基于招聘文本实体挖掘的人才供需分析——以人工智能领域为例

doi:10.13266/j.issn.0252-3116.2022.14.011

图书情报工作 ›› 2022, Vol. 66 ›› Issue (14): 101-118.DOI: 10.13266/j.issn.0252-3116.2022.14.011

基于招聘文本实体挖掘的人才供需分析——以人工智能领域为例

袁毅, 陶鑫琪, 李瑾萱, 刘娅娴, 汪晓芸, 景香玉

华东师范大学经济与管理学部信息管理系上海 200062

收稿日期:2022-03-01 修回日期:2022-05-09 出版日期:2022-07-20 发布日期:2022-07-28
作者简介:袁毅,教授,博士,E-mail:yuanyixz@126.com;陶鑫琪,硕士研究生;李瑾萱,硕士研究生;刘娅娴,硕士研究生;汪晓芸,硕士研究生;景香玉,硕士研究生。
基金资助:
本文系上海市2020年度"科技创新行动计划"软科学重点项目"人工智能复合型人才需求及培养模式研究"(项目编号:20692108300)研究成果之一。

Analysis of Talent Supply and Demand Based on Recruitment Text Entity Mining——Taking Artificial Intelligence Field as an Example

Yuan Yi, Tao Xinqi, Li Jinxuan, Liu Yaxian, Wang Xiaoyun, Jing Xiangyu

Department of Information Management, Faculty of Economics and Management, East China Normal University, Shanghai 200062

Received:2022-03-01 Revised:2022-05-09 Online:2022-07-20 Published:2022-07-28

摘要/Abstract

摘要： [目的/意义]基于网络招聘文本和学科数据,提出"行业-岗位-知识-学科"的人才需求及供给分析框架,以人工智能领域为例进行挖掘与分析,同时对其他领域的人才供需分析也具有借鉴意义。[方法/过程]采集招聘网站中与人工智能相关的职位招聘公告,综合对比CRF、BiLSTM-CRF、BERT-BiLSTM-CRF、BERT模型对招聘文本的实体抽取效果,并运用社会网络分析方法与学科数据进行关联分析。[结果/结论]BERT-BiLSTM-CRF实体抽取实验效果最佳,分别构建"行业-岗位""岗位-知识"以及"知识-学科"3种关系网络,得到与人工智能领域联系最紧密的行业、岗位、知识及学科。该框架能充分地挖掘人才需求现状,并能较精准地将需求定位到人才培养的学科,对于国家发展战略以及高等院校人才培养计划的制订具有现实意义。

关键词: 招聘实体, 人工智能, 供需分析, 人才培养, 深度学习

Abstract: [Purpose/significance] Based on online recruitment texts and subject data, this paper proposes an analysis framework of talent demand and supply of "Industry-Position-Knowledge-Discipline", takes the artificial intelligence industry as an example for mining and analysis, and it also has references and significance for the analysis of supply and demand of talents in other disciplines. [Method/process] This paper collected job announcements related to artificial intelligence from recruitment websites, and compared the effect of CRF, BiLSTM-CRF, BERT-BiLSTM-CRF, and BERT models on entity extraction of recruitment texts, and used social network analysis methods to conduct correlation analysis with subject data. [Result/conclusion] The BERT-BiLSTM-CRF entity extraction experiment is the best. Three relational networks of "industry-post", "post-knowledge" and "knowledge-discipline" are constructed respectively, and the industry, positions, knowledge and disciplines most closely related to artificial intelligence disciplines are obtained. The framework can fully explore the current situation of talent demand and locate the demand to the disciplines of talent cultivation more precisely, which is of practical significance for the national development strategy and the formulation of talent cultivation plan of higher education institutions.

Key words: recruitment entity, artificial intelligence, supply and demand analysis, talent training, deep learning

中图分类号:

G258.2
G251

袁毅, 陶鑫琪, 李瑾萱, 刘娅娴, 汪晓芸, 景香玉. 基于招聘文本实体挖掘的人才供需分析——以人工智能领域为例[J]. 图书情报工作, 2022, 66(14): 101-118.

Yuan Yi, Tao Xinqi, Li Jinxuan, Liu Yaxian, Wang Xiaoyun, Jing Xiangyu. Analysis of Talent Supply and Demand Based on Recruitment Text Entity Mining——Taking Artificial Intelligence Field as an Example[J]. Library and Information Service, 2022, 66(14): 101-118.

