基于知识图谱的中文地址匹配方法研究

doi:10.3778/j.issn.1002-8331.2012-0263

摘要/Abstract

摘要： 随着信息技术的迅猛发展，建设新型高效智慧型城市已成为趋势。智慧城市中有大量以地理信息为基础的应用场景，如在城市规划建设、城市便民生活服务、城市细化管理等都离不开地理信息。由于中文地址的复杂性与人工输入的不确定性，地址数据不规范性、不一致、不明确现象给业务系统之间与内部带来了很多困难。急需优秀的中文地址匹配方法。现有的匹配方法仅从地址文字出发进行匹配，而忽略地址作为一个实体蕴含着丰富的地理知识，这些知识可以有效地协助匹配过程，由此，提出注意力知识图谱的中文地址匹配方法，从而解决复杂中文地址匹配准确率低的问题。通过对传统的标准地址库进行地址分词以及特征抽取，建立标准地址知识图谱与POI知识图谱；采用基于选择注意力机制的知识图谱关系抽取方法来进行对地址的特征提取，从而进行地址分类；通过计算知识图谱实体相似度，从而进行非标中文地址的地址匹配。实验结果表明，该方法较基于Jaccard相似度的地址匹配方法、基于动态规划的地址匹配方法、基于Sorensen Dice的全文检索地址匹配方法和基于bert4keras预训练模型的地址匹配方法准确率分别提高了11.05%、15.30%、11.05%、0.95%，有效对复杂中文地址进行匹配。

关键词: 知识图谱, 中文地址, 地址匹配

Abstract: With the rapid development of information technology, it has become a trend to build new efficient and intelligent cities. In smart cities, there are a large number of application scenarios based on geographic information, such as urban planning and construction, urban convenient life services, urban refinement management and so on, which are inseparable from geographic information. Due to the complexity of Chinese address and the uncertainty of manual input, the non-standardization, inconsistency and ambiguity of address data bring a lot of difficulties between and within business systems. An excellent Chinese address matching method is urgently needed. Matching method only match from address text, and ignoring address as a single entity contains the rich geographical knowledge, these knowledge can effectively assist in matching process, as a result, this paper puts forward attention Chinese address matching method of knowledge graph, so as to solve the problem of low accuracy of complex Chinese address matching. Firstly, the knowledge graph of standard address and the knowledge map of POI are established through the address segmentation and feature extraction of the traditional standard address library. Secondly, a knowledge graph relation extraction method based on selective attention mechanism is used to extract the features of addresses, so as to classify addresses. Finally, the address matching of non-standard Chinese addresses is carried out by calculating the entity similarity of knowledge graph. The experimental results show that the accuracy of this method is improved by 11.05%, 15.30% , 11.05% and 0.95%, respectively, compared with the address matching method based on Jaccard similarity, the address matching method based on dynamic programming , the address matching method based on Sorensen Dice and address matching method based on bert4keras pre-training model, which can effectively match complex Chinese addresses.

Key words: knowledge graph, Chinese address, address matching

陈雨晖, 皮洲, 姜滕圣, 李响, 王震, 奚雪峰, 吴宏杰, 付保川. 基于知识图谱的中文地址匹配方法研究[J]. 计算机工程与应用, 2022, 58(14): 306-312.

CHEN Yuhui, PI Zhou, JIANG Tengsheng, LI Xiang, WANG Zhen, XI Xuefeng, WU Hongjie, FU Baochuan. Research on Chinese Address Matching Based on Knowledge Graph[J]. Computer Engineering and Applications, 2022, 58(14): 306-312.

