检索结果-南通市图书馆

user profile in Smart Elderly Care Community:Findings from Community in Western China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2023年第2期32卷 156-167页

作者： Yan Wei Xiaowei Liu Ruilin Hou School of Statistics Xi’an University of Finance and Economics

With the increase in the aging population,the need for elderly care services has diversified,and smart elderly care has become an effective measure to cope with this increasing aging *** on the data from the platform“Guan Hu Tong”of RQ Company in the community of Shaanxi Province in western China,this study mined the data of smart elderly care services through the recency,frequency and monetary value(RFM)model and the backpropagation(BP)neural network model,constructed the user profile of the elderly,and predicted users’practical *** following conclusions were drawn:The oldest users are important target users of smart elderly care service platforms;Elderly women living alone rely more on smart elderly care services;Meal delivery and health follow-up services are the most popular among elderly users.

关键词： smart elderly care user profile backpropagation(BP)neural network

维普期刊数据库

Identifying user profile by Incorporating Self-Attention Mechanism based on CSDN Data Set

在线全文

学校读者我要写书评

暂无评论

Data Intelligence 2019年第2期1卷 160-175页

作者： Junru Lu Le Chen Kongming Meng Fengyi Wang Jun Xiang Nuo Chen Xu Han Binyang Li School of Information Science and Technology University of International RelationsBeijing 100091China Deep Brain Co.Ltd. Shanghai 201200China University of Chinese Academy of Sciences Beijing 100049China College of Information Engineering Capital Normal UniversityBeijing 100048China

With the popularity of social media,there has been an increasing interest in user profiling and its applications *** paper presents our system named UIR-SIST for user Profiling Technology Evaluation Campaign in SMP CUP ***-SIST aims to complete three tasks,including keywords extraction from blogs,user interests labeling and user growth value *** this end,we first extract keywords from a user’s blog,including the blog itself,blogs on the same topic and other blogs published by the same *** a unified neural network model is constructed based on a convolutional neural network(CNN)for user interests ***,we adopt a stacking model for predicting user growth *** eventually receive the sixth place with evaluation scores of 0.563,0.378 and 0.751 on the three tasks,respectively.

关键词： user profile Convolutional neural network(CNN) Self-attention Keyword extraction

维普期刊数据库

DP-userPro:differentially private user profile construction and publication

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2021年第5期15卷 197-206页

作者： Zheng HUO Ping HE Lisha HU Huanyu ZHAO Information Technology School Hebei University of Economics and BusinessShijiazhuang 050061China The Institute of Applied Mathematics Hebei Academy of SciencesShijiazhuang 050051China Hebei Authentication Technology Engineering Research Center Shijiazhuang 050051China

user profiles are widely used in the age of big ***,generating and releasing user profiles may cause serious privacy leakage,since a large number of personal data are collected and *** this paper,we propose a differentially private user profile construction method DP-userPro,which is composed of DP-CLIQUE and privately top-κtags ***-CLIQUE is a differentially private high dimensional data cluster algorithm based on *** multidimensional tag space is divided into cells,Laplace noises are added into the count value of each *** on the breadth-first-search,the largest connected dense cells are clustered into a *** a privately top-κtags selection approach is proposed based on the score function of each tag,to select the most importantκtags which can represent the characteristics of the *** and utility of DP-userPro are theoretically analyzed and experimentally evaluated in the *** experiments are carried out with Tag Suppression algorithm on two real datasets,to measure the False Negative Rate(FNR)and *** results show that DP-userPro outperforms Tag Suppression by 62.5%in the best case and 14.25%in the worst case on FNR,and DP-userPro is about 21.1%better on precision than that of Tag Suppression,in average.

关键词： user profile DP-CLIQUE clustering differential privacy recommender system

维普期刊数据库

Information Retrieval on Task-Relevant Knowledge Using Fuzzy Concept Network and user profile

在线全文

学校读者我要写书评

暂无评论

Information Retrieval on Task-Relevant Knowledge Using Fuzzy...

