Recommendation Method for Contrastive Enhancement of Neighborhood Information

Knowledge graph can assist in improving recommendation performance and is widely applied in various person-alized recommendation domains.However,existing knowledge-aware recommendation methods face challenges such as weak user-item interaction supervisory signals and noise in the knowledge graph.To tackle these issues,this paper proposes a neighbor information contrast-enhanced recommendation method by adding subtle noise to construct contrast views and employing contrastive learning to strengthen supervisory signals and reduce knowledge noise.Specifically,first,this paper adopts heterogeneous propagation and knowledge-aware attention networks to obtain multi-order neighbor embedding of users and items,mining the high-order neighbor informa-tion of users and items.Next,in the neighbor information,this paper introduces weak noise following a uniform distribution to construct neighbor contrast views,effectively reducing the time overhead of view construction.This paper then performs contrastive learning between neighbor views to promote the uniformity of view information,adjusting the neighbor structure,and achieving the goal of reducing the knowledge noise in the knowledge graph.Finally,this paper introduces multi-task learning to mitigate the problem of weak supervisory signals.To validate the effectiveness of our method,experiments are conducted on theMovieLens-1M,MovieLens-20M,Book-Crossing,and Last-FM datasets.The results showthat compared to the best baselines,our method shows significant improvements in AUC and F1.

Weighted Forwarding in Graph Convolution Networks for Recommendation Information Systems

Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.

Research on the Trust Model Based on the Groups’ Internal Recommendation in E-Commerce Environment

The trust plays an extremely important role in online shopping. In order to make online shopping trusty, this paper puts foreword a new trust model in e-commerce environment GIR-TM (Groups’ Internal Recommendation Trust Model). First, it regarded the network as a combination of groups, and then did the internal recommendation based on these groups. The GIR-TM, in the process of recommendation, distinguished clearly between the trust degrees of recommen-dation node and the trust degrees of recommended node, and then calculated the integrated credibility value of the recommended node according to the weight of recommendation node in the group, the partial trust degree and the de-gree of recommendation when the recommendation node recommends the recommended node, and the overall credibil-ity value of recommended node as well. Lastly through listing the experimental data and comparing with the HHRB-TM (History and Honest Recommendation Based Trust Model) on the same condition, it is verified that GIR-TM is feasible and effective.

An E-Commerce Recommender System Based on Click and Purchase Data to Items and Considered of Interest Shifting of Customers

A well-performed recommender system for an e-commerce web site can help customers easily find favorite items and then increase the turnover of merchants, hence it is important for both customers and merchants. In most of the existing recommender systems, only the purchase information is utilized data and the navigational and behavioral data are seldom concerned. In this paper, we design a novel recommender system for comprehensive online shopping sites. In the proposed recommender system, the navigational and behavioral data, such as access, click, read, and purchase information of a customer, are utilized to calculate the preference degree to each item; then items with larger preference degrees are recommended to the customer. The proposed method has several innovations and two of them are more remarkable: one is that nonexpendable items are distinguished from expendable ones and handled by a different way; another is that the interest shifting of customers are considered. Lastly, we structure an example to show the operation procedure and the performance of the proposed recommender system. The results show that the proposed recommender method with considering interest shifting is superior to Kim et al(2011) method and the method without considering interest shifting.

An E-Commerce Recommender System Based on Content-Based Filtering

Content-based filtering E-commerce recommender system was discussed fully in this paper. Users＇ unique features can be explored by means of vector space model firstly. Then based on the qualitative value of products informa tion, the recommender lists were obtained. Since the system can adapt to the users＇ feedback automatically, its performance were enhanced comprehensively. Finally the evaluation of the system and the experimental results were presented.

Privacy-Preserving Recommendation Based on Kernel Method in Cloud Computing

The application field of the Internet of Things(IoT)involves all aspects,and its application in the fields of industry,agriculture,environment,transportation,logistics,security and other infrastructure has effectively promoted the intelligent development of these aspects.Although the IoT has gradually grown in recent years,there are still many problems that need to be overcome in terms of technology,management,cost,policy,and security.We need to constantly weigh the benefits of trusting IoT products and the risk of leaking private data.To avoid the leakage and loss of various user data,this paper developed a hybrid algorithm of kernel function and random perturbation method based on the algorithm of non-negative matrix factorization,which realizes personalized recommendation and solves the problem of user privacy data protection in the process of personalized recommendation.Compared to non-negative matrix factorization privacy-preserving algorithm,the new algorithm does not need to know the detailed information of the data,only need to know the connection between each data;and the new algorithm can process the data points with negative characteristics.Experiments show that the new algorithm can produce recommendation results with certain accuracy under the premise of preserving users’personal privacy.

