Semantic-Aware Approach to Knowledge Extraction from Industrial Manufacturing Domains

doi:10.3778/j.issn.1002-8331.2303-0467

Abstract

Abstract: The study of generic knowledge extraction methods in industrial manufacturing is of great significance for realizing the automated construction of industrial knowledge bases. Aiming at the problem that industrial ontology definition requires a large amount of labour cost and expert experience for guidance, a semi-automatic ontology construction method is designed based on the sememe analysis, and finally the definition of ontology, ontology class, cascade and relationship is completed, using automobile manufacturing fault repair data as an example. Subsequently, in order to solve the problems of relationship nesting and cascade model error propagation that exist in relationship extraction in the industrial domain, a semantic-aware relationship extraction model is designed. In the three links of potential relationship mining, subject extraction and object extraction in this model, different leading interrogatives are spliced based on reading comprehension methods to obtain sentence codes applicable to different links.In order to make use of the a priori knowledge of the subject, the attention mechanism is incorporated into the object extraction module to improve the expressiveness of the codes in this module. Three sessions of joint optimised training to improve extraction results. Experiments are conducted on the automotive manufacturing fault repair dataset, the automotive industry fault pattern extraction evaluation dataset, and the equipment manufacturing dataset, and the model in this paper achieves better results than other relational extraction baseline models.

Key words: ontology construction, sememe analysis, relation extraction, attention mechanism, industrial manufacturing domain

摘要： 工业制造领域通用知识抽取方法研究对于实现工业知识库自动化构建意义重大。针对工业本体定义需要大量人工成本和专家经验作指导的问题，基于义原分析设计了一种半自动本体构建方法，最后以汽车生产制造故障维修数据为例，完成了本体、本体类、层级和关系定义。为解决工业领域关系抽取存在的关系嵌套和级联模型误差传播问题，设计了一种基于语义感知的关系抽取模型：在该模型的潜在关系挖掘、主语抽取、宾语抽取三个环节中，基于阅读理解方法拼接不同的引导问句，得到适用于不同环节的句子编码；为利用主语先验知识，在宾语抽取模块融入注意力机制，提高了该模块编码的表达能力；三环节联合优化训练提升抽取效果。在汽车生产制造故障维修数据集、汽车工业故障模式抽取评测数据集、装备制造数据集中进行实验，提出的模型比其他关系抽取基线模型取得了更好的效果。

关键词: 本体构建, 义原分析, 关系抽取, 注意力机制, 工业制造领域

HUANG Ziqi, HU Jianpeng. Semantic-Aware Approach to Knowledge Extraction from Industrial Manufacturing Domains[J]. Computer Engineering and Applications, 2024, 60(12): 357-365.

黄子麒, 胡建鹏. 基于语义感知的工业制造领域知识抽取方法[J]. 计算机工程与应用, 2024, 60(12): 357-365.

