CN116992962A - A method of constructing geomorphological knowledge graph based on self-supervised deep learning - Google Patents

A method of constructing geomorphological knowledge graph based on self-supervised deep learning Download PDF

Info

Publication number
CN116992962A
CN116992962A CN202310995603.9A CN202310995603A CN116992962A CN 116992962 A CN116992962 A CN 116992962A CN 202310995603 A CN202310995603 A CN 202310995603A CN 116992962 A CN116992962 A CN 116992962A
Authority
CN
China
Prior art keywords
model
self
landform
supervised
training
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310995603.9A
Other languages
Chinese (zh)
Other versions
CN116992962B (en
Inventor
许珺
杨家齐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Geographic Sciences and Natural Resources of CAS
Original Assignee
Institute of Geographic Sciences and Natural Resources of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Geographic Sciences and Natural Resources of CAS filed Critical Institute of Geographic Sciences and Natural Resources of CAS
Priority to CN202310995603.9A priority Critical patent/CN116992962B/en
Publication of CN116992962A publication Critical patent/CN116992962A/en
Application granted granted Critical
Publication of CN116992962B publication Critical patent/CN116992962B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • G06N5/022Knowledge engineering; Knowledge acquisition
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • G06N3/0455Auto-encoder networks; Encoder-decoder networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/0895Weakly supervised learning, e.g. semi-supervised or self-supervised learning
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Image Analysis (AREA)

Abstract

本发明涉及地貌知识图谱研究技术领域,具体地说是一种基于自监督深度学习的地貌知识图谱构建方法,包括自监督预训练模型构建、自监督预训练模型的评估和语义分析与知识图谱构建,本发明同现有技术相比,在全球多分辨率DEM数据上,学习多尺度的地貌类型语义和空间特征,形成以机器计算为目的的地貌特征向量表示,构建一套计算机可理解、可计算、可推理的地貌知识图谱。

The present invention relates to the technical field of geomorphological knowledge graph research, specifically a geomorphic knowledge graph construction method based on self-supervised deep learning, including self-supervised pre-training model construction, self-supervised pre-training model evaluation and semantic analysis and knowledge graph construction. , compared with the existing technology, this invention learns multi-scale semantics and spatial characteristics of landform types on global multi-resolution DEM data, forms a landform feature vector representation for the purpose of machine calculation, and builds a set of computer-understandable and reproducible Computational, inferable landscape knowledge graphs.

Description

一种基于自监督深度学习的地貌知识图谱构建方法A method for constructing geomorphological knowledge graph based on self-supervised deep learning

技术领域Technical field

本发明涉及地貌知识图谱研究技术领域,具体地说是一种基于自监督深度学习的地貌知识图谱构建方法。The present invention relates to the technical field of geomorphological knowledge graph research, specifically a geomorphic knowledge graph construction method based on self-supervised deep learning.

背景技术Background technique

地貌是最重要的自然地理要素之一,影响着地表气候、生态环境和自然资源的空间分布。地貌研究是地理学的一个重要分支,对了解地球表面的形态、结构、分布变化和规律具有重要作用,并且为人类的生存和发展提供科学依据。随着科技的发展,地貌学的研究日益信息化、智能化。上世纪九十年代末,随着地学信息图谱概念的提出,地貌学领域的学者们突破地貌信息提取、分类等关键技术,构建了地貌形态特征、地貌发育等信息图谱,实现对一系列地貌知识的总结和凝练。Landform is one of the most important physical geographical elements, affecting the surface climate, ecological environment and spatial distribution of natural resources. Landform research is an important branch of geography, which plays an important role in understanding the shape, structure, distribution changes and laws of the earth's surface, and provides scientific basis for human survival and development. With the development of science and technology, the study of geomorphology has become increasingly information-based and intelligent. In the late 1990s, with the introduction of the concept of geological information maps, scholars in the field of geomorphology made breakthroughs in key technologies such as geomorphological information extraction and classification, and constructed information maps such as landform morphological characteristics and landform development to realize a series of geomorphological knowledge. summary and condensation.

当前知识图谱(KnowledgeGraph)成为信息领域的研究热点。知识图谱以结构化的有向图的形式表示知识,以节点和连边表示实体以及实体之间的关系,通过知识表示学习(KnowledgeGraph Embedding)将实体和关系的语义映射到低维连续的向量空间,从而可以通过向量或矩阵操作实现知识推理和预测,因而知识图谱具有强大的语义计算能力,在语义检索、智能问答、个性推荐方面得到广泛应用,地学研究的多个领域也已开展领域知识图谱构建。Currently, knowledge graph (KnowledgeGraph) has become a research hotspot in the information field. Knowledge graph represents knowledge in the form of a structured directed graph, using nodes and edges to represent entities and relationships between entities. The semantics of entities and relationships are mapped to a low-dimensional continuous vector space through knowledge representation learning (KnowledgeGraph Embedding). , so that knowledge reasoning and prediction can be realized through vector or matrix operations. Therefore, knowledge graphs have powerful semantic computing capabilities and are widely used in semantic retrieval, intelligent question answering, and personalized recommendations. Domain knowledge graphs have also been developed in many fields of geoscience research. Construct.

