Large language models hold great promise for transforming K-12 education, but there is an urgent need for systematic evaluation of their core educational capabilities. Existing benchmarks often overlook educational goal cognition and overemphasize answer accuracy, thereby failing to capture deeper subject-level knowledge ability and problem-solving ability. To address this gap, we introduce K-12EduBench: a benchmark for evaluating LLMs’ subject-level knowledge ability, subject-specific problem-solving ability, and educational goal cognition ability in K-12 education. K-12EduBench comprises four components: (1) a dataset of 2,640 objective and 619 subjective questions across nine subjects, annotated with answers, problem-solving processes, and cognitive-level labels; (2) nine Item Response Theory (IRT) models for estimating subject-level knowledge ability; (3) evaluation methods and metrics for assessing multi-step problem-solving ability; and (4) prompts and scoring rubrics for measuring alignment with target cognitive levels. Experiments on advanced LLMs show that education-optimized models consistently outperform general-purpose ones across all three abilities, while under-scaled models lag substantially. We observe a strong positive correlation between subject-level knowledge ability and subject-specific problem-solving ability. Despite gains in educational goal cognition ability, current models—even those tailored for education—still fall short of real-world instructional needs.

Cognitive diagnosis is a fundamental task in intelligent education, aiming to measure students' proficiency on knowledge concepts based on practice data. Traditional methods utilize a broadly-defined latent trait θ to represent knowledge proficiency with some cognitive factors like skill or ability. However, existing methods simplify this to a narrowly-defined latent trait θ, which focuses only on knowledge or treats these cognitive factors as implicit features inferred from data. They fail to explicitly model these cognitive factors, resulting in limited performance and interpretability. To this end, we revisit essence of cognition in Educational Psychology Theory and propose a novel Cognition-aware Cognitive Diagnosis (CCD) model, where we first introduce the Cognition factor as a bridge into the long-standing three-basic-factors (Student, Exercise, Knowledge concept) paradigm. CCD has two main parts: cognition representations and a two-stage diagnostic process. In the first part, we explicitly model cognitive process (CP) dimensions from Bloom's Taxonomy of Educational Objectives, leading to two innovative concepts proposed: the student's Subjective Cognitive Ability (SCA) and the exercise's Objective Cognitive Attribute (OCA), derived by regulating the CP through S-K and E-K interactions, respectively. Then, the SCA and OCA are formed into a new cognition-aware latent trait θ. In the second part, we employ a basic interaction function and a slip and guess influence function, inputting our new θ, a continuous Q-matrix (generated by a siamese PLMs), and other features to obtain the ideal result, followed by feeding it into the slip and guess influence function to obtain the actual result. Extensive experiments on real-world datasets demonstrates the superior effectiveness and good interpretability.

With the rapid evolution of multimedia technologies and its widespread integration into education, adaptive multimedia learning has gained significant prominence. Cognitive diagnosis (CD) is pivotal in this domain, as it models students' cognitive states using practice data captured by multimedia learning applications. However, existing methods often simplify these states to mere proficiency on knowledge concepts. Constructivism in education emphasizes learning as a continuous cognitive development process, during which students' cognitive states become increasingly complex, involving not only their construction of concepts but also their construction of relations between concepts that have long been overlooked. To this end, we propose the Hierarchical Disentanglement of Cognitive States for Enhanced Cognitive Diagnosis (HDCD). Inspired by the Structure of Observed Learning Outcomes (SOLO) taxonomy, which categorizes cognitive development into core hierarchical levels (Multistructural, Relational, Extended Abstract), we introduce a hierarchical disentanglement strategy to define cognitive states aligned with each SOLO level: Intra-Concept Cognitive States, Relational Cognitive States, and Extended Cognitive States. Specifically, (i) At the multistructural level, intra-concept cognitive states are sampled from student's personalized cognitive distribution, representing the construction of individual concepts. (ii) At the relational level, inter-concept cognitive states are first sampled to represent the construction of relations between concepts. We then employ a hypergraph transformation to collaboratively update both intra-concept and inter-concept cognitive states, forming relational cognitive states. Considering that students' self-constructed knowledge systems involve multiple types of inter-concept relations, relational cognitive states are implemented under both undirected and directed relation views in this work, and then fed into local diagnostic functions, respectively. (iii) At the extended abstract level, outputs from the local diagnostic functions are fused using multi-view attention mechanisms, resulting in extended cognitive states, which integrate information from multiple relational views, are then fed into a global diagnostic function for final prediction. Extensive experiments on real-world datasets demonstrate the superior performance and interpretability of our HDCD.

