基于知识蒸馏的企业命名实体识别模型

BERT词嵌入模型能够解决简单命名实体识别模型预测精度低的问题，但基于BERT类的复杂词嵌入模型具有计算复杂度高、模型预测时间过长等缺陷。针对该问题，构建基于知识蒸馏的命名实体识别模型，将BERT+CRF模型作为教师模型，获取较高的命名实体识别精度，并基于模型结构相似原则将BiGRU+CRF作为学生模型，在学生模型训练的过程中进行知识蒸馏。知识蒸馏根据教师模型Softmax层和学生模型Softmax层输出的标注概率矩阵分别作为教师模型的知识和学生模型的知识，通过均方损失函数计算教师模型知识与学生模型知识之间的差距，将获得的结果作为软标签误差，将学生模型预测的标签结果与真实标签之间的误差作为硬标签误差，总误差为软标签误差与硬标签误差的加权和，通过误差反向传播进行模型的训练，在减小总误差的同时缩小教师模型知识与学生模型知识之间的差距，使学生模型预测精度接近教师模型。最终使用学生模型进行预测，在接近教师模型预测精度的同时保证相对较短的预测时间。在DuIE2.0数据集上的实验结果表明，该命名实体识别模型在F1值损失2.6%的情况下，可使模型参数规模缩小93.7%，从而缩短了65.2%的运算时间...     

基于ADVISOR软件的电池模型仿真分析

该文分析了ADVISOR软件中阻容型(RC)电池模型，并且利用ADVISOR软件中的电池模型程序对RC模型进行数据处理和模型验证。结果证明，该RC模型在车辆仿真中运行良好，与开路电压／内阻(Rint)模型相比，预测误差有明显的降低。最后，通过一个具体车型进行仿真，比较了RC模型与Rint模型的性能。     

工业过程混合建模方法研究及应用

文章在分析工业过程模型的经验模型和神经网络模型的基础上，提出了混合模型的建模方法，给出了混合模型结构和应用算法，把该混合模型方法应用于制浆蒸煮过程的建模中，收到了较好的效果，混合模型的建模方法具有较大的推广价值。     

演员模型：一种多媒体数据表达模型

本文提出一种多媒体数据表达模型：演员模型，该模型建立在多媒体数据库概念模型基础之上，基于库所—时间Ｐｅｔｒｉ网，描述多媒体对象之间的时态关系，同时引入与变迁相关联的场景表达式，描述多媒体对象之间的空间关系，从而模拟多媒体数据的时空编组，文中形式化地定义了演员模型的抽象模型和实现模型，提出多媒体对象的表达算法以及多媒体数据库的查询模型．     

基于动态分区的网格水文模型分布式计算

考虑到传统的水文模型串行计算方法无法满足当前复杂的水文模拟预报需求，为提高网格水文模型的计算效率，分析网格化水文模型计算中网格汇流特点，提出基于网格汇流流向的动态数据分区方法，不同分区数据可以并行计算，基于该方法提出基于Spark的网格水文模型分布式计算模型。通过在屯溪流域使用该模型与传统模型进行水文预报计算，验证了模型的高效性。     

基于流程图的资源环境模型复合方法

把资源环境模型抽象为模型类和模型实例2个层次，提出了基于模型类的模型复合策略。在Visual C++ .net 2003和Windows 2000环境下，用面向对象方法构建了模型类和模型实例，结合流程图实现了模型复合的可视化操作。结果表明，流程图较好地集成了可视化的用户界面和内部的模型复合操作，增强了资源环境模型库管理系统的易用性。     

ER模型与多维模型互相转换的研究

ER模型是管理信息系统中广泛使用的模型，但是它不能满足OLAP的需要；多维模型广泛应用在数据仓库的设计中，而企业数据通常又由ER模型定义。因此数据仓库设计的一个关键问题是如何建立ER模型与多维模型之间的关联。该文首先对ER模型与多维模型作了详细比较，然后结合实际应用，提出了ER模型与多维模型进行互相转化的条件和方法，从而将这两种模型有效地统一到了数据仓库设计过程中。     

