中文简历自动解析及推荐算法
|
摘要
为解决企业人工筛选电子简历效率低等问题,提出一种简历自动解析及推荐方案。对中文简历中的句子进行分词、词性标注等预处理,表示为特征向量,并利用SVM分类算法将所有句子划分成预定义的六个通用类别,包括个人基本信息、求职意向和工作经历等。利用个人基本信息的词法和语法特征,手工构建规则来实现姓名、性别及联系方式等关键信息抽取;对复杂的工作经历等文本用HMM模型进一步抽取详细信息,从而形成基于规则和统计相结合的简历文本信息抽取方法。考虑企业和求职者双方偏好,提出基于内容的互惠推荐算法(Content-Based Reciprocal Recommender algorithm,CBRR)。实验结果表明,整个方案能有效处理电子简历,提高简历筛选效率,辅助企业进行人才招聘。
In order to solve the problem of laborious and time-consuming artificial selection from mass electronic resumes,a solution to resumes automatic extraction and recommendation is proposed. Firstly, the sentences in Chinese resume are represented as vectors through word segmentation, part-of-speech tagging and other preprocessing steps, then SVM classification algorithm is used to classify the sentences into six predefined general classes, such as personal basic information,job intension, working experience and so on. Secondly, according to the lexical and grammatical features of personal basic information block, the rules are constructed by hand to extract the key information like Name, Gender, and Contact information. While the HMM model is used to extract the detailed information in complex information blocks, and puts forward rules and statistics based resume information extraction method. Finally, a Content-Based Reciprocal Recommender algorithm(CBRR)is proposed, which takes into account the preferences of both enterprise and job seekers. The experiment results show that the solution proposed in this paper can assist enterprises in recruitment, improve screening efficiency and save recruitment costs.
In order to solve the problem of laborious and time-consuming artificial selection from mass electronic resumes,a solution to resumes automatic extraction and recommendation is proposed. Firstly, the sentences in Chinese resume are represented as vectors through word segmentation, part-of-speech tagging and other preprocessing steps, then SVM classification algorithm is used to classify the sentences into six predefined general classes, such as personal basic information,job intension, working experience and so on. Secondly, according to the lexical and grammatical features of personal basic information block, the rules are constructed by hand to extract the key information like Name, Gender, and Contact information. While the HMM model is used to extract the detailed information in complex information blocks, and puts forward rules and statistics based resume information extraction method. Finally, a Content-Based Reciprocal Recommender algorithm(CBRR)is proposed, which takes into account the preferences of both enterprise and job seekers. The experiment results show that the solution proposed in this paper can assist enterprises in recruitment, improve screening efficiency and save recruitment costs.
引文
[1]艾瑞咨询.2016年中国网络招聘行业发展报告[R].中国:艾瑞咨询,2016:14-15.
[2]Almalis N,Tsihrintzis G,Karagiannis N.A new contentbased recommendation algorithm for job recruiting[M]//Research and Development in Intelligent Systems XXXII.[S.l.]:Springer International Publishing,2015:151-162.
[3]Zhang Y,Yang C,Niu Z.A research of job recommendation system based on collaborative filtering[C]//International Symposium on Computational Intelligence&Design.IEEE,2015:533-538.
[4]Laumer S,Eckhardt A.Help to find the needle in a haystack:Integrating recommender systems in an IT supported staff recruitment system[C]//ACM Sigmis Cpr Conference on Computer Personnel Research,Limerick,Ireland,2009:7-12.
[5]Yi X,Allan J,Croft W B.Matching resumes and jobs based on relevance models[C]//SIGIR 2007:Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval,Amsterdam,the Netherlands,July 2007:809-810.
[6]F?rber F,Weitzel T,Keim T.An automated recommendation approach to selection in personnel recruitment[C]//Americas Conference on Information Systems,AMCIS2003,Tampa,Fl,USA,August 2003.
[7]Keim T.Extending the applicability of recommender systems:A multilayer framework for matching human resources[C]//40th Annual Hawaii International Conference on System Sciences,2007,HICSS 2007.IEEE,2007.
[8]Wang Q M,Liu X,Zhu R,et al.A new personalized recommendation algorithm of combining content-based and collaborative filters[J].Computer&Modernization,2013,1(8):64-67.
[9]Ciravegna F,Lavelli A.Learningpinocchio:Adaptive information extraction for real world applications[J].Natural Language Engineering,2004,10(2):145-165.
[10]Yu K,Guan G,Zhou M.Resume information extraction with cascaded hybrid model[C]//Proceedings of Association for Computational Linguistics,2005:499-506.
[11]Chen J,Gao L,Tang Z.Information extraction from resume documents in PDF format[J].Electronic Imaging,2016.
[12]李保利,陈玉忠,俞士汶.信息抽取研究综述[J].计算机工程与应用,2003,39(10):1-5.
[13]Lin Hailun,Wang Yuanzhuo,Zhang Peng,et al.A rule based open information extraction method using cascaded finite-state transducer[C]//Pacific_asia Conference on Knowledge Discovery&Data Mining,2016,17(3):325-337.
[14]Kluegl P,Toepfer M,Beck P D,et al.UIMA ruta:Rapid development of rule-based information extraction applications[J].Natural Language Engineering,2016,22(1):1-40.
[15]Maarouf I E,Villaneau J.Parenthetical classification for information extraction[C]//Coling 2012:Posters,2012:297-308.
[16]Zhou Fankun.Research of domain-oriented extraction method of text information[D].Nanjing:Nanjing University of Posts and Telecommunications,2014.
