We propose an entity recognition and talent profile model (BERT-BiGRU-Attention-CRF) to identify talent requirements for different jobs in the digital industry. This model combines the two representation learning methods (i.e., BERT and BiGRU) to represents textual contents according to contextual semantics in sentences, uses a multi-head attention mechanism to strengthen the key semantic information, and then employs conditional random field (CRF) to classify texts to identify talent requirements. Moreover, we conduct empirical research by collecting the latest recruitment information about jobs in the digital industry from three major recruiting websites. Experimental results indicate that BERT-BiGRU-Attention-CRF significantly outperforms baseline models in terms of Precision, Recall, and F1 metrics. Based on the relationships between jobs and requirements, we construct knowledge graph and job-specific talent profiles for the digital industry using the proposed model, and reveal similarities and differences between talent requirements for various jobs by analyzing job-related nodes in the knowledge graph.
GAOY, CHIX H, ZHANGC Z, et al. Precise user profile for domain-special talents: A case study of intelligent manufacturing[J]. Library Tribune, 2019, 39(6): 90-97. DOI: 10.3969/j.issn.1002-1167.2019.06.011(Ch ).
RUN, SUJ Y. Analysis of talent training path based on artificial intelligence talent portrait[J]. Journal of Tianjin Academy of Educational Science, 2021, 33(2):5-11. DOI:10.3969/j.issn.1671-2277.2021.02.001(Ch ).
LIY, CHENX T, HUANGG. Talent profiles of artificial intelligence and its training countermeasures based on recruitment data[J]. Chongqing Higher Education Research, 2021, 9(5): 55-68. DOI: 10.15998/j.cnki.issn1673-8012.2021.05.006(Ch ).
XUH. Demand analysis of information management posts based on online recruitment and its enlightenment on talent training [D]. Kunming :Yunnan University, 2021. DOI: 10.27456/d.cnki.gyndu.2021.000382(Ch ).
[9]
SAPUTRAA, WANGG, ZHANGJ Z, et al. The framework of talent analytics using big data[J]. The TQM Journal, 2022, 34(1): 178-198. DOI: 10.1108/tqm-03-2021-0089 .
SONGP Y, LONGC X, LIY R, et al. Identifying academic expertise of researchers based on iceberg model[J]. Data Analysis and Knowledge Discovery, 2023, 7(6): 50-60. DOI: 10.11925/infotech.2096-3467.2022.0542 (Ch ).
[12]
张俊峰. 国内网站招聘岗位需求特征挖掘及其应用研究[D]. 蚌埠: 安徽财经大学, 2017.
[13]
ZHANGJ F. Research on demand characteristics mining and application of domestic website recruitment[D]. Bengbu: Anhui University of Finance and Economics, 2017(Ch).
CHENM H, ZHANGQ L, HANJ. Recruitment demand analysis and training inspirations of information management and information system professionals[J]. Research on Library Science, 2021(20): 9-20. DOI: 10.15941/j.cnki.issn1001-0424.2021.20.004(Ch ).
[16]
杨静. 基于文本挖掘的网络招聘信息分析[D]. 济南: 山东师范大学, 2019.
[17]
YANGJ. Analysis of online recruitment information based on text mining[D]. Jinan: Shandong Normal University, 2019(Ch).
ZHUA L. A Study on the recruitment market of data analysis based on text mining [D]. Nanchang: Jiangxi University of Finance and Economics, 2020. DOI: 10.27175/d.cnki.gjxcu.2020.001524(Ch ).
[20]
LIUY F, WEIS Q, HUANGH J, et al. Naming entity recognition of citrus pests and diseases based on the BERT-BiLSTM-CRF model[J]. Expert Systems with Applications, 2023, 234: 121103. DOI: 10.1016/j.eswa.2023.121103 .
[21]
WANGZ H, HUANGM, LIC X, et al. Intelligent recognition of key earthquake emergency Chinese information based on the optimized BERT-BiLSTM-CRF algorithm[J]. Applied Sciences, 2023, 13(5): 3024. DOI: 10.3390/app13053024 .
[22]
SHIY N, KIMURAM. BERT-based models with attention mechanism and lambda layer for biomedical named entity recognition[C]//Proceedings of the 2024 16th International Conference on Machine Learning and Computing. New York: ACM, 2024: 536-544. DOI: 10.1145/3651671.3651709 .
WANGY B. Research and application of competency in computer field based on knowledge graph [D]. Changchun: Jilin University, 2020. DOI: 10.27162/d.cnki.gjlin.2020.003054(Ch ).
