <target type>

[0017] Among them, "discipline name" indicates the subject field to which the relationship belongs; "concept set" is used to give the definition domain of the relationship, indicating the scope of concepts with defined relationships. If all concepts have defined relationships, "ontology" is used to represent the concept set of the relationship; "relationship name" indicates the name of the relationship, which is named using verbs, nouns and noun phrases; "target type" is used to give the value domain of the relationship, indicating the type of knowledge to which the relationship points, and the values ​​are five target types: "concept", "attribute", "static content", "dynamic content" and "KCO object". Among them, "concept" indicates that the relationship points to the concept in the concept schema, "attribute" indicates that the relationship points to the data entity of text, time and value, "static content" indicates that the relationship points to the web-type teaching content mixed with text and pictures, "dynamic content" indicates that the relationship points to the teaching content of animation and video files, and "KCO object" indicates that the relationship points to a shareable intelligent content object.

[0018] Furthermore, the specific structure of the sub-model 2 is: A KCO content object at least includes an API adapter object for locating the LMS, an initialization API call Initialize() for establishing a dialogue with the teaching system and a termination API call Terminate() for ending the dialogue, as well as API calls GetValue() and SetValue() for accessing the subject knowledge graph. The API is the abbreviation of application programming interface.

[0019] Furthermore, the sub-model 3 specifically includes:

[0020] Sub-model 3.1 Knowledge Graph Communication Data Structure ckg, including communication elements representing the hierarchical structure shown in 1:

[0021] Table 1 Hierarchical data structure of knowledge graph ckg

[0022]

[0023] Sub-model 3.2, the communication data structure lcs of the learner’s cognitive state, includes the communication elements of the hierarchical structure shown in Table 2:

[0024] Table 2 Hierarchical data structure of learner cognitive state LCS

[0025]

[0026] Sub-model 3.3 Distributed query communication interface of subject knowledge graph: extends the functions of the six API methods in the SCORM specification, including:

[0027] (1) Initialize ( ) : extended to be able to activate the learning system LMS to realize the initialization of the communication dialogue with the KCO object, including creating a knowledge graph communication data structure ckg and a learner cognitive state communication data structure lcs for the communicating KCO object on the server side, the interface format is: return_value = Initialize (parameter), wherein the parameter parameter is an empty string, and the return value return_value is a logical value "true" or "false", indicating whether the initialization of the communication dialogue is successful;

[0028] (2) Terminate ( ) : extended to be able to end the communication dialogue of a KCO object, including releasing the knowledge graph communication data structure ckg and the learner cognitive state communication data structure lcs established for the KCO object, the interface format is: return_value = Terminate (parameter), wherein the parameter parameter is an empty string, and the return value return_value is a logical value "true" or "false", indicating whether the end of the communication dialogue is successful;

[0029] (3) SetValue ( ) : extended to be able to realize the KCO object setting the communication data elements in ckg and lcs, the interface format is: return_value = SetValue (parameter1, parameter2), wherein parameter1 is the first string parameter, indicating the communication data element to be set in ckg and lcs, parameter2 is the second string parameter, indicating the value passed to the communication data element specified by parameter1, and the return value return_value is a logical value "true" or "false", indicating whether the setting is successful;

[0030] (4) GetValue ( ) : extended to be able to pass the value of the specified communication data element in ckg and lcs on the server side to the KCO object on the client side as the query result, the interface format is: return_value = GetValue (parameter), wherein the parameter parameter indicates the communication data element to be queried, and the return value return_value is the query result;

[0031] (5) GetError(): extended to return the error code of the last access to ckg and lcs, the interface format is: return_value = GetError(), where the return value symbol return_value receives the returned error code number;

[0032] (6) GetErrorString(): extended to return the error information corresponding to the error code of the last access to ckg and lcs, the interface format is: return_value = GetErrorString(parameter), parameter parameter is the error code number, and the return value symbol return_value receives the returned error information string.