References

[1] 周济. 智能制造——“中国制造2025”的主攻方向[J]. 中国机械工程, 2015, 26(17): 2273-2284.
ZHOU J. Smart manufacturing—the main direction of “Made in China 2025”[J]. China Mechanical Engineering, 2015, 26(17): 2273-2284.
[2] LUO K, LIN F, LUO X, et al. Knowledge base question answering via encoding of complex query graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31-November 4, 2018. PA: Association for Computational Linguistics, 2018: 2185-2194.
[3] BAI T, GE Y, GUO S Y, et al. Enhanced natural language interface for web-based information retrieval[J]. IEEE Access, 2020, 9: 4233-4241.
[4] STUDER R, BENJAMINS V R, FENSEL D. Knowledge engineering: principles and methods[J]. Data & Knowledge Engineering, 2008, 25(1/2): 161-197.
[5] 尚新丽. 国外本体构建方法比较分析[J]. 图书情报工作, 2012, 56: 116-119.
SHANG X L. Comparative analysis of foreign ontology construction methods[J]. Library and Information Service, 2012, 56: 116-119.
[6] 郑姝雅, 黄奇, 张戈, 等. 面向用户生成内容的本体构建方法[J]. 情报科学, 2019, 37(11): 43-47.
ZHENG S Y, HUANG Q, ZHANG G, et al. A ontology construction method for user generated content[J]. Information Science, 2019, 37(11): 43-47.
[7] 唐琳, 郭崇慧, 陈静锋, 等. 基于中文学术文献的领域本体概念层次关系抽取研究[J]. 情报学报, 2020, 39(4): 387-398.
TANG L, GUO C H, CHEN J F, et al. Learning concept hierarchies from chinese academic literature for domain ontology construction[J]. Journal of the China Society for Scientific and Technical Information, 2020, 39(4): 387-398.
[8] 柳少峰, 肖红, 黄子豪, 等. 工业机器人预测式健康管理本体半自动化构建[J]. 组合机床与自动化加工技术, 2022, 575(1) : 29-33.
LIU S F, XIAO H, HUANG Z H, et al. Semi-automatic construction of predictive health management ontology for industrial robots[J]. Modular Machine Tool ＆ Automatic Manufacturing Technique, 2022, 575(1) : 29-33.
[9] 田玲, 张谨川, 张晋豪, 等. 知识图谱综述——表示、构建、推理与知识超图理论[J]. 计算机应用, 2021, 41(8): 2161-2186.
TIAN L, ZHANG J C, ZHANG J H, et al. Knowledge graph survey: representation, construction, reasoning and knowledge hypergraph theory[J]. Journal of Computer Applications, 2021, 41(8): 2161-2186.
[10] WEI Z, SU J, WANG Y, et al. A novel cascade binary tagging framework for relational triple extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. PA: Association for Computational Linguistics, 2020 : 1476-1488.
[11] LI X, LI Y W, YANG J N, et al. A relation aware embedding mechanism for relation extraction[J]. Applied Intelligence, 2022, 52 (9): 10022-10031.
[12] ZHONG Z, CHEN D Q. 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. PA: Association for Computational Linguistics, 2021: 50-61.
[13] TANG R, CHEN Y, QIN Y, et al. Boundary assembling method for joint entity and relation extraction[J]. Knowledge-Based Systems, 2022, 250: 109129.
[14] 李宏宇, 段利国, 候晨蕾, 等. 基于cwhc-Am的实体及关系联合抽取方法[J]. 中文信息学报, 2022, 36(11): 79-90.
LI H Y, DUAN L G, HOU C L, et al. Joint extraction of entities and relations based on CWHC-AM[J]. Journal of Chinese Information Processing, 2022, 36(11): 79-90.
[15] FEI H, REN Y F, JI D H. Boundaries and edges rethinking: an end-to-end neural model for overlapping entity relation extraction[J]. Information Processing & Management, 2020, 57(6): 12.
[16] NOY N F, MCGUINNESS D L. Ontology development 101: a guide to creating your first ontology, SMI-2001-0880[R]. USA: Standford University, 2001.
[17] 梁志宇, 王宏志, 李建中, 等. 制造业中的大数据分析技术应用研究综述[J]. 机械, 2018, 45(6): 1-13.
LIANG Z Y, WANG H Z, LI J Z, et al. A review on the application of big data analysis in manufacturing industry[J]. Machinery, 2018, 45(6): 1-13.
[18] 刘艺, 欧培培, 魏磊, 等. 工业大数据处理技术在汽车制造中的应用[J]. 内燃机与配件, 2022, 369(21) : 70-72.
LIU Y, OU P P, WEI L, et al. Application of industrial big data processing technology in automobile manufacturing[J]. Internal Combustion Engine & Parts, 2022, 369(21) : 70-72.
[19] CHE W, FENG Y, QIN L, et al. N-LTP: an open-source neural language technology platform for Chinese[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Stroudsburg, PA: Association for Computational Linguistics, 2021: 42-49.
[20] QI F, YANG C, LIU Z Y, et al. OpenHowNet: an open sememe-based lexical knowledge base[J]. arXiv:1901. 09957, 2019.
[21] EBERTS M, ULGES A. Span-based joint entity and relation extraction with transformer pre-training[EB/OL]. (2019-09-17)[2023-03-06]. https://arxiv.org/pdf/1909.07755. pdf.