《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 通信與網(wǎng)絡(luò) > 設(shè)計(jì)應(yīng)用 > 基于居民出行特征的職住地精細(xì)化識(shí)別
基于居民出行特征的職住地精細(xì)化識(shí)別
網(wǎng)絡(luò)安全與數(shù)據(jù)治理
黃興如,,李奕萱,,劉中亮,,馮瀚斌,王希昭,,閆龍,,胡博文,李炫孜,,李大中
聯(lián)通數(shù)字科技有限公司數(shù)據(jù)智能事業(yè)部
摘要: 為了解決傳統(tǒng)職住模型測算規(guī)則的單一性和局限性,,降低各區(qū)域居民用戶因作息規(guī)律差異或臨時(shí)性變化而造成的職住地識(shí)別誤差,創(chuàng)新性提出一種基于不同區(qū)域居民出行特征的職住地精細(xì)化識(shí)別方法,。首先,,采用“3 min切片”和“角度+駐留時(shí)間+連接次數(shù)”等多種方式對手機(jī)信令數(shù)據(jù)進(jìn)行降噪提煉;然后,,基于時(shí)空約束密度聚類進(jìn)行駐留點(diǎn)識(shí)別分析,;最后,根據(jù)各城市居民日常出行特征,,通過引入加權(quán)駐留時(shí)長動(dòng)態(tài)更新各城市區(qū)域居民用戶職住地測算規(guī)則,,進(jìn)而精細(xì)化識(shí)別不同城市用戶職住地分布。實(shí)驗(yàn)結(jié)果表明,,所提方法涉及的過程均合理有效,,且最終的職住地識(shí)別效果要明顯優(yōu)于傳統(tǒng)單一職住模型測算規(guī)則,適用于同時(shí)批量處理多個(gè)區(qū)域職住地問題,,尤其對因突發(fā)狀況而產(chǎn)生作息時(shí)間變化的城市效果更為顯著,。
中圖分類號(hào):TP311;F299.2文獻(xiàn)標(biāo)識(shí)碼:ADOI:10.19358/j.issn.2097-1788.2024.08.008
引用格式:黃興如,李奕萱,,劉中亮,,等.基于居民出行特征的職住地精細(xì)化識(shí)別[J].網(wǎng)絡(luò)安全與數(shù)據(jù)治理,2024,,43(8):44-48.
Fine-grained identification method of home-work location based on travel characteristics of residents
Huang Xingru, Li Yixuan, Liu Zhongliang, Feng Hanbin, Wang Xizhao, Yan Long, Hu Bowen, Li Xuanzi, Li Dazhong
Data Intelligence Division,Unicom Digital Technology Co., Ltd.
Abstract: To address the simplicity and limitations of the traditional homework model calculation rules and reduce the identification errors caused by differences in the daily routines of residents in various regions or temporary changes, this study proposed a finegrained identification method of home-work location based on the travel characteristics of residents in different regions. Firstly, various methods such as "3-minute slicing" and "angle + stay time + connection frequency" are used to denoise and refine the mobile phone signaling data. Then, based on spatiotemporal constrained density clustering, stay points are identified and analyzed. Finally, according to the daily travel characteristics of residents in various cities, weighted stay duration is introduced to dynamically update the home-work calculation rules for residents in different city areas, thereby refining the identification of home-work distribution for users in different cities. Experimental results show that the processes involved in this method are reasonable and effective, and the final homework identification results are significantly better than those of traditional single homework model calculation rules. This method is suitable for batch processing of homework problems in multiple regions simultaneously, particularly for cities where changes in routines are caused by unexpected events.
Key words : cellular signaling data; travel characteristics; DBSCAN; weighted stay duration,;home-work location identification

