Urban rainstorm flood disaster chain affair map construction method and system

Abstract

The invention belongs to the technical field of knowledge graph construction, and discloses an urban rainstorm flood disaster chain affair graph construction method and system, and the method comprises the steps: firstly obtaining a research document, a first historical event and a secondary event, constructing a disaster chain directed network graph, and constructing an ontology model according to the disaster chain directed network graph; acquiring a second historical event and a secondary event, preprocessing, and inputting into the ontology model to obtain an event corpus; extracting event trigger words from a corpus to build a database by using a multi-modal dynamic fusion model MDF-Net; performing event extraction in a corpus according to the trigger word to obtain an event type and an argument; extracting a time sequence, a spatial relationship and a semantic relationship of a trigger word by using an improved ELCTRA-BiLSTM model; and finally, constructing a disaster chain affair map by taking the event type, the argument, the time sequence and the spatial relationship as nodes and taking the semantic relationship as an edge. According to the method, multi-source data and complex disaster information can be effectively integrated, and the integrity and accuracy of the urban rainstorm flood disaster chain affair map are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of knowledge graph construction, and specifically relates to a method and system for constructing a knowledge graph of urban rainstorm and flood disaster chain. Background Art

[0002] As an important branch of knowledge graph, the dynamic deduction and causal reasoning characteristics of the event graph provide a new technical path for disaster chain modeling. Among them, the rainstorm and flood disaster chain has typical spatiotemporal coupling characteristics.

[0003] The current research on disaster chain maps mainly adopts three types of technical routes: the first is disaster event association mining based on statistical learning, which uses association rule mining algorithms to extract high-frequency co-occurring disaster elements; the second is an event extraction model based on deep learning, which realizes disaster entity recognition through pre-training models such as BERT; the third is a disaster deduction method based on complex network theory, which constructs a topological network in which nodes represent disaster events and edges represent evolutionary relationships.

[0004] However, the existing methods for constructing urban rainstorm and flood disaster chain maps have many shortcomings. On the one hand, most methods fail to fully consider the spatiotemporal characteristics of urban rainstorm and flood disaster chains. In the actual process of disaster evolution, temporal and spatial factors play a key role in the development and propagation of disaster events, but the existing maps are difficult to accurately reflect these characteristics, resulting in the inability of the constructed maps to truly and comprehensively present the actual evolution process of the disaster chain. On the other hand, the existing map construction methods have obvious limitations in data processing, event extraction, and relationship identification. These methods pay more attention to the primary events of disasters, but pay insufficient attention to the secondary disaster events caused by the primary disaster events, resulting in a large amount of important disaster information being ignored. This leads to the inability to effectively integrate multi-source data and complex disaster information, which in turn affects the integrity and accuracy of the map, and it is difficult to meet the needs of actual disaster research and management. Therefore, there is an urgent need for a method for constructing an urban rainstorm and flood disaster chain map that can fully take into account the spatiotemporal characteristics and effectively integrate multi-source data. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method and system for constructing a map of urban rainstorm and flood disaster chain events, which can solve the problem that the existing methods for constructing urban rainstorm and flood disaster chain maps do not fully take into account the temporal and spatial characteristics and effectively integrate multi-source data.

[0006] In order to solve the above technical problems, this application is implemented as follows: In a first aspect, an embodiment of the present application provides a method for constructing a chain diagram of urban rainstorm and flood disasters, the method comprising: Obtain research literature and first historical events and their secondary events of rainstorm and flood disasters in the target city, and construct a directed network diagram of the disaster chain; According to the directed network diagram of the disaster chain, an ontology model of the rainstorm and flood disaster in the target city is constructed; The second historical event and its secondary events of the rainstorm and flood disaster in the target city are obtained for preprocessing, and the preprocessed second historical event and its secondary events are input into the ontology model to obtain an event corpus; Using a multimodal dynamic fusion model MDF-Net to extract event trigger words from the event corpus to construct an event trigger word library; According to the trigger words in the event trigger word library, event extraction is performed in the event corpus to obtain the event type and event argument corresponding to the trigger words; According to the trigger words in the event trigger vocabulary, performing relationship extraction in the event corpus to obtain semantic relationships, temporal relationships and spatial relationships related to the trigger words, wherein the temporal relationships and the spatial relationships are obtained by an improved ELECTRA-BiLSTM model, and the improved ELECTRA-BiLSTM model includes an ELECTRA model, a hole convolution layer, a gating mechanism layer, a BiLSTM model and a multi-head attention mechanism layer; A disaster chain event graph of rainstorm and flood disasters in the target city is constructed by taking the event type, the event argument, the temporal relationship and the spatial relationship as event nodes and taking the semantic relationship as the edge of the event.

[0007] As an optional implementation manner of the first aspect of the present application, the steps of obtaining research literature and a first historical event and its secondary events on rainstorm and flood disasters in a target city, and constructing a directed network diagram of a disaster chain include: obtaining research literature on rainstorm and flood disasters in the target city, and organizing the research literature into a research review using a literature research method; obtaining the first historical event and its secondary events on rainstorm and flood disasters in the target city, and organizing the first historical event and its secondary events into case events using a case analysis method; constructing a disaster chain event set based on the research review and the case events; and drawing a directed network diagram of a disaster chain corresponding to the rainstorm and flood disasters in the target city based on the disaster chain event set.

