国内社区养老服务热点分析基于LDA模型与生命周期理论

YIN Caiming1YUAN Yongxu12WANG Lian1SUN Yifan1CHEN Junye1 〔Abstract〕Purpose / SignificanceTo review the existing literature and to analyze the main research directions of community elderlycare servicesso as to provide scientific suggestions for improving community elderly care services．Method / ProcessThe literature dataare obtained from CNKI database and combined with the life cycle theorythe related research process is divided into 3 stages． The topicchanges in each stage are identified by LDA modeland the research hotspots and development trends in this field are analyzed and opin-ions are put forward．Ｒesult / ConclusionThe researches on domestic community elderly care services focus on the elderly care modeservice system constructionrural and community services aiming to provide comprehensive and professional services improve servicequalityand meet the diverse needs of the elderly． Community elderly care service is still a hot spot of social concern． In the future weshould strengthen service evaluationpay attention to talent construction and make full use of digital technology in this field． 〔Keywords〕community elderly care servicelatent Dirichlet allocationLDAmodel life cycle 1 141 3. 2 3。 2 2. 1 2. 2LDA 2. 3pyLDAvis 4 5. 1. 3 、、。。1.、、J．202141184149 － 4152．2STEINEＲ － LIM G Z DIANA K GAMZE A et al. I’mon my ownI need support needs assessment of communityaged care servicesJ．International journal of integratedcare2023 23314．3“”J．2022713 － 29．4.J．20211155 － 157．5.J．201327489 － 94．6.J．20093261 － 7．7.LDAJ．2015343286 － 299．8BLEI D M NG A Y JOＲDAN M I. Latent Dirichlet allo-cationJ．Journal of machine learing research 2003 31993 － 1002．9.LDA———J．20231037 － 43．10“+”J．20152011 － 23．11N．2020 － 11 － 041．97 5. 2 5. 2. 1 5. 2. 2 6 2J．201940493．3.J．20232922127 － 130．4HUNG GＲWHITEHOUSESＲO’NEILL Cetal. Computer modeling of patient flow in a pediatirc emergen-cy department using discrete event simulationJ．Pediat-ric emergency care2007 2315 － 10．5SUN Y TEOW L K HENG H B et al. Ｒeal － time pre-diction of waiting time in the emergency departmentusingquantile regressionJ．Annals of emergency medicine2012603299 － 308．6CUＲTIS CLIUCBOLLEＲMANJ Tetal. Machinelearning for predicting patient wait times and appointmentdelaysJ．Journal of the American college of radiology20171591310 － 1316．7HIJＲY HOLAWOYIN Ｒ. Predicting patient waiting timein the queue system using deep learning algorithms in the e-mergency roomJ．International journal of industrial en-gineering2021 3133 － 45．8.J．202243433 － 39．9LI NLI XZHANG Cet al. Integrated optimization ofappointment allocation and access prioritization in patient － centred outpatient schedulingJ．Computers ＆ industrialengineering2021 1541107 － 125．10.J．2016316103 － 105．11.J．2019401148 － 51．12FEＲＲEIＲA D C VIEIＲA I PEDＲO M I et al. Patient sat-isfaction with healthcare services and the techniques used forits assessmenta systematic literature review and a bibliomet-ric analysisJ．Healthcare 2023 11 5639．13MAULUD D ABDULAZEEZ A M.A review on linear re-gression comprehensive in machine learningJ．Journalof applied science and technology trends2020 12140 － 147．14CHEN T GUESTＲIN C.XGBoosta scalable tree boos-ting systemEB / OL．2023－ 08－ 13．https/ /doi. org /10. 1145 /2939672. 2939785．15FAN J MA X WU L et al. Light gradient boosting ma-chinean efficient soft computing model for estimating dailyreference evapotranspiration with local and external meteoro-logical dataEB / OL．2023－ 11－ 20．https/ /doi. org /10. 1016 / j. agwat. 2019. 105758．16PAＲYATI SALAHDDINE K. The implementation of Kruskal’salgorithm for minimum spanning tree in a graphEB / OL．2023 － 09 － 22．https/ / www. e3s － conferences. org / arti-cles / e3sconf / pdf /2021 /73 / e3sconf_iccsre21_ 01062. pdf． J．2021460 － 61．17.J．202338371 － 75．18.J．20244178 － 180．19.J．20243162 － 164．20.J．20232395 － 97．