Recommendation Algorithm Integrating CNN and Attention System in Data Extraction

With the rapid development of the Internet globally since the 21st century,the amount of data information has increased exponentially.Data helps improve people’s livelihood and working conditions,as well as learning efficiency.Therefore,data extraction,analysis,and processing have become a hot issue for people from all walks of life.Traditional recommendation algorithm still has some problems,such as inaccuracy,less diversity,and low performance.To solve these problems and improve the accuracy and variety of the recommendation algorithms,the research combines the convolutional neural networks(CNN)and the attention model to design a recommendation algorithm based on the neural network framework.Through the text convolutional network,the input layer in CNN has transformed into two channels:static ones and non-static ones.Meanwhile,the self-attention system focuses on the system so that data can be better processed and the accuracy of feature extraction becomes higher.The recommendation algorithm combines CNN and attention system and divides the embedding layer into user information feature embedding and data name feature extraction embedding.It obtains data name features through a convolution kernel.Finally,the top pooling layer obtains the length vector.The attention system layer obtains the characteristics of the data type.Experimental results show that the proposed recommendation algorithm that combines CNN and the attention system can perform better in data extraction than the traditional CNN algorithm and other recommendation algorithms that are popular at the present stage.The proposed algorithm shows excellent accuracy and robustness.

Short Video Recommendation Algorithm Incorporating Temporal Contextual Information and User Context

With the popularity of 5G and the rapid development of mobile terminals,an endless stream of short video software exists.Browsing short-form mobile video in fragmented time has become the mainstream of user’s life.Hence,designing an efficient short video recommendation method has become important for major network platforms to attract users and satisfy their requirements.Nevertheless,the explosive growth of data leads to the low efficiency of the algorithm,which fails to distill users’points of interest on one hand effectively.On the other hand,integrating user preferences and the content of items urgently intensify the requirements for platform recommendation.In this paper,we propose a collaborative filtering algorithm,integrating time context information and user context,which pours attention into expanding and discovering user interest.In the first place,we introduce the temporal context information into the typical collaborative filtering algorithm,and leverage the popularity penalty function to weight the similarity between recommended short videos and the historical short videos.There remains one more point.We also introduce the user situation into the traditional collaborative filtering recommendation algorithm,considering the context information of users in the generation recommendation stage,and weight the recommended short-formvideos of candidates.At last,a diverse approach is used to generate a Top-K recommendation list for users.And through a case study,we illustrate the accuracy and diversity of the proposed method.

Explainable Rules and Heuristics in AI Algorithm Recommendation Approaches——A Systematic Literature Review and Mapping Study

The exponential use of artificial intelligence(AI)to solve and automated complex tasks has catapulted its popularity generating some challenges that need to be addressed.While AI is a powerfulmeans to discover interesting patterns and obtain predictive models,the use of these algorithms comes with a great responsibility,as an incomplete or unbalanced set of training data or an unproper interpretation of the models’outcomes could result in misleading conclusions that ultimately could become very dangerous.For these reasons,it is important to rely on expert knowledge when applying these methods.However,not every user can count on this specific expertise;non-AIexpert users could also benefit from applying these powerful algorithms to their domain problems,but they need basic guidelines to obtain themost out of AI models.The goal of this work is to present a systematic review of the literature to analyze studies whose outcomes are explainable rules and heuristics to select suitable AI algorithms given a set of input features.The systematic review follows the methodology proposed by Kitchenham and other authors in the field of software engineering.As a result,9 papers that tackle AI algorithmrecommendation through tangible and traceable rules and heuristics were collected.The reduced number of retrieved papers suggests a lack of reporting explicit rules and heuristics when testing the suitability and performance of AI algorithms.

Collaborative Filtering Algorithms Based on Kendall Correlation in Recommender Systems

In this work, Kendall correlation based collaborative filtering algorithms for the recommender systems are proposed. The Kendall correlation method is used to measure the correlation amongst users by means of considering the relative order of the users＇ ratings. Kendall based algorithm is based upon a more general model and thus could be more widely applied in e-commerce. Another discovery of this work is that the consideration of only positive correlated neighbors in prediction, in both Pearson and Kendall algorithms, achieves higher accuracy than the consideration of all neighbors, with only a small loss of coverage.

Recommendation algorithm of cloud computing system based on random walk algorithm and collaborative filtering model

The traditional collaborative filtering recommendation technology has some shortcomings in the large data environment. To solve this problem, a personalized recommendation method based on cloud computing technology is proposed. The large data set and recommendation computation are decomposed into parallel processing on multiple computers. A parallel recommendation engine based on Hadoop open source framework is established, and the effectiveness of the system is validated by learning recommendation on an English training platform. The experimental results show that the scalability of the recommender system can be greatly improved by using cloud computing technology to handle massive data in the cluster. On the basis of the comparison of traditional recommendation algorithms, combined with the advantages of cloud computing, a personalized recommendation system based on cloud computing is proposed.