[0008] As an optional implementation of the first aspect of the present application, the step of extracting event trigger words from the event corpus using the multimodal dynamic fusion model MDF-Net includes: performing multi-granular annotation on the unstructured text of the event corpus, adopting the BIOES annotation system and combining the disaster field ontology knowledge, generating fine-grained annotation data through entity boundary enhancement and semantic role annotation; performing spatiotemporal alignment of the text data of the event corpus with the real-time meteorological data, geographic information system layer and social media public opinion data of the target city to generate text alignment data; using the cross-modal attention mechanism of the multimodal dynamic fusion model MDF-Net to extract the association weights of the text keywords and spatiotemporal features of the fine-grained annotation data and the text alignment data, and generating a unified multimodal embedding representation; inputting the multimodal embedding representation into the Transformer-GAT-CRF hybrid network model, and the Transformer-GA The pre-training layer of the T-CRF hybrid network model adopts the ELECTRA model enhanced in the disaster field, and generates context-aware word vectors through masked language modeling and causal prediction tasks; the graph attention layer GAT of the Transformer-GAT-CRF hybrid network model embeds the disaster ontology knowledge graph to capture the topological dependencies between event trigger words, and allocates the weights of events, locations, and time nodes through multi-head attention; the temporal-spatial bidirectional gating layer of the Transformer-GAT-CRF hybrid network model combines BiLSTM and dilated temporal convolution DTCN to model the temporal evolution and spatial diffusion characteristics of events respectively; the contrastive learning module of the Transformer-GAT-CRF hybrid network model optimizes the discrimination of trigger word representation by constructing positive and negative sample pairs; the CRF decoder of the Transformer-GAT-CRF hybrid network model outputs event trigger words.

[0009] As an optional implementation manner of the first aspect of the present application, according to the trigger words in the event trigger lexicon, event extraction is performed in the event corpus to obtain the event type and event argument corresponding to the trigger words, the steps comprising: converting the trigger words in the event trigger lexicon into trigger word feature vectors, clustering the trigger word feature vectors to obtain preliminary event types, and aligning the preliminary event types to obtain final event types; converting argument words in the event trigger lexicon into argument word feature vectors, clustering the argument word feature vectors to obtain preliminary event arguments, and aligning the preliminary event arguments to obtain final event arguments.

[0010] As an optional implementation manner of the first aspect of the present application, the step of aligning the preliminary event types to obtain the final event types includes: calculating a first cosine similarity between any two event types, setting a first threshold, and determining whether the first cosine similarity is greater than or equal to the first threshold; if so, the two event types are regarded as the same event type; the step of aligning the preliminary event arguments to obtain the final event arguments includes: calculating a second cosine similarity between any two event arguments, setting a second threshold, and determining whether the second cosine similarity is greater than or equal to the second threshold; if so, the two event arguments are regarded as the same event argument.

[0011] As an optional implementation of the first aspect of the present application, according to the trigger words in the event trigger vocabulary, relationship extraction is performed in the event corpus, and the step of obtaining semantic relationships related to the trigger words includes: selecting text fragments of multiple trigger words in the event trigger vocabulary to form candidate event pairs; after word segmentation and part-of-speech tagging of the candidate event pairs, constructing a dependency syntax tree to analyze the preliminary semantic relationships between words; based on the preliminary semantic relationships, establishing a mapping rule library from specific to abstract events; performing logical deduction and verification on the mapping rule library to obtain a dependency pattern rule library; and adjusting the trigger word weights in the dependency pattern rule library for optimization to obtain extraction results containing semantic relationships.

[0012] As an optional implementation of the first aspect of the present application, the process of obtaining the temporal relationship and the spatial relationship by the improved ELECTRA-BiLSTM model includes: selecting text fragments of multiple trigger words in the event trigger vocabulary, inputting the pre-trained text encoder ELECTRA model for pre-training, and obtaining the corresponding text word vector sequence; inputting the text word vector sequence into the void convolution layer to extract the local-global features of the text; inputting the local-global features into the BiLSTM model to capture the context dependency; inputting the context dependency into the multi-head attention mechanism layer, and calculating the first attention of the temporal task and the second attention of the spatial task respectively; and obtaining the classification prediction results of the temporal relationship and the spatial relationship according to the first attention and the second attention respectively.

