基于伪语义相似度模型的中文地址匹配方法

地址匹配中,由于传统相似度模型受字符重叠数影响大,在处理简写、缩写地址要素单元时,错误匹配问题突出;深度学习方法需要大量样本支撑,但庞大的数据量和多样的形式,导致生成样本的成本过高。为解决上述问题,本文首先应用基于条件随机场和双向长短时记忆神经网络的模型,对地址进行分词;然后通过建立一种伪语义相似度,对地址要素进行分级匹配。通过对公安业务中地址数据进行测试,在对缩写、简写等不规范地址描述方面,本文模型能较理想地完成任务,各参考指标均高于0.9。     

A graph-based method for Chinese address matching

Address matching is a substantial task in location-based services. Currently, major address matching methods either perform rather badly on unstructured data or fail to extract adequate semantic information of address elements. In this article, we propose a graph-based method that can deal with both sides of the problem. First, we use a pretrained transformer neural network to handle address tokenization. Then we parse address tokens into address elements according to their parts of speech. Then the node2vec and tf-idf technique is used to generate node embeddings for each address element. Finally, an address matching graph convolutional network is applied to do the address matching work. We have carried out a series of experiments on a real-world Chinese address corpus, to further evaluate the impacts of our methods. The experimental results indicate our method achieves higher scores than the state-of-the-art methods.     

Machine learning innovations in address matching: A practical comparison of word2vec and CRFs

Record linkage is a frequent obstacle to unlocking the benefits of integrated (spatial) data sources. In the absence of unique identifiers to directly join records, practitioners often rely on text‐based approaches for resolving candidate pairs of records to a match. In geographic information science, spatial record linkage is a form of geocoding that pertains to the resolution of text‐based linkage between pairs of addresses into matches and non‐matches. These approaches link text‐based address sequences, integrating sources of data that would otherwise remain in isolation. While recent innovations in machine learning have been introduced in the wider record linkage literature, there is significant potential to apply machine learning to the address matching sub‐field of geographic information science. As a response, this paper introduces two recent developments in text‐based machine learning—conditional random fields and word2vec—that have not been applied to address matching, evaluating their comparative strengths and drawbacks.     

自然语言理解的中文地址匹配算法

地址匹配算法是位置服务的核心关键技术,具有广泛应用前景。在分析现有三类主要的中文地址匹配算法——要素层级匹配法、全文检索法、正则表达式法的基础上,本文提出了基于自然语言理解的中文地址匹配算法。在这个新算法中,建立了空间关系地址模型以解决中文地址抽象问题、地址库逻辑模型以解决地址信息的空间知识表达问题。新算法的完整流程包括 “预处理”、“地址解析”、“地址要素标准化”、“推理匹配”和“匹配登记”等五个环节,本文重点阐述了“地址解析”和“推理匹配”这两个重要环节,分别依据“自然语言理解”中的“中文分词”和“语义推理”原理,对用非结构化的中文自然语言来描述的中文地址进行处理,实现自然语言理解方法与地址匹配之间的结合,从而建立完整的基于自然语言理解的中文地址匹配算法。为验证该算法,开发了“中文地址智能匹配实验系统”,对河南省濮阳市人口库1000条居民地址数据进行匹配,匹配率达到了95%,准确率高于93%。     

Improving Geocoding Match Rates with Spatially‐Varying Block Metrics

Address ranges used in linear interpolation geocoding often have errors and omissions that result in input address numbers falling outside of known address ranges. Geocoding systems may match these input addresses to the closest available nearby address range and assign low confidence values (match scores) to increase match rates, but little is published describing the matching or scoring techniques used in these systems. This article sheds light on these practices by investigating the need for, technical approaches to, and utility of nearby matching methods used to increase match rates in geocode data. The scope of the problem is motivated by an analysis of a commonly used health dataset. The technical approach of a geocoding system that includes a nearby matching approach is described along with a method for scoring candidates based on spatially‐varying neighborhoods. This method, termed dynamic nearby reference feature scoring, identifies, scores, ranks, and returns the most probable candidate to which the input address feature belongs or is spatially near. This approach is evaluated against commercial systems to assess its effectiveness and resulting spatial accuracy. Results indicate this approach is viable for improving match rates while maintaining acceptable levels of spatial accuracy.     

GIS数据库中地址自动匹配方法研究

在GIS数据库设计与建设中,地址自动匹配一直是一个倍受重视的理论与实践问题.截至目前,还没有非常有效的快速地址自动匹配方法,也没有非常成熟的相关软件可以直接利用.本文针对企业GIS数据库建设,提出了一套地址匹配方法:采用Visual Basic 6.0编程,将20 000多家企业的地址进行预处理、分解和归类,然后将得到的标准化地址导入到数据库,再利用空间插值方法将这些地址数据匹配到地图上.而且,笔者还以上海浦东新区企业GIS数据库建设为例,采用上述方法进行了试验研究,取得了满意的效果.     