Design and Implementation of Book Recommendation Management System Based on Improved Apriori Algorithm

The traditional Apriori applied in books management system causes slow system operation due to frequent scanning of database and excessive quantity of candidate item-sets, so an information recommendation book management system based on improved Apriori data mining algorithm is designed, in which the C/S (client/server) architecture and B/S (browser/server) architecture are integrated, so as to open the book information to library staff and borrowers. The related information data of the borrowers and books can be extracted from books lending database by the data preprocessing sub-module in the system function module. After the data is cleaned, converted and integrated, the association rule mining sub-module is used to mine the strong association rules with support degree greater than minimum support degree threshold and confidence coefficient greater than minimum confidence coefficient threshold according to the processed data and by means of the improved Apriori data mining algorithm to generate association rule database. The association matching is performed by the personalized recommendation sub-module according to the borrower and his selected books in the association rule database. The book information associated with the books read by borrower is recommended to him to realize personalized recommendation of the book information. The experimental results show that the system can effectively recommend book related information, and its CPU occupation rate is only 6.47% under the condition that 50 clients are running it at the same time. Anyway, it has good performance.

Improving Recommendation for Effective Personalization in Context-Aware Data Using Novel Neural Network

The digital technologies that run based on users’content provide a platform for users to help air their opinions on various aspects of a particular subject or product.The recommendation agents play a crucial role in personalizing the needs of individual users.Therefore,it is essential to improve the user experience.The recommender system focuses on recommending a set of items to a user to help the decision-making process and is prevalent across e-commerce and media websites.In Context-Aware Recommender Systems(CARS),several influential and contextual variables are identified to provide an effective recommendation.A substantial trade-off is applied in context to achieve the proper accuracy and coverage required for a collaborative recommendation.The CARS will generate more recommendations utilizing adapting them to a certain contextual situation of users.However,the key issue is how contextual information is used to create good and intelligent recommender systems.This paper proposes an Artificial Neural Network(ANN)to achieve contextual recommendations based on usergenerated reviews.The ability of ANNs to learn events and make decisions based on similar events makes it effective for personalized recommendations in CARS.Thus,the most appropriate contexts in which a user should choose an item or service are achieved.This work converts every label set into a Multi-Label Classification(MLC)problem to enhance recommendations.Experimental results show that the proposed ANN performs better in the Binary Relevance(BR)Instance-Based Classifier,the BR Decision Tree,and the Multi-label SVM for Trip Advisor and LDOS-CoMoDa Dataset.Furthermore,the accuracy of the proposed ANN achieves better results by 1.1%to 6.1%compared to other existing methods.

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.

Design of Hybrid Recommendation Algorithm in Online Shopping System

In order to improve user satisfaction and loyalty on e-commerce websites,recommendation algorithms are used to recommend products that may be of interest to users.Therefore,the accuracy of the recommendation algorithm is a primary issue.So far,there are three mainstream recommendation algorithms,content-based recommendation algorithms,collaborative filtering algorithms and hybrid recommendation algorithms.Content-based recommendation algorithms and collaborative filtering algorithms have their own shortcomings.The content-based recommendation algorithm has the problem of the diversity of recommended items,while the collaborative filtering algorithm has the problem of data sparsity and scalability.On the basis of these two algorithms,the hybrid recommendation algorithm learns from each other’s strengths and combines the advantages of the two algorithms to provide people with better services.This article will focus on the use of a content-based recommendation algorithm to mine the user’s existing interests,and then combine the collaborative filtering algorithm to establish a potential interest model,mix the existing and potential interests,and calculate with the candidate search content set.The similarity gets the recommendation list.

The Books Recommend Service System Based on Improved Algorithm for Mining Association Rules

The Apriori algorithm is a classical method of association rules mining.Based on analysis of this theory,the paper provides an improved Apriori algorithm.The paper puts foward with algorithm combines HASH table technique and reduction of candidate item sets to enhance the usage efficiency of resources as well as the individualized service of the data library.