[0033] Further, the sub-model 4 requires KCO not to specify the subject knowledge graph of the operation in the design stage, and the association of KCO with the subject knowledge graph of the operation in the content package list is delayed until the runtime is completed. The specific implementation method is:

[0034] (1) In the content package model of the SCORM specification, a knowledge graph element is extended <knowledge-graph>, for describing a subject knowledge graph used in a content package;

[0035] (2) In the project element of the content packaging model of the SCORM specification <item>In the embodiment, an optional attribute knowledgeref of an extension of a knowledge graph reference is used to describe the association between the KCO object and the discipline knowledge graph referenced by the KCO object.

[0036] (3) In the resource element of the content packaging model of the SCORM specification <resource>In the middle, an optional attribute kcoimType describing the type of KCO interoperability model is extended and the corresponding attribute value "KCO" is added;

[0037] (4) Extended <knowledge-graph> 、 <item>and <resource>The elements are defined in the XML schema file kcocp.xsd.

[0038] Still further, the extended knowledge graph elements <knowledge-graph>The XML format is as follows:

[0039] (1) Description: <knowledge-graph>elements describe a subject knowledge graph used in content packaging;

[0040] (2) Diversity: <knowledge-graph>Element in content list element <manifest>0 or 1 times;

[0041] (3) attribute identifier: a unique identifier in the content list manifest, must be specified;

[0042] (4) attribute discipline: a string describing the discipline to which the discipline knowledge graph belongs, must be specified;

[0043] (5) attribute href: reference to the entry file of the discipline knowledge graph, must be specified;

[0044] (6) sub-element <metadata>: Metadata describing the subject knowledge graph, optional elements

[0045] (7) Sub-elements <file>: a file list relied on a subject knowledge graph must be specified.

[0046] The present application has the following features and advantages:

[0047] (1) By extending the ADL / SCORM specification, an intelligent teaching system interoperability model based on a subject knowledge graph is formed;

[0048] (2) Under the support of the interoperability model proposed in the present application, the proposed general model of subject knowledge graph can be used as a subject knowledge model in the SCORM specification;

[0049] (3) The API method in the extended SCORM specification running environment is expanded, so that the subject knowledge graph and its intelligent functions can be queried;

[0050] (4) In the communication data model of the SCORM specification running environment, a knowledge graph CKG and its associated learner cognitive state LCS two-level data structure are added, and the design details of the subject knowledge graph and the learner model are encapsulated;

[0051] (5) The content model of the SCORM specification is extended from a multimedia-based structured courseware to an intelligent learning content integrating a subject knowledge graph, which makes it possible to interoperate learning content and learning sequence based on a knowledge graph, and greatly improves the overall intelligence of the teaching system conforming to the SCORM specification. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 is a runtime environment of an intelligent teaching system interoperability model based on a subject knowledge graph;

[0053] Figure 2 is a structural model of a subject knowledge graph;

[0054] Figure 3 is a shareable intelligent content object KCO framework structure based on a subject knowledge graph;

[0055] Figure 4 is an extended SCORM / SCOCP content packaging structure schematic diagram. DETAILED DESCRIPTION

[0056] The present application will be further described below in conjunction with specific embodiments and drawings, but the scope of protection of the present application is not limited to the following embodiments.

[0057] An intelligent teaching system interoperability model based on a subject knowledge graph, a runtime environment as shown in Figure 1 characterized in that it comprises the following sub-models:

[0058] Submodel 1. The structure framework of the subject knowledge map: used to support intelligent teaching, which specifically includes: (1) the concept schema, (2) the content schema, (3) the knowledge schema, (4) the cognitive schema, and (5) the structural definition of the relationship;

[0059] Submodel 2. The sharable intelligent content object KCO based on the subject knowledge map: a special SCO sharable content object in the SCORM specification, which can communicate with the learning management system LMS during operation, and the KCO is extended to access the subject knowledge map and its intelligent teaching function in a unified manner, so as to design adaptive learning content according to the ability and performance of the learner;

