Query：
学者姓名：成全
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
[目的/意义]针对在线健康社区用户生成内容,提出了融合病情特征的多任务用户需求识别模型(MUNI-DC),深入挖掘用户需求,形成由提问意图和提问实体两部分内容组成的用户需求主题体系.[方法/过程]通过构建BERT-wwm模型对用户需求数据进行预训练,融合病情特征实现对用户意图的识别,采用多层标签指针网络实现对在线健康社区用户提问数据的实体识别,以此为基础完成对在线健康社区用户需求的识别任务.[结果/结论]对比实验发现,相比于单一任务模型,本模型在用户需求识别结果的precision、recall、F1等指标上均有所提升;消融实验发现,融合病情特征和多层标签指针网络能够有效提升模型的用户需求识别效果,所提出的融合病情特征的多任务用户需求识别模型在应对在线健康社区用户信息需求分析任务中具有参考价值.
Keyword ：
在线健康社区 在线健康社区 实体识别 实体识别 用户需求识别 用户需求识别 知识图谱嵌入 知识图谱嵌入 语义识别 语义识别
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 成全 , 林颖茹 . 融合病情特征的在线健康社区用户需求识别模型研究 [J]. | 情报理论与实践 , 2025 , 48 (4) : 125-134 . |
| MLA | 成全 等. "融合病情特征的在线健康社区用户需求识别模型研究" . | 情报理论与实践 48 . 4 (2025) : 125-134 . |
| APA | 成全 , 林颖茹 . 融合病情特征的在线健康社区用户需求识别模型研究 . | 情报理论与实践 , 2025 , 48 (4) , 125-134 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Acute complication prediction model is of great importance for the overall reduction of premature death in chronic diseases.The CLSTM-BPR proposed in this paper aims to improve the accuracy,interpretability,and generalizability of the existing disease prediction models.Firstly,through its complex neural network structure,CLSTM-BPR considers both disease commonality and patient characteristics in the prediction process.Secondly,by splicing the time series prediction algorithm and classifier,the judgment basis is given along with the prediction results.Finally,this model introduces the pairwise algorithm Bayesian Personalized Ranking(BPR)into the medical field for the first time,and achieves a good result in the diagnosis of six acute complications.Experiments on the Medical Information Mart for Intensive Care Ⅳ(MIMIC-Ⅳ)dataset show that the average Mean Absolute Error(MAE)of biomarker value prediction of the CLSTM-BPR model is 0.26,and the average accuracy(ACC)of the CLSTM-BPR model for acute complication diagnosis is 92.5％.Comparison experiments and ablation experiments further demonstrate the reliability of CLSTM-BPR in the prediction of acute complication,which is an advancement of current disease prediction tools.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xi Chen , Quan Cheng . Acute Complication Prediction and Diagnosis Model CLSTM-BPR:A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking [J]. | 清华大学学报自然科学版（英文版） , 2024 , 29 (5) : 1509-1523 . |
| MLA | Xi Chen 等. "Acute Complication Prediction and Diagnosis Model CLSTM-BPR:A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking" . | 清华大学学报自然科学版（英文版） 29 . 5 (2024) : 1509-1523 . |
| APA | Xi Chen , Quan Cheng . Acute Complication Prediction and Diagnosis Model CLSTM-BPR:A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking . | 清华大学学报自然科学版（英文版） , 2024 , 29 (5) , 1509-1523 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
研究政策工具对企业原始性创新能力的影响是提升企业原始性创新能力的基本前提,也是政府制定原始性创新政策的重要依据.本研究基于2011-2019 年的规模以上工业企业科技活动数据,选取六种相关的原始性创新政策工具,并将其划分为供给型、需求型及环境型,然后通过改进柯布-道格拉斯生产函数,从政策工具协同作用及政策工具类型分布两类情境进行回归分析.研究扩展了企业原始性创新的政策工具箱,揭示了政策工具在实践应用中对企业原始性创新能力的影响.实证分析结果表明,相关部门应进一步开发与运用需求型、环境型政策工具,优化创新政策工具体系,加强对企业原始性创新政策工具的协同管理,强化监管力度,确保企业原始性创新的有效性与持续性.