Composite Recommendation of Artworks in E-Commerce Based on User Keyword-Driven Correlation Graph Search

With the ever-increasing diversification of people’s interests and preferences,artwork has become one of the most popular commodities or investment goods in E-commerce,and it increasingly attracts the attention of the public.Currently,many real-world or virtual artworks can be found in E-commerce,and finding a means to recommend them to appropriate users has become a significant task to alleviate the heavy burden on artwork selection decisions by users.Existing research mainly studies the problem of single-artwork recommendation while neglecting the more practical but more complex composite recommendation of artworks in E-commerce,which considerably influences the quality of experience of potential users,especially when they need to select a set of artworks instead of a single artwork.Inspired by this limitation,we put forward a novel composite recommendation approach to artworks by a user keyword-driven correlation graph search named ART_(com-rec).Through ART_(com-rec),the recommender system can output a set of artworks(e.g.,an artwork composite solution)in E-commerce by considering the keywords typed by a user to indicate his or her personalized preferences.Finally,we validate the feasibility of the ART_(com-rec) approach by a set of simulated experiments on a real-world PW dataset.

Problems and Recommendations for Rural Statistics and Survey Methods

With constant deepening of the reform and opening-up,national economic system has changed from planned economy to market economy,and rural survey and statistics remain in a difficult transition period. In this period,China needs transforming original statistical mode according to market economic system. All levels of government should report and submit a lot and increasing statistical information. Besides,in this period,townships,villages and counties are faced with old and new conflicts. These conflicts perplex implementation of rural statistics and survey and development of rural statistical undertaking,and also cause researches and thinking of reform of rural statistical and survey methods.

Poverty alleviation through e-commerce:Village involvement and demonstration policies in rural China

The diffusion of e-commerce has played a significant role in recent rural economic development in China.E-commerce is also considered as an efficient channel to alleviate poverty in rural China.Voluminous studies have investigated the contribution of e-commerce to agricultural development,yet it is lacking empirical evidence as to the effects of e-commerce on rural poverty alleviation.Since the year of 2014,in order to develop rural e-commerce,Chinese government launched the National Rural E-commerce Comprehensive Demonstration Project.This gradual involvement policy offered a natural experiment for evaluation of e-commerce.Based on village-level survey data from rural China and Heckit method,our study finds that rural e-commerce has a significantly positive effect on rural income.Moreover,the effect is inverted U-shaped for the relative-poverty villages.The estimation of the propensity scores matching model confirms that the results are robust.The following policy recommendations are proposed:(1)policy support to rural e-commerce should prioritize the povertystricken villages.By doing so,the marginal income effects of e-commerce will be maximized.(2)Investment in internet infrastructure and establishment of human resources for e-commerce in rural areas will have spillover effects,increasing rural income through the"digital dividend".

A New Time-Aware Collaborative Filtering Intelligent Recommendation System

Aiming at the problem that the traditional collaborative filtering recommendation algorithm does not fully consider the influence of correlation between projects on recommendation accuracy,this paper introduces project attribute fuzzy matrix,measures the project relevance through fuzzy clustering method,and classifies all project attributes.Then,the weight of the project relevance is introduced in the user similarity calculation,so that the nearest neighbor search is more accurate.In the prediction scoring section,considering the change of user interest with time,it is proposed to use the time weighting function to improve the influence of the time effect of the evaluation,so that the newer evaluation information in the system has a relatively large weight.The experimental results show that the improved algorithm improves the recommendation accuracy and improves the recommendation quality.

Problems in Development of Rural E- commerce and Logistics and Recommendations

Rural e-commerce and logistics development is of great significance to promote rural economic development and increase farmers' income. This paper analyzed existing problems in development of rural e-commerce and logistics in China,mainly including objective restriction of rural e-commerce and logistics by economic level,relatively backward capital construction facilities,lack of logistics information service platform,and insufficient professional personnel,and shortage of rural logistics professional personnel,and weak financial support of government. On the basis of these problems,it came up with pertinent recommendations from government,enterprises,and rural areas.

