Keyphrase Generation Based on Self-Attention Mechanism

Keyphrase greatly provides summarized and valuable information. This information can help us not only understand text semantics, but also organize and retrieve text content effectively. The task of automatically generating it has received considerable attention in recent decades. From the previous studies, we can see many workable solutions for obtaining keyphrases. One method is to divide the content to be summarized into multiple blocks of text, then we rank and select the most important content. The disadvantage of this method is that it cannot identify keyphrase that does not include in the text, let alone get the real semantic meaning hidden in the text. Another approach uses recurrent neural networks to generate keyphrases from the semantic aspects of the text, but the inherently sequential nature precludes parallelization within training examples, and distances have limitations on context dependencies. Previous works have demonstrated the benefits of the self-attention mechanism, which can learn global text dependency features and can be parallelized. Inspired by the above observation, we propose a keyphrase generation model, which is based entirely on the self-attention mechanism. It is an encoder-decoder model that can make up the above disadvantage effectively. In addition, we also consider the semantic similarity between keyphrases, and add semantic similarity processing module into the model. This proposed model, which is demonstrated by empirical analysis on five datasets, can achieve competitive performance compared to baseline methods.     

ACLSTM: A Novel Method for CQA Answer Quality Prediction Based on Question-Answer Joint Learning

Given the limitations of the community question answering (CQA) answer quality prediction method in measuring the semantic information of the answer text, this paper proposes an answer quality prediction model based on the question-answer joint learning (ACLSTM). The attention mechanism is used to obtain the dependency relationship between the Question-and-Answer (Q&A) pairs. Convolutional Neural Network (CNN) and Long Short-term Memory Network (LSTM) are used to extract semantic features of Q&A pairs and calculate their matching degree. Besides, answer semantic representation is combined with other effective extended features as the input representation of the fully connected layer. Compared with other quality prediction models, the ACLSTM model can effectively improve the prediction effect of answer quality. In particular, the mediumquality answer prediction, and its prediction effect is improved after adding effective extended features. Experiments prove that after the ACLSTM model learning, the Q&A pairs can better measure the semantic match between each other, fully reflecting the model’s superior performance in the semantic information processing of the answer text.     

Neural Dialogue Model with Retrieval Attention for Personalized Response Generation

With the success of new speech-based human-computer interfaces, there is agreat need for effective and friendly dialogue agents that can communicate with peoplenaturally and continuously. However, the lack of personality and consistency is one ofcritical problems in neural dialogue systems. In this paper, we aim to generate consistentresponse with fixed profile and background information for building a realistic dialoguesystem. Based on the encoder-decoder model, we propose a retrieval mechanism to delivernatural and fluent response with proper information from a profile database. Moreover, inorder to improve the efficiency of training the dataset related to profile information, weadopt a method of pre-training and adjustment for general dataset and profile dataset. Ourmodel is trained by social dialogue data from Weibo. According to both automatic andhuman evaluation metrics, the proposed model significantly outperforms standardencoder-decoder model and other improved models on providing the correct profile andhigh-quality responses.     

基于特征金字塔的多尺度特征融合网络

特征金字塔网络（FPN）是CNN网络对图像信息进行表达输出的一种有效方法,在目标检测网络中广泛应用．然而,FPN没有充分地将浅层的细节信息传递到深层的语义特征,存在特征融合不足的缺陷,因而只能依靠深层语义信息来进行预测,从而忽略了网络低层细节信息,对各种视觉学习的效果造成了一定的影响．针对FPN存在的以上问题,本文提出基于特征金字塔的多尺度特征融合网络模型,在FPN主干网络的基础上,设计了混合特征金字塔和金字塔融合模块,并结合注意力机制,对特征金字塔进行了多尺度的深度融合．本文在PASCAL VOC2012和MS COCO2014数据集上,以Faster R-CNN作为基础检测器进行实验,验证了MFPN对特征融合的有效性．     