[0013] In a second aspect, the embodiment of the present application provides a system for constructing a chain diagram of urban rainstorm and flood disasters, the system comprising: The data acquisition module is used to obtain research literature and the first historical events and their secondary events of rainstorm and flood disasters in the target city, and to construct a directed network diagram of the disaster chain; An ontology modeling module, used to construct an ontology model of the rainstorm and flood disaster in the target city according to the directed network diagram of the disaster chain; A corpus generation module is used to obtain the second historical event and its secondary events of the rainstorm and flood disaster in the target city for preprocessing, and input the preprocessed second historical event and its secondary events into the ontology model to obtain an event corpus; A trigger word extraction module, used for extracting event trigger words from the event corpus using a multimodal dynamic fusion model MDF-Net to construct an event trigger word library; An event extraction module, used to extract events from the event corpus according to the trigger words in the event trigger word library, and obtain event types and event arguments corresponding to the trigger words; A relationship extraction module, used for performing relationship extraction in the event corpus according to the trigger words in the event trigger vocabulary, and obtaining semantic relations, temporal relations and spatial relations related to the trigger words, wherein the temporal relations and the spatial relations are obtained by an improved ELECTRA-BiLSTM model, and the improved ELECTRA-BiLSTM model includes an ELECTRA model, a hole convolution layer, a gating mechanism layer, a BiLSTM model and a multi-head attention mechanism layer; The graph construction module is used to construct a disaster chain event graph of the rainstorm and flood disaster in the target city with the event type, the event argument, the temporal relationship and the spatial relationship as event nodes and the semantic relationship as the edge of the event.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] Compared with the prior art, this application has the following beneficial effects: First, we obtain research literature, first historical events, and secondary events to construct a directed network diagram of the disaster chain, which can sort out the relationship between disasters and their secondary events from a macro perspective and provide a framework for subsequent modeling. Then, we construct an ontology model based on the directed network diagram to formally describe disaster-related concepts, attributes, and relationships, unify the semantic framework, and facilitate the processing of multi-source data. After obtaining the second historical event preprocessing, we input it into the ontology model to obtain the event corpus, remove noise and improve data quality, and provide high-quality data for subsequent extraction. The multimodal dynamic fusion model MDF-Net is used to extract event trigger words from the corpus to build a vocabulary, and accurately locate event clues based on the advantages of the model. Event extraction is performed based on the trigger words to obtain event types and arguments, clarify the specific content and elements of the event, and provide detailed event information for the map. The improved ELECTRA-BiLSTM model is used to extract the semantics, temporal and spatial relationships of trigger words, and a variety of neural network layers are integrated to comprehensively mine event associations. Finally, a disaster chain graph is constructed with event types, arguments, and spatiotemporal relationships as nodes and semantic relationships as edges to comprehensively and accurately describe the complex relationship between disasters and their secondary events, fully taking into account spatiotemporal characteristics and integrating multi-source data. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for constructing a chain diagram of urban rainstorm and flood disasters provided by the first embodiment of the present application; Figure 2 It is a structural schematic diagram of a system for constructing a chain event graph of urban rainstorm and flood disasters provided in the second embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0020] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0021] Example 1 See also Figure 1 , which is a flow chart of a method for constructing a chain event graph of urban rainstorm and flood disasters proposed in the first embodiment of the present application. The proposed method includes S01 to S07.

[0022] Step S01: Obtain research literature and the first historical event and its secondary events of rainstorm and flood disasters in the target city, and construct a directed network diagram of the disaster chain.

[0023] In some embodiments, research literature on rainstorm and flood disasters in the target city is obtained, and the research literature is organized into a research review using a literature research method; the first historical event and its secondary events of the rainstorm and flood disasters in the target city are obtained, and the first historical event and its secondary events are organized into case events using a case analysis method; a disaster chain event set is constructed based on the research review and the case events; and a disaster chain directed network diagram corresponding to the rainstorm and flood disasters in the target city is drawn based on the disaster chain event set.

[0024] Specifically, first, research literature collection and review: collect research literature on disaster and disaster chain theory, urban rainstorm and flood disaster formation mechanism, disaster risk assessment, disaster risk analysis, and natural disaster emergency management plan. Use literature research method to sort out these documents and form a review of urban rainstorm and flood disaster chain research. At the same time, list the relevant norms and laws and regulations on urban flood disasters.

[0025] Furthermore, case data collection and analysis: collect case data of rainstorm and flood disaster chain in target cities. The selected cases should be representative, typical and relevant, and the data should be authentic, reliable, detailed and sufficient. Use case analysis method to sort out the first historical events and secondary events of rainstorm and flood disasters in target cities, analyze the evolution process of disasters in detail, and organize them into case events.

[0026] Furthermore, a disaster chain event set is constructed: the disaster events that occurred are listed by combining the research review formed by literature research and the case events obtained by case analysis. According to the principle of comprehensive and concise summary of disaster events, the final disaster chain disaster event set is constructed.

[0027] Furthermore, draw a directed network diagram of the disaster chain: based on the constructed disaster chain event set, draw a directed network diagram of the disaster chain corresponding to the rainstorm and flood disasters in the target city to provide a reference for the subsequent construction of the disaster chain event map.

[0028] In this step, by obtaining research literature and historical events and their secondary events, data from different sources and types are integrated. This integration makes the originally multi-dispersed data form an organic whole, providing a comprehensive and systematic data basis for subsequent analysis. In addition, this basic data is applicable to the target city of the study and has a certain regionality, making the research data more accurate. The directed network diagram of the disaster chain can reflect the dynamic relationship between disaster events. Heavy rain and flood disasters do not occur in isolation, but will trigger a series of secondary events over time. By constructing a directed network diagram, the development process from primary disasters to secondary disasters is recorded, reflecting the dynamic changes of the data. This helps researchers understand the evolution of disasters and predict possible disaster events and their development trends in the future.

[0029] Step S02: construct an ontology model of rainstorm and flood disasters in the target city according to the directed network diagram of the disaster chain.

[0030] Specifically, on the basis of step S01, the hierarchical relationship of the urban rainstorm and flood disaster chain is further clarified, covering the relevant concepts of the urban rainstorm and flood disaster chain, the attributes of disaster events and the relationship between disaster events. Among them, the relevant concepts include the concepts related to disaster-causing events, disaster-bearing events and disaster relief events. The attributes of disaster events include the time, location, participants and objects of the disaster event. The relationship between disaster events mainly includes the semantic relationship, temporal relationship and spatial relationship between disaster events.