[0060] Submodel 3. The KCO runtime environment conforming to the SCORM specification: including a knowledge map communication data structure encapsulating the design details of the subject knowledge map, a learner cognitive state communication data structure encapsulating the design details of the learner model, and a set of distributed query communication interfaces of the subject knowledge map, used for the KCO object to access the subject knowledge map in a unified manner; the learner model is based on the concept schema in the subject knowledge map, and the concepts in the concept schema are used as the examination points of the subject knowledge of the learner model;

[0061] Submodel 4. The KCO content packaging model KCOCP conforming to the SCORM specification: used to define the interoperable content structure based on the KCO object, and describe the content list file conforming to the SCORM specification by using the extensible markup language XML, requiring that the KCO does not specify the operated subject knowledge map in the design stage, and the association between the KCO and the subject knowledge map operated by the KCO in the content packaging list is completed at runtime;

[0062] The SCORM specification is the sharable content object reference model.

[0063] Further, the structure model of the submodel 1 is as shown in Figure 2 The specific features are:

[0064] (1) The concept schema is used to reflect the concept, concept synonym, and concept classification structure of the subject field, which is composed of the synonym set of the concept and the "is-a" classification graph, and is the constraint model of the subject knowledge map, which can provide concept association for the content schema, the knowledge schema, and the cognitive schema;

[0065] (2) The content schema is used to reflect the multimedia teaching content, which is composed of media relationships, and the media targets include the multimedia teaching content units of the document, the picture, the animation, the video, and the KCO object, which explain the knowledge of a certain aspect of the concept in the form of the document, the animation, and the video.

[0066] (3) The knowledge schema is used to reflect the subject knowledge of the concept, which is composed of semantic relations and attribute relations of the concept, wherein the semantic relations of the concept are used to reflect the connection between the concepts in the subject field, and the attribute relations are used to reflect the connection between the concept and the attribute entity, the attribute entity refers to the data reflecting the characteristics of the concept, including text, time and numerical value;

[0067] (4) The cognitive schema is used to reflect the learning order relation between the concepts, which is composed of "predecessor" relation and "successor" relation;

[0068] (5) The structure definition of the relation, characterized in that: the relation in the subject knowledge graph is defined as a quadruple separated by a diagonal slash " / " as follows:

[0069] <relation> := <subject name> / <concept set> / <relation name> / <target type>

[0070] Wherein, "subject name" indicates the subject field to which the relation belongs; "concept set" is used to give the definition domain of the relation, indicating the range of concepts with the defined relation, if all concepts have the defined relation, "ontology" is used to represent the concept set of the relation; "relation name" indicates the name of the relation, which is named using verbs, nouns and noun phrases; "target type" is used to give the value domain of the relation, indicating the knowledge type pointed to by the relation, taking values of "concept", "attribute", "static content", "dynamic content" and "KCO object" five target types, wherein "concept" indicates that the relation points to the concept in the concept schema, "attribute" indicates that the relation points to the data entity of text, time and numerical value, "static content" indicates that the relation points to the web type teaching content mixed with text and pictures, "dynamic content" indicates that the relation points to the teaching content of animation and video file, and "KCO object" indicates that the relation points to a shareable intelligent content object.

[0071] Further, the specific model structure of the submodel 2 is that a KCO content object at least contains an API adapter object for positioning the LMS, an initialization API call Initialize() for establishing a dialogue with the teaching system and a termination API call Terminate() for ending the dialogue, and contains API calls GetValue() and SetValue() for accessing the subject knowledge graph, as shown in Figure 3 .