引言

精準(zhǔn)有效識(shí)別不同區(qū)域居民職住地以及挖掘居民處于職住地的時(shí)空規(guī)律可為城市職住規(guī)劃、經(jīng)濟(jì)發(fā)展布局,、公共資源分配和交通管理決策提供數(shù)據(jù)支持,。手機(jī)信令數(shù)據(jù)具有覆蓋廣、延遲低,、時(shí)效高,、周期長等特點(diǎn),因此借助手機(jī)信令位置數(shù)據(jù)進(jìn)行居民活動(dòng)分析研究具有良好的基礎(chǔ)和開端,,能夠從大規(guī)模時(shí)空軌跡信息中挖掘居民的活動(dòng)范圍,、出行時(shí)長、駐留興趣點(diǎn)和出行方式等重要時(shí)空屬性特征[1-3],。

由于設(shè)備測量,、計(jì)算方法、數(shù)據(jù)傳輸?shù)纫蛩赜绊?,致使獲得的軌跡數(shù)據(jù)多存有誤差,,而研究表明利用空間聚類算法將鄰近的位置點(diǎn)進(jìn)行聚合形成累計(jì)停留時(shí)間可減少該影響[4-5]。在此基礎(chǔ)上,,通過設(shè)置多日夜間和多日日間的駐留日長以及每日的最短駐留時(shí)長等指標(biāo),,可對用戶的居住地、工作地和慣常性活動(dòng)點(diǎn)進(jìn)行識(shí)別[6],。Zang等[7]依據(jù)手機(jī)用戶在自定義的職住時(shí)間段內(nèi)分別產(chǎn)生的業(yè)務(wù)頻繁程度來確定職住地,。Isaacman等[8]基于手機(jī)通話定位,通過空間聚類識(shí)別用戶的重要活動(dòng)地點(diǎn),,進(jìn)而通過時(shí)間分析確定職住地,。唐小勇等[9]提出一種職住計(jì)算框架,,識(shí)別用戶在一天內(nèi)的多日穩(wěn)定點(diǎn)和綜合工作日與節(jié)假日穩(wěn)定點(diǎn),基于此來判斷用戶的職住地,。張?zhí)烊唬?0]利用每日20:00至次日8:00和工作日9:00~18:00的手機(jī)數(shù)據(jù)訓(xùn)練識(shí)別,,將出現(xiàn)概率最高且超過 60%的區(qū)域作為用戶的職住地??梢姰?dāng)前職住地測算方法的基本原理是采用某種規(guī)則對居住,、工作行為的時(shí)間、空間特征進(jìn)行歸納測算,。然而,,上述方法中所設(shè)定的時(shí)間規(guī)則具有一定的局限性,并未兼顧到不同區(qū)域因地理位置,、經(jīng)濟(jì)條件,,甚至重大事件造成的各種作息時(shí)間差異,進(jìn)而導(dǎo)致識(shí)別的用戶職住地可能存在誤差,;尤其是疫情期間各區(qū)域居民職住地會(huì)存在不規(guī)律性變化[11],。

職住地測算的關(guān)鍵問題是如何解決手機(jī)信令數(shù)據(jù)的時(shí)間連續(xù)性(用戶信令事件記錄的時(shí)間間隔不固定),以時(shí)間特征作為識(shí)別規(guī)則的相關(guān)方法可以分類四種:累積時(shí)間法,、特征時(shí)間法,、信息熵法、時(shí)間閾值法[12]?,F(xiàn)基于累積時(shí)間法,、特征時(shí)間法和時(shí)間閾值法,提出一種適用于全國不同區(qū)域的職住地精細(xì)化識(shí)別方法,,以消除不同區(qū)域用戶因作息時(shí)間差異造成的職住地識(shí)別誤差,。


本文詳細(xì)內(nèi)容請下載:

http://forexkbc.com/resource/share/2000006105


作者信息:

黃興如,李奕萱,,劉中亮,,馮瀚斌,王希昭,,閆龍,,胡博文,李炫孜,,李大中

(聯(lián)通數(shù)字科技有限公司數(shù)據(jù)智能事業(yè)部,北京100010)


Magazine.Subscription.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。