检索结果-南通市图书馆

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

通过个性化推荐系统提升消费者购物体验

数字经济 2024年第6期 83-85页

作者：张玮佳 ntt data China

本研究基于大数据,深入分析了电商平台用户的行为数据,建立了用户行为分析模型,并通过聚类分析和协同过滤算法,构建了个性化商品推荐系统。该系统能够精准识别用户的购物偏好,提供个性化推荐,有效提升了用户购买转化率和满意度,具有显... 详细信息

本研究基于大数据,深入分析了电商平台用户的行为数据,建立了用户行为分析模型,并通过聚类分析和协同过滤算法,构建了个性化商品推荐系统。该系统能够精准识别用户的购物偏好,提供个性化推荐,有效提升了用户购买转化率和满意度,具有显著的实际应用价值。

关键词：个性化推荐大数据协同过滤算法聚类分析购物体验电商平台精准识别行为数据

基于大数据的电商平台用户分析及个性化推荐研究

在线全文

学校读者我要写书评

暂无评论

现代计算机 2024年第16期30卷 57-62页

作者：张玮佳 ntt data China 上海200051

在基于大数据的电子商务蓬勃发展的今天,受到云计算、大数据以及机器学习技术发展的影响,零售企业得以从多角度去做更多的在线业务的尝试和突破。其中,对于公共平台和自有电商平台用户分析及个性化推荐正在成为一个焦点。基于大数据的... 详细信息

在基于大数据的电子商务蓬勃发展的今天,受到云计算、大数据以及机器学习技术发展的影响,零售企业得以从多角度去做更多的在线业务的尝试和突破。其中,对于公共平台和自有电商平台用户分析及个性化推荐正在成为一个焦点。基于大数据的电商平台用户分析,对零售企业基于当前市场环境下所采用的典型的用户分析和个性化推荐的业务和技术解决方案进行研究。

关键词：云计算数据分析机器学习 AWS A/B测试

Graph reasoning over explicit semantic relation

在线全文

学校读者我要写书评

暂无评论

High-Confidence Computing

High-Confidence Computing 2024年第2期4卷 136-144页

作者： Tianyou Zhu Shi Liu Bo Li Junjian Liu Pufan Liu Fei Zheng State Grid corporation of China Beijing 100031China

Multi-hop reasoning over language or graphs represents a significant challenge in contemporary research,particularly with the reliance on deep neural *** networks are integral to text reasoning processes,yet they present challenges in extracting and representing domain or commonsense knowledge,and they often lack robust logical reasoning *** address these issues,we introduce an innovative text reasoning *** framework is grounded in the use of a semantic relation graph and a graph neural network,designed to enhance the model’s ability to encapsulate knowledge and facilitate complex multi-hop *** framework operates by extracting knowledge from a broad range of *** constructs a semantic relationship graph based on the logical relationships inherent in the reasoning *** with the core question,the framework methodically deduces key knowledge,using it as a guide to iteratively establish a complete evidence chain,thereby determining the final *** the advanced reasoning capabilities of the graph neural network,this approach is adept at multi-hop logical *** demonstrates strong performance in tasks like machine reading comprehension and question answering,while also clearly delineating the path of logical reasoning.

关键词： Semantic relation graph Multi-hop reasoning Graph neural network

Evolution of Cenozoic sedimentary architecture in Central and Southern South China Sea basins

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Palaeogeography 2024年第1期13卷 35-53页

作者： Wu Tang Xiao-Jun Xie Yi-Bo Wang Lian-Qiao Xiong Jia Guo Xin Li China National Offshore Oil corporation Research Institute Beijing 100028China

