A novel similarity measurement approach considering intrinsic user groups in collaborative filtering

To improve the similarity measurement between users, a similarity measurement approach incorporating clusters of intrinsic user groups（ SMCUG） is proposed considering the social information of users. The approach constructs the taxonomy trees for each categorical attribute of users. Based on the taxonomy trees, the distance between numerical and categorical attributes is computed in a unified framework via a proper weight. Then, using the proposed distance method, the nave k-means cluster method is modified to compute the intrinsic user groups. Finally, the user group information is incorporated to improve the performance of traditional similarity measurement. A series of experiments are performed on a real world dataset, M ovie Lens. Results demonstrate that the proposed approach considerably outperforms the traditional approaches in the prediction accuracy in collaborative filtering.

Current Situation and Mode of Talent Training in Marine Cultural Industry Based on Collaborative Innovation of Governments,Enterprises,Colleges,Scientific Institutions and Users

Based on the present situation of talent training in marine cultural industry,the collaborative innovation mechanism of governments,enterprises,colleges,scientific institutions and users was used to construct the mode of talent training in marine cultural industry. It is needed to give full play to the active roles of governments,enterprises,colleges,scientific institutions and users in the training of marine cultural talents,develop training mode of innovative scientific and technological talents,speed up the construction of collaborative innovation ability of marine cultural talents,and improve the efficiency of talent training.

Improved Collaborative Filtering Recommendation Based on Classification and User Trust

When dealing with the ratings from users,traditional collaborative filtering algorithms do not consider the credibility of rating data,which affects the accuracy of similarity.To address this issue,the paper proposes an improved algorithm based on classification and user trust.It firstly classifies all the ratings by the categories of items.And then,for each category,it evaluates the trustworthy degree of each user on the category and imposes the degree on the ratings of the user.Finally,the algorithm explores the similarities between users,finds the nearest neighbors,and makes recommendations within each category.Simulations show that the improved algorithm outperforms the traditional collaborative filtering algorithms and enhances the accuracy of recommendation.

Choice between Ways of Talent Training in Marine Cultural Industry--Based on Collaborative Innovation of Governments, Enterprises, Colleges, Scientific Institutions and Users

Based on the present situation of talent training in marine cultural industry,the collaborative innovation mode of governments,enterprises,colleges,scientific institutions and users was used to study the ways of talent training in marine cultural industry.

Study on Talent Training Mechanisms of Marine Cultural Industry Based on Collaborative Innovation of Governments,Enterprises,Colleges,Scientific Institutions and Users

Based on the review of related concepts,the current situation and problems of talent training in marine cultural industry in China were analyzed,and talent training mechanisms of marine cultural industry based on collaborative innovation of governments,enterprises,colleges,scientific institutions and users were proposed to promote the transformation,upgrading and vigorous development of marine cultural industry,accelerate the spread of marine culture with Chinese characteristics,and build China into a maritime power.

Improved Hybrid Deep Collaborative Filtering Approach for True Recommendations

Recommendation services become an essential and hot research topic for researchers nowadays.Social data such asReviews play an important role in the recommendation of the products.Improvement was achieved by deep learning approaches for capturing user and product information from a short text.However,such previously used approaches do not fairly and efficiently incorporate users’preferences and product characteristics.The proposed novel Hybrid Deep Collaborative Filtering(HDCF)model combines deep learning capabilities and deep interaction modeling with high performance for True Recommendations.To overcome the cold start problem,the new overall rating is generated by aggregating the Deep Multivariate Rating DMR(Votes,Likes,Stars,and Sentiment scores of reviews)from different external data sources because different sites have different rating scores about the same product that make confusion for the user to make a decision,either product is truly popular or not.The proposed novel HDCF model consists of four major modules such as User Product Attention,Deep Collaborative Filtering,Neural Sentiment Classifier,and Deep Multivariate Rating(UPA-DCF+NSC+DMR)to solve the addressed problems.Experimental results demonstrate that our novel model is outperforming state-of-the-art IMDb,Yelp2013,and Yelp2014 datasets for the true top-n recommendation of products using HDCF to increase the accuracy,confidence,and trust of recommendation services.

Application of Collaborative Innovation of Governments,Enterprises,Colleges,Scientific Institutions and Users in the Talent Training of Marine Cultural Industry: A Case Study of Maritime Universities

Based on the literature review of collaborative innovation of governments, enterprises, colleges, scientific institutions and users, the ap-plication situation of collaborative innovation of governments, enterprises, colleges, scientific institutions and users in the talent training of marine cultural industry in maritime universities was analyzed, and the problems existing in the talent training of marine cultural industry were explored. Finally, corresponding countermeasures and suggestions were put forward.