具体到地貌学领域,由于地貌本身存在边界模糊、类型难确定、多尺度的问题,使得地貌分类困难,地貌分类体系多样,不同体系之间难以统一,构建地貌知识本体存在困难。且地貌本身边界模糊难确定,目前的地貌类型划分均是以人的认知为核心,不是面向机器计算、以机器理解为核心的体系,难以实现计算机可理解并利用的定量表达和计算。Specific to the field of geomorphology, due to the problems of blurred boundaries, difficult to determine types, and multi-scale problems in landforms, it is difficult to classify landforms. There are various landform classification systems, and it is difficult to unify different systems, and it is difficult to construct a landform knowledge ontology. Moreover, the boundaries of the landforms themselves are fuzzy and difficult to determine. The current classification of landform types is based on human cognition and is not a system oriented toward machine calculations and centered on machine understanding. It is difficult to achieve quantitative expressions and calculations that can be understood and utilized by computers.

现有技术中的国内外研究需要专家知识,自上而下构建本体层,自动化程度不高,且现有地貌分类体系多样,难以构建统一的知识本体,根据本体从文本中抽取的三元组难以提供充足的各种地貌类型实体及其特征。Domestic and foreign research in the existing technology requires expert knowledge, and the ontology layer is constructed from top to bottom. The degree of automation is not high, and the existing landform classification systems are diverse, making it difficult to construct a unified knowledge ontology. The triples extracted from the text are based on the ontology. It is difficult to provide sufficient entities of various landform types and their characteristics.

因此,为了解决上述问题,本申请提出了一种基于自监督深度学习的地貌知识图谱构建方法,通过深度学习领域自监督深度学习发展迅速。基于自监督学习策略的预训练模型在大量数据上进行训练,可在没有领域专家知识的情况下自动提取数据中的通用特征,形成适合DEM数据的自监督深度学习模型和训练策略,达到能够充分学习地貌语义和空间特征的目的,探究人工智能视角下的地貌分类体系,实现自下而上自动化构建计算机可理解、可计算的地貌知识图谱。Therefore, in order to solve the above problems, this application proposes a method of constructing a geomorphological knowledge graph based on self-supervised deep learning. Self-supervised deep learning has developed rapidly in the field of deep learning. The pre-training model based on the self-supervised learning strategy is trained on a large amount of data, and can automatically extract common features in the data without domain expert knowledge, forming a self-supervised deep learning model and training strategy suitable for DEM data, so as to fully achieve the goal. The purpose is to learn the semantics and spatial characteristics of landforms, explore the landform classification system from the perspective of artificial intelligence, and realize the bottom-up automated construction of a computer-understandable and computable landform knowledge map.

发明内容Contents of the invention

本发明的目的是填补现有技术的空白,提供了一种基于自监督深度学习的地貌知识图谱构建方法,通过深度学习领域自监督深度学习发展迅速。基于自监督学习策略的预训练模型在大量数据上进行训练,可在没有领域专家知识的情况下自动提取数据中的通用特征,形成适合DEM数据的自监督深度学习模型和训练策略,达到能够充分学习地貌语义和空间特征的目的,探究人工智能视角下的地貌分类体系,实现自下而上自动化构建计算机可理解、可计算的地貌知识图谱。The purpose of the present invention is to fill the gaps in the existing technology and provide a method for constructing a geomorphological knowledge map based on self-supervised deep learning. Self-supervised deep learning has developed rapidly through the field of deep learning. The pre-training model based on the self-supervised learning strategy is trained on a large amount of data, and can automatically extract common features in the data without domain expert knowledge, forming a self-supervised deep learning model and training strategy suitable for DEM data, so as to fully achieve the goal. The purpose is to learn the semantics and spatial characteristics of landforms, explore the landform classification system from the perspective of artificial intelligence, and realize the bottom-up automated construction of a computer-understandable and computable landform knowledge map.