参考文献

[1] 艾瑞咨询. 2021年中国人工智能产业研究报告(Ⅳ)[EB/OL].[2022-02-28]. https://report.iresearch.cn/report_pdf.aspx?id=3925.
[2] 国务院发展中心.王明辉:人工智能为"十四五"时期现代化建设提供创新动能[EB/OL].[2022-02-28]. https://www.drc.gov.cn/DocView.aspx?chnid=379&leafid=1338&docid=2902895.
[3] 工业和信息化部人才交流中心.人工智能产业人才发展报告[EB/OL].[2022-02-28]. https://www.miitec.cn/home/index/detail?id=2249.
[4] 国务院.国务院关于印发新一代人工智能发展规划的通知(国发35号)[EB/OL].[2022-05-05]. http://www.gov.cn/zhengce/content/2017-07/20/content_5211996.htm.
[5] 中华人民共和国教育部.教育部关于印发《高等学校人工智能创新行动计划》的通知[EB/OL].[2022-05-05]. http://www.moe.gov.cn/srcsite/A16/s7062/201804/t20180410_332722.html.
[6] 周志华.创办一流大学人工智能教育的思考[J].中国高等教育, 2018(9):52-53.
[7] 武迪,戴琼海.高校人工智能人才培育战略的道与路[J].中国高等教育, 2021(20):13-15.
[8] 王永华.新工科人才培养模式创新的三个维度[J].中国高等教育, 2021(19):50-52.
[9] 赵志伟,李莉,崔福义,等.面向水系统智能化发展的人才培养知识体系构建研究[J].给水排水, 2021,57(S2):525-530.
[10] 曾红宇,颜家水,叶奕.人工智能背景下传媒专业课程教学"泛在化"创新策略[J].传媒, 2021(22):91-93.
[11] 陆伟,杨金庆.数智赋能的情报学学科发展趋势探析[J].信息资源管理学报, 2022,12(2):4-12.
[12] 杨青,刘英,曹福亮.新农科背景下工程创新人才培养的路径与启示——基于N大学工程创新人才培养的实践[J].高校教育管理, 2021,15(6):114-124.
[13] 刘奕琳,徐勇.新农科建设的必要性、框架设计与实施路径[J].黑龙江高教研究, 2022,40(2):145-149.
[14] 宋元明."人工智能+医学"新医科人才培养探索——以部分高校实践为例[J].中国高校科技, 2020(8):65-68.
[15] 何峰,万亮,明东.智能医学工程:新医科的探索与实践[J].中国高等教育, 2021(Z1):15-17.
[16] 贾君怡,于明哲.金融科技专业建设与人才培养的实践探索研究[J].科学决策, 2021(12):145-150.
[17] 陈晓芳,夏文蕾,张逸石,等.新时代新商科的内涵及"多维度协同"培养体系改革[J].财会月刊, 2021(5):107-113.
[18] 吴飞,吴超,朱强.科教融合和产教协同促进人工智能创新人才培养[J].中国大学教学, 2022(Z1):15-19.
[19] 胡清华,王国兰,王鑫.校企深度融合的人工智能复合型人才培养探索[J].中国大学教学, 2022(3):43-50.
[20] 买琳燕,樊明成.人工智能时代高职院校专业建设探析[J].职业技术教育, 2022,43(4):46-52.
[21] 何聚厚,李天宇,何秀青.中小学人工智能教育大单元设计的意蕴、困境和路径[J].中国电化教育, 2022(2):30-37.
[22] BIKEL D M, SCHWARTZ R, WEISCHEDEL R M. An algorithm that learns what's in a name[J]. Machine learning, 1999,34(1/3):211-231.
[23] MCCALLUM A, LI W. Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons[J]. Association for Computational Linguistics, 2003,4:188-191.
[24] BORTHWICK A. A maximum entropy approach to named entity recognition[M]. New York:New York University, 1999.
[25] ISOZAKI H, KAZAWA H. Efficient support vector classifiers for named entity recognition[C]//COLING 2002:the 19th international conference on computational linguistics. Stroudsburg:ACL, 2002:1-7.
[26] 向晓雯,史晓东,曾华琳.一个统计与规则相结合的中文命名实体识别系统[J].计算机应用, 2005(10):2404-2406.
[27] 鞠久朋,张伟伟,宁建军,等. CRF与规则相结合的地理空间命名实体识别[J].计算机工程, 2011,37(7):210-212.
[28] LI J, SUN A, HAN J, et al. A survey on deep learning for named entity recognition[J]. IEEE transactions on knowledge and data engineering, 2020,34(1):50-70.
[29] KONG J, ZHANG L, JIANG M, et al. Incorporating multi-level CNN and attention mechanism for Chinese clinical named entity recognition[J]. Journal of biomedical informatics, 2021,116:103737-103743.
[30] LI J, ZHAO S, YANG J, et al. WCP-RNN:a novel RNN-based approach for Bio-NER in Chinese EMRs[J]. The journal of supercomputing, 2020,76(3):1450-1467.
[31] JIA C, ZHANG Y. Multi-cell compositional LSTM for NER domain adaptation[C]//Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Stroudsburg:ACL, 2020:5906-5917.
[32] DEVLIN J, CHANG M, LEE K, et al. Bert:pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint, 2018,arXiv:1810.04805.
[33] HAN X, ZHANG Z, DING N, et al. Pre-trained models:past, present and future[J]. AI open, 2021,2:225-250.
[34] JIA C, SHI Y, YANG Q, et al. Entity enhanced BERT pre-training for Chinese NER[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:Association for Computational Linguistics, 2020:6384-6396.
[35] CUI Y, CHE W, LIU T, et al. Pre-training with whole word masking for Chinese bert[J]. IEEE/ACM transactions on audio, speech, and language processing, 2021,29:3504-3514.