[0031] Furthermore, according to the theory of disaster science, based on the description of the disaster chain ,in It is a chain of urban rainstorm and flood disasters. For disaster-prone environment, As a disaster factor, For the disaster-bearing body, the knowledge domain boundary of the urban rainstorm and flood disaster chain is determined, the model layer of the urban rainstorm and flood disaster chain is formed, and a unified description of the urban flood disaster chain is achieved.

[0032] Furthermore, the ontology modeling software Protégé is used to construct an ontology model of the urban rainstorm and flood disaster chain in a semi-automatic way.

[0033] In this step, the ontology modeling software Protégé is used to construct an ontology model of the urban rainstorm and flood disaster chain. This model not only clearly defines the relevant concepts and attributes in the disaster chain, such as disaster-causing events, disaster-bearing events, and disaster relief events, but also includes the attributes of the disaster event, such as time, location, participants, and objects. In addition, it also clarifies the semantic, temporal, and spatial relationships between disaster events, provides a clear definition of the knowledge domain boundary of the disaster chain, and forms a model layer that uniformly describes the urban flood disaster chain, thus providing an application basis for disaster management and research.

[0034] Step S03: obtaining the second historical event and its secondary events of the rainstorm and flood disaster in the target city for preprocessing, and inputting the preprocessed second historical event and its secondary events into the ontology model to obtain an event corpus.

[0035] Specifically, in the data acquisition stage, illustratively, a collection program is written in a programming language to collect news reports on urban rainstorm and flood disaster events and their secondary events from the websites of emergency management departments and large news media websites.

[0036] In the data preprocessing stage, data cleaning and word segmentation and tagging are included. For example, the collected data is preprocessed for redundant values ​​and missing values ​​by using regular expressions and manual review. The collected content is segmented, POS tagged, and syntactically analyzed using the Chinese word segmentation library, stop words and irrelevant characters are deleted, and regular expressions are used to filter news reports and delete irrelevant content.

[0037] In this step, we wrote a collection program to obtain the second historical events and secondary events of rainstorm and flood disasters in the target city from the emergency management department and large news media websites, and preprocessed the collected data, including data cleaning, word segmentation and annotation, and syntactic analysis, effectively removing redundant values ​​and irrelevant content, ensuring the accuracy and consistency of the data. Finally, the preprocessed event data was input into the ontology model to build a high-quality event corpus, providing a reliable data foundation for subsequent analysis and research.

[0038] Step S04: extracting event trigger words from the event corpus using the multimodal dynamic fusion model MDF-Net to construct an event trigger word library.

[0039] In some implementations, the unstructured text of the event corpus is annotated at multiple granularities, and the BIOES annotation system is used in combination with ontology knowledge in the disaster field to generate fine-grained annotation data through entity boundary enhancement and semantic role annotation; The text data of the event corpus is spatiotemporally aligned with the real-time meteorological data, geographic information system layers, and social media public opinion data of the target city to generate text alignment data; The cross-modal attention mechanism of the multimodal dynamic fusion model MDF-Net is used to extract the association weights of text keywords and spatiotemporal features of fine-grained annotation data and text alignment data, and generate a unified multimodal embedding representation; The multimodal embedding representation is input into the Transformer-GAT-CRF hybrid network model. The pre-training layer of the Transformer-GAT-CRF hybrid network model adopts the ELECTRA model enhanced in the disaster field, and generates context-aware word vectors through masked language modeling and causal prediction tasks; the graph attention layer GAT of the Transformer-GAT-CRF hybrid network model embeds the disaster ontology knowledge graph to capture the topological dependencies between event trigger words, and assigns weights to events, locations, and time nodes through multi-head attention; the temporal-spatial bidirectional gating layer of the Transformer-GAT-CRF hybrid network model combines BiLSTM and dilated temporal convolution DTCN to model the temporal evolution and spatial diffusion characteristics of events respectively; the contrastive learning module of the Transformer-GAT-CRF hybrid network model optimizes the discrimination of trigger word representation by constructing positive and negative sample pairs; the CRF decoder of the Transformer-GAT-CRF hybrid network model outputs event trigger words.

[0040] In this step, firstly, through the integration of multimodal data, this step breaks through the limitation of a single modality. The model can integrate text data, real-time meteorological data of the target city, geographic information system (GIS) layers, and social media public opinion data to generate a unified multimodal embedding representation. This integration of multimodal data enables the model to capture multiple features and contextual information of events more comprehensively. Secondly, the model fully considers the spatiotemporal characteristics of events. Through spatiotemporal alignment, the model can capture the spatiotemporal associations between text data and real-time meteorological, GIS layers, and social media public opinion data, and generate text alignment data. This helps the model better understand the spatiotemporal evolution and diffusion patterns of events. Furthermore, the application of the Transformer-GAT-CRF hybrid network model further improves the accuracy of event trigger word extraction. The model combines pre-training, graph attention mechanism, temporal-spatial bidirectional gating layer, contrastive learning module, and CRF decoder to more effectively capture the topological dependencies between event trigger words and model the temporal evolution and spatial diffusion characteristics of events. In addition, the pre-training layer of the model uses the ELECTRA model enhanced in the disaster field, and generates context-aware word vectors through masked language modeling and causal prediction tasks to further improve the semantic understanding ability of the model. Finally, the implementation of this step can build a more accurate event trigger vocabulary. Through the joint action of multimodal dynamic fusion and Transformer-GAT-CRF hybrid network model, event trigger words can be extracted more accurately.