[0072] Further, the submodel 3 specifically includes:

[0073] Submodel 3.1 knowledge graph communication data structure ckg, including the hierarchical structure of the communication elements as shown in representation 1:

[0074] Table 1 Hierarchical data structure of knowledge graph ckg

[0075]

[0076] The sub-model 3.2 learns the communication data structure of the learner cognitive state LCS, including the hierarchical communication elements shown in Table 2:

[0077] Table 2 Hierarchical data structure of the learner cognitive state LCS

[0078]

[0079] The sub-model 3.3 is a distributed query communication interface of the subject knowledge graph, which extends the functions of the six API methods in the SCORM specification, including:

[0080] (1) Initialize (): extended to be able to activate the learning system LMS to realize the initialization of the communication dialogue with the KCO object, including creating a knowledge graph communication data structure ckg and a learner cognitive state communication data structure lcs for the KCO object on the server side, the interface format is: return_value = Initialize (parameter), where the parameter parameter is an empty string, and the return value return_value is a logical value "true" or "false", indicating whether the initialization of the communication dialogue is successful;

[0081] (2) Terminate (): extended to be able to end the communication dialogue of a KCO object, including releasing the knowledge graph communication data structure ckg and the learner cognitive state communication data structure lcs established for the KCO object, the interface format is: return_value = Terminate (parameter), where the parameter parameter is an empty string, and the return value return_value is a logical value "true" or "false", indicating whether the end of the communication dialogue is successful;

[0082] (3) SetValue (): extended to be able to realize the setting of the communication data elements in ckg and lcs by the KCO object, the interface format is: return_value = SetValue (parameter1, parameter2), where parameter1 is the first string parameter, indicating the communication data element to be set in ckg and lcs, parameter2 is the second string parameter, indicating the value passed to the communication data element specified by parameter1, and the return value return_value is a logical value "true" or "false", indicating whether the setting is successful;

[0083] (4) GetValue(): extended to pass the value of the specified communication data element in the ckg and lcs to the client as the query result, the interface format is: return_value = GetValue(parameterl, parameter2), where parameterl represents the communication data element to be queried, parameter2 is a variable name in the KCO object receiving the query result, and the return value return_value is a logical value "true" or "false", indicating whether the query is successful;

[0084] (5) GetLastError(): extended to return the error code of the last access to the ckg and lcs, the interface format is: return_value = GetError(), where the return value symbol return_value receives the returned error code number;

[0085] (6) GetErrorString(): extended to return the error information corresponding to the error code of the last access to the ckg and lcs, the interface format is: return_value = GetErrorString(parameter), where parameter is the error code number, and the return value symbol return_value receives the returned error information string.

[0086] Further, the sub-model 4 requires KCO not to specify the subject knowledge graph of the operation in the design stage, and the association of KCO with the subject knowledge graph of the operation in the content package list is delayed until the runtime, and the specific implementation method is:

[0087] (1) In the content package model of SCORM specification, an extended knowledge graph element <knowledge-graph>, for describing a subject knowledge graph used in a content package;

[0088] (2) In the project element of the content packaging model of the SCORM specification <item>In the embodiment, an optional attribute knowledgeref of an extension of a knowledge graph reference is used to describe the association between the KCO object and the discipline knowledge graph referenced by the KCO object.

[0089] (3) In the resource element of the content packaging model of the SCORM specification <resource>In the middle, an optional attribute kcoimType describing the type of KCO interoperability model is extended and the corresponding attribute value "KCO" is added;

[0090] (4) Extended <knowledge-graph> 、 <item>and <resource>The elements are defined in the XML schema file kcocp.xsd.

[0091] Still further, the extended knowledge graph elements <knowledge-graph>The XML format is as follows:

[0092] (1) Description: <knowledge-graph>elements describe a subject knowledge graph used in content packaging;

[0093] (2) Diversity: <knowledge-graph>Element in content list element <manifest>0 or 1 times;

[0094] (3) attribute identifier: a unique identifier in the content list manifest, which must be specified;

[0095] (4) attribute discipline: a string describing the discipline to which the discipline knowledge graph belongs, which must be specified;

[0096] (5) attribute href: a reference to the entry file of the discipline knowledge graph, which must be specified;

[0097] (6) sub-element <metadata>: Metadata describing the subject knowledge graph, optional elements

[0098] (7) Sub-elements <file>: The file list on which the subject knowledge graph depends must be specified.