The Central and Southern South China Sea(CSSCS) has a complex tectonic dynamic background and abundant oil and gas resources, which has always been a hot topic of academic and industrial ***, systematic analyses are still lacking regarding its sediment filling structure and evolution, mostly due to limited borehole penetration and poor quality of seismic reflection data for deeply buried sequences. No consensus has been reached yet on the sedimentary infilling processes, which impeded the reconstruction of the palaeogeography of Southeast Asia and the oil-and-gas exploration undertakings. Here, we illustrate the Cenozoic sedimentary evolution of the CSSCS region by synthesizing relevant data from previous literature and our own observations and displaying the evolution of depositional systems in sequential reconstructions. Besides, the controlling factors of preferred sedimentary scenarios in the CSSCS incorporate the latest interpretations of the spreading of South China Sea(SCS) as well as the demise of the hypothetical Proto-South China Sea(PSCS). The results show that there are three types of sedimentary basins in the CSSCS(foreland,strike-slip, and rift basins) with different sedimentary filling structures. The foreland basins formed a depositional pattern of ‘transition from deep water to shallow water environments', dominated by deep-water depositional systems which were formed before the Early Oligocene with submarine fans developed. Later,the foreland basins were gradually dominated by shallow-water depositional systems with deltas and shallow marine facies. The strike-slip basins showed the depositional architecture of ‘transition from lake to marine environments', i.e. the basins were dominated by lacustrine deposits during the Eocene and evolved into the marine depositional environment since Oligocene with delta developed in the western part of the basin. The depositional evolution of rift basins illustrated the characteristics of 'transiti

关键词： Central and Southern South China Sea Sedimentary filling Main controlling factors Proto-South China Sea South China Sea

Combinatorial reasoning-based abnormal sensor recognition method for subsea production control system

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第4期21卷 2758-2768页

作者： Rui Zhang Bao-Ping Cai Chao Yang Yu-Ming Zhou Yong-Hong Liu Xin-Yang Qi College of Mechanical and Electronic Engineering China University of Petroleum BGP Inc. China National Petroleum Corporation

The subsea production system is a vital equipment for offshore oil and gas production. The control system is one of the most important parts of it. Collecting and processing the signals of subsea sensors is the only way to judge whether the subsea production control system is normal. However, subsea sensors degrade rapidly due to harsh working environments and long service time. This leads to frequent false alarm incidents. A combinatorial reasoning-based abnormal sensor recognition method for subsea production control system is proposed. A combinatorial algorithm is proposed to group sensors. The long short-term memory network(LSTM) is used to establish a single inference model. A counting-based judging method is proposed to identify abnormal sensors. Field data from an offshore platform in the South China Sea is used to demonstrate the effect of the proposed method. The results show that the proposed method can identify the abnormal sensors effectively.

关键词： Abnormal sensor Combinatorial algorithm Fault identification Subsea production control system

Causal temporal graph attention network for fault diagnosis of chemical processes

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第6期70卷 20-32页

作者： Jiaojiao Luo Zhehao Jin Heping Jin Qian Li Xu Ji Yiyang Dai School of Chemical Engineering Sichuan UniversityChengdu 610065China China Three Gorges corporation Beijing 100038China

Fault detection and diagnosis(FDD)plays a significant role in ensuring the safety and stability of chemical *** the development of artificial intelligence(AI)and big data technologies,data-driven approaches with excellent performance are widely used for FDD in chemical ***,improved predictive accuracy has often been achieved through increased model complexity,which turns models into black-box methods and causes uncertainty regarding their *** this study,a causal temporal graph attention network(CTGAN)is proposed for fault diagnosis of chemical processes.A chemical causal graph is built by causal inference to represent the propagation path of *** attention mechanism and chemical causal graph were combined to help us notice the key variables relating to fault *** in the Tennessee Eastman(TE)process and the green ammonia(GA)process showed that CTGAN achieved high performance and good explainability.

