Knowledge-Based Systems最新文献

{"title":"CQSA-KT: Research on personalized knowledge tracing based on quantum-constructivism in sparse learning environments","authors":"Chengke Bao ,&nbsp;Zhiliang Xu ,&nbsp;Weidong Ji","doi":"10.1016/j.knosys.2025.114493","DOIUrl":"10.1016/j.knosys.2025.114493","url":null,"abstract":"<div><div>Knowledge tracing (KT), as a key technology to enable personalized instruction, faces the challenges of data sparsity and insufficient personalization modeling in large-scale instructional environments. To this end, this paper proposes a constructivist-inspired quantum self-attention knowledge tracing model (CQSA-KT). The deep mapping relationship between Constructivist Learning Theory (CLT) and Quantum Computing (QC) is established by characterizing the multilevel nature of learning states through quantum states, modeling knowledge associations through quantum entanglement, and simulating the assessment process through quantum measurements. The model contains four core modules: The quantum knowledge representation embedding module (QKREM) utilizes quantum complex embedding to achieve a high-dimensional representation of knowledge states; the quantum attention interaction module (QAIM) applies quantum entanglement to model the non-local nature of knowledge associations; the quantum measurement module (QMM) introduces the quantum measurement theory for learning assessment; and the hybrid cognitive feature fusion module (HCFFM) integrates classical and quantum features. Experiments on three publicly available datasets show that CQSA-KT maintains better performance under high sparsity (&gt;98 %) conditions, significantly outperforming ten existing benchmark models. Especially in extremely sparse scenarios (only 20 % training data), the model’s AUC improves by 8.5 percentage points over the benchmark models. This theory-driven technological innovation validates the application potential of QC in education and provides a new theoretical framework for the development of intelligent education.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114493"},"PeriodicalIF":7.6,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing the performance of power distribution systems through integrated network reconfiguration and distributed generation design","authors":"K. Dharani Sree ,&nbsp;P. Karpagavalli","doi":"10.1016/j.knosys.2025.114512","DOIUrl":"10.1016/j.knosys.2025.114512","url":null,"abstract":"<div><div>Reconfiguration of networks and distributed generation (DG) together leads to better performance of a network. To ensure system enactment, it is therefore necessary to determine appropriate size and placement of DG. However, there is a huge solution search space for sizing and situating of demand generation with Network Reconfiguration (NR), which makes it a complicated problem. Throughout the optimization process, removing these non-radial choices adds computational burden and lead to a local optimal solution. To reduce complexity of searching, Modified Chaotic Particle Swarm Optimization (MCPSO) algorithm is adopted to obtain a near optimal solution of designing, sizing, and placing the network with improved voltage profiles and minimized power loss. It introduces a combination of chaotic inertia adaptation, uniform initialization and a stochastic personal learning strategy contributing to improved search diversity and convergence stability. For the purpose of demonstrating efficacy of a simultaneous approach taking changeable power factor, the proposed approach is assessed using IEEE-33 and 69 bus using MATLAB. The findings demonstrate that discretizing reconfiguration search space implemented by encoding the network configuration as a discrete set of switching states prevents MCPSO from getting trapped in local optimums. On contrasting with conventional Particle Swarm Optimization (PSO), the proposed MCPSO algorithm results in active and reactive power loss reduction of <span><math><mrow><mn>27.78</mn><mo>%</mo></mrow></math></span> and <span><math><mrow><mn>76.36</mn><mo>%</mo></mrow></math></span> respectively for 33 bus system and <span><math><mrow><mn>6.67</mn><mo>%</mo></mrow></math></span> and <span><math><mrow><mn>25.5</mn><mo>%</mo></mrow></math></span> respectively for 69 bus system. The outcomes reveal that suggested algorithm provides optimal solution contrasted to state of art approaches.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114512"},"PeriodicalIF":7.6,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intention-guided imitation learning methods under limited expert demonstration data","authors":"Yilin Liu,&nbsp;Xiangfeng Luo,&nbsp;Shaorong Xie","doi":"10.1016/j.knosys.2025.114455","DOIUrl":"10.1016/j.knosys.2025.114455","url":null,"abstract":"<div><div>Imitation Learning has achieved significant results in various fields, such as robot control, autonomous driving, and unmanned vessel decision-making. This technology aims to mimic human behavior in specific tasks by learning the mapping between states and actions, enabling agents to execute tasks based on demonstrations. However, these methods rely on the acquisition of high-quality demonstration data, facing challenges such as difficulties in collecting expert samples, high costs, and low efficiency in policy learning. Particularly under limited sample conditions, imitation learning can easily get trapped in local