基于user profile的个性化信息推荐

第一届交通运输工程国际学术会议

作者： Xiong Feng 1 2 1School of Management Wuhan University of Technology P.R.China 430070 2School of Business NingBo University P.R.China 315211

In complex and knowledge-intensive environments, it is important that effective knowledge management can help users find pertinent task-relevant knowledge to improve their task performance. This work proposes a new information retrieval algorithm using fuzzy concept network and user profile in order to retrieve task-relevant information to fulfill the information needs of knowledge workers. In the algorithm, a user’s profile based on interest and task of user is represented using ontology. The algorithm can expand users’ queries for fuzzy information retrieval in a more effective manner. Experiment result show the algorithm can provide efficiently task-relevant knowledge by user’s query.

关键词： fuzzy concept network user profile information retrieval

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

基于User Profile的个性化信息推荐

作者：康亚如北京工业大学

学位级别：硕士

近年来,随着互联网上产生的数据越来越多,用户面临着“信息过载”的问题。如何从海量的数据中快速找到用户所需的信息,并利用这些数据来进行个性化推荐已经成为趋势。对于当下最流行的社交网络-微博,吸引了数以亿计的微博用户使用,用户... 详细信息

近年来,随着互联网上产生的数据越来越多,用户面临着“信息过载”的问题。如何从海量的数据中快速找到用户所需的信息,并利用这些数据来进行个性化推荐已经成为趋势。对于当下最流行的社交网络-微博,吸引了数以亿计的微博用户使用,用户可以通过微博平台来获取、发布信息以及拓展社交圈,其产生的数据是巨大的。因此,以微博数据为基础,挖掘用户兴趣并进行个性化推荐很有意义。传统微博个性化推荐算法采用的数据来源单一,模型简单,导致推荐准确率不高。针对这一问题,本文开展了如下主要工作:第一,提出一种基于user profile的微博用户推荐算法。根据微博数据的特点,深入研究了“微博文本”、“标签”、“社交关系”和“用户自身基本信息”等因素对微博个性化推荐的影响,通过训练LDA主题模型和SVM分类器将它们转变为标签,并赋予权重来描述用户兴趣,进行用户推荐以提高推荐准确性。并与基于传统VSM模型和HMM模型的推荐算法进行了对比实验,结果表明,该算法有更佳的推荐效果。第二,提出一种基于user profile的微博个性化推荐算法。首先计算user profile和微博profile的相似度;其次考虑到微博用户的社交特征,提出一种根据评论、转发和收藏等行为来计算用户之间的亲密度的方法;最后将两者结合来计算微博评分,根据评分高低进行微博推荐以提高推荐准确性。并与基于VSM算法的推荐算法相比较,结果表明,该算法准确率和召回率有明显的提高。第三,利用本文提出的算法理论,结合实际需求,在具体的应用场景下设计实现了微博个性化信息推荐系统。系统包括了数据采集模块、数据处理模块、创建profile模块和个性化推荐模块。

关键词：微博标签 user profile 个性化推荐

AMachine Learning Approach to user Profiling for Data Annotation of Online Behavior

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2419-2440页

作者： Moona Kanwal Najeed AKhan Aftab A.Khan Computer Science and Information Technology Department NED University of Engineering and TechnologyKarachiPakistan Computer Engineering Department Sir Syed University of Engineering and TechnologyKarachiPakistan College of Education Health and Human ServicesLongwood UniversityFarmvilleVAUSA

The user’s intent to seek online information has been an active area of research in user *** profiling considers user characteristics,behaviors,activities,and preferences to sketch user intentions,interests,and *** user characteristics can help capture implicit and explicit preferences and intentions for effective user-centric and customized content *** user’s complete online experience in seeking information is a blend of activities such as searching,verifying,and sharing it on social ***,a combination of multiple behaviors in profiling users has yet to be *** research takes a novel approach and explores user intent types based on multidimensional online behavior in information *** research explores information search,verification,and dissemination behavior and identifies diverse types of users based on their online engagement using machine *** research proposes a generic user profile template that explains the user characteristics based on the internet experience and uses it as ground truth for data *** feedback is based on online behavior and practices collected by using a survey *** participants include both males and females from different occupation sectors and different *** data collected is subject to feature engineering,and the significant features are presented to unsupervised machine learning methods to identify user intent classes or profiles and their *** techniques are evaluated,and the K-Mean clustering method successfully generates five user groups observing different user characteristics with an average silhouette of 0.36 and a distortion score of *** average is computed to identify user intent type *** user intent classes are then further generalized to create a user intent template with an Inter-Rater Reliability of 75%.This research successfully extracts different user types based on th