为了达到上述目的,本发明提供一种基于自监督深度学习的地貌知识图谱构建方法,包括自监督预训练模型构建、自监督预训练模型的评估和语义分析与知识图谱构建;In order to achieve the above objectives, the present invention provides a method for constructing a geomorphological knowledge graph based on self-supervised deep learning, including self-supervised pre-training model construction, self-supervised pre-training model evaluation and semantic analysis and knowledge graph construction;

自监督预训练模型构建:完善自监督学习的策略,包括构建训练数据集、设计模型结构、探究学习策略和设计损失函数,并进行模型训练;Self-supervised pre-training model construction: improve the self-supervised learning strategy, including building training data sets, designing model structures, exploring learning strategies, designing loss functions, and conducting model training;

自监督预训练模型的评估:将预训练模型应用到下游任务中,评估模型的学习性能和迁移性能,并发现问题反馈到预训练模型,调节模型参数;Evaluation of self-supervised pre-training models: Apply the pre-training model to downstream tasks, evaluate the learning performance and transfer performance of the model, and feed back problems to the pre-training model to adjust model parameters;

语义分析与知识图谱构建:对预训练得到的地貌向量表征进行语义分析,构建地貌知识图谱;Semantic analysis and knowledge graph construction: Semantic analysis is performed on the pre-trained landscape vector representation to construct a landscape knowledge graph;

自监督预训练模型构建具体包括:The construction of self-supervised pre-training model specifically includes:

S1,预训练数据集:S1, pre-training data set:

利用现有不同分辨率的全球DEM产品,构建大规模的预训练数据集的数据来源,随机选择部分区域构建预训练数据集,将数据切割为统一大小的栅格图幅,构建数据规模总量在900,000~1,000,000幅的预训练数据集,将较小比例的数据划分为验证集,其余作为训练集;Utilize existing global DEM products of different resolutions to build data sources for large-scale pre-training data sets, randomly select some areas to build pre-training data sets, cut the data into raster images of uniform size, and build a total data scale In the pre-training data set of 900,000 to 1,000,000 images, a smaller proportion of the data is divided into the verification set, and the rest is used as the training set;

S2,模型设计:S2, model design:

构建自监督的DEM深度学习模型,设计编码器和解码器的结构,选用MAE模型的掩码结构以及基于ViT模型的基本架构,将对比不同ViT模型结构的性能,以及其他卷积神经网络模型的性能,通过多组对比实验,选定最佳模型,解决编码关键技术;Construct a self-supervised DEM deep learning model, design the structure of the encoder and decoder, select the mask structure of the MAE model and the basic architecture based on the ViT model, and compare the performance of different ViT model structures, as well as the performance of other convolutional neural network models. Performance, through multiple sets of comparative experiments, the best model is selected to solve key coding technologies;

改变编码器数据输入方式,采用同一区域多分辨率数据同步输入的方法,使得模型同步学习不同分辨率特征;由于同样图幅不同分辨率数据的像素不一致,改变MAE的像素位置编码方式,借鉴Scale-MAE的绝对距离编码方式,针对不同图幅之间地形的相关性,设计合适的位置编码方式,使得不同分辨率数据的位置信息保持一致,既要避免绝对位置编的信息泄露问题,又在一定程度上反映地形特征的周期性模式,并通过调整解码器结构,提高模型的对不同尺度数据的通用性;Change the encoder data input method and adopt the method of synchronous input of multi-resolution data in the same area, so that the model can learn the features of different resolutions synchronously; because the pixels of the same image at different resolutions are inconsistent, change the pixel position encoding method of MAE and learn from Scale -MAE's absolute distance encoding method, based on the correlation of terrain between different frames, designs an appropriate position encoding method to keep the position information of different resolution data consistent, which not only avoids the information leakage problem of absolute position encoding, but also It reflects the periodic patterns of terrain features to a certain extent, and improves the model’s versatility for data of different scales by adjusting the decoder structure;

S3,自监督学习策略:S3, self-supervised learning strategy:

完善自监督学习策略,探究不同超参数的设置,自监督学习采用图像掩码的方式,随机对DEM图幅进行一定比例的遮盖,将未被遮盖的部分作为预训练模型的输入,通过编码器和解码器后得到恢复的图像,与原始图像相比计算损失,对模型进行优化;尝试不同数据遮盖方式或者以随机生成的任意形状遮盖数据,尝试不同的遮盖比例,探索最佳比例;Improve the self-supervised learning strategy and explore the settings of different hyperparameters. Self-supervised learning uses image masking to randomly cover a certain proportion of the DEM image, and uses the uncovered part as the input of the pre-training model, through the encoder After decoding the recovered image, calculate the loss compared with the original image, and optimize the model; try different data covering methods or cover the data with randomly generated arbitrary shapes, try different covering ratios, and explore the best ratio;

S4,损失函数:S4, loss function:

设计合理的损失函数,在自监督学习过程中,最直接的指标是恢复的数值与真实数值之间的数值差异,引入地形因子控制模型的训练效果,并在损失函数中加入这些因子的损失值,使模型在优化时考虑地形因素;Design a reasonable loss function. In the self-supervised learning process, the most direct indicator is the numerical difference between the restored value and the real value. Introduce terrain factors to control the training effect of the model, and add the loss values of these factors to the loss function. , so that the model considers terrain factors when optimizing;

语义分析与知识图谱构建具体包括:Semantic analysis and knowledge graph construction specifically include:

S10,监督学习模型将地貌特征用向量表示,通过对向量的相似性计算,将特征相似且空间邻近的地块合并成地貌单元,一个地貌单元就是一个地貌类型实体;S10, the supervised learning model represents the landform features as vectors. By calculating the similarity of the vectors, plots with similar characteristics and spatial proximity are merged into landform units. A landform unit is a landform type entity;

S20,通过层次聚类,得到地貌类型的等级结构;S20, obtain the hierarchical structure of landform types through hierarchical clustering;

S30,通过自监督学习的注意力机制,得到每两个地块相互之间的注意力得分,构建注意力得分矩阵,计算地块之间的相互依赖程度,采用可视化分析,探索不同地貌实体之间的相互依赖关系,研究地貌类型分布空间模式,并构建地貌空间语法树;S30, through the attention mechanism of self-supervised learning, the attention scores between each two plots are obtained, an attention score matrix is constructed, the degree of interdependence between the plots is calculated, and visual analysis is used to explore the relationship between different landform entities. study the interdependence between landform types, study the spatial pattern of landform type distribution, and construct a landform space syntax tree;

S40,形成包含地貌类型等级结构、地貌实体语义表征和地貌类型空间关系的地貌知识图谱。S40: Form a geomorphic knowledge graph including the hierarchical structure of geomorphic types, semantic representation of geomorphic entities, and spatial relationships of geomorphic types.

本发明同现有技术相比,在全球多分辨率DEM数据上,学习多尺度的地貌类型语义和空间特征,形成以机器计算为目的的地貌特征向量表示。Compared with the existing technology, the present invention learns multi-scale semantics and spatial features of landform types on global multi-resolution DEM data to form a landform feature vector representation for the purpose of machine calculation.

通过探索,形成适合DEM数据的自监督深度学习模型和训练策略,达到能够充分学习地貌语义和空间特征的目的;通过地貌特征向量表示的分析和计算,探究人工智能视角下的地貌分类体系,实现自下而上自动化构建计算机可理解、可计算的地貌知识图谱。Through exploration, a self-supervised deep learning model and training strategy suitable for DEM data are formed to achieve the purpose of fully learning the semantics and spatial characteristics of landforms; through the analysis and calculation of landform feature vector representation, the landform classification system from the perspective of artificial intelligence is explored to achieve Automatically build a computer-understandable and computable geomorphological knowledge graph from the bottom up.

附图说明Description of the drawings

图1为本发明项目总体研究框架和技术路线示意图。Figure 1 is a schematic diagram of the overall research framework and technical route of the present invention project.

图2为本发明MAE模型结构示意图。Figure 2 is a schematic structural diagram of the MAE model of the present invention.

图3为本发明知识图谱构建技术路线示意图。Figure 3 is a schematic diagram of the technical route for constructing a knowledge graph according to the present invention.

具体实施方式Detailed ways

现结合附图对本发明做进一步描述。The present invention will now be further described with reference to the accompanying drawings.

请参阅图1~3,一种基于自监督深度学习的地貌知识图谱构建方法,包括自监督预训练模型构建、自监督预训练模型的评估和语义分析与知识图谱构建;Please refer to Figures 1 to 3, a method of constructing a geomorphological knowledge graph based on self-supervised deep learning, including self-supervised pre-training model construction, evaluation of the self-supervised pre-training model, semantic analysis and knowledge graph construction;

自监督预训练模型构建:完善自监督学习的策略,包括构建训练数据集、设计模型结构、探究学习策略和设计损失函数,并进行模型训练;Self-supervised pre-training model construction: improve the self-supervised learning strategy, including building training data sets, designing model structures, exploring learning strategies, designing loss functions, and conducting model training;

自监督预训练模型的评估:将预训练模型应用到下游任务中,评估模型的学习性能和迁移性能,并发现问题反馈到预训练模型,调节模型参数;Evaluation of self-supervised pre-training models: Apply the pre-training model to downstream tasks, evaluate the learning performance and transfer performance of the model, and feed back problems to the pre-training model to adjust model parameters;

语义分析与知识图谱构建:对预训练得到的地貌向量表征进行语义分析,构建地貌知识图谱;Semantic analysis and knowledge graph construction: Semantic analysis is performed on the pre-trained landscape vector representation to construct a landscape knowledge graph;