optima, leading to lower success rates and accuracy in decision-making. Researchers have used data augmentation and transfer learning to tackle limited data. However, in complex scenarios, these methods are less effective due to a lack of domain-specific knowledge, which affects the interpretability of the model. To address these challenges, we propose an Intention-guided Imitation Learning method under limited expert demonstration data (ITIL), which extracts deep intent features from a small number of samples to enhance the agent’s understanding of the scene and improve the accuracy of the mapping from states to actions during Imitation Learning. Specifically, the core method consists of three modules: (1) Semantic Enhancement Module, which extracts spatiotemporal feature maps from a small number of raw trajectories to enrich the semantic information of expert data; (2) Intention Expression Module, which constructs an intention tree network to establish connections between different levels, effectively expressing and capturing expert intent; (3) Strategy Generation Module, which integrates the outputs of the first two modules as input to form efficient decision-making, creating a closed-loop architecture of cognitive understanding-knowledge expression-decision optimization. Experimental results show that our model outperforms baseline methods in navigation, capture, and formation tasks, with an average success rate improvement of approximately +6 % compared to the baseline method (ValueDICE).</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114455"},"PeriodicalIF":7.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient yet secure: An archive knowledge graph-enhanced native sparse attention network for lightweight privacy-preserving recommendation","authors":"Juan Du ,&nbsp;Chenxi Ma ,&nbsp;Yaobin Wang ,&nbsp;Limei Sun","doi":"10.1016/j.knosys.2025.114490","DOIUrl":"10.1016/j.knosys.2025.114490","url":null,"abstract":"<div><div>Recommendation Systems (RSs) aim to provide personalized recommendations by modeling user-item interaction patterns. Current attribute-enhanced RSs leverage user archival attributes to improve predictive performance. However, the use of attribute information introduces two critical challenges: 1) the risk of privacy leakage, as sensitive user attributes can be inferred from learned representations, and 2) high computational complexity, primarily due to the quadratic complexity of attention mechanisms. To address the accuracy-privacy-efficiency trilemma, we propose an Archive Knowledge Graph-enhanced Native Sparse Attention network (AKG-NSA) for privacy-preserving lightweight recommendation. Specifically, AKG-NSA introduces a two-stage privacy protection mechanism. First, we pseudonymize user identities in the archive knowledge graph, breaking the direct linkage between users and their attributes. Second, we design a Multi-channel Native Sparse Attention (MNSA) network that utilizes compressed user representations as queries to retrieve attribute patterns from the archive knowledge graph in a privacy-preserved manner. Moreover, we also construct a parallel user-item bipartite graph and operate graph convolutions to learn the representations for users and items. By employing the native sparse attention mechanism, AKG-NSA refines the learned representations while maintaining a low computational complexity. Extensive experiments on three real-world datasets demonstrate that AKG-NSA outperforms nine state-of-the-art baselines in terms of prediction accuracy, privacy preservation, and computational efficiency. The data and source codes of this work are available at <span><span>https://github.com/juandu113/AKG-NSA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114490"},"PeriodicalIF":7.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing forex market forecasting with feature-augmented multivariate LSTM models using real-time data","authors":"Duong Thi Kim Chi ,&nbsp;Ho Ngoc Trung Kien ,&nbsp;Thanh Q. Nguyen","doi":"10.1016/j.knosys.2025.114500","DOIUrl":"10.1016/j.knosys.2025.114500","url":null,"abstract":"<div><div>This study proposes a feature-augmented multivariate LSTM model for real-time Forex market forecasting. By incorporating engineered financial indicators—such as Close_Change, RSI, and gold price—alongside traditional OHLCV data, the model captures nonlinear temporal dynamics and macro-financial interactions. A sliding window approach structures input sequences for a stacked LSTM network optimized for short-term prediction. Experimental results on major currency pairs demonstrate that the proposed model outperforms baseline LSTM, GRU, and classical machine learning methods in RMSE, MAE, and MAPE metrics. Statistical validation using the Wilcoxon signed-rank test confirms the improvements are significant. The model's robustness under volatility stress and noisy inputs highlights its practical relevance for real-time decision-making. Potential extensions include incorporating news-based sentiment and multimodal signals to enhance adaptability.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114500"},"PeriodicalIF":7.