基于碳排放权交易的发电用煤价格模型

2017年12月我国正式下发《全国碳排放权交易市场建设方案（发电行业）》,发电企业率先开展全国碳排放权交易,碳排放权交易价格将显著影响发电企业的燃料总成本。通过分析国内主要碳排放权交易市场现状、核算燃煤发电企业碳排放量以及分析现有煤炭交易价格变化,探讨了典型煤炭平仓价格模型,建立了燃煤发电企业在碳排放权交易约束条件下的煤炭平仓价格主要模型。碳成本占燃料成本约20%,新模型综合考虑碳排放权交易的需求,为燃煤发电企业完善燃料采购策略和抵御碳排放权交易风险提供了新的核算方法。     

有限元领域中基于孔特征抑制的模型态生成研究

在有限元领域,对复杂模型进行分析需要耗费巨大的计算资源,如何在保证计算精度的前提下有效提高计算效率一直是一项研究重点。为解决这个问题,引入多态模型理论,通过生成合适的模型态来取得结果精度与计算时间的平衡点。因此,模型态的质量直接关系到计算效率的提升程度。孔特征作为有限元分析模型的常见特征,对计算规模有重要影响。文章基于特征抑制的方式探索模型中孔特征的合适处理策略,并结合孔特征的几何属性估计不同策略下生成的模型态的计算精度和计算规模。在此基础上找出几何属性之间存在相互制约的关系,根据经典的加权方法将多目标问题转化成单目标问题,建立模型态选择标准并使用遗传算法选择出最优模型态。     

垃圾填埋场气体产生及其模型研究

对填埋气的回收利用，既能减排温室气体，又能回收能源。分析了填埋气产生的原理和过程，对目前出现的填埋场产气模型进行了分类，并系统地分析了各种产气模型的计算方法、优缺点以及适用条件，为填埋气体的大规模利用提供可靠的方法。     

Information Extraction Based on Multi-turn Question Answering forAnalyzing Korean Research Trends

Analyzing Research and Development (R&D) trends is important because it can influence future decisions regarding R&D direction. In typical trend analysis, topic or technology taxonomies are employed to compute the popularities of the topics or codes over time. Although it is simple and effective, the taxonomies are difficult to manage because new technologies are introduced rapidly. Therefore, recent studies exploit deep learning to extract pre-defined targets such as problems and solutions. Based on the recent advances in question answering (QA) using deep learning, we adopt a multi-turn QA model to extract problems and solutions from Korean R&D reports. With the previous research, we use the reports directly and analyze the difficulties in handling them using QA style on Information Extraction (IE) for sentence-level benchmark dataset. After investigating the characteristics of Korean R&D, we propose a model to deal with multiple and repeated appearances of targets in the reports. Accordingly, we propose a model that includes an algorithm with two novel modules and a prompt. A newly proposed methodology focuses on reformulating a question without a static template or pre-defined knowledge. We show the effectiveness of the proposed model using a Korean R&D report dataset that we constructed and presented an in-depth analysis of the benefits of the multi-turn QA model.     

基于非线性黏弹性本构模型的轮胎滚动和生热

轮胎的滚动阻力和自生热是造成轮胎失效的原因之一,轮胎内部能量的产生主要取决于轮胎中橡胶材料的黏弹性能量耗散。文中基于超弹性模型和并行流变模型(PRF)描述了橡胶材料的非线性黏弹性响应特征,提出了一种预测实心轮胎温度分布和滚动阻力的方法。首先将线性黏弹性Prony级数转化为PRF模型的初始参数,并利用Isight软件根据多应变工况加载得到的应力松弛测试数据来校准材料参数,然后采用显式-热力耦合分析方法分析基于Prony级数和PRF模型的实心轮胎滚动过程的差异。结果表明,Prony级数无法描述橡胶材料的非线性行为,在显式动力学下计算的轮胎生热结果为0;PRF模型可以表征橡胶材料的非线性行为,并且计算的轮胎模型在0.3 s内温度上升了0.14℃。     

基于自动拆卸过程的装配序列生成方法研究

装配序列生成是装配工艺规划的基本任务,设计了一个基于自动拆卸过程的装配序列生成算法。首先,进行自动拆卸仿真,通过过程中的干涉检查生成可行的装配序列集。然后,定义了三类装配序列优先约束规则,对可行序列集进行过滤选择,得到可用于最终评价的少量装配序列。该算法在SolidWorks平台上得到了实现,给出了实例验证。     