[36] WEI J, REN X, LI X, et al. Nezha:neural contextualized representation for chinese language understanding[J]. arXiv preprint, 2019,arXiv:1909.00204.
[37] YIN X, ZHENG S, WANG Q. Fine-grained Chinese named entity recognition based on RoBERTa-WWM-BiLSTM-CRF model[C]//20216th international conference on image, vision and computing. Piscataway:IEEE, 2021:408-413.
[38] SUN Y, GAO D, SHEN X, et al. Multi-label classification in patient-doctor dialogues with the RoBERTa-WWM-ext+CNN (robustly optimized bidirectional encoder representations from transformers pretraining approach with whole word masking extended combining a convolutional neural network) model:named entity study[J]. JMIR medical informatics, 2022,10(4):e35606.
[39] LI Z, CHENG N, SONG W. Research on Chinese event extraction method based on RoBERTa-WWM-CRF[C]//2021 IEEE 12th international conference on software engineering and service science. Piscataway:IEEE, 2021:100-104.
[40] 王东波,胡昊天,周鑫,等.基于深度学习的数据科学招聘实体自动抽取及分析研究[J].图书情报工作, 2018,62(13):64-73.
[41] 俞琰,陈磊,姜金德,等.网络招聘文本技能信息自动抽取研究[J].图书情报工作, 2019,63(13):105-113.
[42] 文益民,杨鹏,文博奚,等.基于深度学习的中文网络招聘文本中的技能词抽取方法[J].桂林电子科技大学学报, 2020,40(4):338-348.
[43] 胡昊天,王东波,邓三鸿,等.基于情报学招聘实体挖掘的情报学教育及人才培养分析[J].情报理论与实践, 2021,44(1):8-17.
[44] 梁媛,彭秋茹,王东波,等.数据科学任职要求挖掘下的情报学教育及人才培养[J].情报理论与实践, 2021,44(2):8-15.
[45] CUI X, DAI F, SUN C, et al. BiLSTM-Attention-CRF model for entity extraction in internet recruitment data[J]. Procedia computer science, 2021,183:706-712.
[46] YI X H, YANG P, WEN Y M. Cross-domain transfer learning for recognizing professional skills from Chinese job postings[J]. Data analysis and knowledge discovery, 2022,6(2/3):274-288.
[47] JAGANNATHA A, LIU F, LIU W, et al. Overview of the first natural language processing challenge for extracting medication, indication, and adverse drug events from electronic health record notes (MADE 1.0)[J]. Drug safety, 2019,42(1):99-111.
[48] LUO Y, MA J, LI C. Entity name recognition of cross-border e-commerce commodity titles based on TWs-LSTM[J]. Electronic commerce research, 2020,20(2):405-426.
[49] MOLINA-VILLEGAS A, MUÑIZ-SANCHEZ V, ARREOLA-TRAPALA J, et al. Geographic named entity recognition and disambiguation in Mexican News using word embeddings[J]. Expert systems with applications, 2021,176:114855-114862.
[50] 马玉凤,向南,豆亚杰,等.军事系统工程中的知识图谱应用及研究[J].系统工程与电子技术, 2022,44(1):146-153.
[51] 章成志,张颖怡.基于学术论文全文的研究方法实体自动识别研究[J].情报学报, 2020,39(6):589-600.
[52] 艾瑞咨询. 2021年中国网络招聘行业市场发展研究报告[EB/OL].[2022-02-28]. https://report.iresearch.cn/report/202103/3753.shtml.
[53] 国家统计局.《国民经济行业分类》(2019年修订版全)(GB/T4754-2017)[EB/OL].[2022-02-28]. http://www.stats.gov.cn/tjgz/tzgb/201905/t20190521_1666106.html.
[54] 摩根斯坦利,标准普尔.全球行业分类系统(GICS)[EB/OL].[2022-02-28]. https://www.spglobal.com/spdji/zh/landing/topic/gics/.
[55] 教育部国务院学位委员会.学位授予和人才培养学科目录(2018年4月更新)[EB/OL].[2022-05-05]. http://www.moe.gov.cn/srcsite/A22/moe_833/201103/t20110308_116439.html.
[56] LAFFERTY J, MCCALLUM A, PEREIRA F. Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Proceedings of 18th international conference on machine learning. New York:ACM, 2001:282-289.
[57] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986,323(6088):533-536.
[58] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997,9(8):1735-1780.
[59] GRAVES A, SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural networks, 2005,18(5/6):602-610.
[60] 胡晓鹏.嵌入互联网的现代服务业结构升级研究[J].企业经济, 2020,39(11):5-12.
[61] 工业和信息化部.人工智能产业人才岗位能力标准[EB/OL].[2022-02-28]. https://pj.miitec.cn/evaluate/system/AIAbilityStandard.
[62] 高新波,苗启广,公茂果,等.计算机视觉:理论与应用专题序言[J].计算机科学, 2022,49(2):1-3.作者贡献说明:袁毅:论文框架设计、研究方法指导,论文最终版本修订;陶鑫琪:论文撰写、数据分析;李瑾萱:论文撰写、数据分析;刘娅娴:模型构建、实验实施;汪晓芸:数据清洗及标注;景香玉:数据采集。