Keyword ：
企业原始性创新 企业原始性创新 原始性创新能力 原始性创新能力 政策工具 政策工具
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 成全 , 蒋世辉 , 王海燕 . 政策工具对企业原始性创新能力的影响 [J]. | 管理评论 , 2024 , 36 (5) : 75-88 . |
| MLA | 成全 等. "政策工具对企业原始性创新能力的影响" . | 管理评论 36 . 5 (2024) : 75-88 . |
| APA | 成全 , 蒋世辉 , 王海燕 . 政策工具对企业原始性创新能力的影响 . | 管理评论 , 2024 , 36 (5) , 75-88 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
研究政策工具对企业原始性创新能力的影响是提升企业原始性创新能力的基本前提，也是政府制定原始性创新政策的重要依据。本研究基于2011—2019年的规模以上工业企业科技活动数据，选取六种相关的原始性创新政策工具，并将其划分为供给型、需求型及环境型，然后通过改进柯布-道格拉斯生产函数，从政策工具协同作用及政策工具类型分布两类情境进行回归分析。研究扩展了企业原始性创新的政策工具箱，揭示了政策工具在实践应用中对企业原始性创新能力的影响。实证分析结果表明，相关部门应进一步开发与运用需求型、环境型政策工具，优化创新政策工具体系，加强对企业原始性创新政策工具的协同管理，强化监管力度，确保企业原始性创新的有效性与持续性。
Keyword ：
企业原始性创新 企业原始性创新 原始性创新能力 原始性创新能力 政策工具 政策工具
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 成全 , 蒋世辉 , 王海燕 . 政策工具对企业原始性创新能力的影响——基于省域工业企业科技活动面板数据的实证 [J]. | 管理评论 , 2024 , 36 (05) : 75-88 . |
| MLA | 成全 等. "政策工具对企业原始性创新能力的影响——基于省域工业企业科技活动面板数据的实证" . | 管理评论 36 . 05 (2024) : 75-88 . |
| APA | 成全 , 蒋世辉 , 王海燕 . 政策工具对企业原始性创新能力的影响——基于省域工业企业科技活动面板数据的实证 . | 管理评论 , 2024 , 36 (05) , 75-88 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In the context of high-quality economic development, technological innovation has emerged as a fundamental driver of socio-economic progress. The consequent proliferation of science and technology news, which acts as a vital medium for disseminating technological advancements and policy changes, has attracted considerable attention from technology management agencies and innovation organizations. Nevertheless, online science and technology news has historically exhibited characteristics such as limited scale, disorderliness, and multi-dimensionality, which is extremely inconvenient for users of deep application. While single-label classification techniques can effectively categorize textual information, they face challenges in leading science and technology news classification due to a lack of a hierarchical knowledge framework and insufficient capacity to reveal knowledge integration features. This study proposes a hierarchical multi-label classification model for science and technology news, enhanced by heterogeneous graph semantics. The model captures multi-dimensional themes and hierarchical structural features within science and technology news through a hierarchical transmission module. It integrates graph convolutional networks to extract node information and hierarchical relationships from heterogeneous graphs, while also incorporating prior knowledge from domain knowledge graphs to address data scarcity. This approach enhances the understanding and classification capabilities of the semantics of science and technology news. Experimental results demonstrate that the model achieves precision, recall, and F1 scores of 84.21%, 88.89%, and 86.49%, respectively, significantly surpassing baseline models. This research presents an innovative solution for hierarchical multi-label classification tasks, demonstrating significant application potential in addressing data scarcity and complex thematic classification challenges.