参考文献

[1] 侯梦薇，卫荣，陆亮，等.知识图谱研究综述及其在医疗领域的应用[J].计算机研究与发展，2018，55（12）：2587-2599.
HOU Mengwei，WEI Rong，LU Liang，et al.Research review of knowledge graph and its application in medical domain[J].Journal of Computer Research and Development，2015，55（12）：2587-2599.
[2] PAULHEIM H.Knowledge graph refinement：a survey of approaches and evaluation methods[J].Semantic Web，2017，8（3）：489-508.
[3] ZHAO Y，LI H，YIN S，et al.A new Chinese word segmentation method based on maximum matching[J].Journal of Information Hiding and Multimedia Signal Processing，2018，9（6）：1528-1535.
[4] NIU Y，HUAN L.The secondary Hash MM algorithm based on probability factor[M]//Advances in computer science and education.Berlin，Heidelberg：Springer，2012：313-318.
[5] MO J W，ZHENG Y，SHOU Z Y，et al.Improved Chinese word segmentation method based on dictionary[J].Computer Engineering and Design，2013，34（5）：1802-1807.
[6] LIN Y，KANG M，WU Y，et al.A deep learning architecture for semantic address matching[J].International Journal of Geographical Information Science，2020，34（3）：559-576.
[7] 赵阳阳，王亮，仇阿根.地址要素识别机制的地名地址分词算法[J].测绘科学，2013，38（5）：74-76.
ZHAO Yangyang，WANG Liang，QIU A’gen.An improved algorithm for address segmentation[J].Science of Surveying and Mapping，2013，38（5）：74-76.
[8] 张雪英，闾国年，李伯秋，等.基于规则的中文地址要素解析方法[J].地球信息科学学报，2010，12（1）：9-16.
ZHANG Xueying，LV Guonian，LI Boqiu，et al.Rule-based analytic method of Chinese address elements[J].Journal of Geo-Information Science，2010，12（1）：9-16.
[9] 谢婷婷，严柯.基于统计的中文地址位置语义解析方法研究[J].软件导刊，2017，16（10）：19-21.
XIE Tingting，YAN Ke.The method of semantic resolution of Chinese addresses based on statistics[J].Software Guide，2017，16（10）：19-21.
[10] 许普乐，王杨，黄亚坤，等.大数据环境下基于贝叶斯推理的中文地名地址匹配方法[J].计算机科学，2017，44（9）：266-271.
XU Pule，WANG Yang，HUANG Yakun，et al.Chinese place-name address matching method based on large data analysis and Bayesian decision[J].Computer Science，2017，44（9）：266-271.
[11] 邹恩岑，曾诚，张谦，等.一种面向中文非标建筑地址标准化的自动匹配方法[J].苏州科技大学学报（自然科学版），2019，36（4）：66-74.
ZOU Encen，ZENG Cheng，ZHANG Qian，et al.An automatic matching approach to standardizing nonstandard Chinese building addresses[J].Journal of Suzhou University of Science and Technology（Natural Science），2019，36（4）：66-74.
[12] THANGAVELU S，SIRANJEEVI N，SHANMUGAM P K.Fuzzy keyword search over encrypted data in cloud computing using string matching algorithm[J].Journal of Operating Systems Development & Trends，2017，4（2）：8-12.
[13] TIAN C，YU H，MENG X.Knowledge reasoning based on knowledge graph[C]//2018 3rd International Conference on Advances in Materials，Mechatronics and Civil Engineering（ICAMMCE 2018），2018.
[14] ZHOU Z T，ZHAO P P，SHENG V S，et al.Efficient sampling methods for characterizing POIs on maps based on road networks[J].Frontiers of Computer Science，2018，12（3）：582-592.
[15] 任星怡，宋美娜，宋俊德.基于位置社交网络的上下文感知的兴趣点推荐[J].计算机学报，2017，40（4）：824-841.
REN Xingyi，SONG Meina，SONG Junde.Context-aware point-of-interest recommendationin location-based social networks[J].Chinese Journal of Computers，2017，40（4）：824-841.
[16] MUELDER C，CHEN L，THOMASON R，et al.Intelligent classification and visualization of network scans[M]//VizSEC 2007.Berlin，Heidelberg：Springer，2008：237-253.
[17] 高强，张凤荔，王瑞锦，等.轨迹大数据：数据处理关键技术研究综述[J].软件学报，2017，28（4）：959-992.
GAO Qiang，ZHANG Fengli，WANG Ruijin，et al.Trajectory big data：a review of key technologies in data processing[J].Journal of Software，2017，28（4）：959-992.
[18] QIAN W，FU C，ZHU Y，et al.Translating embeddings for knowledge graph completion with relation attention mechanism[C]//Proceedings of IJCAI，2018：4286-4292.
[19] 周才东，曾碧卿，王盛玉，等.结合注意力与卷积神经网络的中文摘要研究[J].计算机工程与应用，2019，55（8）：132-137.
ZHOU Caidong，ZENG Biqing，WANG Shengyu，et al.Chinese summarization research on combination of local attention and convolutional neural network[J].Computer Engineering and Applications，2019，55（8）：132-137.
[20] 郑志蕴，吴建萍，李钝，等.一种基于短文本相似度计算的知识子图融合方法[J].小型微型计算机系统，2020，41（1）：6-11.
ZHENG Zhiyun，WU Jianping，LI Dun，et al.Knowledge subgraph fusion method based on short text similarity calculation[J].Journal of Chinese Computer Systems，2020，41（1）：6-11.
[21] DONG Y，LIU Y，LIANG H，et al.Strategic weight manipulation in multiple attribute decision making[J].Omega，2018，75：154-164.
[22] 陈俊月，郝文宁，张紫萱，等.基于改进句子相似度算法的释义识别研究[J].计算机工程，2020，46（9）：76-82.
CHEN Junyue，HAO Wenning，ZHANG Zixuan，et al.Research on paraphrase identification based on improved sentence similarity algorithm[J].Computer Engineering，2020，46（9）：76-82.
[23] 陈细谦，迟忠先，昃宗亮，等.地理编码在空间数据仓库ETL中的应用[J].小型微型计算机系统，2005（4）：628-630.
CHEN Xiqian，CHI Zhongxian，ZE Zongliang，et al.Application of geocoding in ETL of spatial data warehouse[J].Mini-Micro Systems，2005（4）：628-630.
[24] 卢盛祺，何施晶，韩景倜.基于Apache Lucene的地址匹配技术研究[J].微型机与应用，2015，34（18）：73-75.
LU Shengqi，HE Shijing，HAN Jingti.Research on geocoding based on Apache Lucene[J].Microcomputer & Its Applications，2015，34（18）：73-75.
[25] 李舟军，范宇，吴贤杰.面向自然语言处理的预训练技术研究综述[J].计算机科学，2020，47（3）：162-173.
LI Zhoujun，FAN Yu，WU Xianjie.Survey of natural language processing pre-training techniques[J].Computer Science，2020，47（3）：162-173.
[26] YOUNG T，HAZARIKA D，PORIA S，et al.Recent trends in deep learning based natural language processing[J].IEEE Computational Intelligence Magazine，2018，13（3）：55-75.
[27] SUN Z，HU W，ZHANG Q，et al.Bootstrapping entity alignment with knowledge graph embedding[C]//Proceedings of IJCAI，2018：4396-4402.