Web平台无关模型到J2EE平台模型的转换

平台无关模型到平台相关模型的转换是OMG提出的模型驱动架构（MDA）中的关键技术。综合当前J2EE平台下广泛使用的多种应用框架，提出了一种包括静态模型、行为模型和展示模型3个部分的J2EE平台相关模型，将其作为目标模型并按结构定义、映射规则实现模型转换。该文描述了一种Web平台无关模型到J2EE平台模型的转换，体现了模型驱动开发的优点，提升了开发层次，由于受目标应用领域和特定技术对该模型限制较小，因此其具有较好的通用性。     

支持模型集成和重用的仿真语言研究

SRML是一种基于XML和脚本语言，用于表示仿真模型的参考标记语言。它试图确定一个灵活的表示仿真模型的参考标准，以加快模型的开发速度，支持模型的集成和重用，但是其草案大纲存在很多不足，需要进行扩展完善。总结了仿真模型集成和重用的关键因素，并提出结合DEVS、DEVS定义语言，研究扩展SRML的途径。重点介绍了DEVS和SRML之间的映射关系，以及SRML用于描述仿真模型的能力，如数据交互格式、继承关系、原子模型、组合模型、交互关系、仿真想定的描述等。扩展的SRML实现了仿真模型与仿真执行的分离，并继承了DEVS的所有特性，是一种平台无关的仿真语言，可以有效地支持仿真模型的集成和重用。     

基于关联假设的定性组合建模算法

组合建模是基于建模假设和模型片断库，构造定性仿真模型的自动化方法。关联假设是一类模型假设，它既可以用来定义模型片断本身，也可以定义有关模型片断使用的决策信息，将模型库与建模任务联系起来。在知识分类的基础上，该文提出了基于关联假设的模型组合算法，解决了定性仿真模型的构造问题，主要内容包括关联性的表示、关联推理算法及其具体实现，最后给出一个实例。     

一种基于UML用例模型的软件可靠性分配方法

基于统一建模语言(UML)用例模型描述软件系统需求方面的特点;提出了以UML用例图中所包含的各个用例的使用频率作为衡量该用例的重要程度的依据,从而确定每个用例的重要度的权重因子。根据每个用例的权重因子来确定每个用例该承担的可靠性指标任务,实现软件可靠性指标在各个用例之间进行合理的分配。这种分配方案对保证软件系统的可靠性目标具有重大的现实意义,为软件后续开发、测试、维护提供可以参考的依据。     

用例分析技术在需求建模中的应用

用例分析技术通过用例、执行者以及用例之间的关系来描绘系统外在可见的需求情况。文中介绍了用例分析技术易于软件开发人员与用户之间开展沟通与交流的特点,阐明了用例分析技术有助于提高需求分析的效率和质量。通过高炉开炉装料系统的开发实践,从执行者、用例和用例规约三方面,探讨了用例分析技术的建模步骤,从而描述了一种使用用例分析技术开展需求建模的有效的实现方法。     

Do perceived use contexts influence usage behavior? An instrument development of perceived use context

In this study, we advance current knowledge on IS usage behavior by introducing the concepts of time, location, social, and technological use in perceived use context. We develop an instrument to verify the effects of use context on intention-to-use game services. We find that contextual factors of perceived use context (i.e., perceived time use, perceived location use, perceived social use, and perceived technological use) influence users’ behavioral beliefs (i.e., perceived usefulness and perceived ease of use), which leads to their subsequent attitude and behavioral intention toward using game services. Grounded in our findings, key implications for theory and practice are discussed.     