Keyword ：
Graph convolutional neural network Graph convolutional neural network Hierarchical multi-label classification Hierarchical multi-label classification Knowledge graph Knowledge graph Science and technology news Science and technology news
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Quan , Cheng, Jingyi , Chen, Jian et al. Hierarchical multi-label classification model for science and technology news based on heterogeneous graph semantic enhancement [J]. | PEERJ COMPUTER SCIENCE , 2024 , 10 . |
| MLA | Cheng, Quan et al. "Hierarchical multi-label classification model for science and technology news based on heterogeneous graph semantic enhancement" . | PEERJ COMPUTER SCIENCE 10 (2024) . |
| APA | Cheng, Quan , Cheng, Jingyi , Chen, Jian , Liu, Shaojun . Hierarchical multi-label classification model for science and technology news based on heterogeneous graph semantic enhancement . | PEERJ COMPUTER SCIENCE , 2024 , 10 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Acute complication prediction model is of great importance for the overall reduction of premature death in chronic diseases. The CLSTM-BPR proposed in this paper aims to improve the accuracy, interpretability, and generalizability of the existing disease prediction models. Firstly, through its complex neural network structure, CLSTM-BPR considers both disease commonality and patient characteristics in the prediction process. Secondly, by splicing the time series prediction algorithm and classifier, the judgment basis is given along with the prediction results. Finally, this model introduces the pairwise algorithm Bayesian Personalized Ranking (BPR) into the medical field for the first time, and achieves a good result in the diagnosis of six acute complications. Experiments on the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset show that the average Mean Absolute Error (MAE) of biomarker value prediction of the CLSTM-BPR model is 0.26, and the average accuracy (ACC) of the CLSTM-BPR model for acute complication diagnosis is 92.5%. Comparison experiments and ablation experiments further demonstrate the reliability of CLSTM-BPR in the prediction of acute complication, which is an advancement of current disease prediction tools.
Keyword ：
Bayesian Personalized Ranking (BPR) Bayesian Personalized Ranking (BPR) Biological system modeling Biological system modeling Business process re-engineering Business process re-engineering Classification algorithms Classification algorithms disease predictions disease predictions Long Short-Term Memory (LSTM) Long Short-Term Memory (LSTM) MIMICs MIMICs Prediction algorithms Prediction algorithms Predictive models Predictive models sudden illnesses sudden illnesses Time series analysis Time series analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Xi , Cheng, Quan . Acute Complication Prediction and Diagnosis Model CLSTM-BPR: A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking [J]. | TSINGHUA SCIENCE AND TECHNOLOGY , 2024 , 29 (5) : 1509-1523 . |
| MLA | Chen, Xi et al. "Acute Complication Prediction and Diagnosis Model CLSTM-BPR: A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking" . | TSINGHUA SCIENCE AND TECHNOLOGY 29 . 5 (2024) : 1509-1523 . |
| APA | Chen, Xi , Cheng, Quan . Acute Complication Prediction and Diagnosis Model CLSTM-BPR: A Fusion Method of Time Series Deep Learning and Bayesian Personalized Ranking . | TSINGHUA SCIENCE AND TECHNOLOGY , 2024 , 29 (5) , 1509-1523 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In the era of big data, classifying online tourism resource information can facilitate the matching of user needs with tourism resources and enhance the efficiency of tourism resource integration. However, most research in this field has concentrated on a simple classification problem with a single level of single labelling. In this paper, a Hierarchical Label-Aware Tourism-Informed Dual Graph Attention Network (HLT-DGAT) is proposed for the complex multi-level and multi-label classification presented by online textual information about Chinese tourism resources. This model integrates domain knowledge into a pre-trained language model and employs attention mechanisms to transform the text representation into the label-based representation. Subsequently, the model utilizes dual Graph Attention Network (GAT), with one component capturing vertical information and the other capturing horizontal information within the label hierarchy. The model's performance is validated on two commonly used public datasets as well as on a manually curated Chinese tourism resource dataset, which consists of online textual overviews of Chinese tourism resources above 3A level. Experimental results indicate that HLT-DGAT demonstrates superiority in threshold-based and area-under-curve evaluation metrics. Specifically, the AU(PRC) reaches 64.5 % on the Chinese tourism resource dataset with enforced leaf nodes, which is 3 % higher than the optimal corresponding metric of the baseline model. Furthermore, ablation studies show that (1) integrating domain knowledge, (2) combining local information, (3) considering label dependencies within the same level of label hierarchy, and (4) merging dynamic reconstruction can enhance overall model performance.