Research and implementation of a personalized book recommendation algorithm --Taking the library of Jinan University as an example

Abstract： Taking the basic data and the log data of the various businesses of the automation integrated management system of the library in Jinan University as the research object this paper analyzes the internal relationship between books and between the books and the readers, and designs a personalized book recommendation algorithm, the BookSimValue, on the basis of the user collaborative filteringtechnology. The experimental results show that the recommended book information produced by this algorithm can effectively help the readers to solve the problem of the book information overload, which can bring great convenience to the readers and effectively save the time of the readers＇ selection of the books, thus effectively improving the utilization of the library resources and the service levels.

基于RoBERTa和图增强Transformer的序列推荐方法

自推荐系统出现以来,有限的数据信息就一直制约着推荐算法的进一步发展。为降低数据稀疏性的影响,增强非评分数据的利用率,基于神经网络的文本推荐模型相继被提出,但主流的卷积或循环神经网络在文本语义理解和长距离关系捕捉方面存在明显劣势。为了更好地挖掘用户与商品之间的深层潜在特征,进一步提高推荐质量,提出一种基于Ro BERTa和图增强Transformer的序列推荐(RGT)模型。引入评论文本数据,首先利用预训练的Ro BERTa模型捕获评论文本中的字词语义特征,初步建模用户的个性化兴趣,然后根据用户与商品的历史交互信息,构建具有时序特性的商品关联图注意力机制网络模型,通过图增强Transformer的方法将图模型学习到的各个商品的特征表示以序列的形式输入Transformer编码层,最后将得到的输出向量与之前捕获的语义表征以及计算得到的商品关联图的全图表征输入全连接层,以捕获用户全局的兴趣偏好,实现用户对商品的预测评分。在3组真实亚马逊公开数据集上的实验结果表明,与Deep FM、Conv MF等经典文本推荐模型相比,RGT模型在均方根误差(RMSE)和平均绝对误差(MAE)2种指标上有显著提升,相较于最优对比模型最高分别提升4.7%和5.3%。

个性化推荐算法的法律风险规制

信息爆发增长催生了个性化推荐算法技术的兴起。个性化推荐算法在解决信息过载和长尾问题、满足用户个性化需求、提高互联网信息服务效率的同时,也引发了用户意思自治受限、隐私泄露、信息茧房、算法歧视等诸多法律风险,亟需法律作出必要的回应。为此,应当在诚信原则、自主原则、公正原则、比例原则的指导下,树立开放的隐私保护观,强化算法告知义务与用户拒绝权利,完善算法解释权,构建算法审计制度,以降低个性化推荐算法所带来的法律风险。

数字资源的信息过滤与精准推荐算法

为了解决如何利用无限容量的数字资源与有限的用户信息及时而精准地向用户推荐可用的电子资源等问题,本研究设计了一种可以过滤不良信息的准确推荐算法。该算法为基于协同过滤与内容推荐的混合推荐算法,其中,协同过滤算法提取用户的特征,计算用户间的相似度并对相应的资源进行打分估计从而根据估分进行推荐;而基于内容推荐的算法用于处理用户无法求算相似度的冷启动问题,不良信息利用基于内容推荐的算法提取关键词并与不良关键词库对照,然后从前述推荐结果去掉不良信息;算法还考虑了用户兴趣随时间变化的问题。使用大规模图书馆数字资源数据集对本研究算法进行测试,结果表明,使用本研究算法,邻居数的增加对推荐精度有改善作用;对使用平均相似度和加权相似度的结果比较表明,加权相似度可以获得更好的推荐效果;加入时间因素,可以有效改进推荐精度,进而实现了对不良信息的过滤,保证了资源的质量。本研究算法基本实现了精准推荐,可适用于大数据环境下数字资源的推荐操作。

如何实现“黑箱”下的算法治理?——平台推荐算法监管的测量实验与策略探索

近年来,平台推荐算法的快速发展和广泛应用深刻改变了互联网信息内容的供给方式,同时也引发了一系列算法风险与现实问题。平台推荐算法治理与监管成为政府规范算法应用的重点内容之一,无论是算法备案制度的探索,还是实现算法透明化的设想,均面临着一定的困难和挑战。在不打开算法“黑箱”的前提下,平台推荐算法规制与监管是否有可行之道?论文基于机器行为学思想,采用实验方法,以用户视角对推荐结果进行跟踪记录,通过实验数据的对比分析,验证了平台推荐算法结果差异的可测性。基于实验结果,论文提出了通过对不同平台推荐结果进行大规模数据测试和检验,测量平台推荐算法运行逻辑与推荐效果,从而实现“黑箱”下有效的逆向监管,以期丰富未来算法治理的选择。