基于注意力模型的多传感器人类活动识别

深度循环神经网络适用于处理时间序列数据, 然而循环神经网络特征提取能力差, 时间依赖关系挖掘不足。针对此问题, 提出了3种注意力机制和长短时记忆(LSTM)神经网络结合的模型用于人类活动识别问题, 并研究了3种注意力机制在不同数据集上单独及配合使用时对模型精度的影响。对于UCI_HAR数据集, 3种注意力LSTM模型准确率分别为94.13%、95.15%和94.81%,高于LSTM模型识别准确率93.2%。此外, 针对人类活动识别的传感器时间序列数据的标签特点, 提出将时间段分类任务转化为分割任务, 设计了2个基于分割任务的注意力门控循环单元(GRU)神经网络模型, Bahdanau注意力GRU模型在Skoda数据集和机会(Oppor)数据集准确率为84.61%和89.54%, 高于基准UNet模型的70.40%和88.51%。     

基于表面等离子体的非线性二次谐波增强效应

本文研究一种利用金属光栅结构激发表面等离子体,实现增强非线性二次谐波激发效率的方法.通过设计金属光栅周期、沟槽深度等结构参数,使其满足推导出的准相位匹配条件,实现泵浦光与倍频光的表面等离子体模式同时共振激发,得到高效输出的倍频光.文中利用时域有限差分方法对该方法进行了模拟仿真,验证了准相位匹配条件和共振激发表面等离子体模式对提高二次谐波输出的关键性作用,同时分析了光栅结构参数变化对二次谐波激发效率的影响规律.     

基于深度学习的虚拟人物形象生成和设计研究

目的 为实现虚拟人物形象与用户情感偏好的匹配,提高虚拟人物形象设计效率,提出基于深度学习方法的虚拟人物图像生成方法。方法 首先收集相关风格图片并制作数据集,用于初始模型的微调;其次确定用户对虚拟形象的情感偏好与细节要求,得到生成所需的文本提示词;再次通过文本生成的方式迭代生成目标形象并初步筛选符合要求的形象;最后通过图像生成对形象进行局部优化和调整,使其符合用户情感目标。结果 以虚拟人物形象为研究对象,运用基于Stable diffusion模型的文本和图像两种生成方法得到符合用户情感需求与偏好的虚拟人物形象产品,并可快速调整人物形象的细节特征。结论 通过实例验证,所提方法可快速、高质量生成符合用户情感目标的虚拟人物形象,极大地提高虚拟人物形象设计的效率,丰富设计方法。     

一种基于注意机制和卷积神经网络的视觉模型

针对目前的深度卷积神经网络(CNN)模型规模大、训练参数多、计算速度慢以及难以移植到移动端等问题,提出了一种深度可分离卷积结合3重注意机制模块(DSC-TAM)的视觉模型.首先,通过深度可分离卷积网络来减少模型参数,提高网络模型的计算速度;其次,引入3重注意机制模块提高网络的特征提取能力,改善网络性能.实验结果表明:该...     

机械制图试题库系统的研究与开发

机械制图试题库系统的研究是工程制图计算机辅助教学软件开发的热点之一。由于多种原因,成熟的机械制图试题库系统尚不多见。本文以ＡｕｔｏＣＡＤ为支撑软件,在微机上开发了内容体系比较完整的机械制图试题库系统,系统是一个具有人工智能性质的图形计算机辅助设计系统,管理系统及度题全部用高级语言开发,较好的解决了空间占用、运行速度、加扩展、用户友好、开放性等技术问题。     

基于子图拓扑扩展的徼派建筑快速建模方法

古代传统特色建筑快速建模技术的研究是虚拟现实研究领域的重要课题。同时也具有重大的文化意义。该文在总结徽派建筑模块化的基础上,提出了一种基于拓扑自动生成的徽派建筑快速建模方法。通过对生成的拓扑图进行遍历渲染得到徽派建筑场景模型,说明了算法适合类似于徽派建筑的特色建筑的快速、自动建模。     

藏族家具装饰纹样与风格探讨

概括了藏族装饰纹样及其美感形式,对传统藏族家具进行分类并分析其结构特点、装饰纹样及装饰手法,总结了藏族家具的风格特点,不仅展示了藏族家具独特的装饰艺术,更加强人们对藏族家具的认知,以及为设计师提供一些新的设计思路。