面向退役机电产品全生命周期的知识图谱统一建模方法研究

doi:10.3901/JME.2023.07.052

摘要/Abstract

摘要： 针对退役机电产品逆向物流信息追溯过程中时空分散度高、质量不确定性强、跨组织信息关联度弱等问题，基于知识图谱技术构建了退役机电产品全生命周期统一数据模型。首先提出了从跨组织多源数据到知识图谱构建和应用的全生命周期统一数据建模方法，然后提出了知识图谱构建关键技术，针对知识图谱构建过程中的实体关系联合抽取问题，建立了基于分段注意力融合机制的实体关系联合抽取模型，解决了实体关系重叠问题，并在标准数据集和退役机电产品领域数据集上进行测试，取得了很好的效果，最后建立了退役机电产品全生命周期信息追溯系统。知识图谱的构建实现了退役机电产品生命周期中跨组织信息的统一数据结构，为退役机电产品逆向物流信息追溯提供了强有力的支撑。

关键词: 退役机电产品, 全生命周期信息追溯, 统一数据模型, 知识图谱, 实体关系联合抽取

Abstract: To solve the issues of high spatial and temporal dispersion, strong quality uncertainty and weak inter-organizational information correlation in tracing reverse logistics information of retired mechanical and electrical products, a unified data model based on knowledge graph for the full life cycle information of retired mechanical and electrical products is constructed. Firstly, the architecture to build the unified data model is proposed to deal with the data from different organizations, and then it's key technology is discussed. A joint entity relation extraction model based on segmental attention fusion mechanism is developed to jointly extract the entities and relations task in building the knowledge graph, which can effectively solve the overlapping issue of entities and relationships. The model is tested in the standard datasets and the decommissioned electromechanical products datasets and the results show that the proposed model is effective. Finally, a dynamic information traceability system is developed. The knowledge graph realizes the unified data structure of the cross-organization information of retired electromechanical products in the whole life cycle, and provides a strong support for the reverse logistics information traceability of retired electromechanical products.

Key words: decommissioned mechanical and electrical products, full life cycle information traceability, unified data model, knowledge graph, joint extraction of entities and relations

中图分类号:

吴秀丽, 马隆洲, 向东, 唐英. 面向退役机电产品全生命周期的知识图谱统一建模方法研究[J]. 机械工程学报, 2023, 59(7): 52-67.

WU Xiuli, MA Longzhou, XIANG Dong, TANG Ying. Research on Unified Modeling Method of Knowledge Graph towards the Full Life Cycle of Decommissioned Electromechanical Products[J]. Journal of Mechanical Engineering, 2023, 59(7): 52-67.