关键词： Chemical processes Safety Fault diagnosis Causal discovery Attention mechanism Explainability

An intelligent control method based on artificial neural network for numerical flight simulation of the basic finner projectile with pitching maneuver

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第2期32卷 663-674页

作者： Yiming Liang Guangning Li Min Xu Junmin Zhao Feng Hao Hongbo Shi Northwestern Polytechnical University School of Astronautics Xi’an 710072China China North Industries Group corporation No 203 Research Institute Xi’an 710065China

In this paper,an intelligent control method applying on numerical virtual flight is *** proposed algorithm is verified and evaluated by combining with the case of the basic finner projectile model and shows a good application ***,a numerical virtual flight simulation model based on overlapping dynamic mesh technology is *** order to verify the accuracy of the dynamic grid technology and the calculation of unsteady flow,a numerical simulation of the basic finner projectile without control is carried *** simulation results are in good agreement with the experiment data which shows that the algorithm used in this paper can also be used in the design and evaluation of the intelligent controller in the numerical virtual flight ***,combined with the real-time control requirements of aerodynamic,attitude and displacement parameters of the projectile during the flight process,the numerical simulations of the basic finner projectile’s pitch channel are carried out under the traditional PID(Proportional-Integral-Derivative)control strategy and the intelligent PID control strategy *** intelligent PID controller based on BP(Back Propagation)neural network can realize online learning and self-optimization of control parameters according to the acquired real-time flight *** with the traditional PID controller,the concerned control variable overshoot,rise time,transition time and steady state error and other performance indicators have been greatly improved,and the higher the learning efficiency or the inertia coefficient,the faster the system,the larger the overshoot,and the smaller the stability *** intelligent control method applying on numerical virtual flight is capable of solving the complicated unsteady motion and flow with the intelligent PID control strategy and has a strong promotion to engineering application.

关键词： Numerical virtual flight Intelligent control BP neural network PID Moving chimera grid

Effect of Skeleton Grain Size on the Saturation of Gas Hydrate in Natural Sediments

在线全文

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2024年第3期23卷 676-682页

作者： XU Zhenqiang LI Yang College of Marine Sciences Ocean University of ChinaQingdao 266100China China Petroleum&Chemical corporation Beijing 100728China

Natural gas hydrate is prospected as a new and promising,highly clean energy resource that mainly occurs in perma-frost or at continental *** formation is subject to many soil conditions,such as grain size,matrix materials,pore morphology,and *** this study,we propose that grain size is the most decisive parameter that affects the saturation of gas hydrate in sediments based on data from Ocean Drilling Program Leg 164 and Mallik 5L-38,which represent marine sediments and terrestrial sediments,*** study reveals that high gas hydrate saturation generally occurs in coarse-grained sand,regardless of whether sediment formation is homogeneous or inhomogeneous,and the sorting of sediments may affect the hydrate saturation to a certain *** grain size and sorting of sediments may be the most intuitive proxy method for a rough estimation of hydrate *** study is necessary to fully understand the relationship between hydrate morphology and sediment grain size,even though massive hydrates are typically found in fine clayey-rich sediments.

关键词： grain size saturation gas hydrates ODP Leg 164 Mallik 5L-38

Proposal of Rip-up &Re-allocate Algorithm for Optical Layer-2 Switch Network

在线全文

学校读者我要写书评

暂无评论

光子学报 2014年第7期43卷 34-41页

作者： Masahiro NAKAGAWA Kyota HATTORI Naoki KIMISHIMA Masaru KATAYAMA Akira MISAWA ntt Network Service Systems Laboratories NTT Corporation

We are developing an optical layer-2s witch network that uses both wavelength-division multiplexing and time-division multiplexing technologies for efficient traffic aggregation in metro *** efficient traffic aggregation,path bandwidth control is key because it strongly affects bandwidth *** this paper,we propose a dynamic time-slot allocation method that uses periodic information of difference values of traffic *** method can derive near-optimal allocation with lower computational cost,which enlarges the maximum available network size compared with conventional time-slot allocation *** results show that the proposed method enables dynamic path control in 1K-node-scale optical layer-2s witch network,which leads to cost-effective metro networks.

关键词：交通聚集技术地铁网络成本效益交通管理