关键词： user intent cluster user profile online search information sharing user behavior search reasons

Discovering user profiles for Web Personalized Recommendation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2004年第3期19卷 320-328页

作者： Ai-BoSong Mao-XianZhao Zuo-PengLiang Yi-ShengDong Jun-ZhouLuo DepartmentofComputerScienceandEngineering SoutheastUniversityNanjing210096P.R.China InformationSchool ShandongUniversityofScienceandTechnologyTaian271019P.R.China

With the growing popularity of the World Wide Web, large volume of useraccess data has been gathered automatically by Web servers and stored in Web logs. Discovering andunderstanding user behavior patterns from log files can provide Web personalized recommendationservices. In this paper, a novel clustering method is presented for log files called Clusteringlarge Weblog based on Key Path Model (CWKPM), which is based on user browsing key path model, to getuser behavior profiles. Compared with the previous Boolean model, key path model considers themajor features of users'' accessing to the Web: ordinal, contiguous and duplicate. Moreover, forclustering, it has fewer dimensions. The analysis and experiments show that CWKPM is an efficientand effective approach for clustering large and high-dimension Web logs.

关键词： web log user profile personalization generalized suffix tree clustering

user centric dynamic web information visualization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2013年第5期56卷 36-49页

作者： SALEHEEN Shibli LAI Wei Faculty of Information and Communication Technologies Swinburne University of TechnologyHawthorn 3122VictoriaAustralia

Visualization of information after retrieval from the World Wide Web is a very challenging task because of the huge amount of data in *** on rules,information is retrieved through mining techniques and then visualized in different *** web-graph is one way for users to visualize web data and its *** because of its huge size,the web-graph lacks simplicity for end *** clustering plays a very important role in reducing the complexity of the web graph by making it compact and simple,existing clustering techniques are insufficient to provide personalized visualization for ***,these clustering techniques end up showing the same clustered graph to every user,despite their varying *** work aims to make information visualization personalized based on user interests;to provide a good first impression of web information to end users;to make web navigation easier;and to create scope for further ***,we develop a system for clustering which first considers user interests and then visualizes the clustered web graph to make the information more useful to the end *** this paper,we present some experimental examples that show the improvements achieved by our approach over existing ones.

关键词： information retrieval user profile clustering personalization visualization

A semantic web services discovery approach based on a mobile agent using metadata

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2017年第1期10卷 12-29页

作者： Nadia Ben Seghir Okba Kazar Khaled Rezeg Samir Bourekkache LINFI Laboratory Computer Science DepartmentUniversity of BiskraBiskraAlgeria

Purpose-The success of web services involved the adoption of this technology by different service providers through the web,which increased the number of web services,as a result making their discovery a tedious *** UDDI standard has been proposed for web service publication and ***,it lacks sufficient semantic description in the content of web services,which makes it difficult to find and compose suitable web services during the analysis,search,and matching *** addition,few works on semantic web services discovery take into account the user’s *** purpose of this paper is to optimize the web services discovery by reducing the search space and increasing the number of relevant ***/methodology/approach-The authors propose a new approach for the semantic web services discovery based on the mobile agent,user profile and metadata *** the approach,each user can be described by a profile which is represented in two dimensions:personal dimension and preferences *** description of web service is based on two levels:metadata catalog and ***-First,the semantic web services discovery reduces the number of relevant services through the application of matching algorithm“semantic match”.The result of this first matching restricts the search space at the level of UDDI registry,which allows the users to have good results for the“functional match”.Second,the use of mobile agents as a communication entity reduces the traffic on the network and the quantity of exchanged ***,the integration of user profile in the service discovery process facilitates the expression of the user needs and makes intelligible the selected ***/value-To the best knowledge of the authors,this is the first attempt at implementing the mobile agent technology with the semantic web service technology.

关键词： Metadata Semantic web Mobile agent Ontologie user profile Web service Paper type Technical paper