[0099] Application Example

[0100] In the KCOCP of the KCOIM content packaging model of the present application example, the extended <knowledge-graph>An XML format for describing the subject knowledge graph used in the content package is as follows:

[0101] <knowledge-graph>Element

[0102] Description: This element describes the subject knowledge graph used in the content package.

[0103] Diversity: This element is in <manifest>0 or 1 times.

[0104] Attributes:

[0105] identifier (required). A unique identifier within the manifest.

[0106] discipline (required). A string describing the discipline to which the knowledge graph belongs.

[0107] href (required). A reference to the entry file of the knowledge graph.

[0108] Sub-elements:

[0109] <metadata>(Optional): Metadata describing the subject knowledge graph.

[0110] <file>(Optional): List of files on which this discipline knowledge graph depends. This element needs to be repeated for each file of the given ontology. <file>Elements that represent files local to the content package via the href attribute.

[0111] In the KCOIM content packaging model KCOCP of the present application instance, the association between a KCO object and the discipline knowledge graph it references is in the content manifest <organization>hierarchy sub-element <item>To achieve this association, this example is the content packaging model of the SCORM specification. <item>The element adds a knowledgeref optional attribute. In addition, in order to identify our proposed KCO content object in the "Resource" section of the content manifest, we add a new "KCO" section to the content manifest as follows: <resource>An element extends a property kcoimType and a corresponding property value "KCO". Finally, all extended elements are defined in an XML schema file kcocp.xsd, which contains a hypothetical schema namespace "http: / / ***.***.*** / xsd / icocp_v1p0", thus extending the structure of SCORM content package SCOCP from a three-layer structure to a four-layer structure, as shown in Figure 4

[0112] In the present application example, it is assumed that an intelligent answering system based on a certain subject knowledge graph has been designed, and the Web homepage of the answering system is Answer.html. By applying the above KCO content packaging model designed by us, the intelligent answering system is identified as a Q&A KCO object, and it is associated with a computer subject knowledge graph composed of kg1.date, kg2.date and kg3.date three files. The corresponding content packaging manifest file is as shown below:

[0113] .​< / resource> < / item> < / item> < / organization> < / file> < / file> < / metadata> < / manifest> < / file> < / metadata> < / manifest> < / resource> < / item> < / knowledge-graph> < / resource> < / item> < / file> < / metadata> < / manifest> < / resource> < / item> < / knowledge-graph> < / resource> < / item>

Claims

1. The interoperability model of intelligent teaching system based on subject knowledge graph is characterized by Includes the following sub-models: Sub-model 1. Structural framework of subject knowledge graph: used to support intelligent teaching, the framework specifically includes: (1) concept schema, (2) content schema, (3) knowledge schema, (4) cognitive schema, and (5) structural definition of relationships; Sub-model 2. Subject Knowledge Graph-based Shareable Intelligent Content Object (KCO): This is a special SCO shareable content object in the SCORM specification. It can communicate with the Learning Management System (LMS) during operation. KCO is also extended to uniformly access the subject knowledge graph and its intelligent teaching functions, enabling the design of adaptive learning content based on learners' abilities and performance. Sub-model 3. A SCORM-compliant KCO runtime environment: This includes a knowledge graph communication data structure that encapsulates the design details of the subject knowledge graph, a learner cognitive state communication data structure that encapsulates the design details of the learner model, and a set of distributed query communication interfaces for the subject knowledge graph, allowing KCO objects to access the subject knowledge graph in a unified manner. The learner model is based on the concept schema in the subject knowledge graph, with concepts in the concept schema serving as assessment points for the subject knowledge in the learner model. Sub-model 4. SCORM-compliant KCO Content Packaging Model (KCOCP): This model defines an interoperable content structure based on KCO objects. It uses XML to describe SCORM-compliant content manifest files. It requires that KCOs do not specify the subject knowledge graphs they operate on during the design phase and defers the association of KCOs with the subject knowledge graphs they operate on in the content packaging manifest until runtime. The concept schema is used to reflect subject domain concepts, concept synonyms, and concept classification structure. It is composed of a concept synonym set and an "is-a" classification diagram. It is a constraint model for the subject knowledge graph and can provide concept associations for content schemas, knowledge schemas, and cognitive schemas. The content schema is used to reflect multimedia teaching content and is composed of media relationships. Media targets include documents, pictures, animations, videos, and multimedia teaching content units with KCO objects. Knowledge of a certain aspect of a concept is explained through documents, animations, and videos that are mixed with pictures and texts. The knowledge schema is used to reflect the subject knowledge of concepts and is composed of semantic relationships and attribute relationships of concepts. Concept semantic relationships are used to reflect the connection between concepts in the subject field, and attribute relationships are used to reflect the connection between concepts and attribute entities. The attribute entities refer to data that reflects the characteristics of concepts, including text, time, and numerical values. The cognitive schema is used to reflect the learning order relationship between concepts, which is composed of "predecessor" relationship and "successor" relationship; The SCORM specification is the Sharable Content Object Reference Model.