参考文献

[1] 中国家用电器研究院,生产者责任延伸产业技术创新联盟,中国绿色供应链联盟电器电子产品专委会. 中国废弃电器电子产品回收处理及综合利用行业白皮书2021[EB/OL].[2022-05-25]. https://www.citymine.com. cn/a/3188.html. China Household Electric Appliance Research Institute,Extended Producer Responsibility Alliance,Electrical and Electronic Equipment Committee of China Green Supply Chain Alliance. White paper on waste electrical and electronic equipment recycling industry in China 2021[EB/OL].[2022-05-25]. https://www.citymine.com. cn/a/3188.html.
[2] 中国家用电器研究院,生产者责任延伸产业技术创新联盟,中国绿色供应链联盟电器电子产品专委会. 中国废弃电器电子产品回收处理及综合利用行业白皮书2020[J]. 家用电器,2021(6):68-87. China Household Electric Appliance Research Institute,Extended Producer Responsibility Alliance,Electrical and Electronic Equipment Committee of China Green Supply Chain Alliance. White paper on waste electrical and electronic equipment recycling industry in China 2020[J] Home Appliance,2021(6):68-87.
[3] 中国家用电器研究院,生产者责任延伸产业技术创新联盟,中国绿色供应链联盟电器电子产品专委会. 中国废弃电器电子产品回收处理及综合利用行业白皮书2019[J]. 家用电器,2020(7):58-77. China Household Electric Appliance Research Institute,Extended Producer Responsibility Alliance,Electrical and Electronic Equipment Committee of China Green Supply Chain Alliance. White paper on waste electrical and electronic equipment recycling industry in China 2019[J] Home Appliance,2020(7):58-77.
[4] 中国家用电器研究院,生产者责任延伸产业技术创新联盟. 中国废弃电器电子产品回收处理及综合利用行业白皮书2018[EB/OL].[2022-05-25]. http://www.weee-epr.com/article/detail_176.html. China Household Electric Appliance Research Institute,Extended Producer Responsibility Alliance. White paper on waste electrical and electronic equipment recycling industry in China 2018[EB/OL].[2022-05-25]. http://www.weee-epr.com/article/detail_176.html.
[5] 中国家用电器研究院,中国再生资源回收利用协会废弃电器电子产品分会. 中国废弃电器电子产品回收处理及综合利用行业白皮书2017[EB/OL].[2022-05-25]. http://www.weee-epr.com/article/detail_129.html. China Household Electric Appliance Research Institute,Waste Electrical and Electronic Products Branch of China Renewable Resources Recycling and Utilization Association. White paper on waste electrical and electronic equipment recycling industry in China 2017[EB/OL].[2022-05-25]. http://www.weee-epr. com/article/detail_129.html.
[6] 中国家用电器研究院. 中国废弃电器电子产品回收处理及综合利用行业白皮书2016[EB/OL].[2022-05-25]. http://www.weee-epr.com/article/detail_91.html. China Household Electric Appliance Research Institute. White paper on waste electrical and electronic equipment recycling industry in China 2016[EB/OL].[2022-05-25]. http://www.weee-epr.com/article/detail_91.html.
[7] 前瞻产业研究院. 2022-2027年中国工程机械制造行业市场需求预测与投资战略规划分析报告[EB/OL].[2022-05-25]. https://bg.qianzhan.com/report/detail/1807271822103707.html?v=footer2. Prospective Industrial Research Institute. Report of market demand forecast and investment strategy planning on China machinery manufacturing industry(2022-2027)[EB/OL].[2022-05-25]. https://bg.qianzhan.com/report/detail/1807271822103707.html?v=footer2.
[8] 徐博文. 退役工程机械回收与再制造系统的资源及环境效益模型研究[D]. 长沙:湖南大学,2016. XU Bowen. The Resource and environment benefits evaluation models on the recycling and remanufacturing system of end-of-life construction machinery products[D]. Changsha:Hunan University,2016.
[9] 杜汶遥. 废旧家电逆向物流网络构建及绿色度评价研究[D]. 成都:成都理工大学,2020. DU Wenyao. Research on the construction of reverse logistics network and the evaluation of green degree of waste household appliances[D]. Chengdu:Chengdu University of Technology,2020.
[10] 刘汝佳. 车间制造大数据统一建模与集成化管理研究[D]. 武汉:武汉理工大学,2017.. LIU Rujia. Research on unified modeling and integrated management of big data of workshop manufacturing[D]. Wuhan:Wuhan University of Technology,2017.
[11] GAO Hui,JIANG Jun,LI She,et al. A new agglomerative hierarchical clustering algorithm implementation based on the map reduce framework[J]. International Journal of Digital Content Technology and Its Applications,2010,4(3):95-100.
[12] YAN Weizhong,BRAHMAKSHATRIYA U,XUE Ya,et al. p-PIC:Parallel power iteration clustering for big data[J]. Journal of Parallel and Distributed Computing,2013,73(3):352-359.
[13] 李帅. 基于领域本体的制造大数据统一建模技术研究[D]. 成都:四川大学,2021. LI Shuai. Research on unified modeling technology of manufacturing big data based on domain ontology[D]. Chengdu:Sichuan University,2021.
[14] SINGHAL A. Introducing the knowledge graph:Things,not strings[EB/OL]. (2012-05-16)[2022-05-25].http://blog.google/products/search/introducing-knowledge-graph-things-not.
[15] 苏菁. 基于领域知识图谱的网络信息可信度测度[D]. 镇江:江苏科技大学,2018. SU Jing. Credibility measurement of network information based on domain knowledge graph[D]. Zhenjiang:Jiangsu University of Science and Technology,2018.
[16] 鄂海红,张文静,肖思琪,等. 深度学习实体关系抽取研究综述[J]. 软件学报,2019,30(6):1793-1818. E Haihong,ZHANG Wenjing,XIAO Siqi,et al. Survey of entity relationship extraction based on deep learning[J]. Journal of Software,2019,30(6):1793-1818.
[17] ZHONG Zexuan,CHEN Danqi. A frustratingly easy approach for entity and relation extraction[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Online:Association for Computational Linguistics,2021:50-61.
[18] JI Bin,YU Jie,LI Shasha,et al. Span-based joint entity and relation extraction with attention-based span-specific and contextual semantic representations[C]//Proceedings of the 28th International Conference on Computational Linguistics. Barcelona,Spain (Online):International Committee on Computational Linguistics,2020:88-99.
