In order to provide high-quality learning services,various online systems should possess the fundamental ability to predict the knowledge points and units to which a given test question belongs.The existing methods ty...In order to provide high-quality learning services,various online systems should possess the fundamental ability to predict the knowledge points and units to which a given test question belongs.The existing methods typically rely on manual labeling or traditional machine learning methods.Manual labeling methods have high time costs and high demands for human resources,while traditional machine learning methods only focus on the shallow features of the topics,ignoring the deep semantic relationship between the topic text and the knowledge point units.These two methods have relatively large limitations in practical applications.This paper proposes a convolutional neural network method combined with multiple features to predict the knowledge point units.We construct a binary classification dataset in the three grades of primary mathematics.Considering the supplementary role of Pinyin to Chinese text and the unique identification characteristics of Unicode encoding for characters,we obtain the Pinyin representation and the Unicode encoding representation of the original Chinese text.Then,we put the three representation methods into the convolutional neural network for training,obtain three kinds of semantic vectors,fuse them,and finally obtain higher-dimensional fusion features.Our experimental results demonstrate that our approach achieves good performance in predicting the knowledge units of test questions.展开更多
With market competition becoming fiercer,enterprises must update their products by constantly assimilating new big data knowledge and private knowledge to maintain their market shares at different time points in the b...With market competition becoming fiercer,enterprises must update their products by constantly assimilating new big data knowledge and private knowledge to maintain their market shares at different time points in the big data environment.Typically,there is mutual influence between each knowledge transfer if the time interval is not too long.It is necessary to study the problem of continuous knowledge transfer in the big data environment.Based on research on one-time knowledge transfer,a model of continuous knowledge transfer is presented,which can consider the interaction between knowledge transfer and determine the optimal knowledge transfer time at different time points in the big data environment.Simulation experiments were performed by adjusting several parameters.The experimental results verified the model’s validity and facilitated conclusions regarding their practical application values.The experimental results can provide more effective decisions for enterprises that must carry out continuous knowledge transfer in the big data environment.展开更多
New theories,methodologies,and technologies have been continuously invented and widely applied in modern software development,along with many new tools and best practices that are of remarkable significance in the sof...New theories,methodologies,and technologies have been continuously invented and widely applied in modern software development,along with many new tools and best practices that are of remarkable significance in the software industry.In Software Engineering(SE)programs of universities,it is quite difficult for their curricula to chase after the fast-evolving technology trend.As a consequence,there have been significant challenges in designing an evolvable SE curriculum.In this paper,we present a knowledge graph based curriculum design method for SE programs.Knowledge Points(KPs)are organized into a multi-layer and multi-dimensionally annotated knowledge graph called SEKG,and five principles are applied to partition the SEKG into a set of inter-related courses.Metrics for evaluating the quality of an SE curriculum are briefly discussed.This method can not only help design a systematic curriculum from existing software engineering KPs but also facilitate curriculum evolution to adapt to technology trends.展开更多
The aim of this work is mathematical education through the knowledge system and mathematical modeling. A net model of formation of mathematical knowledge as a deductive theory is suggested here. Within this model the ...The aim of this work is mathematical education through the knowledge system and mathematical modeling. A net model of formation of mathematical knowledge as a deductive theory is suggested here. Within this model the formation of deductive theory is represented as the development of a certain informational space, the elements of which are structured in the form of the orientated semantic net. This net is properly metrized and characterized by a certain system of coverings. It allows injecting net optimization parameters, regulating qualitative aspects of knowledge system under consideration. To regulate the creative processes of the formation and realization of mathematical know- edge, stochastic model of formation deductive theory is suggested here in the form of branching Markovian process, which is realized in the corresponding informational space as a semantic net. According to this stochastic model we can get correct foundation of criterion of optimization creative processes that leads to “great main points” strategy (GMP-strategy) in the process of realization of the effective control in the research work in the sphere of mathematics and its applications.展开更多
基金supported by the National Natural Science Foundation of China(Nos.62377009,62102136,61902114,61977021)the Key R&D projects in Hubei Province(Nos.2021BAA188,2021BAA184,2022BAA044)the Ministry of Education’s Youth Fund for Humanities and Social Sciences Project(No.19YJC880036)。
文摘In order to provide high-quality learning services,various online systems should possess the fundamental ability to predict the knowledge points and units to which a given test question belongs.The existing methods typically rely on manual labeling or traditional machine learning methods.Manual labeling methods have high time costs and high demands for human resources,while traditional machine learning methods only focus on the shallow features of the topics,ignoring the deep semantic relationship between the topic text and the knowledge point units.These two methods have relatively large limitations in practical applications.This paper proposes a convolutional neural network method combined with multiple features to predict the knowledge point units.We construct a binary classification dataset in the three grades of primary mathematics.Considering the supplementary role of Pinyin to Chinese text and the unique identification characteristics of Unicode encoding for characters,we obtain the Pinyin representation and the Unicode encoding representation of the original Chinese text.Then,we put the three representation methods into the convolutional neural network for training,obtain three kinds of semantic vectors,fuse them,and finally obtain higher-dimensional fusion features.Our experimental results demonstrate that our approach achieves good performance in predicting the knowledge units of test questions.