The knowledge concept recommendation in Massive Open Online Courses (MOOCs) is a significant issue that has garnered widespread attention. Existing methods primarily rely on the explicit relations between users and knowledge concepts on the MOOC platforms for recommendation. However, there are numerous implicit relations (e.g., shared interests or same knowledge levels between users) generated within the users' learning activities on the MOOC platforms. Existing methods fail to consider these implicit relations, and these relations themselves are difficult to learn and represent, causing poor performance in knowledge concept recommendation and an inability to meet users' personalized needs. To address this issue, we propose a novel framework based on contrastive learning, which can represent and balance the explicit and implicit relations for knowledge concept recommendation in MOOCs (CL-KCRec). Specifically, we first construct a MOOCs heterogeneous information network (HIN) by modeling the data from the MOOC platforms. Then, we utilize a relation-updated graph convolutional network and stacked multi-channel graph neural network to represent the explicit and implicit relations in the HIN, respectively. Considering that the quantity of explicit relations is relatively fewer compared to implicit relations in MOOCs, we propose a contrastive learning with prototypical graph to enhance the representations of both relations to capture their fruitful inherent relational knowledge, which can guide the propagation of students' preferences within the HIN. Based on these enhanced representations, to ensure the balanced contribution of both towards the final recommendation, we propose a dual-head attention mechanism for balanced fusion. Experimental results demonstrate that CL-KCRec outperforms several state-of-the-art baselines on real-world datasets in terms of HR, NDCG and MRR.

Frequent itemset mining serves as the main method of association rule mining. With the limitations in computing space and performance, the association of frequent items in large data mining requires both extensive time and effort, particularly when the datasets become increasingly larger. In the process of associated data mining in a big data environment, the MapReduce programming model is typically used to perform task partitioning and parallel processing, which could improve the execution efficiency of the algorithm. However, to ensure that the associated rule is not destroyed during task partitioning and parallel processing, the inner-relationship data must be stored in the computer space. Because inner-relationship data are redundant, storage of these data will significantly increase the space usage in comparison with the original dataset. In this study, we find that the formation of the frequent pattern (FP) mining algorithm depends mainly on the conditional pattern bases. Based on the parallel frequent pattern (PFP) algorithm theory, the grouping model divides frequent items into several groups according to their frequencies. We propose a non-group PFP (NG-PFP) mining algorithm that cancels the grouping model and reduces the data redundancy between sub-tasks. Moreover, we present the NG-PFP algorithm for task partition and parallel processing, and its performance in the Hadoop cluster environment is analyzed and discussed. Experimental results indicate that the non-group model shows obvious improvement in terms of computational efficiency and the space utilization rate.

The indoor positioning technology plays a significant role in the scenarios of the Internet of Things which require indoor location context. In this paper, the WiFi signals under modern enterprise WiFi infrastructure, signal patterns between coexisting access points (APs), and signals’ correlation with indoor pathway map are investigated to address the problem of inconsistent WiFi signal observations. The sibling signal patterns (SSPs) are defined for the first time and processed to generate Beacon APs which have higher confidence in positioning. The spatial signal patterns are used to bring the estimated location into a limited area through signal coverage constraint (SCC). A positioning scheme using SSP and SCC is proposed and shows improved positioning accuracy. The proposed scheme is fully designed, implemented, and evaluated in a real-world environment, revealing its effectiveness and efficiency.

Domain-specific modelling is used to construct and realise the different application models upon the same specific domain for software reuse. The paper integrates domain-specific modelling and web service techniques with model-driven development, and proposes a unified approach named SODSMI (Service Oriented executable Domain-Specific Modelling and Implementation) to build the executable domain-specific model so as to achieve the target of model-driven development and reuse. The approach is organised by domain space, which is employed as the elementary unit of the domain-specific modelling and implementation framework. It makes software reuse at the domain level, realises the reuse of domain knowledge, and openly extends the range and scale of domain-specific model and its implementation.

In this paper, we consider a smart power model, where some subscribers share several energy providers and there are some malicious users in this power grid. The energy providers are managed by a power market scheduling center (PMSC), which broadcasts electricity price to subscribers and energy providers. The energy providers and subscribers update their capacities and energy consumption requirements, respectively, according to the electricity prices received. In order to identify the malicious users and the unstable energy providers, the mechanism of identification and processing (MIP) for the malicious users and unstable energy providers is proposed. By integrating the MIP, we proposed a heuristic algorithm called the dynamic pricing algorithm with malicious users and unstable energy providers (DPAMU) to get the optimal electricity price as well as the optimal power requirement and the load capacity. Finally, the simulation results show that the proposed DPAMU has good convergence performance and can shave and clip the peak load effectively.

Following the wired network virtualization, virtualization of wireless networks becomes the next step aiming to provide network or infrastructure providers with the ability to manage and control their networks in a more dynamic fashion. The benefit of the wireless mobile network virtualization is a more agile business model where virtual mobile network operators (MNOs) can request and thus pay physical MNOs in a more pay-as-you-use manner. This paper presents some resource allocation algorithms for joint network virtualization and resource allocation of wireless networks. The overall algorithm involves the following two major processes: firstly, to virtualize a physical wireless network into multiple slices, each representing a virtual network, and secondly, to carry out physical resource allocation within each virtual network (or slice). In particular, the paper adopts orthogonal frequency division multiplexing (OFDM) as its physical layer to achieve more efficient resource utilization. Therefore, the resource allocation is conducted in terms of sub-carriers. Although the motivation and algorithm design are based on IEEE 802.16 or WiMAX networks, the principle and algorithmic essence are also applicable to other OFDM access-based wireless networks. The aim was to achieve the following design goals: virtual network isolation and resource efficiency. The latter is measured in terms of network throughput and packet delivery ratio. The simulation results show that the aforementioned goals have been achieved.