[0041] Step S05: extracting events from the event corpus according to the trigger words in the event trigger word library, and obtaining the event type and event argument corresponding to the trigger words.

[0042] In some embodiments, trigger words in an event trigger vocabulary are converted into trigger word feature vectors, the trigger word feature vectors are clustered to obtain preliminary event types, and the preliminary event types are aligned to obtain final event types; argument words in an event trigger vocabulary are converted into argument word feature vectors, the event argument feature vectors are clustered to obtain preliminary event arguments, and the preliminary event arguments are aligned to obtain final event arguments.

[0043] Among them, the step of aligning preliminary event types to obtain final event types includes: calculating the first cosine similarity between any two event types, setting a first threshold, judging whether the first cosine similarity is greater than or equal to the first threshold, and if so, the two event types are regarded as the same event type; the step of aligning preliminary event arguments to obtain final event arguments includes: calculating the second cosine similarity between any two event arguments, setting a second threshold, judging whether the second cosine similarity is greater than or equal to the second threshold, and if so, the two event arguments are regarded as the same event argument.

[0044] Specifically, first, trigger word clustering and preliminary event type determination: the trigger words in the event trigger word library are converted into trigger word feature vectors, and these feature vectors are input into the clustering algorithm (such as the DBSCAN algorithm) for clustering analysis. After clustering, a group of clusters will be obtained, each cluster represents a class of similar trigger words, and noise points that do not meet the cluster conditions are excluded. The clustering results are visualized using scatter plots, and the clustering quality is evaluated using evaluation indicators such as the silhouette coefficient. It is continuously iterated and adjusted to obtain the optimal trigger word cluster, and the trigger words in the same cluster are classified as the same preliminary event type.

[0045] At the same time, argument word clustering and preliminary event argument determination: the argument words in the event trigger vocabulary are converted into argument word feature vectors, and these feature vectors are input into the clustering algorithm (such as DBSCAN algorithm) for clustering. After clustering, a group of clusters are obtained, each cluster represents the event argument of a certain type of disaster event, and noise points are also excluded. The clustering results are visualized and the quality is evaluated. After iterative adjustment, the optimal event argument cluster is obtained, and the event arguments of the same cluster are classified as the same preliminary event argument to determine the role of the event argument.

[0046] Furthermore, the preliminary event types are aligned to obtain the final event type: the first cosine similarity between any two preliminary event types is calculated, and a first threshold is set. It is determined whether the first cosine similarity is greater than or equal to the first threshold, and if so, the two event types are regarded as the same event type, thereby obtaining the final event type.

[0047] At the same time, the preliminary event arguments are aligned to obtain the final event arguments: the second cosine similarity between any two preliminary event arguments is calculated, and the second threshold is set. It is determined whether the second cosine similarity is greater than or equal to the second threshold. If the condition is met, it is considered that the two event arguments have a high similarity, and they are regarded as the same or similar event arguments, so that the event arguments are aligned to obtain the final event argument.

[0048] Furthermore, disaster event alignment and event node acquisition: Based on the determined event type, the core trigger word of each event is determined as the event identifier, and the standard structure of the event tuple is defined. The event type is combined with the standardized event argument to form an event tuple set, and the similarity of the two event tuple sets is calculated to find events with similar argument combinations, and similar structural patterns or logical associations are found between different event types to achieve disaster event alignment. Finally, the obtained disaster event tuple is embedded as a vector as a whole, and clustering is performed again using a clustering algorithm. After visualization, quality assessment and iterative adjustment, the optimal event cluster is obtained, and then the nodes of the disaster event can be obtained.

[0049] In this step, the unstructured event corpus is converted into standardized event types and arguments through trigger word and argument feature vectorization, clustering algorithm (such as DBSCAN) and cosine similarity alignment, eliminating semantic redundancy and achieving accurate classification of event elements; at the same time, through the structured expression of event tuples and secondary clustering, the semantic alignment and logical association of disaster event nodes are established, providing highly consistent and parsable disaster event structured data support for disaster chain evolution reasoning, knowledge graph construction and emergency decision-making.

[0050] Step S06: According to the trigger words in the event trigger vocabulary, relationship extraction is performed in the event corpus to obtain semantic relationships, temporal relationships and spatial relationships related to the trigger words, wherein the temporal relationships and spatial relationships are obtained by the improved ELECTRA-BiLSTM model, and the improved ELECTRA-BiLSTM model includes the ELECTRA model, the void convolution layer, the gating mechanism layer, the BiLSTM model and the multi-head attention mechanism layer.

[0051] In some embodiments, the process of acquiring semantic relationships related to trigger words includes: selecting text fragments of multiple trigger words in an event trigger word library to form candidate event pairs; after word segmentation and part-of-speech tagging of the candidate event pairs, constructing a dependency syntax tree to analyze the preliminary semantic relationships between words; based on the preliminary semantic relationships, establishing a mapping rule library from specific to abstract events; performing logical deduction and verification on the mapping rule library to obtain a dependency pattern rule library; and adjusting the trigger word weights in the dependency pattern rule library for optimization to obtain extraction results containing semantic relationships.

[0052] Specifically, firstly, based on the event trigger vocabulary and the event types it identifies, the urban rainstorm and flood disaster chain event text corpus is scanned to identify and extract text fragments containing more than two trigger words, and these text fragments containing multiple trigger words are constituted into candidate event pairs.