自监督预训练模型构建具体包括:The construction of self-supervised pre-training model specifically includes:

S1,预训练数据集:S1, pre-training data set:

利用现有不同分辨率的全球DEM产品,构建大规模的预训练数据集的数据来源,随机选择部分区域构建预训练数据集,将数据切割为统一大小的栅格图幅,构建数据规模总量在900,000~1,000,000幅的预训练数据集,将较小比例的数据划分为验证集,其余作为训练集;Utilize existing global DEM products of different resolutions to build data sources for large-scale pre-training data sets, randomly select some areas to build pre-training data sets, cut the data into raster images of uniform size, and build a total data scale In the pre-training data set of 900,000 to 1,000,000 images, a smaller proportion of the data is divided into the verification set, and the rest is used as the training set;

S2,模型设计:S2, model design:

构建自监督的DEM深度学习模型,设计编码器和解码器的结构,选用MAE模型的掩码结构以及基于ViT模型的基本架构,将对比不同ViT模型结构的性能,以及其他卷积神经网络模型的性能,通过多组对比实验,选定最佳模型,解决编码关键技术;Construct a self-supervised DEM deep learning model, design the structure of the encoder and decoder, select the mask structure of the MAE model and the basic architecture based on the ViT model, and compare the performance of different ViT model structures, as well as the performance of other convolutional neural network models. Performance, through multiple sets of comparative experiments, the best model is selected to solve key coding technologies;

改变编码器数据输入方式,采用同一区域多分辨率数据同步输入的方法,使得模型同步学习不同分辨率特征;由于同样图幅不同分辨率数据的像素不一致,改变MAE的像素位置编码方式,借鉴Scale-MAE的绝对距离编码方式,针对不同图幅之间地形的相关性,设计合适的位置编码方式,使得不同分辨率数据的位置信息保持一致,既要避免绝对位置编的信息泄露问题,又在一定程度上反映地形特征的周期性模式,并通过调整解码器结构,提高模型的对不同尺度数据的通用性;Change the encoder data input method and adopt the method of synchronous input of multi-resolution data in the same area, so that the model can learn the features of different resolutions synchronously; because the pixels of the same image at different resolutions are inconsistent, change the pixel position encoding method of MAE and learn from Scale -MAE's absolute distance encoding method, based on the correlation of terrain between different frames, designs an appropriate position encoding method to keep the position information of different resolution data consistent, which not only avoids the information leakage problem of absolute position encoding, but also It reflects the periodic patterns of terrain features to a certain extent, and improves the model’s versatility for data of different scales by adjusting the decoder structure;

S3,自监督学习策略:S3, self-supervised learning strategy:

完善自监督学习策略,探究不同超参数的设置,自监督学习采用图像掩码的方式,随机对DEM图幅进行一定比例的遮盖,将未被遮盖的部分作为预训练模型的输入,通过编码器和解码器后得到恢复的图像,与原始图像相比计算损失,对模型进行优化;尝试不同数据遮盖方式或者以随机生成的任意形状遮盖数据,尝试不同的遮盖比例,探索最佳比例;Improve the self-supervised learning strategy and explore the settings of different hyperparameters. Self-supervised learning uses image masking to randomly cover a certain proportion of the DEM image, and uses the uncovered part as the input of the pre-training model, through the encoder After decoding the recovered image, calculate the loss compared with the original image, and optimize the model; try different data covering methods or cover the data with randomly generated arbitrary shapes, try different covering ratios, and explore the best ratio;

S4,损失函数:S4, loss function:

设计合理的损失函数,在自监督学习过程中,最直接的指标是恢复的数值与真实数值之间的数值差异,引入地形因子控制模型的训练效果,并在损失函数中加入这些因子的损失值,使模型在优化时考虑地形因素;Design a reasonable loss function. In the self-supervised learning process, the most direct indicator is the numerical difference between the restored value and the real value. Introduce terrain factors to control the training effect of the model, and add the loss values of these factors to the loss function. , so that the model considers terrain factors when optimizing;

语义分析与知识图谱构建具体包括:Semantic analysis and knowledge graph construction specifically include:

S10,监督学习模型将地貌特征用向量表示,通过对向量的相似性计算,将特征相似且空间邻近的地块合并成地貌单元,一个地貌单元就是一个地貌类型实体;S10, the supervised learning model represents the landform features as vectors. By calculating the similarity of the vectors, plots with similar characteristics and spatial proximity are merged into landform units. A landform unit is a landform type entity;

S20,通过层次聚类,得到地貌类型的等级结构;S20, obtain the hierarchical structure of landform types through hierarchical clustering;