Study on the Development of Yunnan Floral E-commerce

Cut flower production in Yunnan accounts for 80%nationwide.In order to expand the Yunnan Flower sales channels,the promotion of the development of e-commerce is necessary.In 2012 China's online shopping users reached 247 million people,but e-commerce of fresh flowers lagged behind due to the constraints of preservation facilities and logistics cost.The analysis of the factors restricting the development of floral e-commerce and the proposition of solutions to this problem can promote faster development of Yunnan floral e-commerce.

Predicting the CME arrival time based on the recommendation algorithm

CME is one of the important events in the sun-earth system as it can induce geomagnetic disturbance and an associated space environment effect.It is of special significance to predict whether CME will reach the Earth and when it will arrive.In this paper,we firstly built a new multiple association list for 215 different events with 18 characteristics including CME features,eruption region coordinates and solar wind parameters.Based on the CME list,we designed a novel model based on the principle of the recommendation algorithm to predict the arrival time of CMEs.According to the two commonly used calculation methods in the recommendation system,cosine distance and Euclidean distance,a controlled trial was carried out respectively.Every feature has been found to have its own appropriate weight.The error analysis indicates the result using the Euclidean distance similarity is much better than that using cosine distance similarity.The mean absolute error and root mean square error of test data in the Euclidean distance are 11.78 and 13.77 h,close to the average level of other CME models issued in the CME scoreboard,which verifies the effectiveness of the recommendation algorithm.This work gives a new endeavor using the recommendation algorithm,and is expected to induce other applications in space weather prediction.

Interpretation and Classification of P-Series Recommendations in ITU-R

As ITU-R Recommendations is widely implemented for countries all over the world, the role and status of ITU-R Recommendations are increasingly prominent in the field of radio engineering. ITU and ITU-R Study Groups are summarized. Furthermore, the operating mode of the third study group, and the input documents are interpreted in detail. Lastly, from both wireless system design and electromagnetic compatibility analysis perspective, all of 79 P-series Recommendations are analyzed and classified, and the main contents of each Recommendation are summarized. The above research promote P-series Recommendations are widely used in China.

The Mobile Personalized Recommendation Model Containing Implicit Intention

Because mobile e-commerce is limited by the mobile terminal,network environment and other factors,accurate personalized recommendations become more and more important.We establish a large data intelligence platform,aiming at the characteristics of mobile e-commerce;we put forward a personalized recommendation model with implicit intention further.Firstly,create an intelligence unit with the virtual individual association set,virtual demand association set and virtual behavior associated set;Secondly,calculate the complex buying behavior prediction engine;Finally,give the predictive value of complex buying behavior.This method takes full account of factors such as hidden wishes perturbations that affect the predict of complex buying behavior,which to some extent solve a long-span composite purchasing behavior prediction.It shows that this method improves the purchasing behavior prediction accuracy effectively through experiments.

结合图卷积神经网络和集成方法的推荐系统恶意攻击检测

推荐系统已被广泛应用于电子商务、社交媒体、信息分享等大多数互联网平台中,有效解决了信息过载问题。然而,这些平台面向所有互联网用户开放,导致不法用户利用系统设计缺陷通过恶意干扰、蓄意攻击等行为非法操纵评分数据,进而影响推荐结果,严重危害推荐服务的安全性。现有的检测方法大多都是基于从评级数据中提取的人工构建特征进行的托攻击检测,难以适应更复杂的共同访问注入攻击,并且人工构建特征费时且区分能力不足,同时攻击行为规模远远小于正常行为,给传统检测方法带来了不平衡数据问题。因此,文中提出堆叠多层图卷积神经网络端到端学习用户和项目之间的多阶交互行为信息得到用户嵌入和项目嵌入,将其作为攻击检测特征,以卷积神经网络作为基分类器实现深度行为特征提取,结合集成方法检测攻击。在真实数据集上的实验结果表明,与流行的推荐系统恶意攻击检测方法相比,所提方法对共同访问注入攻击行为有较好的检测效果并在一定程度上克服了不平衡数据的难题。

