認(rèn)知與智能信息處理實(shí)驗(yàn)室新學(xué)期首篇產(chǎn)學(xué)研合作論文“An Efficient Passenger-Hunting Recommendation Framework with Multi-Task Deep Learning”被?物聯(lián)網(wǎng)領(lǐng)域頂級期刊IEEE Internet of Things Journal（中科院一區(qū)，五年IF：8.385）錄用。

該論文華南師范大學(xué)為第一完成單位，是與“DataGrand（達(dá)觀數(shù)據(jù)）”合作完成（論文第一作者黃震華老師目前為DataGrand技術(shù)顧問）。目前該論文的研究成果正與智能交通領(lǐng)域的企業(yè)商談應(yīng)用和推廣。

DataGrand：推薦系統(tǒng)、自然語言處理和深度學(xué)習(xí)領(lǐng)域上海市重點(diǎn)支持企業(yè)，2017年獲“未來獨(dú)角獸TOP30”，2018年獲中國最具潛力企業(yè)獎(jiǎng)。目前，達(dá)觀團(tuán)隊(duì)由來自騰訊、盛大、百度、阿里等知名企業(yè)的高管和技術(shù)專家組成，曾經(jīng)多次榮獲ACM國際數(shù)據(jù)挖掘競賽冠軍，申請六十余項(xiàng)發(fā)明專利，出版兩本人工智能著作和數(shù)百篇技術(shù)論文。達(dá)觀數(shù)據(jù)是微軟加速器、聯(lián)想之星、SAP創(chuàng)新營的成員，并先后獲得了真格基金、軟銀賽富、方廣資本等著名機(jī)構(gòu)的數(shù)億元投資。

********************************************************************************************************

Abstract—Using large-scale GPS trajectory data to improve taxi services has recently attracted much attention in Internet of Things and smart city communities. In this paper, we use a large-scale GPS trajectory dataset generated by over 12,000 taxis in a period of three months in Shanghai, China, and present an efficient passenger-hunting recommendation framework with the multi-task deep learning paradigm. This framework contains two modules: offline training of passenger-hunting recommendation model (OT-PHRM) and online application of passenger-hunting recommendation model (OA-PHRM). The module OT-PHRM mainly includes two DCNNs (Deep Convolutional Neural Networks) and uses the multi-task learning strategy. The first DCNN realizes the region prediction for picking up passengers, while the second DCNN uses the weight-sharing structure to predict the levels of road congestion and earnings of carrying passengers. In particular, for the input of two DCNNs, we not only consider contextual features of taxi driving, region features and valuable statistical features, but also combine individual features into meaningful ones. In the module OA-PHRM, we propose DL-PHRec, which calculates three prediction values using two trained DCNNs in OT-PHRM in real time, and then recommends a personal ranking-list of regions to each taxi driver according to their scores. Experimental results show the feasibility and effectiveness of our recommendation framework.

**************************************************************************************************