[0053] Further, the preliminary semantic relationship is analyzed: the common associations between disaster events are identified and defined, such as causality, sequence, concurrency, condition, and hyponymy. The candidate event pairs are segmented into words or vocabulary units, and each word is assigned a part-of-speech tag (such as noun, verb, adjective, etc.). Then it is input into the dependency syntactic analysis to determine the dependency relationship between words or vocabulary, and a dependency syntactic tree is constructed based on this. The candidate event pairs are matched, and the specific association relationship between the event relationship and the candidate events is determined and marked, so as to analyze the preliminary semantic relationship between words.

[0054] Furthermore, a mapping rule base is established: a set of abstract events that can summarize the common characteristics of specific urban rainstorm and flood disaster events is defined, and based on the characteristics and attributes of disaster events, a mapping rule base from specific disaster events to abstract disaster events is constructed to map the identified specific disaster events to abstract disaster events.

[0055] Furthermore, the dependency pattern rule base is derived and verified: based on the relationship between the determined specific disaster events, the generalization method is used to infer the possible relationship between abstract events, and then the logical relationship between abstract disaster events is determined by logical reasoning. The accuracy and rationality of the determined logical relationship are verified through expert verification or analogy with historical disaster events, thus obtaining the dependency pattern rule base.

[0056] Furthermore, the extraction results are optimized: in the dependency pattern rule base, an iterative method is used to continuously update and improve the event relationship extraction results by adjusting the trigger word weights, and finally an extraction result containing semantic relationships is obtained.

[0057] In some embodiments, the temporal and spatial relationships related to trigger words are obtained by an improved ELECTRA-BiLSTM model, and the process includes: selecting text fragments of multiple trigger words in the event trigger vocabulary, inputting the pre-trained text encoder ELECTRA model for pre-training, and obtaining corresponding text word vector sequences; inputting the text word vector sequence into the void convolution layer to extract the local-global features of the text; inputting the local-global features into the BiLSTM model to capture the context dependencies; inputting the context dependencies into the multi-head attention mechanism layer to calculate the first attention of the temporal task and the second attention of the spatial task respectively; inputting the first attention and the second attention into the classifier to obtain the classification prediction results of the temporal relationship and the spatial relationship respectively.

[0058] The process of extracting spatial relationships is similar to that of extracting temporal relationships. First, obtain a text word vector sequence: select multiple trigger word text fragments in the event trigger vocabulary, use them as input data, and input them into the pre-trained text encoder ELECTRA model for pre-training to obtain the corresponding text word vector sequence.

[0059] Furthermore, extract local-global features: input the obtained text word vector sequence into the dilated convolutional layer (such as the dilated convolutional neural network, DGCNN). In this process, it is necessary to determine the number of convolutional layers, the size of the convolution kernel, the dilation rate and other parameters, and calculate the dilated convolution formula to expand the receptive field of the convolution kernel. Apply the activation function after the convolution layer to introduce nonlinearity, introduce the gated mechanism Gated Recurrent Unit (GRU) to control the information flow, add residual connections to solve the gradient vanishing problem in the deep network, and finally extract the local-global features of the text.

[0060] Furthermore, context dependencies are captured: the extracted local-global features are input into the BiLSTM model to capture context dependencies and obtain context semantic features.

[0061] Furthermore, attention is calculated: the context dependency is input into the multi-head attention mechanism layer, and the first attention of the temporal task and the second attention of the spatial task are calculated respectively. Specifically, the output features of the BiLSTM layer are linearly transformed to obtain the query matrix, key matrix and value matrix, the query matrix is ​​divided into several heads, the attention weights are calculated, and then the value matrix is ​​weighted summed using the attention weights, and the outputs of each head are merged and linearly transformed to obtain the output of the multi-head attention.

[0062] Finally, the first attention and the second attention are input into the classifier respectively, converted into scores for each category through a linear layer, and then the probability of each category is calculated. The cross entropy loss function is used to calculate the difference between the predicted probability distribution and the true label, and finally the classification prediction results of temporal relationship and spatial relationship are obtained respectively.

[0063] In this step, in terms of semantic relationship acquisition, we start with constructing candidate event pairs, determine preliminary semantic relationships through word segmentation, part-of-speech tagging, and dependency syntactic analysis, then establish a mapping rule base, obtain a dependency pattern rule base through logical deduction and verification, and finally optimize the weights to obtain extraction results containing semantic relationships, thus achieving accurate mining of the semantic relationship of trigger words. For temporal and spatial relationships, we use the improved ELECTRA-BiLSTM model, starting from pre-training to obtain text word vector sequences, extract local-global features through the dilated convolution layer, capture contextual dependencies through the BiLSTM model, and calculate attention through the multi-head attention mechanism layer. Finally, the classification prediction results are obtained by the classifier, which provides strong support for a comprehensive understanding of the complex relationships between events in the urban rainstorm and flood disaster chain, and helps to analyze and respond to disasters more deeply.

[0064] Step S07: Using event types, event arguments, temporal relationships and spatial relationships as event nodes, and semantic relationships as event edges, a disaster chain event graph of rainstorm and flood disasters in the target city is constructed.

[0065] For example, the graph database Neo4j can be used for storage to obtain a disaster chain event map of rainstorm and flood disasters in the target city.

