本文關(guān)鍵詞：基于位置社交網(wǎng)絡(luò)的用戶(hù)行為建模與研究　出處：《中國(guó)科學(xué)技術(shù)大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

  更多相關(guān)文章： 位置社交網(wǎng)絡(luò) 用戶(hù)行為偏好 興趣點(diǎn)推薦 地點(diǎn)預(yù)測(cè) 表示學(xué)習(xí)

【摘要】：近年來(lái),隨著移動(dòng)互聯(lián)網(wǎng)的快速擴(kuò)展和定位技術(shù)的日趨成熟,與位置社交網(wǎng)絡(luò)相關(guān)的服務(wù)平臺(tái)和信息被廣泛應(yīng)用于生活中。位置服務(wù)的廣泛應(yīng)用使得大量的位置數(shù)據(jù)得以積淀下來(lái),這為挖掘位置數(shù)據(jù)背后用戶(hù)的行為偏好提供了有力的支撐。通過(guò)分析用戶(hù)的行為偏好,所構(gòu)建的位置社交平臺(tái)可以更好地便利人們的生活與出行,同時(shí)有關(guān)于用戶(hù)偏好的分析結(jié)果也可以給予商家和相關(guān)行業(yè)的決策者更有益的建議和指導(dǎo)。因此,本文的工作重點(diǎn)是從現(xiàn)在和未來(lái)兩個(gè)角度出發(fā),挖掘和分析用戶(hù)的行為偏好,從而進(jìn)行興趣點(diǎn)推薦和位置預(yù)測(cè)。雖然位置社交網(wǎng)絡(luò)提供了豐富的位置數(shù)據(jù)來(lái)源,但是位置數(shù)據(jù)本身的異構(gòu)性和稀疏性等特點(diǎn)給現(xiàn)有的推薦和預(yù)測(cè)方法帶來(lái)了諸多挑戰(zhàn)。針對(duì)位置數(shù)據(jù)的這一系列特點(diǎn)和存在的挑戰(zhàn),本文分別提出了相應(yīng)的方法來(lái)更好地應(yīng)對(duì)在推薦和預(yù)測(cè)問(wèn)題建模過(guò)程中遇到的相關(guān)情況。具體來(lái)說(shuō)包含以下兩個(gè)方面:1.針對(duì)興趣點(diǎn)推薦問(wèn)題,本文構(gòu)建了一個(gè)基于多源異構(gòu)信息的混合興趣點(diǎn)推薦模型。位置社交網(wǎng)絡(luò)中蘊(yùn)含著豐富的實(shí)體和關(guān)聯(lián)關(guān)系,體現(xiàn)在位置數(shù)據(jù)上就是豐富的多源異構(gòu)信息。通過(guò)合理的建模和算法設(shè)計(jì)來(lái)有效地整合這些信息可以改善興趣點(diǎn)推薦的實(shí)際效果。針對(duì)位置社交網(wǎng)絡(luò)中的多源異構(gòu)信息,本文提出了一種基于用戶(hù)虛擬興趣和現(xiàn)實(shí)距離相結(jié)合的混合興趣點(diǎn)推薦方法。具體來(lái)說(shuō),本文采用核密度估計(jì)的方法對(duì)地理空間距離來(lái)進(jìn)行度量,使用基于好友和有共同簽到地點(diǎn)的用戶(hù)的協(xié)同過(guò)濾方法來(lái)衡量好友和興趣相似的其他用戶(hù)對(duì)于用戶(hù)本身對(duì)興趣點(diǎn)的心理認(rèn)同度的影響,同時(shí)使用基于用戶(hù)和興趣點(diǎn)文本聚集的概率話題模型來(lái)挖掘用戶(hù)和興趣點(diǎn)的偏好,從而對(duì)用戶(hù)虛擬興趣中可解釋的部分進(jìn)行建模。相應(yīng)的,本文使用概率隱因子模型對(duì)用戶(hù)虛擬興趣中不可解釋的部分加以建模。最終本文將上述子模塊有機(jī)地結(jié)合起來(lái)得到混合興趣點(diǎn)推薦模型。本文在兩個(gè)典型的位置數(shù)據(jù)集上進(jìn)行了充分的實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明本文提出的混合興趣點(diǎn)推薦算法優(yōu)于當(dāng)前已有的興趣點(diǎn)推薦算法。此外,模型還具有更準(zhǔn)確的預(yù)測(cè)性和很好的健壯性等優(yōu)勢(shì)。2.針對(duì)地點(diǎn)預(yù)測(cè)問(wèn)題,本文提出了一種基于簽到序列的隱話題向量位置預(yù)測(cè)模型。研究表明,位置社交網(wǎng)絡(luò)中用戶(hù)的行為偏好具有很強(qiáng)的規(guī)律性和可預(yù)測(cè)性,并且和用戶(hù)與地點(diǎn)所在的情境密切相關(guān)。對(duì)于大多數(shù)用戶(hù)來(lái)說(shuō),其簽到記錄相比于整個(gè)數(shù)據(jù)的分布而言具有很強(qiáng)的稀疏性。因此如何針對(duì)位置數(shù)據(jù)的上述特點(diǎn)構(gòu)建預(yù)測(cè)模型來(lái)進(jìn)行地點(diǎn)預(yù)測(cè)是一個(gè)亟待解決的重要問(wèn)題。本文提出了一種基于簽到序列的隱話題模型。具體來(lái)說(shuō),對(duì)于位置社交網(wǎng)絡(luò)中的地理空間信息,本文采用基于區(qū)域的高斯分布模型進(jìn)行建模。為了緩解社交關(guān)系稀疏性對(duì)預(yù)測(cè)結(jié)果的影響,本文對(duì)用戶(hù)的社交關(guān)系進(jìn)行了擴(kuò)展。同時(shí)本文把基于上下文的詞向量模型和基于時(shí)間的主題模型結(jié)合起來(lái),構(gòu)建隱話題向量模型來(lái)對(duì)用戶(hù)簽到行為的情境進(jìn)行建模。對(duì)于其簽到的規(guī)律性行為,本文對(duì)連續(xù)時(shí)間進(jìn)行了橫向與縱向的分割,把連續(xù)時(shí)間離散化。綜合上述建模方法可以得到用戶(hù)在不同時(shí)間模式下的興趣偏好表示以及地點(diǎn)的表征向量,從而有效地預(yù)測(cè)下一時(shí)間模式下用戶(hù)訪問(wèn)的地點(diǎn)。本文在典型的位置數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果表明與傳統(tǒng)的地點(diǎn)預(yù)測(cè)方法相比,本文提出的模型具有更高的準(zhǔn)確性。
[Abstract]:In recent years, with the rapid expansion of the Internet and mobile positioning technology is becoming more and more mature, and the position related social network service platform and information is widely used in daily life. Widely used location service that the position data settled and provides a strong support for the behavior preference mining. Through the data behind the user location analysis of user preferences, social position of the platform can better facilitate people's life and travel at the same time, there are more useful advice and guidance on user preference results can also be given to related businesses and industry decision makers. Therefore, the emphasis of this paper is to start from now and in the future two aspects of mining and analysis of user behavior, so as to predict the point of interest and recommended position. Although the location of social network provides a rich source of data location, but The location of the data itself characteristics of heterogeneous and sparseness and recommend the existing prediction methods have brought many challenges. For this series of characteristics of the position data and the challenges, this paper puts forward