Keyword ：
Attention mechanism Attention mechanism Hierarchical multi-label text classification Hierarchical multi-label text classification Natural language processing Natural language processing Tourism resources Tourism resources
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Quan , Shi, Wenwan . Hierarchical multi-label text classification of tourism resources using a label-aware dual graph attention network [J]. | INFORMATION PROCESSING & MANAGEMENT , 2024 , 62 (1) . |
| MLA | Cheng, Quan et al. "Hierarchical multi-label text classification of tourism resources using a label-aware dual graph attention network" . | INFORMATION PROCESSING & MANAGEMENT 62 . 1 (2024) . |
| APA | Cheng, Quan , Shi, Wenwan . Hierarchical multi-label text classification of tourism resources using a label-aware dual graph attention network . | INFORMATION PROCESSING & MANAGEMENT , 2024 , 62 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Energy supply policy quality is an important factor that would impact national energy security. While existing research conducted policy evaluation from the lens of performance assessment, less study has been devoted to evaluating energy supply policy from the perspective of policy making. This study takes the energy supply policy documents issued by China's central government during the '13th Five-Year Plan' period (2016-2020) as the research sample, and pioneers the use of the extended policy modelling consistency (PMC) index model combined with the text mining methodology to construct a policy evaluation index system with the characteristics of the energy supply policy which conducts a more in-depth quantitative evaluation of the energy supply policy documents. The results show that the average PMC index value of China's energy supply policies is 7.26, and the overall quality is high. The concerns of existing policies are mainly focused on reform and development planning, safety production management and project engineering construction, but there is still room for improvement in policy predictability, coordination of policy areas, clarity of policy basis and goals and comprehensiveness of policy tool combinations. Based on this, China should improve the comprehensiveness of its energy supply policy tool combinations in terms of policy design norm; strengthen policy predictability and coordination of policy areas in terms of policy implementation guarantee; and clarify the basis and goals of policies in terms of policy orientation enhancement, to provide a reference basis for the formulation and improvement of future energy supply policies and to realise the sustainable development of energy supply. This study takes the energy supply policies issued by China's central government during the '13th Five-Year Plan' period as the object of research and utilises the extended policy modelling consistency index model to conduct a multidimensional evaluation of energy supply policies. The results show that the overall quality of China's energy supply policies is high, but there is still room for improvement in terms of policy predictability, coordination of policy areas, clarity of policy basis and goals and comprehensiveness of policy tool combinations. Based on this, this paper gives the corresponding suggestions to provide a reference basis for the formulation and improvement of subsequent energy supply policies.image
Keyword ：
energy supply policy energy supply policy PMC index model PMC index model policy evaluation policy evaluation text mining text mining
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Quan , Chen, Zhongzhen , Lin, Minwang et al. Quantitative evaluation of China's energy supply policies in the '13th Five-Year Plan' period (2016-2020): A PMC index modelling approach incorporating text mining [J]. | ENERGY SCIENCE & ENGINEERING , 2024 , 12 (3) : 596-616 . |
| MLA | Cheng, Quan et al. "Quantitative evaluation of China's energy supply policies in the '13th Five-Year Plan' period (2016-2020): A PMC index modelling approach incorporating text mining" . | ENERGY SCIENCE & ENGINEERING 12 . 3 (2024) : 596-616 . |
| APA | Cheng, Quan , Chen, Zhongzhen , Lin, Minwang , Wang, Haiyan . Quantitative evaluation of China's energy supply policies in the '13th Five-Year Plan' period (2016-2020): A PMC index modelling approach incorporating text mining . | ENERGY SCIENCE & ENGINEERING , 2024 , 12 (3) , 596-616 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
[目的]实现对互联网医疗健康平台用户生成的大量复杂信息的语义发现与关系揭示.[方法]构建基于改进CasRel实体关系抽取模型的在线健康信息语义发现模型,基于CasRel模型在文本编码层引入更适用于医疗健康领域的ERNIE-Health预训练模型,在主体、关系及客体解码层使用多级指针网络标注和神经网络融合主体特征进行关系及客体的解码.[结果]相较于原始CasRel模型,改进后的CasRel实体关系抽取模型在在线健康信息语义发现的实体识别和实体关系抽取任务中,F,值分别提升7.62个百分点和4.87个百分点.[局限]模型的整体效果还需要在数据集的体量扩充、不同疾病类型的健康信息实证环节进行验证.[结论]本研究提出的改进CasRel实体关系抽取模型能有效提升在线健康信息的语义发现能力.