[0066] Example 2 See also Figure 2 , which is a schematic diagram of the structure of a system for constructing a chain of urban rainstorm and flood disasters according to a second embodiment of the present application, and which includes: The data acquisition module 100 is used to acquire research documents and primary historical events and secondary events of rainstorm and flood disasters in the target city, and construct a directed network diagram of the disaster chain; An ontology modeling module 200 is used to construct an ontology model of the rainstorm and flood disaster in the target city according to the disaster chain directed network diagram; The corpus generation module 300 is used to obtain the second historical event and its secondary events of the rainstorm and flood disaster in the target city for preprocessing, and input the preprocessed second historical event and its secondary events into the ontology model to obtain an event corpus; A trigger word extraction module 400 is used to extract event trigger words from the event corpus using a multimodal dynamic fusion model MDF-Net to construct an event trigger word library; An event extraction module 500 is used to extract events from the event corpus according to the trigger words in the event trigger word library, and obtain event types and event arguments corresponding to the trigger words; A relation extraction module 600 is used to extract relations in the event corpus according to the trigger words in the event trigger lexicon, and obtain semantic relations, temporal relations and spatial relations related to the trigger words, wherein the temporal relations and the spatial relations are obtained by an improved ELECTRA-BiLSTM model, and the improved ELECTRA-BiLSTM model includes an ELECTRA model, a hole convolution layer, a gating mechanism layer, a BiLSTM model and a multi-head attention mechanism layer; The graph construction module 700 is used to construct a disaster chain event graph of the rainstorm and flood disaster in the target city with the event type, the event argument, the temporal relationship and the spatial relationship as event nodes and the semantic relationship as the edge of the event.

[0067] A system for constructing a chain of urban rainstorm and flood disasters in an embodiment of the present application may be a device, or a component, integrated circuit, or chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a server, a network attached storage (NAS), a personal computer (PC), etc., which is not specifically limited in the embodiment of the present application.

[0068] In the embodiment of the present application, a system for constructing a chain of urban rainstorm and flood disasters can be a device with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0069] The system for constructing a chain diagram of urban rainstorm and flood disasters provided in the embodiment of the present application can achieve Figure 1 In the method embodiment, the various processes of implementing a method for constructing a chain event graph of urban rainstorm and flood disasters are not described here to avoid repetition.

[0070] Optionally, an embodiment of the present application also provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, each process of the above-mentioned embodiment of a method for constructing a chain cause graph of urban rainstorm and flood disasters is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0071] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned embodiment of a method for constructing a chain of urban rainstorm and flood disasters cause map is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0072] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0073] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0075] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for constructing a chain diagram of urban rainstorm and flood disasters, characterized in that: The method comprises: Obtain research literature and first historical events and their secondary events of rainstorm and flood disasters in the target city, and construct a directed network diagram of the disaster chain; According to the directed network diagram of the disaster chain, an ontology model of the rainstorm and flood disaster in the target city is constructed; The second historical event and its secondary events of the rainstorm and flood disaster in the target city are obtained for preprocessing, and the preprocessed second historical event and its secondary events are input into the ontology model to obtain an event corpus; Using a multimodal dynamic fusion model MDF-Net to extract event trigger words from the event corpus to construct an event trigger word library; According to the trigger words in the event trigger word library, event extraction is performed in the event corpus to obtain the event type and event argument corresponding to the trigger words; According to the trigger words in the event trigger vocabulary, performing relationship extraction in the event corpus to obtain semantic relationships, temporal relationships and spatial relationships related to the trigger words, wherein the temporal relationships and the spatial relationships are obtained by an improved ELECTRA-BiLSTM model, and the improved ELECTRA-BiLSTM model includes an ELECTRA model, a hole convolution layer, a gating mechanism layer, a BiLSTM model and a multi-head attention mechanism layer; A disaster chain event graph of rainstorm and flood disasters in the target city is constructed by taking the event type, the event argument, the temporal relationship and the spatial relationship as event nodes and taking the semantic relationship as the edge of the event.

2. The method for constructing a chain diagram of urban rainstorm and flood disasters according to claim 1 is characterized in that: The steps of obtaining the research literature and the first historical events and their secondary events of rainstorm and flood disasters in the target city and constructing the directed network diagram of the disaster chain include: Obtain research literature on rainstorm and flood disasters in the target city, and organize the research literature into a research review using literature research methods; Obtaining the first historical event and its secondary events of the rainstorm and flood disaster in the target city, and organizing the first historical event and its secondary events into case events by using a case analysis method; Construct a disaster chain event set based on the research review and the case events; A disaster chain directed network diagram corresponding to the rainstorm and flood disaster in the target city is drawn according to the disaster chain event set.