Research on Talent Training System of Marine Cultural Industry Based on Collaborative Innovation of Governments,Enterprises,Colleges,Scientific Institutions and Users

This paper focuses on the coupling between talent training system of marine cultural industry and collaborative innovation of govern-ments, enterprises, colleges, scientific institutions and users. Firstly, the significance of talent training in marine cultural industry for the construction of China as a maritime power was analyzed. Secondly, the current situation of talent training in China＇s marine cultural industry and the existing problems were analyzed. Finally, how to integrate the collaborative innovation of governments, enterprises, colleges, scientific institutions and us-ers into the talent training system of marine cultural industry was explored to help talent training to break through the bottleneck and promote the vig-orous development of marine cultural industry.

协同视域下工科研究生产学研用培养模式探究与实践

加强协同创新是提高工科研究生创新实践能力的内在要求,完善产学研用是建立以创新创业为导向培养机制的必然方式。当前,地方高校工科研究生创新实践能力与经济社会对人才的需求仍存在一定的差距,主要表现在创新意识淡薄、实用成果匮乏、聚焦思考不足,究其原因,问题意识缺乏、知识来源单一、学习氛围封闭是导致问题出现的主要因素。为此,作者团队与行业企业联合建成太阳能光热产业示范基地,以实际需求为导向,以工程示范为载体,以成果转化为驱动,以产业应用为目标,探索产学研用的协同创新工科研究生培养新模式,尝试在多个产业示范基地建立具有鲜明工科特色的“科技小站”,通过模式与实践的高效融合,充分释放研究生的内在创新要素活力。

参与式设计影响要素探析

针对参与式设计概念模糊以及用户参与性较弱现状,明确参与式设计要素,梳理用户参与目的、参与方法和工具。围绕参与式设计协作要素:参与者知识和参与工具,具体阐述参与对象和参与模式。并将参与式设计中的工具、技术和方法从参与形式角度分成制作、讲述和表演3类,探讨具体应用时目的与方式。参与式设计是一种设计理念,在设计过程中应用各种工具和方法获取用户的需求以及创新想法。通过分析参与要素与方法特点,设计实现非专家用户参与设计过程的工具,将对参与式设计在用户研究领域的应用具有重要意义。

基于用户兴趣模型的个性化旅游线路生成建模研究

针对个性化旅游线路生成过程中用户个人喜好分析环节较为薄弱,依照用户兴趣分析结果生成路线景点过于分散,旅游线路景区覆盖率较低的问题,提出一种基于用户兴趣模型的个性化旅游线路生成建模方法。获取用户数据,并按照显性兴趣、隐性兴趣的分类方式设定数据标签,完成数据预处理。根据关联规则结合数据预处理结果,构建用户兴趣模型,分析用户对部分旅游目的地的兴趣值以及用户的旅游行为特征。基于用户兴趣模型的个性化旅游线路生成建模方法设计完成。实验结果证实,所提模型可有效克服用户个人喜好分析问题,提升旅游线路景区覆盖率。

九论以用户为中心的设计:智能时代的“用户体验3.0”范式

基于“以用户为中心设计”理念的用户体验(UX)领域正在迈向智能时代,但是现有的UX范式主要针对非智能系统,缺乏针对智能系统UX的系统化方法。纵观UX的发展历程,UX范式呈现出跨技术时代的演进特征。当前,智能时代对UX范式提出了新要求。为此,本文从UX范式出发,提出智能时代的“UX 3.0”范式框架以及相应的方法体系。“UX 3.0”范式框架包括五大类UX方法:生态化体验、创新赋能体验、AI赋能体验、人智交互体验、人智协同合作体验方法,其中每一类方法都包括相应的UX范式取向。“UX 3.0”范式的提出有助于提升现有UX方法,为智能系统UX研究和应用提供方法论支持。最后,本文展望“UX 3.0”范式今后的研究和应用。

考虑数据稀疏性的图书推荐协同过滤算法仿真

图书推荐算法易忽略数据稀疏性问题,导致推荐结果与用户感兴趣内容之间存在较大的偏差。在考虑数据稀疏性的基础上提出一种图书推荐协同过滤算法,对数据预处理,通过对用户和用户之间综合信任度分析,利用分布估计算法对用户兴趣建模;构建用户兴趣簇类集,划分用户兴趣,从中选择出与检索对象最接近的邻居;计算邻近项目得分,按照从大到小的顺序排列,排名靠前的资源项即为图书推荐结果。实验结果表明,所提方法在推荐500本图书时,用时在12s内,且降低了平均绝对误差和均方根误差,实现了最精准的图书推荐。