基金supported by the National Natural Science Foundation of China(Grant No.71704016,71331008)the Natural Science Foundation of Hunan Province(Grant No.2017JJ2267)+1 种基金Key Projects of Chinese Ministry of Education(17JZD022)the Project of China Scholarship Council for Overseas Studies(201208430233,201508430121),which are acknowledged.
文摘With market competition becoming fiercer,enterprises must update their products by constantly assimilating new big data knowledge and private knowledge to maintain their market shares at different time points in the big data environment.Typically,there is mutual influence between each knowledge transfer if the time interval is not too long.It is necessary to study the problem of continuous knowledge transfer in the big data environment.Based on research on one-time knowledge transfer,a model of continuous knowledge transfer is presented,which can consider the interaction between knowledge transfer and determine the optimal knowledge transfer time at different time points in the big data environment.Simulation experiments were performed by adjusting several parameters.The experimental results verified the model’s validity and facilitated conclusions regarding their practical application values.The experimental results can provide more effective decisions for enterprises that must carry out continuous knowledge transfer in the big data environment.
文摘New theories,methodologies,and technologies have been continuously invented and widely applied in modern software development,along with many new tools and best practices that are of remarkable significance in the software industry.In Software Engineering(SE)programs of universities,it is quite difficult for their curricula to chase after the fast-evolving technology trend.As a consequence,there have been significant challenges in designing an evolvable SE curriculum.In this paper,we present a knowledge graph based curriculum design method for SE programs.Knowledge Points(KPs)are organized into a multi-layer and multi-dimensionally annotated knowledge graph called SEKG,and five principles are applied to partition the SEKG into a set of inter-related courses.Metrics for evaluating the quality of an SE curriculum are briefly discussed.This method can not only help design a systematic curriculum from existing software engineering KPs but also facilitate curriculum evolution to adapt to technology trends.
文摘The aim of this work is mathematical education through the knowledge system and mathematical modeling. A net model of formation of mathematical knowledge as a deductive theory is suggested here. Within this model the formation of deductive theory is represented as the development of a certain informational space, the elements of which are structured in the form of the orientated semantic net. This net is properly metrized and characterized by a certain system of coverings. It allows injecting net optimization parameters, regulating qualitative aspects of knowledge system under consideration. To regulate the creative processes of the formation and realization of mathematical know- edge, stochastic model of formation deductive theory is suggested here in the form of branching Markovian process, which is realized in the corresponding informational space as a semantic net. According to this stochastic model we can get correct foundation of criterion of optimization creative processes that leads to “great main points” strategy (GMP-strategy) in the process of realization of the effective control in the research work in the sphere of mathematics and its applications.
文摘知识追踪任务旨在通过对学生历史学习数据实时准确地追踪学生知识状态,并预测学生未来的答题表现.针对当前研究忽略了题目涵盖知识点中复杂的高阶关系的问题,提出一种融合知识点关系的深度记忆网络知识追踪模型(deep memory network knowledge tracing model incorporating knowledge point relationships,HRGKT).首先,HRGKT使用知识点关系图定义图中节点之间的关系信息,表示知识点之间的丰富信息.使用GAT获取两者之间的高阶关系.然后,学习过程中存在着遗忘,HRGKT综合考虑4个影响知识遗忘的因素来更准确地追踪学生知识状态.最后,根据真实在线教育数据集上的实验比较结果,与当前知识追踪模型相比,HRGKT在追踪学生知识掌握状态方面表现更加准确,并且具备更好的预测性能.