农用地土壤重金属来源解析与健康风险空间分异特征研究——以重庆市巫山县笃坪乡为例

【目的】探明长江上游地区农用地土壤重金属来源及生态风险状况,进行人体健康风险空间分析,有助于提出有效的土壤重金属污染防治建议。【方法】以重庆市巫山县笃坪乡为研究对象,采集表层土壤样品(深度0~20 cm)45件,基于主成分分析/绝对主成分分数(PCA/APCS)受体模型进行土壤重金属(Cd、Hg、Pb、As和Cr)来源定量分析,通过人体健康风险评价模型进行人体健康风险评价,利用地统计法进行人体健康风险空间分析,得出不同区域的风险等级及影响因素,并针对性地提出风险管控建议。【结果】(1)研究区土壤Cd、Hg、Pb、As、Cr平均含量分别是重庆市土壤背景值的10.67、3.18、1.03、2.05、4.22倍,土壤重金属含量存在显著异常;(2)土壤综合环境质量优先保护类、安全利用类和严格管控类点位占比分别为2.23%、44.44%和53.33%,主要影响因子为Cd和Cr,土壤以酸性为主,对农产品质量安全及土壤生态环境的风险较高;(3)土壤Cd含量主要受到农业活动和成土母质的影响,贡献率分别为58.55%和30.30%,土壤Hg和Cr含量主要受到成土母质的影响,贡献率分别为71.55%和75.41%,土壤As含量主要受到农业活动的影响,贡献率为63.12%,土壤Pb含量主要受到道路交通的影响,贡献率为90.90%;(4)成人非致癌健康风险指数HI>1的点位占比为6.67%,总体健康风险较低,高风险区集中在研究区北部和中部地区,主要影响因子为Cr;农业活动与道路交通贡献率的高值区主要分布在研究区北部。【结论】建议研究区加强对农业投入品的监测,积极开展有机肥代替等化肥减量措施,推广使用电动农用车,减少由于农业活动对土壤重金属的输入。

滨海软土地基二次堆载预压固结沉降研究

滨海软土往往工程性质较差,一次堆载预压通常达不到设计要求而需要进行二次堆载预压。本文通过现场原位试验和室内试验,对二次堆载预压2年后的地基软土开展物理力学性质研究,并将试验获得的土体参数用于规范法和数值模拟,对地基未来20年的沉降进行预测。结果表明,二次堆载预压2年后,部分软土层力学参数提升显著,但淤泥层力学参数未见明显改善,地基承载力未达到设计要求,后续仍有较大的沉降变形。同时,对比规范法和研究开始前18个月沉降规律发现,经过二次堆载预压后的地基,数值模拟采用弹塑性模型能更准确地预测后续沉降,二次堆载预压20年后地基最大的沉降量可达1 m,位于12号钻孔位置处,其次是18号钻孔位置处,沉降量为0.9 m,10号钻孔位置处沉降量为0.8 m,并且沉降主要集中在淤泥层中。

基于LDA-MURE模型的背景音乐自适应推荐方法

用户的情绪状态不同,需要的背景音乐也不同,因此提出基于LDA-MURE模型的背景音乐自适应推荐方法。提取背景音乐的音频特征和社会化标签,通过Fisher线性判别分析方法融合上述数据的特征,结合投影变换方法获得不同类别背景音乐的类内离散度和类间离散度。通过现代心理学分析人类情绪的节律周期变化,在此基础上判断用户当前的情绪状态。最后在LDA模型的基础上构建LDA-MURE模型,为用户推荐不同类别的背景音乐。实验结果表明,所提方法的MEA指标值较低、P@N指标值较高、用户满意度较高。

基于知识图谱的制造资源推荐方法研究

在新时期智能制造飞速发展的背景下,制造业规模持续扩大但是制造模式和技术平台落后,许多企业制造资源联系不紧密,难以形成高效协同的产品制造方法。为在产品制造加工时给出合理的制造资源推荐方案,提高产品制造效率量,提出了一种基于知识图谱的制造资源推荐方法,通过本体构建和实体抽取技术构建制造领域知识图谱以及零件需求知识图谱,实现供需信息的表达,然后根据知识图谱嵌入方法,实现制造资源和产品需求的匹配,得到最优的制造资源推荐,实现了对于产品制造需求的快速响应和精准资源推荐,并通过实例对该方法进行了验证。