Keyword ：
关系抽取 关系抽取 在线健康信息 在线健康信息 实体抽取 实体抽取 语义发现 语义发现
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 成全 , 蒋世辉 , 李卓卓 . 基于改进CasRel实体关系抽取模型的在线健康信息语义发现研究 [J]. | 数据分析与知识发现 , 2024 , 8 (10) : 112-124 . |
| MLA | 成全 et al. "基于改进CasRel实体关系抽取模型的在线健康信息语义发现研究" . | 数据分析与知识发现 8 . 10 (2024) : 112-124 . |
| APA | 成全 , 蒋世辉 , 李卓卓 . 基于改进CasRel实体关系抽取模型的在线健康信息语义发现研究 . | 数据分析与知识发现 , 2024 , 8 (10) , 112-124 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
As big data and artificial intelligence technologies are being increasingly applied in emergency management activities, effective information resource management has become more important. To support decision-making in emergency management, it is essential to effectively collect, integrate, organize, mine, develop and apply various emergency information resources. Therefore, research on Emergency Information Resource Management (EIRM) is urgently needed to develop a complete emergency management discipline system. The aim of this study is to conduct a systematic literature review of EIRM research in order to identify key areas of research progress and hotspots. This study used the bibliometric tool to analyze 6608 articles in the field of EIRM that were published from 2003 to 2022, which included research trend analysis, research power analysis, and research content analysis. The results revealed an upward trend in EIRM research over the past 20 years, with an average annual number of articles published of 330 and an average growth rate of 20.64 %. The countries with the highest number of publications in EIRM research are the USA (n = 1523), CHINA (n = 1233), and UNITED KINGDOM (n = 329). Moreover, the content analysis of these studies showed an evolution in the topics of EIRM research, moving from early medically controlled experimental studies to more specific disaster management and resilience studies. In conclusion, EIRM is a cross-disciplinary research field. Its important future research direction is to study how to process large-scale emergency information quickly and efficiently. Thus, it is essential to focus on overcoming the limitations of theoretical frameworks, technological development and application scenarios in order to realize a more efficient EIRM.
Keyword ：
Bibliometric analysis Bibliometric analysis Emergency information resource management (EIRM) Emergency information resource management (EIRM) Systematic review Systematic review
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Quan , Zhang, Shuangbao . Research status and evolution trends of emergency information resource management: Based on bibliometric analysis from 2003 to 2022 [J]. | INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION , 2023 , 97 . |
| MLA | Cheng, Quan et al. "Research status and evolution trends of emergency information resource management: Based on bibliometric analysis from 2003 to 2022" . | INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION 97 (2023) . |
| APA | Cheng, Quan , Zhang, Shuangbao . Research status and evolution trends of emergency information resource management: Based on bibliometric analysis from 2003 to 2022 . | INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION , 2023 , 97 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