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-source heterogeneous sensor information fusion framework for intelligent online chatter detection in different milling conditions","authors":"Liangshi Sun ,&nbsp;Xianzhen Huang ,&nbsp;Zhiyuan Jiang ,&nbsp;Jiatong Zhao ,&nbsp;Xu Wang","doi":"10.1016/j.knosys.2025.114488","DOIUrl":"10.1016/j.knosys.2025.114488","url":null,"abstract":"<div><div>Online chatter detection is a critical technology in intelligent manufacturing systems, essential for ensuring high-quality and efficient milling operations. Although artificial intelligence models have been developed to automatically identify chatter, the accuracy improvement is limited by the use of single sensor signals. Therefore, a multi-source heterogeneous sensor information fusion framework is proposed for intelligent online chatter detection in this paper. To effectively mitigate noise and eliminate interference from milling parameters, a heterogeneous sensor signal processing strategy is proposed based on wavelet packet decomposition and successive variational mode decomposition. Next, a multi-source, multi-stage, and multi-scale spatial-temporal fusion attention network is proposed for extracting chatter features and achieving high-precision chatter detection. It is noteworthy that multi-source signals are fused at the feature level, and comprehensive chatter features are extracted through the multi-source information fusion module, the multi-stage spatial-temporal feature extraction and fusion module, and the multi-scale gated channel attention module. In milling experiments across different conditions, the chatter detection performance of the proposed framework is evaluated in three scenarios. The results indicate that this framework can provide more accurate and reliable detection results compared to other methods.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114488"},"PeriodicalIF":7.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DAMR: Multi-scale graph contrastive learning with dynamic adjustment and mutual rectification","authors":"Dengdi Sun ,&nbsp;Zhixiang Wu ,&nbsp;Mingwei Cao ,&nbsp;Zhifu Tao ,&nbsp;Zhuanlian Ding","doi":"10.1016/j.knosys.2025.114482","DOIUrl":"10.1016/j.knosys.2025.114482","url":null,"abstract":"<div><div>Graph contrastive learning (GCL) has emerged as a powerful self-supervised approach for learning generalized graph representations, achieving remarkable advancements in recent years. However, most existing GCL methods ignore the noise of the augmented global structure and the dynamic change in training, and lack detailed consideration in calculating local structural homogeneity. These limitations may lead to the model’s insufficient performance in capturing fine-grained semantic features at the node level, making it difficult to fully explore the potential semantic associations between adjacent nodes. Meanwhile, on a global scale, there is also a lack of the ability to model complex topological structures. To this end, we propose a new multi-scale graph contrastive learning with dynamic adjustment and mutual rectification. This method dynamically adjusts the global structure via graph reconstruction and adaptively learns node representations; Meanwhile, a mutual rectification module is designed to predict the support scores of neighbors relative to anchors and quantify each neighbor’s contribution to view agreement. Both reconstruction and rectification are integrated into the training objective and effectively capture the graph structure information from both global and local scales, improving the quality and robustness of graph representations. We conduct extensive experiments on three downstream tasks: node classification, node clustering, and link prediction. The experimental results demonstrate that our method outperforms existing GCL methods across multiple tasks and datasets, validating the effectiveness and generalizability of the proposed model.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114482"},"PeriodicalIF":7.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bias-in-debias-out: Hierarchical channel-spatial bias calibration for cross-domain few-shot classification","authors":"Minghui Li ,&nbsp;Hongxun Yao","doi":"10.1016/j.knosys.2025.114475","DOIUrl":"10.1016/j.knosys.2025.114475","url":null,"abstract":"<div><div>The core challenge of cross-domain few-shot learning (CD-FSL) stems from models’ inability to generalize source-domain inductive biases to target domains under significant distribution shifts. While existing methods predominantly employ strategies like auxiliary target data adaptation, feature disentanglement, or metric space alignment, they overlook two inherent biases entrenched during source-domain training: (1) channel-wise dependency on source-specific feature patterns and (2) spatial-wise preference for source-typical structures, both of which hinder cross-domain transfer. We propose the first unified <u><em>C</em></u>hannel-<u><em>S</em></u>patial <u><em>D</em></u>ual-dimensional <u><em>B</em></u>ias <u><em>C</em></u>alibration (CSDBC) framework to systematically address these biases through progressive dilution, recomposition, and alignment. Our approach integrates three key innovations: (1) a parameter-free <u><em>S</em></u>tatic <u><em>B</em></u>ase-class <u><em>B</em></u>ias <u><em>D</em></u>ilution (SBBD) module that dilutes source-specific channel-spatial biases through layer-wise and point-wise modulation, effectively suppressing overfitting to source-specific patterns; (2) a <u><em>D</em></u>ynamic <u><em>N</em></u>ovel-class <u><em>B</em></u>ias <u><em>R</em></u>ecomposition (DNBR) module that generates target-adaptive channel-spatial soft masks via meta-optimized lightweight depthwise separable convolutions, enabling target-domain channel reweighting and spatial preference adjustment; and (3) a <u><em>N</em></u>ovel-class <u><em>C</em></u>ross-image <u><em>S</em></u>emantic <u><em>A</em></u>lignment (NCSA) module that establishes channel correlations and spatial correspondences between support-query pairs, significantly enhancing both discriminability and semantic consistency of target-domain features. Extensive experiments across eight CD-FSL benchmarks demonstrate consistent improvements, outperforming SOTA methods by 1.35 % (5-way 1-shot) and 2.00 % (5-way 5-shot) in average accuracy under varying domain shifts.