基于终身教育数据的用户画像构建和个性化推荐模型研究

随着终身教育的兴起,个性化推荐在学习资源的提供中愈发重要。本文以浙江省海宁市“潮学通”终身学习平台的用户数据为研究对象,通过构建用户-学习资源评分矩阵对数据进行收集与预处理。在此基础上,通过深入分析用户画像的构建,以及协同过滤算法的设计,实现更精准的个性化学习资源推荐。

面向稀疏数据的协同过滤算法相似度

针对数据稀疏加剧导致传统相似度模型的推荐准确性低的问题,提出一种混合的协同过滤相似度模型。引入Jensen-Shannon(JS)散度作为基函数,利用全局评级概率分布衡量用户间评级偏好相似度。定义融合评级值的结构型相似度作为权重因子,针对用户的共同评级项目设计差异化的相似度计算方式,提高相似用户的区分度,得到基于相对区间跨度的相似度。在不同稀疏度数据集上与7种具有代表性的相似度方法进行对比实验,其结果表明了所提方法在预测和推荐准确性指标上均有良好性能。

融合巴氏系数与综合相似度的改进加权Slope One算法

针对传统加权Slope One算法因过度依赖用户共同评分项导致在过稀疏数据集中预测准确度低的问题,提出一种融合巴氏系数与综合相似度的改进加权Slope One算法(BS-WSO)。首先,引入巴氏系数和用户行为偏好对用户相似度计算方法进行改进,依此筛选出待预测的近邻集合;其次,为了优化预测评分,利用巴氏系数和项目流行度计算项目相似度,并将其作为权重因子融入评分计算;最后,将BS-WSO与几种代表性算法进行比较,仿真实验结果表明,BS-WSO算法能有效克服数据过稀疏情况下预测准确度低的缺陷,提高推荐精确度。

面向异构传输需求的多无人机通信协同抗干扰决策方法

干扰条件下的多无人机通信中,用户根据业务有不同的通信需求,而各个信道质量也不同,对抗干扰通信决策提出了业务需求与资源匹配的新要求。针对外部对抗性干扰场景下,多个用户如何选择适合的信道和功率,在干扰躲避、内部冲突控制以及功率优化的同时实现有限资源的高效利用这一问题进行研究,提出了一种面向传输需求匹配的抗干扰决策方法。首先,利用部分重叠信道的特性进行信道资源复用;然后,运用多用户协同强化学习训练用户信道选择策略,并使用斯坦伯格博弈对功率进行优化,实现对用户异构传输需求进行资源匹配。所提方法能实现干扰条件下的多用户异构传输需求的信道和功率联合优化,提升资源利用合理性,实现传输效果的提升。

GNRF:基于关系融合的图神经网络推荐系统

当前的推荐方法普遍引入知识图谱作为辅助信息来缓解协同过滤算法的缺陷,如数据稀疏和冷启动问题.然而,基于知识图谱的推荐方法大都专注于利用知识图谱来构建用户及物品的特征表示,忽略了对用户交互信息的有效利用.本文在引入用户-物品交互图和知识图谱两种图结构信息基础上,通过图神经网络融合用户-物品间的交互特征、物品间的相似特征以及知识图谱中实体的知识特征,来构建用户物品的特征表示,并将之应用于推荐系统.实验表明,相对于基线模型,本文提出的模型具有较好的推荐效果.

在线协同设计中用户的产品偏好差异检验与识别

在线协同设计平台中的定制行为会影响用户对产品的态度,识别具体的产品偏好差异有助于进行针对性的产品设计,迎合用户需求并提高满意度。针对这一现象,采用卡方检验和单因素方差分析比较平台内外的产品数据,识别用户在协同设计平台和电商平台中的产品偏好转变现象,从款式、色彩、图案和文化元素四项指标,检验并查看产品偏好的差异性和变化特征。研究表明,与普通电商平台相比,在线协同设计时的四项偏好指标均存在差异表现,且色彩和文化元素指标差异显著,还反映出用户个性化需求的增长以及产品识别能力和形态包容度的提高。该结果为在线协同设计平台中的产品设计与开发提供参考资料,有望推动平台的发展与普及。

融合用户活跃度的上下文感知兴趣点推荐算法

为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographical,categorical,and temporal factors,while simultaneously considering user activity),简称AU-GCTRS。首先,为缓解数据稀疏性和冷启动问题,引入多维上下文信息;其次,通过挖掘用户签到频率、签到兴趣点数量和签到时间,将用户划分为不同活跃度的群体;最后,综合用户活跃度与上下文分数,将得分高的前K个兴趣点推荐给用户。在真实数据集上进行实验表明,AU-GCTRS算法比其他流行算法更有效地缓解了数据稀疏性和冷启动问题,提高了推荐准确率和召回率。