Cognitive diagnosis is crucial for evaluating learners’ cognitive traits and skills. Current methods often rely on linear or logical functions, limiting their ability to handle complex relationships and requiring manual labeling. This paper proposes the CK-CD model, which addresses these limitations by integrating knowledge concept enhancement and knowledge point importance. The model employs self-attention mechanisms to uncover hidden relationships between concepts and uses attention mechanisms to explore the importance of knowledge points within each item. This comprehensive approach improves diagnostic accuracy and provides valuable insights into learners’ cognitive processes. Experimental results on a real-world dataset demonstrate the effectiveness of the CK-CD model in predicting student performance, outperforming traditional and neural network-based models

A user model with emotional analysis in intelligent tutoring systems is presented in this paper. After introducing user characteristics, an emotional analysis module is introduced to discuss expression recognition, expression classification and emotional states confirming in our user model in detail, in order to improve pedagogical effects.

In this paper, a formal model of intelligent query systems is proposed. After giving the architecture of our intelligent query answering system, we discuss ontology environment, user models, and query answering module in detail, and then propose a formal model of intelligent query systems. Finally, the running process of this model is studied.

Learner models are of great importance in the construction of intelligent tutoring systems. In this paper, after introducing intelligent tutoring systems and learner models, four kinds of classical learner models called Stereotypes Models, Overlay Models, Buggy Models and Constraint-Based Models and their properties are discussed in detail. Finally, we compare these four kinds of learner models in detail, according to their characteristics and functions.

A model of intelligent tutoring systems with emotional pedagogical agents is presented in this paper, and the functionalities of the key components of the system are described. To improve the interaction between learners and the system, a kind of emotional pedagogical agents which can deduce users' emotional statues, is introduced in order to improve pedagogical effects. The emotional pedagogical agents produces personalized learning units dynamically based on the information provided by user models and the expression information collected from cameras, in order to improve the self-adaptability and pedagogical effects of the system.

In representing ontologies there are two kinds of default statements: one is the default assertions which say that some concept has some property defaultly, another is the default inheritance of default assertions. The latter actually is a default rule of default rules (called super default rules), that is, a default rule in which the formulas occur in the default are default rules. In this paper we shall give a formal description of such super default rules, a super default theories and the definitions of the extensions of the super default theories.

In this paper, an ontology is regarded as an information system in formal concept analysis. Then, based on theories of concepts, a formal context in ontologies defined by a set of properties is conceptualized as a concept with the extent and the intent. There are two kinds of properties implied by a formal context: one is the set of properties in its intent and another is the set of default properties. Then the features of formal contexts in ontologies are discussed in detail.

A formal model of a personalized recommendation system in intelligent tutoring systems is presented in this paper. Users' queries, domain knowledge, user models and teaching knowledge extraction processes are four key factors that support a personalized recommendation system. After introducing the construction of domain knowledge and user models, the formal model of our personalized recommendation system is presented and discussed in detail to show that it is practicable.

A model of a web-based personalized intelligent tutoring system with a user module, a resource management module, a pedagogical module and a guide module is presented in this paper, and the realization of the system and its properties are discussed. The user module makes use of learners’ knowledge levels, psychological characteristics and learning styles, etc., to construct and update user models. The resource management module utilizes multi-media teaching material to represent and update domain knowledge. The pedagogical module produces personalized learning units dynamically based on the information provided by user models and domain knowledge bases in order to improve the self-adaptability and pedagogical effects of the system. The guide module interacts with learners during the whole learning process to improve their confidence to continue a course. Keywords-module; multi-media teaching material; knowledge base; web; intelligent tutoring system

In this paper, after the introduction of ontology-based domain knowledge bases and domain knowledge representation, a formal query model of intelligent search agents that can search over distributed knowledge bases with heterogeneity for web-based intelligent tutoring systems is proposed; and the searching process of these agents is analyzed. Ontologies are introduced to describe the semantic information of knowledge bases in order to express fully the semantics of queries in our web-based intelligent tutoring system. This model improves the relevance of the searching results. At the same time, it reflects the dynamic change of the information in the knowledge bases and reduces the consistency and efficiency problem caused by using globe ontology.

In this paper, after the discussion of user models and ontology-based domain knowledge representation in intelligent tutoring systems, a formal model of intelligent pedagogical agents is presented and the teaching processes of these agents is analyzed. Domain knowledge are represented based on ontologies to improve the sharing and reusing of teaching materials; and user models are constructed according to learnerspsila psychology characteristics, knowledge levels, etc., in order to improve the self-adaptability and pedagogical effects. Based on user models and domain knowledge, intelligent pedagogical agents design formally the teaching processes for learners and these teaching processes are discussed in detail to show that they are practicable.