2. The interoperability model of the intelligent teaching system based on the subject knowledge graph according to claim 1 is characterized by: The specific features of the sub-model 1 are: The structural definition of the relationship is characterized in that the relationship in the subject knowledge graph is defined as a four-tuple separated by a slash " / ": <relationship>:=<discipline name> / <concept set> / <relationship name> / <target type> Among them, "Discipline Name" indicates the subject area to which the relationship belongs; "Concept Set" is used to give the definition domain of the relationship, indicating the range of concepts with defined relationships. If all concepts have defined relationships, "Ontology" is used to represent the concept set of the relationship; "Relationship Name" indicates the name of the relationship, which is named using verbs, nouns, and noun phrases; "Target Type" is used to give the value domain of the relationship, indicating the type of knowledge the relationship points to, and its values ​​are "Concept", "Attribute", "Static Content", "Dynamic Content", and "KCO Object". Among them, "Concept" indicates that the relationship points to a concept in the concept schema; "Attribute" indicates that the relationship points to data entities such as text, time, and numerical values; "Static Content" indicates that the relationship points to web-type teaching content mixed with text and images; "Dynamic Content" indicates that the relationship points to teaching content such as animation and video files; and "KCO Object" indicates that the relationship points to a shareable intelligent content object.

3. The interoperability model of the intelligent teaching system based on subject knowledge graph according to claim 2 is characterized by: The specific structure of the sub-model 2 is: A KCO content object at least includes an API adapter object for locating the LMS, an initialization API call Initialize() for establishing a dialogue with the teaching system and a termination API call Terminate() for ending the dialogue, as well as API calls GetValue() and SetValue() for accessing the subject knowledge graph. The API is the abbreviation of application programming interface.