Measuring the neighbourhood effect to calibrate land use models

Many spatially explicit land use models include the neighbourhood effect as a driver of land use changes. The neighbourhood effect includes the inertia of land uses over time, the conversion from one land use to another, and the attraction or repulsion of surrounding land uses. The neighbourhood effect is expressed in the neighbourhood rules, but calibration of the neighbourhood rules is not straightforward. This paper aims to characterise the neighbourhood effect of observed land use changes and use this information to improve the calibration of land use models. We measured the over- and underrepresentation of land uses in the neighbourhood of observed land use changes using a modified version of the enrichment factor. Enrichment factors of observed land use changes in Germany between 1990 and 2000 indicate that the neighbourhood effect exists. This suggests that it is appropriate to use neighbourhood rules to simulate urban land use changes. Observed enrichment factors were used to calibrate a land use model for Germany from 1990 to 2000 and the obtained neighbourhood rules were validated independently from 2000 to 2006. The results show that both the allocation accuracy and the pattern accuracy of the land use model improved for the calibration period, as well as for the independent validation period. This indicates that enrichment factors can be used to improve the calibration of the neighbourhood rules in land use models.     

The interplay between users’ intraorganizational social media use and social capital

The wide acceptance of social media by the public has caused companies try to use intraorganizational social media to increase employee work performance. However, simply implementing a platform is insufficient for success. Companies must encourage employees to use social media for work-related purposes. This study divided the use of intraorganizational social media into social- and work-related use and proposed a model based on the theory of social capital to explore the effects of social-related use on work-related use. The model was tested using a survey of users of intraorganizational microblog systems in China. The results indicate the relationships among two types of intraorganizational use and the dimensions of social capital, and that social-related use fosters work-related use directly and indirectly by enhancing social capital. These results facilitate an understanding of the value of social activities conducted using intraorganizational social media in organizations.     

基于遥感与GIS的黄土丘陵半干旱区土地利用定量化研究-以中国定西县为例

研究区域为典型的黄土丘陵沟壑半干旱区,以中国定西县为例。从1990年和2000年的Landsat TM影像图中提取两个时段的土地利用图,包括9种土地利用类型。从1∶10万的等高线数据中提取坡度数据。参考景观生态指标,我们选择或修改了10个指标实现定量化土地利用特征,动态监测土地利用变化,并分析地形与土地利用和土地利用变化的关系及土地利用变化与政府政策之间的关系。结果表明:①所选择的指标可以量化中国典型的黄土丘陵半干旱区土地利用及其变化特征,当转移矩阵采用不同的基数,可以体现不同的转换的量的特征;②土地利用与土地利用变化在不同坡度的空间分布上有很好的规律性;③政府政策是土地利用变化的主要驱动力因素,包括梯田改造、集雨工程和退耕还林还草。     

The Five Factor Model of personality and employees’ excessive use of technology

Prior research has stressed the negative effects employee technology addiction, or excessive use, may have in the workplace. This study explored personality, through use of the Five Factor Model (FFM), and problem and pathological technology (Internet and text-messaging) use. Personality was found to predict certain aspects of technology use. Specifically, conscientiousness was negatively related to problem Internet use. However, the FFM did not add to the prediction of pathological Internet use or problem and pathological text-messaging use. These findings suggest that some dimensions of the FFM may be useful in explaining why certain employees may be predisposed to developing problem use tendencies. Implications of the current findings as well as limitations and future directions are discussed.     

A method to analyse neighbourhood characteristics of land use patterns

Neighbourhood interactions between land use types are often included in the spatially explicit analysis of land use change. Especially in the context of urban growth, neighbourhood interactions are often addressed both in theories for urban development and in dynamic models of (urban) land use change. Neighbourhood interactions are one of the main driving factors in a large group of land use change models based on cellular automata (CA).This paper introduces a method to analyse the neighbourhood characteristics of land use. For every location in a rectangular grid the enrichment of the neighbourhood by specific land use types is studied. An application of the method for the Netherlands indicates that different land use types have clearly distinct neighbourhood characteristics. Land use conversions can be explained, for a large part, by the occurrence of land uses in the neighbourhood.The neighbourhood characterization introduced in this paper can help to further unravel the processes of land use change allocation and assist in the definition of transition rules for cellular automata and other land use change models.