S30,通过自监督学习的注意力机制,得到每两个地块相互之间的注意力得分,构建注意力得分矩阵,计算地块之间的相互依赖程度,采用可视化分析,探索不同地貌实体之间的相互依赖关系,研究地貌类型分布空间模式,并构建地貌空间语法树;S30, through the attention mechanism of self-supervised learning, the attention scores between each two plots are obtained, an attention score matrix is constructed, the degree of interdependence between the plots is calculated, and visual analysis is used to explore the relationship between different landform entities. study the interdependence between landform types, study the spatial pattern of landform type distribution, and construct a landform space syntax tree;

S40,形成包含地貌类型等级结构、地貌实体语义表征和地貌类型空间关系的地貌知识图谱。S40: Form a geomorphic knowledge graph including the hierarchical structure of geomorphic types, semantic representation of geomorphic entities, and spatial relationships of geomorphic types.

以上仅是本发明的优选实施方式,只是用于帮助理解本申请的方法及其核心思想,本发明的保护范围并不仅局限于上述实施例,凡属于本发明思路下的技术方案均属于本发明的保护范围。应当指出,对于本技术领域的普通技术人员来说,在不脱离本发明原理前提下的若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。The above are only the preferred embodiments of the present invention, and are only used to help understand the method and its core idea of the present application. The protection scope of the present invention is not limited to the above-mentioned embodiments. All technical solutions that fall under the ideas of the present invention belong to the present invention. scope of protection. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications may be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

本发明从整体上解决了现有技术中地貌学领域构建知识图谱时,地貌分类体系多样,不同体系之间难以统一,依赖度高和自动化程度不高,且现有地貌分类体系多样,难以构建统一的知识本体等问题,通过适合DEM数据的自监督深度学习模型和训练策略,达到能够充分学习地貌语义和空间特征的目的。通过地貌特征向量表示的分析和计算,探究人工智能视角下的地貌分类体系,实现自下而上自动化构建计算机可理解、可计算的地貌知识图谱。The present invention comprehensively solves the problem that when building a knowledge map in the field of geomorphology in the prior art, the landform classification systems are diverse, it is difficult to unify different systems, the degree of dependence is high and the degree of automation is not high, and the existing landform classification systems are diverse and difficult to construct. Unified knowledge ontology and other issues, through self-supervised deep learning models and training strategies suitable for DEM data, can fully learn the semantics and spatial characteristics of landforms. Through the analysis and calculation of landform feature vector representation, the landform classification system from the perspective of artificial intelligence is explored, and a bottom-up automated construction of a computer-understandable and computable landform knowledge map is realized.

Claims (1)