4. The interoperability model of the intelligent teaching system based on subject knowledge graph according to claim 3 is characterized by: The sub-model 3 specifically includes: Sub-model 3.1 Knowledge Graph Communication Data Structure ckg: includes the following hierarchical communication elements: (1) Query concept element cmi.ckg.concept: represents the concept currently queried by the KCO object, with access rights: W+R, where the symbol "cmi" stands for Computer Managed Instruction, "ckg" represents the knowledge graph communication data structure, "concept" represents the concept, "W" represents write permission, which means that the KCO object can set the value of the element, "R" represents read permission, which means that the KCO object can query the value of the element, and "." represents a hierarchical structure; (2) Concept attribute set element cmi.ckg.concept.attributeSet: represents the attribute set of the current query concept, access right: R, where the symbol "attributeSet" represents the attribute set; (3) Concept attribute element cmi.ckg.concept.attribute: represents the current query attribute of the current query concept, access rights: W+R, where the symbol "attribute" represents the attribute; (4) Concept attribute value element cmi.ckg.concept.attribute.hasValu: indicates the value of the current query attribute, access right: R, where the symbol "hasValue" indicates the value; (5) Concept relation set element cmi.ckg.concept.relationSet: represents the relation set of the current query concept, with access right: R, where the symbol "relationSet" represents the relation set; (6) Concept relation element cmi.ckg.concept.relation: represents the current query relation of the current query concept, with access rights: W+R, where the symbol "relation" represents a relation; (7) Concept relation target element cmi.ckg.concept.relation.target: represents the target of the current query relation, access right R, where the symbol "target" represents the target; (8) Concept instance set element cmi.ckg.concept.instanceSet: represents the instance set of the current query concept, access right: R, where the symbol "instanceSet" represents the instance set; (9) Concept synonym set element cmi.ckg.concept.synonymSet: represents the synonym set of the current query concept, access right: R, where the symbol "synonymSet" represents the synonym set; (10) The direct superordinate element of the concept cmi.ckg.concept.parents: represents the direct superordinate set of the current query concept, with access rights: R, where the symbol "parents" represents the direct superordinate set; (11) The direct subordinate set element of the concept cmi.ckg.concept.directHyponymSet: represents the direct subordinate set of the current query concept, with access right: R, where the symbol "directHyponymSet" represents the direct subordinate set; (12) Conceptual relationship interference set element cmi.ckg.concept.relation.disturbSet: represents the interference set of a concept relationship, where the interference is a relationship that is easily confused with the specified target relationship. Access right: R, where the symbol "disturbSet" represents the interference set; (13) Next learning concept element cmi.ckg.concept.nextConcept: represents the subsequent learning concept of the current query concept, access right: R, where: the symbol "nextConcept" represents the next concept; (14) The root node element cmi.ckg.root of the is-a classification structure: represents the root node of the is-a classification structure of the subject knowledge graph, with access right R, where the symbol "root" represents the root node of the is-a classification structure; (15) All lower-level elements of the root node cmi.ckg.root.allHyponymNum: indicates the number of all lower-level nodes of the root node, access permission: R, where the symbol "allHyponymNum" indicates the number of all lower-level nodes; (16) Knowledge graph element cmi.ckg.KnowledgeGraph: represents the knowledge graph of the current query, access permission: R, where the symbol "KnowledgeGraph" represents the knowledge graph; (17) The discipline element cmi.ckg.KnowledgeGraph.discipline of the knowledge graph: represents the discipline of the knowledge graph currently being queried, with access rights of R, where the symbol "discipline" represents the discipline; Sub-model 3.2 Communication data structure lcs of learner cognitive state: includes the following hierarchical communication elements: (1) Learner element cmi.lcs.learner: represents the current learner, access right: R, where the symbol "lcs" represents the learner cognitive state communication data structure, and "learner" represents the learner; (2) Learner identification code element cmi.lcs.learner.id: represents the identification code of the current learner, access right: R, where the symbol "id" represents the identification code; (3) Learner name element cmi.lcs.learner.name: represents the name of the current learner, with access rights of W+R, where the symbol "name" represents the name; (4) Current learning concept element cmi.lcs.concept: represents the learner's current learning concept, access right: R, where the symbol "concept" represents the concept; (5) Concept learning assessment score element cmi.lcs.concept.AssessmentScore: represents the assessment score of the current learning concept, access rights: W+R, where the symbol "AssessmentScore" represents the assessment score; (6) Assessment date element cmi.lcs.concept.AssessmentDate for concept learning: indicates the date of assessment of the current learning concept, access rights: W+R, where the symbol "AssessmentDate" indicates the assessment date; (7) Concept cognitive prediction element cmi.lcs.concept.predict: represents the cognitive prediction of the current learning concept, access rights: W+R, where the symbol "predict" represents cognitive prediction; (8) The element cmi.lcs.discipline of the current subject: represents the current subject, with access right: R, where the symbol "discipline" represents the subject; (9) Subject assessment score element cmi.lcs.discipline.AssessmentScore: represents the assessment score of subject learning, access rights: W+R, where the symbol "AssessmentScore" represents the assessment score; (10) Discipline assessment date element cmi.lcs.discipline.AssessmentDate: indicates the date of discipline assessment, access rights: W+R, where the symbol "AssessmentDate" indicates the assessment date; Sub-model 3.3 Distributed query communication interface of subject knowledge graph: extends the functions of the six API methods in the SCORM specification, specifically: (1) Initialize(): It is extended to activate the learning system LMS to initialize the communication dialogue with the KCO object, including creating a knowledge graph communication data structure ckg and a learner cognitive state communication data structure lcs for the communicating KCO object on the server side. Its interface format is: return_value = Initialize(parameter), where the parameter parameter is an empty string and the return value return_value is a logical value "true" or "false", indicating whether the initialization communication dialogue is successful; (2) Terminate(): It is extended to terminate the communication dialogue of a KCO object, including releasing the knowledge graph communication data structure ckg and the learner cognitive state communication data structure lcs established for the KCO object. Its interface format is: return_value = Terminate (parameter), where parameter parameter is an empty string and return value return_value is a logical value "true" or "false", indicating whether the communication dialogue is terminated successfully; (3) SetValue(): It is extended to enable the KCO object to set the communication data elements in ckg and lcs. Its interface format is: return_value = SetValue(parameter1, parameter2), where parameter1 is the first string parameter, which represents the communication data element of ckg and lcs to be set, and parameter2 is the second string parameter, which represents the value of the communication data element specified by parameter1. The return value return_value is a logical value "true" or "false", indicating whether the setting is successful; (4) GetValue(): This function is extended to pass the value of the communication data element specified in the ckg and lcs on the server side to the KCO object on the client side as the query result. Its interface format is: return_value = GetValue(parameter), where the parameter parameter represents the communication data element to be queried, and the return value return_value is the query result. (5) GetLastError(): Extended to return the error code of the most recent access to ckg and lcs. Its interface format is: return_value = GetError(), where the return value symbol return_value receives the returned error code number; (6) GetErrorString(): It is extended to return the error information corresponding to the error code of the most recent access to ckg and lcs. Its interface format is: return_value = GetErrorString(parameter), the parameter parameter is the error code number, and the return value symbol return_value receives the returned error information string.