ZHANGX X. Research and application of data post knowledge graph construction based on competency model [D]. Changchun: Jilin University, 2022. DOI: 10.27162/d.cnki.gjlin.2022.002029(Ch ).
WANGN, GER F, YUANC F, et al. Company name identification in Chinese financial domain[J]. Journal of Chinese Information Processing, 2002, 16(2): 1-6. DOI: 10.3969/j.issn.1003-0077.2002.02.001(Ch ).
[29]
HANISCHD, FUNDELK, MEVISSENH T, et al. ProMiner: Rule-based protein and gene entity recognition[J]. BMC Bioinformatics, 2005, 6(S1): S14. DOI: 10.1186/1471-2105-6-S1-S14 .
HUANGS L, ZHENGX L, CHEND R. A semi-supervised learning method for product named entity recognition[J]. Journal of Beijing University of Posts and Telecommunications, 2013, 36(2): 20-23. DOI: 10.13190/jbupt.201302.20.huangshl(Ch ).
[32]
LIJ, SUNA X, HANJ L, et al. A survey on deep learning for named entity recognition[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1): 50-70. DOI: 10.1109/TKDE.2020.2981314 .
[33]
YADAVV, BETHARDS. A survey on recent advances in named entity recognition from deep learning models [C]// Proceedings of the 27th International Conference on Computational Linguistics.Stroundsbug:Association for Computational Linguistics,2018:2145-2158. DOI: 10.18653/v1/s18-2021 .
LIX L, SUNS F, TANGT L, et al. Construction of knowledge graph for breast cancer diagnosis based on ultrasound examination reports[J]. Journal of Wuhan University (Natural Science Edition), 2023, 69(1): 69-78. DOI: 10.14188/j.1671-8836.2022.0005(Ch ).
MAX Z, HOVYE. End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg: Association for Computational Linguistics, 2016: 1064-1074. DOI: 10.18653/v1/p16-1101 .
[38]
DONGC H, ZHANGJ J, ZONGC Q, et al. Character-based LSTM-CRF with radical-level features for Chinese named entity recognition[C]//Natural Language Understanding and Intelligent Application. Cham: Springer International Publishing, 2016, 239-250. DOI:10.1007/978-3-319-50496-4_20 .
[39]
CHOK, VAN MERRIENBOERB, GULCEHREC, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg: Association for Computational Linguistics, 2014: 1724-1734. DOI: 10.3115/v1/d14-1179 .
[40]
CHUNGJ, GÜLÇEHREÇ, CHOK H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. [2024-02-03]. DOI: 10.1007/978-3-030-89929-5_3 .
[41]
DEVLINJ, CHANGM W, LEEK, et al. BERT: Pre-training of deep bidirectional transformers for language understanding [EB/OL]. [2024-05-06]. DOI: 10.18653/v1/n18-2 .
[42]
VASWANIA, SHAZEERN, PARMARN, et al. Attention is all you need[EB/OL].[2024-05-06]. DOI: 10.1007/978-3-031-84300-6_13 .
[43]
CAHUANTZIR, CHENX Y, GÜTTELS. A comparison of LSTM and GRU networks for learning symbolic sequences[C]//Lecture Notes in Networks and Systems. Cham: Springer Nature Switzerland, 2023: 771-785. DOI: 10.1007/978-3-031-37963-5_53 .
[44]
LIUJ, YANGY H, LVS Q, et al. Attention-based BiGRU-CNN for Chinese question classification[J]. Journal of Ambient Intelligence and Humanized Computing, 2019: 1-12. DOI: 10.1007/s12652-019-01344-9 .
[45]
ZHAIP Y, YANGY W, ZHANGC J. Causality-based CTR prediction using graph neural networks[J]. Information Processing & Management, 2023, 60(1): 103137. DOI: 10.1016/j.ipm.2022.103137 .
ZHAIS P, BAIX X, ZHANGY H, et al. Triple extraction of combining dependency analysis and graph attention network[J]. Computer Engineering and Applications, 2023, 59(12): 148-156. DOI: 10.3778/j.issn.1002-8331.2203-0578(Ch ).
[48]
YANGY W, ZHAIP Y. Click-through rate prediction in online advertising: A literature review[J]. Information Processing & Management, 2022, 59(2): 102853. DOI: 10.1016/j.ipm.2021.102853 .
[49]
CAIX C, SUNE H, LEIJ L. Research on application of named entity recognition of electronic medical records based on BERT-IDCNN-CRF model[C]//2022 The 6th International Conference on Graphics and Signal Processing (ICGSP). New York: ACM, 2022: 80-85. DOI: 10.1145/3561518.3561531 .