一种中文地址知识库支撑的中文地址分词算法

针对中文地址非结构化、不规范的特点,在构建中文地址模版和中文地址词典等重要知识库基础上,基于中文地址模版引入了中文地址分词的预处理;并在中文地址词典的支撑下采用逆向最大匹配算法实现了中文地址分词。新中文地址分词算法不仅在正确率和召回率等指标上优于传统算法,更提出了一种用于解决未登录地址名词识别问题的新方法。     

一种使用RoBERTa-BiLSTM-CRF的中文地址解析方法

针对当前地址匹配方法严重依赖分词词典、无法有效识别地址中的地址元素及其所属类型的问题,提出了使用深度学习的中文地址解析方法,该方法能够对解析后的地址进行标准化和构成分析以改善地址匹配结果。通过对地址的不同词向量表示及不同序列标注模型的对比评估,结果表明,使用双向门递归单元和双向长短时记忆网络对中文地址解析差别较小,稀疏注意力机制有助于提高地址解析的$F_{\mathrm{1}}$值。所提出的方法在泛化能力测试集上的$F_{\mathrm{1}}$值达到了0.940,在普通测试集上的$F_{\mathrm{1}}$值达到了0.968。     

A deep learning approach for rooftop geocoding

Geocoding has become a routine task for many research investigations to conduct spatial analysis. However, the output quality of geocoding systems is found to impact the conclusions of subsequent studies that employ this workflow. The published development of geocoding systems has been limited to the same set of interpolation methods and reference data sets for quite some time. We introduce a novel geocoding approach utilizing object detection on remotely sensed imagery based on a deep learning framework to generate rooftop geocoding output. This allows geocoding systems to use and output exact building locations without employing typical geocoding interpolation methods or being completely limited by the availability of reference data sets. The utility of the proposed approach is demonstrated over a sample of 22,481 addresses resulting in significant spatial error reduction and match rates comparable to typical geocoding methods. For different land‐use types, our approach performs better on low‐density residential and commercial addresses than on high‐density residential addresses. With appropriate model setup and training, the proposed approach can be extended to search different object locations and to generate new address and point‐of‐interest reference data sets.     

多策略中文地址匹配方法

地址匹配是地理编码过程中一个关键环节,是实现数据空间化的关键技术之一。针对当前中文地址匹配方法的精确率、匹配率和时间开销不能兼顾的问题,本文提出了一种多策略中文地址匹配方法。通过建立轻量级的词典进行中文地址分词,同时构建多叉树存储分词后的地址数据,匹配过程中结合模糊匹配和层级回溯匹配共同完成地址匹配工作,最终基于真实数据进行了试验。试验结果表明,该方法在匹配率、精确率和时间开销3个指标上较当前其他匹配方法表现得更加均衡。     

颜色不变量与AKAZE特征相结合的无人机影像匹配算法

基于特征的影像匹配方法是无人机影像匹配中较为实用的一类方法。针对传统特征匹配方法主要以灰度影像作为输入量,难以利用颜色特征高效区分同名点这一问题,本文结合颜色不变量,设计了一种运用AKAZE特征的匹配算法,克服了传统无人机影像匹配忽略彩色信息的缺点;然后通过灰度级变换,使特征点数目大量减少而又不失其可靠性。试验表明,该方法不仅能够准确识别同名点,而且还提高了运行效率。     

顾及位置关系的网络POI地址信息标准化处理方法

针对互联网POI(兴趣点)地址信息中广泛存在的地址要素不完整、文字表达不一致等不规范现象,提出一种顾及位置关系的网络POI地址信息标准化处理方法,首先对POI信息进行切分提取并逐层匹配地址树模型;然后基于4种位置关系从标准POI库中选出相应集合,作为丰富和修正非标准POI地址要素的候选;最后通过最小粒度地址要素的回溯,实现POI地址信息的快速标准化处理。试验表明该方法可以获得较高的准确率,尤其适用于在互联网数据环境中的POI地址信息标准化。     

A Back‐Propagation Neural Network‐Based Approach for Multi‐Represented Feature Matching in Update Propagation

Spatial data infrastructures, which are characterized by multi‐represented datasets, are prevalent throughout the world. The multi‐represented datasets contain different representations for identical real‐world entities. Therefore, update propagation is useful and required for maintaining multi‐represented datasets. The key to update propagation is the detection of identical features in different datasets that represent corresponding real‐world entities and the detection of changes in updated datasets. Using polygon features of settlements as examples, this article addresses these key problems and proposes an approach for multi‐represented feature matching based on spatial similarity and a back‐propagation neural network (BPNN). Although this approach only utilizes the measures of distance, area, direction and length, it dynamically and objectively determines the weight of each measure through intelligent learning; in contrast, traditional approaches determine weight using expertise. Therefore, the weight may be variable in different data contexts but not for different levels of expertise. This approach can be applied not only to one‐to‐one matching but also to one‐to‐many and many‐to‐many matching. Experiments are designed using two different approaches and four datasets that encompass an area in China. The goals are to demonstrate the weight differences in different data contexts and to measure the performance of the BPNN‐based feature matching approach.     