5. The interoperability model of the intelligent teaching system based on subject knowledge graph according to claim 4 is characterized by: The sub-model 4 requires that KCO does not specify the subject knowledge graph it operates on during the design phase, and postpones the association between KCO and the subject knowledge graph it operates on in the content packaging list until runtime. The specific implementation method is as follows; (1) Expand a knowledge graph element in the SCORM content packaging model <knowledge-graph> , used to describe the subject knowledge graph used in the content package;< / knowledge-graph> (2) Project elements in the content packaging model of the SCORM specification <item> In , an optional attribute knowledgeref of the knowledge graph reference is extended to describe the relationship between the KCO object and the subject knowledge graph it references;< / item> (3) Resource elements in the SCORM content packaging model <resource> In, extend an optional attribute kcoimType describing the KCO interoperability model type and the corresponding attribute value "KCO";< / resource> (4) Extended <knowledge-graph> 、 <item>and <resource> The elements are defined in the XML schema file kcocp.xsd.< / resource> < / item> < / knowledge-graph> 6. The interoperability model of the intelligent teaching system based on subject knowledge graph according to claim 5 is characterized by: The extended knowledge graph elements <knowledge-graph> The XML format is as follows:< / knowledge-graph> (1) Description: <knowledge-graph> Elements describe the subject knowledge graph used in content packaging;< / knowledge-graph> (2) Diversity: <knowledge-graph>Element in the manifest element <manifest> It may appear 0 or 1 times;< / manifest> (3) Attribute identifier: A unique identifier in the content manifest, which must be specified; (4) Attribute discipline: a string describing the discipline to which the discipline knowledge graph belongs, which must be specified; (5) Attribute href: a reference to the entry file of the subject knowledge graph, which must be specified; (6) Child elements <metadata> : metadata describing the subject knowledge graph, optional element;< / metadata> (7) Child elements <file> : A list of files that the subject knowledge graph depends on, which must be specified.< / file>

Images