[19] ZENG Xiangrong,ZENG Daojian,HE Shizhu,et al. Extracting relational facts by an end-to-end neural model with copy mechanism[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne,Australia:Association for Computational Linguistics,2018:506-514.
[20] MIWA M,SASAKI Y. Modeling joint entity and relation extraction with table representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha,Qatar:Association for Computational Linguistics,2014:1858-1869.
[21] LI Ren,LI Dong,YANG Jianxi,et al. Joint extraction of entities and relations via an entity correlated attention neural model[J]. Information Sciences,2021,581:179-193.
[22] ROTH D,YIH W T. A linear programming formulation for global inference in natural language tasks[C]//Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004. Boston,Massachusetts,USA:Association for Computational Linguistics,2004:1-8.
[23] DAI Dai,XIAO Xinyan,LYU Yajuan,et al. Joint extraction of entities and overlapping relations using position-attentive sequence labeling[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2019,33:6300-6308.
[24] WANG Jue,LU Wei. Two are better than one:Joint entity and relation extraction with table-sequence encoders[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online:Association for Computational Linguistics,2020:1706-1721.
[25] MA Longzhou,WU Xiuli,KUANG Yuan,et al. Knowledge graph-based approach to trace the full life information of decommissioned electromechanical products[C]//2022 18th IEEE International Conference on Automation Science and Engineering(CASE 2022),Mexico City,August 20-24,2022:2028-2033.
[26] 蔡新辉. 基于多源异构数据的地方风土人情知识图谱构建方法及应用研究[D]. 呼和浩特:内蒙古工业大学,2021. CAI Xinhui. Research on the construction method and application of local customs and human conditions knowledge graph based on multi-source and heterogeneous data[D]. Hohhot:Inner Mongolia University of Technology,2021.
[27] JI Donghong,GAO Jun,FEI Hao,et al. A deep neural network model for speakers coreference resolution in legal texts[J]. Information Processing & Management,2020,57(6):102365.
[28] 汪欢. 基于注意力池化机制和额外知识的事实型知识问答研究[D]. 杭州:浙江大学,2019. WANG Huan. Research on the factoid question answering based on attention pooling mechanism and external knowledge[D]. Hangzhou:Zhejiang University,2019.
[29] DEVLIN J,CHANG M W,LEE K,et al. BERT:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis,Minnesota:Association for Computational Linguistics,2019:4171-4186.
[30] FU T J,LI P H,MA W Y. GraphRel:Modeling text as relational graphs for joint entity and relation extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence,Italy:Association for Computational Linguistics,2019:1409-1418.
[31] VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al. Graph attention networks[C]//International Conference on Learning Representations 2018.[2022-5-25]. http://arxiv.org/abs/1710.10903.
[32] LIN Min,CHEN Qiang,YAN Shuicheng. Network in network[C]//International Conference on Learning Representations 2014.[2022-5-25]. https://arxiv.org/abs/1312.4400.
[33] VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[C]//Advances in Neural Information Processing Systems. 2017:5998-6008.
[34] ZHENG Hengyi,WEN Rui,CHEN Xi,et al. PRGC:Potential relation and global correspondence based joint relational triple extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1:Long Papers). Online:Association for Computational Linguistics,2021:6225-6235.
[35] RIEDEL S,YAO Limin,MCCALLUM A. Modeling relations and their mentions without labeled text[C]//European Conference on Machine Learning and Knowledge Discovery in Databases 2010,2010:148-63.
[36] GARDENT C,SHIMORINA A,NARAYAN S,et al. Creating training corpora for NLG micro-planners[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver,Canada:Association for Computational Linguistics,2017:179-188.
[37] HE Tong,ZHANG Zhi,ZHANG Hang,et al. Bag of tricks for image classification with convolutional neural networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019:558-567.
[38] ZENG Xiangrong,HE Shizhu,ZENG Daojian,et al. Learning the extraction order of multiple relational facts in a sentence with reinforcement learning[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong,China:Association for Computational Linguistics,2019:367-377.
[39] ZENG Daojian,ZHANG Haoran,LIU Qianying. Copymtl:Copy mechanism for joint extraction of entities and relations with multi-task learning[C]//In Proceedings of the 34rd AAAI conference on artificial intelligence. New York,USA:American Association for Artificial Intelligence,2020:9507-9514.
[40] NAYAK T,NG H T. Effective modeling of encoder-decoder architecture for joint entity and relation extraction[C]//In Proceedings of the 34rd AAAI conference on artificial intelligence. New York,USA:American Association for Artificial Intelligence,2020:8528-8535.
[41] YUAN Yue,ZHOU Xiaofei,PAN Shirui,et al. A relation-specific attention network for joint entity and relation extraction[C]//Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20). Yokohama,Japan. International Joint Conference on Artificial Intelligence,2020:4054-4060.