An address regional tessellation method for spatial subdivision and geocoding in digital earth system

With the increased use of locational information, spatial location referencing and coding methods have become much more important to the mining of both geographical and nongeographical data in digital earth system. Unfortunately, current methods of geocoding, based on reverse lookup of coordinates for a given address, have proven too lossy with respect to administrative and socioeconomic data. This paper proposes a spatial subdivision and geocoding model based on spatial address regional tessellation (SART). Given a hierarchical address object definition, and based on the ‘region of influence’ characteristics of an address, SART creates multiresolution spatial subdivisions by irregular and continuous address regions. This model reflects most of the geographical features and many of the social and economic implications for a given address. It also better reflects the way people understand addresses and spatial locations. We also propose an appropriate method of geocoding for standard addresses (SART-GC). The codes generated by this method can record address footprints, hierarchical relationships, and spatial scales in a single data structure. Finally, by applying our methods to the Shibei District of Qingdao, we demonstrate the suitability of SART-GC for multi-scale spatial information representation in digital earth systems.     

深度卷积特征表达的多模态遥感影像模板匹配方法

多模态遥感影像间(光学、红外、SAR等)存在显著的非线性辐射差异,传统方法难以有效地提取影像间的共有特征,匹配效果不佳.鉴于此,本文将深度学习方法引入影像匹配中,提出了一种基于Siamese网络提取多模态影像共有特征的匹配方法.首先通过去除Siamese网络中的池化层和抽取特征来优化该网络,保持特征信息的完整性和位置精度,使其可有效地提取多模态影像间的共有特征,然后采用模板匹配策略,实现多模态遥感影像高精度匹配.通过利用多组多模态遥感影像进行试验,结果表明,本文方法的匹配正确率和匹配精度都优于传统的模板匹配方法.     

局部物体块匹配的图像匹配算法

构建具有较强表达能力的图像特征是图像匹配应用的核心环节.训练孪生神经(Siamese)特征提取网络构建图像局部特征,通过图像局部特征的匹配解决整体图像匹配的问题.在图像匹配过程中,首先检测图像中包含的物体块,采用特征提取网络构建各物体块的特征表达,然后计算各物体块间的相似度,组成图像对相似矩阵,最后基于相似矩阵构建图像...     

一种模拟纠正影像的SAR立体影像匹配方法

针对常规SAR影像匹配方法在地形起伏较大区域无法获取理想的SAR立体影像匹配结果的问题,该文提出了一种基于模拟纠正影像的SAR立体影像匹配方法。利用观测区域粗分辨率DEM进行SAR影像模拟,进而获取几何纠正SAR影像,在几何纠正SAR影像上实现影像匹配,等效于常规基于灰度影像匹配中进行的影像粗配准工作,并且相比于常规粗配准,该等效粗配准过程能够均衡地顾及到整幅影像的像元,最终实现了地形起伏较大区域的高精度SAR立体影像匹配。采用COSMO-Skyped影像数据进行了实验,实验结果表明,匹配精度达到了3个像素左右,比常规的基于灰度影像匹配方法有较大提高,能够有效解决地形起伏较大区域SAR立体影像匹配问题。     

A REVIEW OF MAP REVISION BY PHOTOGRAMMETRY

Revision has become a task equally as important as new mapping. Photogrammetric methods, however, have developed around the latter rather than the former. Modern instrumentation rejects this growth process. This paper examines the efficacy of various photogrammetric approaches for revision with respect to both detection and plotting of change.     

多模态时空数据多层次可视化任务模型

针对现有时空数据可视化方法主要面向单一的低层次展示性可视化任务,难以满足多模态时空数据多层次多样化可视化任务高并发的难题,从展示、分析和探索3个层次构建了面向多模态时空数据自适应可视化的多层次可视化任务模型。重点剖析了不同任务的时空信息需求及其可视化表达驱动力,刻画了任务需求与存算绘资源之间的依赖关系,设计了任务感知的多模态时空数据自适应可视化引擎。以微观精细化管理与宏观综合决策协同的智能设施管理为例进行了试验分析,证明该模型能够有效满足多层次可视分析应用需求,为数字城市和智慧社会等重大工程建设提供了有力的技术方法支撑。     

Fundamental aspects of access control for geospatial data

Abstract

In recent years, geographical information systems have been employed in a wide variety of application domains, and as a result many research efforts are being devoted to those upcoming problems. Geospatial data security, especially access control, has attracted increased research interests within the academic community. The tendency towards sharing and interoperability of geospatial data and applications makes it common to acquire and integrate geospatial data from multiple organisations to accomplish a complex task. Meanwhile, many organisations have the requirement for securing access to possessed sensitive or proprietary geospatial data. In this heterogeneous and distributed environment, consistent access control functionality is crucial to promote controlled accessibility. As an extension of general access control mechanisms in the IT domain, the mechanism for geospatial data access control has its own requirements and characteristics of granularity and geospatial logic. In this paper, we address several fundamental aspects concerning the design and implementation of an access control system for geospatial data, including the classification, requirements, authorisation models, storage structures and management approaches for authorisation rules, matching and decision-making algorithms between authorisation rules and access requests, and its policy enforcement mechanisms. This paper also presents a system framework for realising access control functionality for geospatial data, and explain access control procedures in detail.