基于招聘文本实体挖掘的人才供需分析——以人工智能领域为例

Analysis of Talent Supply and Demand Based on Recruitment Text Entity Mining——Taking Artificial Intelligence Field as an Example

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	孙迟瑶, 刘继安, 徐艳茹. 美国一流大学本科数据科学教育体系——建设路径、体系特征与发展趋势[J]. 图书情报工作, 2022, 66(8): 134-143.
[2]	张靖, 杨乃一. 完美的明天,不如不完美的今天——学科建设的逻辑与行动[J]. 图书情报工作, 2022, 66(4): 67-72.
[3]	杨杰, 赵星. 大数据专业培养内容的主题分析及对图情档学科的启示[J]. 图书情报工作, 2022, 66(2): 109-116.
[4]	陆颖颖, 孙裕彤, 张瑶, 李旭光. 人工智能、机器学习、自动化和机器人技术对信息行业的影响——2021年CILIP专题研讨会综述与启示[J]. 图书情报工作, 2022, 66(19): 143-152.
[5]	韩普, 顾亮. 基于混合深度学习的中文医学实体抽取研究[J]. 图书情报工作, 2022, 66(14): 119-127.
[6]	周潇, 许银彪, 史益. 基于深度学习与语义挖掘的技术创新组合识别与追踪[J]. 图书情报工作, 2022, 66(10): 33-44.
[7]	李娜, 姜恩波, 朱一真, 刘婷. 政策工具自动识别方法与实证研究[J]. 图书情报工作, 2021, 65(7): 115-122.
[8]	刘坤锋, 李艳红, 张心源. 信任视角下数据智能与专家知识的对比实证研究[J]. 图书情报工作, 2021, 65(6): 110-117.
[9]	杜悦, 王东波, 江川, 徐润华, 李斌, 许超, 徐晨飞. 数字人文下的典籍深度学习实体自动识别模型构建及应用研究[J]. 图书情报工作, 2021, 65(3): 100-108.
[10]	吴高, 黄晓斌. 人工智能时代文本与数据挖掘合理使用规则设计研究[J]. 图书情报工作, 2021, 65(22): 3-13.
[11]	邓三鸿. 数薮之研问渠之究——评《情报学教育和人才培养研究》[J]. 图书情报工作, 2021, 65(21): 14-16.
[12]	桂美增, 许学国. 基于深度学习的技术机会预测研究——以新能源汽车为例[J]. 图书情报工作, 2021, 65(19): 130-141.
[13]	王晰巍, 李玥琪, 贾若男, 孟盈. 新文科背景下大数据管理与应用专业人才培养模式[J]. 图书情报工作, 2021, 65(17): 45-56.
[14]	孔德婧, 董放, 陈子婧, 刘宇涵, 周源. 离群专利视角下的新兴技术预测——基于BERT模型和深度神经网络[J]. 图书情报工作, 2021, 65(17): 131-141.
[15]	黄国彬, 初景利, 崔瑞琴, 李景, 魏来, 李睿, 周倩, 符绍宏. 修身立学化知行言传身教育良才——孟连生图书情报学术思想与研究生培养概述[J]. 图书情报工作, 2021, 65(15): 12-21.