基于隐式偏好的多目标推荐算法研究

推荐的准确性(accuracy)和多样性(diversity)是推荐算法研究的二个重要指标,能够最大程度地满足用户的喜好.然而,基于准确性的推荐将导致推荐结果过于聚焦集中在某类特征上,使得多样性降低,导致用户选择的广度不足而整体效果不佳.针对推荐算法的两个指标之间的平衡以满足用户的需求,本文采用最大预测评分和最大内部相似度差异的两目标模型,选取极值点和膝点为隐式偏好,利用隐式偏好改进推荐方案搜索优化策略,提出了一种基于隐式偏好的多目标推荐算法.该算法利用切比雪夫距离在迭代过程中对偏好点动态标定,以引导个体收敛于隐式偏好区域,得到具有不同偏好的推荐方案.在Movielens和Netflix数据集上实验结果表明,与Item-based协同过滤推荐算法相比,该算法的推荐结果在确保准确率性能情况下多样性平均提升了38%和33.4%,新颖度平均提升了58.6%和125.4%,降低了多目标推荐算法的复杂度,有效解决了实际应用问题.

多任务联合学习的图卷积神经网络推荐

基于图神经网络的协同过滤推荐可以更有效地挖掘用户项目之间的交互信息,但其性能依然受到数据稀疏和表征学习质量不高问题的影响,因此提出一种多任务联合学习的图卷积神经网络推荐(multi-task joint learning for graph convolutional neural network recommendations,MTJL-GCN)模型。利用图神经网络在用户-项目交互图上所聚集到的同质结构信息与初始嵌入信息形成结构邻居关系,设计节点邻居关系的对比学习辅助任务来缓解数据稀疏问题;向节点的原始表征添加随机的统一噪声进行表征级数据增强,构建节点表征关系的对比学习辅助任务,并提出直接优化对齐性和均匀性两个属性的学习目标来提高表征学习质量;将图协同过滤推荐任务与对比学习辅助任务和直接优化学习目标进行联合训练,从而提升推荐性能。在Amazon-books和Yelp2018两个公开数据集上进行实验,该模型在Recall@k和NDCG@k两个推荐性能指标上的表现均优于基线模型,证明了MTJL-GCN模型的有效性。

基于用户画像的图书推荐算法实证研究

个性化推荐算法能够帮助读者从图书馆海量馆藏中发现所需图书,有助于提高馆藏利用率和读者服务效率。文章以高校图书馆图书数据、读者数据和借阅数据为数据源,从中抽取关键词构建图书画像和读者画像;利用向量空间模型计算图书与读者之间的相似度,向读者推荐与其相似度排名靠前的图书;并进行推荐算法效果实证分析,揭示著录数据、读者类型、推荐窗口等变量对推荐准确率的影响。

算法推荐技术赋能青少年民族团结进步教育的逻辑理路、价值意蕴与实践路径

算法推荐技术是引领新时代青少年民族团结进步教育高质量开展的新兴力量。算法推荐技术与青少年民族团结进步教育在条件、过程、结果上的关联耦合,为充分发挥算法推荐技术的积极功能,提升青少年民族团结进步教育实效,提供了适切性与可行性。通过精准传递、精准生产、精准过滤等优势赋能,算法推荐技术可以助力青少年民族团结进步教育实现对象大众化、内容智慧化和方式生活化。深化算法推荐理念认识、加强算法推荐素养教育、健全算法推荐技术规范,可以促进算法推荐技术势能充分释放,使之成为青少年民族团结进步教育现代化的强大技术支撑。

融合时间和知识信息的生成对抗网络序列推荐算法

序列推荐作为一种常用的推荐系统技术,通过对用户的历史交互序列进行建模来预测下一个可能交互的项目。现有的序列推荐方法主要利用用户交互序列和上下文信息进行推荐,忽略了序列中交互项目之间的时间间隔信息,交互项目之间的组合依赖以及上下文信息中存在噪声的问题,导致推荐结果受限。针对以上问题,提出一种基于生成对抗网络的序列推荐模型TKWGAN,该模型包含一个生成器和一个判别器。生成器结合了用户历史交互序列和各项目之间的时间间隔信息对用户偏好进行建模并生成预测,判别器则引入了知识图谱信息对项目进行语义扩充,从而能更准确地对生成器的预测进行合理性判断。针对用户交互序列和知识图谱信息中可能存在噪声的问题,提出一种基于小波变换的多核卷积神经网络来构造判别器,以更全面、准确地捕获用户的潜在兴趣,提高推荐的准确性。在MovieLens-1M、Amazon Books和Yelp2018这3个公开数据集上的实验结果表明,与8个序列化推荐算法相比,提出的TKWGAN模型在命中率(HR@N)和归一化折损累计增益(NDCG@N)指标上均有显著提升。