the corresponding methods to better respond to the relevant circumstances encountered in the process of the prediction and recommendation problem specifically includes modeling. The following two aspects: 1. to the point of interest problems is recommended, this paper constructs a hybrid recommendation model of multi-source heterogeneous information based on social network position. Points of interest are rich in entity and relationship, reflected in the position of the data is rich in multi-source heterogeneous information. Through the modeling and design of reasonable algorithm to effectively integrate this information can improve the actual effect of interest recommendation. For multi-source heterogeneous information position in social networks, this paper proposes a method based on user interest and virtual The real distance of combining interest recommendation methods. Specifically, this paper uses the method of kernel density estimation for spatial distance measurement, based on the use of friends and common collaborative filtering method to measure the user sign in place of friends and other users with similar interests to the user itself to the point of interest is the influence of psychological identity at the same time, the use of probabilistic topic model and user interest aggregation to text mining user preferences and points of interest, in order to model the interpretation of part of the user interest. The corresponding virtual modeling of virtual users, it can not explain the interest in this part of the use of probabilistic latent factor model. Finally the sub module organically mixed interest recommendation model. This paper has carried on the experiment in two typical position data sets, experimental results table The proposed hybrid algorithm is better than the current recommended interest interest recommendation algorithm. In addition, the model has more accurate prediction and good robustness for the.2. advantage location prediction problem, this paper proposes a prediction model based on hidden topic vector position sign sequence. The results show that the position of the user in a social network behavior preference has strong regularity and predictability, and closely related to the user's location and context. For most users, the attendance record distribution compared to the entire data sparsity has very strong. So how to according to the characteristics of the position data prediction model is constructed to place forecasting is an important problem to be solved. This paper proposes a topic model based on implicit sign sequence. Specifically, the position of social networks in the geographical space The information modeling of Gauss distribution model based on region. In order to alleviate the impact of social relations the sparsity of the forecast results, the relationships of the users of the expansion. At the same time the word context vector model and topic model based on time based on user behavior, to construct the context modeling sign the hidden topic vector model. For the regularity of the sign of sexual behavior, the horizontal and vertical segmentation of continuous time, continuous time discretization. The modeling method can get the user preference vector characterization in different time under the mode of representation and location, which can effectively predict the next time the user mode to access a location. Based on the position data of the typical set of experimental results show that compared with the traditional location prediction method, the model proposed in this paper. There is a higher accuracy.

【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 楊陽(yáng);向陽(yáng);熊磊;;基于矩陣分解與用戶(hù)近鄰模型的協(xié)同過(guò)濾推薦算法[J];計(jì)算機(jī)應(yīng)用;2012年02期

2 鄧愛(ài)林,朱揚(yáng)勇,施伯樂(lè);基于項(xiàng)目評(píng)分預(yù)測(cè)的協(xié)同過(guò)濾推薦算法[J];軟件學(xué)報(bào);2003年09期

相關(guān)博士學(xué)位論文 前1條

1 連德富;基于位置社交網(wǎng)絡(luò)的數(shù)據(jù)挖掘[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年

，

本文編號(hào)：1386247