Social networks are becoming increasingly popular and influential,and users are frequently registered on multiple networks simultaneously,in many cases leaving large quantities of personal information on each network....Social networks are becoming increasingly popular and influential,and users are frequently registered on multiple networks simultaneously,in many cases leaving large quantities of personal information on each network.There is also a trend towards the personalization of web applications;to do this,the applications need to acquire information about the particular user.To maximise the use of the various sets of user information distributed on the web,this paper proposes a method to support the reuse and sharing of user profiles by different applications,and is based on user profile integration.To realize this goal,the initial task is user identification,and this forms the focus of the current paper.A new user identification method based on Multiple Attribute Decision Making(MADM) is described in which a subjective weight-directed objective weighting,which is obtained from the Similarity Weight method,is proposed to determine the relative weights of the common properties.Attribute Synthetic Evaluation is used to determine the equivalence of users.Experimental results show that the method is both feasible and effective despite the incompleteness of the candidate user dataset.展开更多
In order to improve the accuracy of target intent recognition,a recognition method based on XGBoost(eXtreme Gradient Boosting)decision tree is proposed.This paper adopts relevant data and program of python to calculat...In order to improve the accuracy of target intent recognition,a recognition method based on XGBoost(eXtreme Gradient Boosting)decision tree is proposed.This paper adopts relevant data and program of python to calculate the probability of tactical intention.Then the sequence intention probability is obtained by applying Dempster-Shafer rule of combination.To verify the accuracy of recognition results,we compare the experimental results of this paper with the results in the literatures.The experiment shows that the probability of tactical intention recognition through this method is improved,so this method is feasible.展开更多
基金supported in part by the Natural Science Basic Research Plan in Shaanxi Province of China under Grant No.2013JM8021the National Natural Science Foundation of China under Grant No.61272458
文摘Social networks are becoming increasingly popular and influential,and users are frequently registered on multiple networks simultaneously,in many cases leaving large quantities of personal information on each network.There is also a trend towards the personalization of web applications;to do this,the applications need to acquire information about the particular user.To maximise the use of the various sets of user information distributed on the web,this paper proposes a method to support the reuse and sharing of user profiles by different applications,and is based on user profile integration.To realize this goal,the initial task is user identification,and this forms the focus of the current paper.A new user identification method based on Multiple Attribute Decision Making(MADM) is described in which a subjective weight-directed objective weighting,which is obtained from the Similarity Weight method,is proposed to determine the relative weights of the common properties.Attribute Synthetic Evaluation is used to determine the equivalence of users.Experimental results show that the method is both feasible and effective despite the incompleteness of the candidate user dataset.
文摘In order to improve the accuracy of target intent recognition,a recognition method based on XGBoost(eXtreme Gradient Boosting)decision tree is proposed.This paper adopts relevant data and program of python to calculate the probability of tactical intention.Then the sequence intention probability is obtained by applying Dempster-Shafer rule of combination.To verify the accuracy of recognition results,we compare the experimental results of this paper with the results in the literatures.The experiment shows that the probability of tactical intention recognition through this method is improved,so this method is feasible.