3. The method for constructing a chain diagram of urban rainstorm and flood disasters according to claim 1, characterized in that: The steps of extracting event trigger words from the event corpus using the multimodal dynamic fusion model MDF-Net include: Perform multi-granular annotation on the unstructured text of the event corpus, adopt the BIOES annotation system and combine it with the disaster domain ontology knowledge, and generate fine-grained annotation data through entity boundary enhancement and semantic role annotation; Performing spatiotemporal alignment of the text data of the event corpus with the real-time meteorological data, geographic information system layers, and social media public opinion data of the target city to generate text alignment data; The cross-modal attention mechanism of the multimodal dynamic fusion model MDF-Net is used to extract the association weights of the text keywords and spatiotemporal features of the fine-grained annotation data and the text alignment data, and generate a unified multimodal embedding representation; The multimodal embedding representation is input into the Transformer-GAT-CRF hybrid network model. The pre-training layer of the Transformer-GAT-CRF hybrid network model adopts the ELECTRA model enhanced in the disaster field, and generates context-aware word vectors through masked language modeling and causal prediction tasks; the graph attention layer GAT of the Transformer-GAT-CRF hybrid network model embeds the disaster ontology knowledge graph to capture the topological dependencies between event trigger words, and allocates the weights of events, locations, and time nodes through multi-head attention; the temporal-spatial bidirectional gating layer of the Transformer-GAT-CRF hybrid network model combines BiLSTM and dilated temporal convolution DTCN to model the temporal evolution and spatial diffusion characteristics of events respectively; the contrastive learning module of the Transformer-GAT-CRF hybrid network model optimizes the discrimination of trigger word representation by constructing positive and negative sample pairs; the CRF decoder of the Transformer-GAT-CRF hybrid network model outputs event trigger words.

4. The method for constructing a chain diagram of urban rainstorm and flood disasters according to claim 1, characterized in that: The step of extracting events from the event corpus according to the trigger words in the event trigger word library to obtain the event type and event argument corresponding to the trigger words comprises: Converting trigger words in the event trigger word library into trigger word feature vectors, clustering the trigger word feature vectors to obtain preliminary event types, and aligning the preliminary event types to obtain final event types; The argument words in the event triggering vocabulary are converted into argument word feature vectors, the argument word feature vectors are clustered to obtain preliminary event arguments, and the preliminary event arguments are aligned to obtain final event arguments.

5. The method for constructing a chain diagram of urban rainstorm and flood disasters according to claim 4 is characterized in that: The steps of aligning the preliminary event types to obtain the final event types include: Calculate the first cosine similarity between any two event types, set a first threshold, and determine whether the first cosine similarity is greater than or equal to the first threshold. If so, the two event types are considered to be the same event type. The step of aligning the preliminary event arguments to obtain the final event arguments comprises: The second cosine similarity between any two event arguments is calculated, and a second threshold is set to determine whether the second cosine similarity is greater than or equal to the second threshold. If so, the two event arguments are regarded as the same event argument.

6. The method for constructing a chain diagram of urban rainstorm and flood disasters according to claim 1, characterized in that: According to the trigger words in the event trigger word library, the step of performing relation extraction in the event corpus to obtain the semantic relations related to the trigger words comprises: Selecting multiple text segments of trigger words in the event trigger word library to form candidate event pairs; After word segmentation and part-of-speech tagging of the candidate event pairs, a dependency syntax tree is constructed to analyze the initial semantic relationship between the words; According to the preliminary semantic relationship, a mapping rule base from specific to abstract events is established; Performing logical deduction and verification on the mapping rule base to obtain a dependency pattern rule base; The trigger word weights are adjusted in the dependency pattern rule base for optimization to obtain extraction results containing semantic relationships.

7. The method for constructing a chain diagram of urban rainstorm and flood disasters according to claim 1, characterized in that: The process of obtaining the temporal relationship and the spatial relationship by the improved ELECTRA-BiLSTM model includes: Selecting multiple text fragments of trigger words in the event trigger word library, inputting them into the pre-trained text encoder ELECTRA model for pre-training, and obtaining corresponding text word vector sequences; Input the text word vector sequence into the dilated convolutional layer to extract local-global features of the text; Input the local-global features into the BiLSTM model to capture contextual dependencies; Input the dependency of the context into the multi-head attention mechanism layer to calculate the first attention of the temporal task and the second attention of the spatial task respectively; Classification prediction results of temporal relationship and spatial relationship are obtained respectively according to the first attention and the second attention.

8. A system for constructing a chain diagram of urban rainstorm and flood disasters, characterized in that: The system comprises: The data acquisition module is used to obtain research literature and the first historical events and their secondary events of rainstorm and flood disasters in the target city, and to construct a directed network diagram of the disaster chain; An ontology modeling module, used to construct an ontology model of the rainstorm and flood disaster in the target city according to the directed network diagram of the disaster chain; A corpus generation module is used to obtain the second historical event and its secondary events of the rainstorm and flood disaster in the target city for preprocessing, and input the preprocessed second historical event and its secondary events into the ontology model to obtain an event corpus; A trigger word extraction module, used for extracting event trigger words from the event corpus using a multimodal dynamic fusion model MDF-Net to construct an event trigger word library; An event extraction module, used to extract events from the event corpus according to the trigger words in the event trigger word library, and obtain the event type and event argument corresponding to the trigger words; A relationship extraction module, used for performing relationship extraction in the event corpus according to the trigger words in the event trigger vocabulary, and obtaining semantic relations, temporal relations and spatial relations related to the trigger words, wherein the temporal relations and the spatial relations are obtained by an improved ELECTRA-BiLSTM model, and the improved ELECTRA-BiLSTM model includes an ELECTRA model, a hole convolution layer, a gating mechanism layer, a BiLSTM model and a multi-head attention mechanism layer; The graph construction module is used to construct a disaster chain event graph of the rainstorm and flood disaster in the target city with the event type, the event argument, the temporal relationship and the spatial relationship as event nodes and the semantic relationship as the edge of the event.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of a method for constructing a chain cause graph of urban rainstorm and flood disasters as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the method for constructing a chain event graph of urban rainstorm and flood disasters as described in any one of claims 1-7 are implemented.

Images