[17]Arendarenko E,Kakkonen T.Ontology-based information and event extraction for business intelligence[C]//International Conference on Artificial Intelligence:Methodology,Systems,and Applications,2012:89-102.
[18]Maheshwari S,Sainani A,Krishna Reddy P.An approach to extract special skills to improve the performance of resume selection[C]//Proceedings of the 6th International Conference on Databases in Networked Information Systems,Aizu-Wakamatsu,Japan,March 29-31,2010.
[19]?elik D,El?i A.An ontology-based information extraction approach for résumés[C]//Proceedings of the 2012International Conference on Pervasive Computing and the Networked World,Istanbul,Turkey,November 28-30,2012:165-179.
[20]Sainani A,Reddy P K,Maheshwari S.Mining special features to improve the performance of e-commerce product selection and resume processing[J].International Journal of Computational Science and Engineering,2012,7(1):82-95.
[21]Singh A,Rose C,Visweswariah K,et al.Prospect:A system for screening candidates for recruitment[C]//Proceedings of the 19th ACM International Conference on Information and Knowledge Management,Toronto,ON,Canada,October 26-30,2010.
[22]Tang Jie,Yao Limin,Zhang Duo,et al.A combination approach to Web user profiling[J].ACM Transactions on Knowledge Discovery from Data(TKDD),2010,5(1):1-44.
[2]Almalis N,Tsihrintzis G,Karagiannis N.A new contentbased recommendation algorithm for job recruiting[M]//Research and Development in Intelligent Systems XXXII.[S.l.]:Springer International Publishing,2015:151-162.
[3]Zhang Y,Yang C,Niu Z.A research of job recommendation system based on collaborative filtering[C]//International Symposium on Computational Intelligence&Design.IEEE,2015:533-538.
[4]Laumer S,Eckhardt A.Help to find the needle in a haystack:Integrating recommender systems in an IT supported staff recruitment system[C]//ACM Sigmis Cpr Conference on Computer Personnel Research,Limerick,Ireland,2009:7-12.
[5]Yi X,Allan J,Croft W B.Matching resumes and jobs based on relevance models[C]//SIGIR 2007:Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval,Amsterdam,the Netherlands,July 2007:809-810.
[6]F?rber F,Weitzel T,Keim T.An automated recommendation approach to selection in personnel recruitment[C]//Americas Conference on Information Systems,AMCIS2003,Tampa,Fl,USA,August 2003.
[7]Keim T.Extending the applicability of recommender systems:A multilayer framework for matching human resources[C]//40th Annual Hawaii International Conference on System Sciences,2007,HICSS 2007.IEEE,2007.
[8]Wang Q M,Liu X,Zhu R,et al.A new personalized recommendation algorithm of combining content-based and collaborative filters[J].Computer&Modernization,2013,1(8):64-67.
[9]Ciravegna F,Lavelli A.Learningpinocchio:Adaptive information extraction for real world applications[J].Natural Language Engineering,2004,10(2):145-165.
[10]Yu K,Guan G,Zhou M.Resume information extraction with cascaded hybrid model[C]//Proceedings of Association for Computational Linguistics,2005:499-506.
[11]Chen J,Gao L,Tang Z.Information extraction from resume documents in PDF format[J].Electronic Imaging,2016.
[12]李保利,陈玉忠,俞士汶.信息抽取研究综述[J].计算机工程与应用,2003,39(10):1-5.
[13]Lin Hailun,Wang Yuanzhuo,Zhang Peng,et al.A rule based open information extraction method using cascaded finite-state transducer[C]//Pacific_asia Conference on Knowledge Discovery&Data Mining,2016,17(3):325-337.
[14]Kluegl P,Toepfer M,Beck P D,et al.UIMA ruta:Rapid development of rule-based information extraction applications[J].Natural Language Engineering,2016,22(1):1-40.
[15]Maarouf I E,Villaneau J.Parenthetical classification for information extraction[C]//Coling 2012:Posters,2012:297-308.
[16]Zhou Fankun.Research of domain-oriented extraction method of text information[D].Nanjing:Nanjing University of Posts and Telecommunications,2014.
[17]Arendarenko E,Kakkonen T.Ontology-based information and event extraction for business intelligence[C]//International Conference on Artificial Intelligence:Methodology,Systems,and Applications,2012:89-102.
[18]Maheshwari S,Sainani A,Krishna Reddy P.An approach to extract special skills to improve the performance of resume selection[C]//Proceedings of the 6th International Conference on Databases in Networked Information Systems,Aizu-Wakamatsu,Japan,March 29-31,2010.
[19]?elik D,El?i A.An ontology-based information extraction approach for résumés[C]//Proceedings of the 2012International Conference on Pervasive Computing and the Networked World,Istanbul,Turkey,November 28-30,2012:165-179.
[20]Sainani A,Reddy P K,Maheshwari S.Mining special features to improve the performance of e-commerce product selection and resume processing[J].International Journal of Computational Science and Engineering,2012,7(1):82-95.
[21]Singh A,Rose C,Visweswariah K,et al.Prospect:A system for screening candidates for recruitment[C]//Proceedings of the 19th ACM International Conference on Information and Knowledge Management,Toronto,ON,Canada,October 26-30,2010.
[22]Tang Jie,Yao Limin,Zhang Duo,et al.A combination approach to Web user profiling[J].ACM Transactions on Knowledge Discovery from Data(TKDD),2010,5(1):1-44.