1.一种基于自监督深度学习的地貌知识图谱构建方法,其特征在于,包括自监督预训练模型构建、自监督预训练模型的评估和语义分析与知识图谱构建;1. A method of constructing a geomorphological knowledge graph based on self-supervised deep learning, which is characterized by including the construction of a self-supervised pre-training model, the evaluation and semantic analysis of the self-supervised pre-training model, and the construction of a knowledge graph; 所述自监督预训练模型构建:完善自监督学习的策略,包括构建训练数据集、设计模型结构、探究学习策略和设计损失函数,并进行模型训练;所述自监督预训练模型的评估:将预训练模型应用到下游任务中,评估模型的学习性能和迁移性能,并发现问题反馈到预训练模型,调节模型参数;The construction of the self-supervised pre-training model: improving the self-supervised learning strategy, including constructing training data sets, designing model structures, exploring learning strategies and designing loss functions, and conducting model training; the evaluation of the self-supervised pre-training model: The pre-trained model is applied to downstream tasks, the learning performance and transfer performance of the model are evaluated, and problems found are fed back to the pre-trained model to adjust model parameters; 所述语义分析与知识图谱构建:对预训练得到的地貌向量表征进行语义分析,构建地貌知识图谱;The semantic analysis and knowledge map construction: perform semantic analysis on the landform vector representation obtained by pre-training, and construct a landform knowledge map; 所述自监督预训练模型构建具体包括:The construction of the self-supervised pre-training model specifically includes: S1,预训练数据集:S1, pre-training data set: 利用现有不同分辨率的全球DEM产品,构建大规模的预训练数据集的数据来源,随机选择部分区域构建预训练数据集,将数据切割为统一大小的栅格图幅,构建数据规模总量在900,000~1,000,000幅的预训练数据集,将较小比例的数据划分为验证集,其余作为训练集;Utilize existing global DEM products of different resolutions to build data sources for large-scale pre-training data sets, randomly select some areas to build pre-training data sets, cut the data into raster images of uniform size, and build a total data scale In the pre-training data set of 900,000 to 1,000,000 images, a smaller proportion of the data is divided into the verification set, and the rest is used as the training set; S2,模型设计:S2, model design: 构建自监督的DEM深度学习模型,设计编码器和解码器的结构,选用MAE模型的掩码结构以及基于ViT模型的基本架构,将对比不同ViT模型结构的性能,以及其他卷积神经网络模型的性能,通过多组对比实验,选定最佳模型,解决编码关键技术;Construct a self-supervised DEM deep learning model, design the structure of the encoder and decoder, select the mask structure of the MAE model and the basic architecture based on the ViT model, and compare the performance of different ViT model structures, as well as the performance of other convolutional neural network models. Performance, through multiple sets of comparative experiments, the best model is selected to solve key coding technologies; 改变编码器数据输入方式,采用同一区域多分辨率数据同步输入的方法,使得模型同步学习不同分辨率特征;由于同样图幅不同分辨率数据的像素不一致,改变MAE的像素位置编码方式,借鉴Scale-MAE的绝对距离编码方式,针对不同图幅之间地形的相关性,设计合适的位置编码方式,使得不同分辨率数据的位置信息保持一致,既要避免绝对位置编的信息泄露问题,又在一定程度上反映地形特征的周期性模式,并通过调整解码器结构,提高模型的对不同尺度数据的通用性;S3,自监督学习策略:Change the encoder data input method and adopt the method of synchronous input of multi-resolution data in the same area, so that the model can learn the features of different resolutions synchronously; because the pixels of the same image at different resolutions are inconsistent, change the pixel position encoding method of MAE and learn from Scale -MAE's absolute distance encoding method, based on the correlation of terrain between different frames, designs an appropriate position encoding method to keep the position information of different resolution data consistent, which not only avoids the information leakage problem of absolute position encoding, but also To a certain extent, it reflects the periodic patterns of terrain features, and by adjusting the decoder structure, it improves the model's versatility for data of different scales; S3, self-supervised learning strategy: 完善自监督学习策略,探究不同超参数的设置,自监督学习采用图像掩码的方式,随机对DEM图幅进行一定比例的遮盖,将未被遮盖的部分作为预训练模型的输入,通过编码器和解码器后得到恢复的图像,与原始图像相比计算损失,对模型进行优化;尝试不同数据遮盖方式或者以随机生成的任意形状遮盖数据,尝试不同的遮盖比例,探索最佳比例;S4,损失函数:Improve the self-supervised learning strategy and explore the settings of different hyperparameters. Self-supervised learning uses image masking to randomly cover a certain proportion of the DEM image, and uses the uncovered part as the input of the pre-training model, through the encoder After decoding the restored image, calculate the loss compared with the original image, and optimize the model; try different data covering methods or cover the data with randomly generated arbitrary shapes, try different covering ratios, and explore the best ratio; S4, Loss function: 设计合理的损失函数,在自监督学习过程中,最直接的指标是恢复的数值与真实数值之间的数值差异,引入地形因子控制模型的训练效果,并在损失函数中加入这些因子的损失值,使模型在优化时考虑地形因素;所述语义分析与知识图谱构建具体包括:Design a reasonable loss function. In the self-supervised learning process, the most direct indicator is the numerical difference between the restored value and the real value. Introduce terrain factors to control the training effect of the model, and add the loss values of these factors to the loss function. , so that the model considers terrain factors when optimizing; the semantic analysis and knowledge graph construction specifically include: S10,监督学习模型将地貌特征用向量表示,通过对向量的相似性计算,将特征相似且空间邻近的地块合并成地貌单元,一个地貌单元就是一个地貌类型实体;S10, the supervised learning model represents the landform features as vectors. By calculating the similarity of the vectors, plots with similar characteristics and spatial proximity are merged into landform units. A landform unit is a landform type entity; S20,通过层次聚类,得到地貌类型的等级结构;S20, obtain the hierarchical structure of landform types through hierarchical clustering; S30,通过自监督学习的注意力机制,得到每两个地块相互之间的注意力得分,构建注意力得分矩阵,计算地块之间的相互依赖程度,采用可视化分析,探索不同地貌实体之间的相互依赖关系,研究地貌类型分布空间模式,并构建地貌空间语法树;S30, through the attention mechanism of self-supervised learning, the attention scores between each two plots are obtained, an attention score matrix is constructed, the degree of interdependence between the plots is calculated, and visual analysis is used to explore the relationship between different landform entities. study the interdependence between landform types, study the spatial pattern of landform type distribution, and construct a landform space syntax tree; S40,形成包含地貌类型等级结构、地貌实体语义表征和地貌类型空间关系的地貌知识图谱。S40: Form a geomorphic knowledge graph including the hierarchical structure of geomorphic types, semantic representation of geomorphic entities, and spatial relationships of geomorphic types.
CN202310995603.9A 2023-08-09 2023-08-09 A method of constructing geomorphological knowledge graph based on self-supervised deep learning Active CN116992962B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310995603.9A CN116992962B (en) 2023-08-09 2023-08-09 A method of constructing geomorphological knowledge graph based on self-supervised deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310995603.9A CN116992962B (en) 2023-08-09 2023-08-09 A method of constructing geomorphological knowledge graph based on self-supervised deep learning