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114475"},"PeriodicalIF":7.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing leadership-based metaheuristics using reinforcement learning: A case study in grey wolf optimizer","authors":"Afifeh Maleki ,&nbsp;Mehdy Roayaei ,&nbsp;Seyedali Mirjalili","doi":"10.1016/j.knosys.2025.114471","DOIUrl":"10.1016/j.knosys.2025.114471","url":null,"abstract":"<div><div>Metaheuristics are widely applied in optimization because of their flexibility and ability to address complex and high-dimensional problems. Nevertheless, they face persistent challenges, including susceptibility to local optima, limited parameter adaptability, and premature convergence. Leadership-based metaheuristics, in which leaders guide the search process, encounter additional difficulties such as limited exploration capacity, leader stagnation, and reduced diversity, often stemming from underutilization of data generated during the search. To overcome these limitations, this study proposes a reinforcement learning–based approach, RL-LGWO, which enhances the Grey Wolf Optimizer (GWO) by integrating multi-agent reinforcement learning. In RL-LGWO, agents share experiences to improve decision-making, and reinforcement learning is employed to decouple and adapt the leader update mechanism, thereby improving the exploration–exploitation balance and enabling leaders to dynamically escape local optima. The proposed method was evaluated against two GWO-enhancing algorithms, three RL-based GWO variants, PSO, WOA, and the original GWO across 23 well-known benchmark functions, in addition to the recent CEC2022 benchmark suite. Experimental results show that RL-LGWO achieved the best solutions on 17 of the 23 benchmark functions, with superior convergence speed and improved stability, while incurring only a minor runtime increase compared with the original GWO. Furthermore, on the CEC2022 suite, RL-LGWO outperformed competing algorithms on 10 of 12 test functions, underscoring its robustness and adaptability to recent and challenging benchmarks. Overall, the findings indicate that RL-LGWO delivers a substantive improvement over state-of-the-art alternatives and holds strong potential to advance leadership-based metaheuristics for a wide range of optimization problems.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114471"},"PeriodicalIF":7.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Aspect-level sentiment analysis in social media using a hybrid deep transfer learning approach","authors":"Kia Jahanbin,&nbsp;Mohammed Ali Zare Chahooki","doi":"10.1016/j.knosys.2025.114125","DOIUrl":"10.1016/j.knosys.2025.114125","url":null,"abstract":"<div><div>In recent years, researchers have become interested in aspect-level sentiment analysis. In the traditional sentiment analysis of documents or sentences, a label was assigned to the entire sentence or document. Whereas a sentence or document can have aspects with different sentiments. Although deep learning models have succeeded in aspect-level sentiment analysis, these models require rich labeled datasets in different domains to extract text features and sentiment analysis. This paper uses deep transfer learning for sentiment analysis of aspect-level sentiment analysis (AHDT) of social network data. The backbone of the AHDT model is a version of RoBERTa’s pre-trained deep neural network specially trained to work on social data. The features extracted from the pre-trained RoBERTa network for sentiment analysis are injected into the Bi-GRU deep neural network and then the attention layer. BI-GRU can process sequences from both sides (left to right and vice versa) and extract hidden relationships. In addition, the attention layer allows the model to pay attention to the more influential aspects of the text and provide a better interpretation. Also, this article uses the Class imbalance method to balance for training the model with almost the same polarities. The test results of the AHDT model on four SemEval datasets for the aspect-sentiment analysis task show that the model has improved the F1-score value in Resturan2014, 2015, and 2016 datasets by 0.63, 27.01, and 15.93, respectively. Also, this model has increased the accuracy value in Resturan2015 and 2016 datasets to 9.21 and 0.54, respectively. In addition, the results of experimental tests in all datasets show that the obtained values of accuracy and F1-score are close to each other, which indicates the stability of the AHDT model.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"330 ","pages":"Article 114125"},"PeriodicalIF":7.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}