Publications (2)

Publication Number Publication Date
CN116992962A true CN116992962A (en) 2023-11-03
CN116992962B CN116992962B (en) 2024-02-06

Family

ID=88529937

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310995603.9A Active CN116992962B (en) 2023-08-09 2023-08-09 A method of constructing geomorphological knowledge graph based on self-supervised deep learning

Country Status (1)

Country Link
CN (1) CN116992962B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117574844A (en) * 2023-11-23 2024-02-20 华南理工大学 A self-supervised learning DTCO process parameter performance specification feedback method
CN117656082A (en) * 2024-01-29 2024-03-08 青岛创新奇智科技集团股份有限公司 Industrial robot control method and device based on multi-mode large model

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210192372A1 (en) * 2019-12-19 2021-06-24 Electronics And Telecommunications Research Institute Multi-layered knowledge base system and processing method thereof
CN113590799A (en) * 2021-08-16 2021-11-02 东南大学 Weak supervision knowledge graph question-answering method based on multi-view reasoning

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210192372A1 (en) * 2019-12-19 2021-06-24 Electronics And Telecommunications Research Institute Multi-layered knowledge base system and processing method thereof
CN113590799A (en) * 2021-08-16 2021-11-02 东南大学 Weak supervision knowledge graph question-answering method based on multi-view reasoning

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117574844A (en) * 2023-11-23 2024-02-20 华南理工大学 A self-supervised learning DTCO process parameter performance specification feedback method
CN117656082A (en) * 2024-01-29 2024-03-08 青岛创新奇智科技集团股份有限公司 Industrial robot control method and device based on multi-mode large model
CN117656082B (en) * 2024-01-29 2024-05-14 青岛创新奇智科技集团股份有限公司 Industrial robot control method and device based on multi-mode large model

Also Published As

Publication number Publication date
CN116992962B (en) 2024-02-06

Similar Documents

Publication Publication Date Title
Zhu et al. A global context-aware and batch-independent network for road extraction from VHR satellite imagery
CN116992962B (en) A method of constructing geomorphological knowledge graph based on self-supervised deep learning
Zhu et al. Adaptive deep sparse semantic modeling framework for high spatial resolution image scene classification
Tasnim et al. Automatic classification of textile visual pollutants using deep learning networks
Liu et al. Survey of road extraction methods in remote sensing images based on deep learning
Han Evaluation of English online teaching based on remote supervision algorithms and deep learning
Li et al. An aerial image segmentation approach based on enhanced multi-scale convolutional neural network
Zhang et al. A novel effective and efficient capsule network via bottleneck residual block and automated gradual pruning
Wang et al. Learning visual features from figure-ground maps for urban morphology discovery
Zhao et al. RFE-LinkNet: LinkNet with Receptive Field Enhancement for Road Extraction from High Spatial Resolution Imagery
Chen et al. Research on object detection algorithm based on multilayer information fusion
Cui et al. WetlandNet: Semantic segmentation for remote sensing images of coastal wetlands via improved UNet with deconvolution
INTHIYAZ et al. YOLO (YOU ONLY LOOK ONCE) Making Object detection work in Medical Imaging on Convolution detection System.
CN114549689A (en) River pattern recognition method and device based on graph convolution neural network
Wang et al. Self-attention deep saliency network for fabric defect detection
Jin et al. Semantic segmentation of remote sensing images based on dilated convolution and spatial-channel attention mechanism
CN111967516A (en) Pixel-by-pixel classification method, storage medium and classification equipment
Pourmohammadi et al. Predicting developed land expansion using deep convolutional neural networks
CN117635820A (en) A spatio-temporal reconstruction method for missing information in MODIS snow area products
Chen et al. Hierarchical Dynamic Graph Clustering Network
Gao et al. GeoAI Methodological Foundations: Deep Neural Networks and Knowledge Graphs
Ai Some thoughts on deep learning empowering cartography
Liu et al. A lightweight convolutional neural network based on dense connection for open-pit coal mine service identification using the edge-cloud architecture
Jeny et al. A model for identifying Historical Landmarks of Bangladesh from image content using a Depth-wise Convolutional Neural Network
Zhang Behavior recognition algorithm based on a dual-stream residual convolutional neural network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant