Urban inland inundation disaster risk assessment method, device, equipment and medium

Abstract

The embodiment of the invention provides an urban waterlogging disaster risk assessment method and device, equipment and a medium. The method comprises the steps that multi-source data of urban waterlogging disaster risks to be evaluated are acquired, knowledge extraction is carried out on the multi-source data, a waterlogging disaster risk data set is obtained, and the waterlogging disaster risk data set comprises a plurality of risk elements and characterization dimensions and quantitative indexes of the risk elements; performing classification processing on the waterlogging disaster risk data set according to a plurality of risk influence sources to obtain a classification result, and constructing an urban waterlogging disaster risk knowledge graph based on the classification result and the waterlogging disaster risk data set; and based on the knowledge graph, performing waterlogging disaster risk quantitative calculation on the to-be-assessed city to obtain a waterlogging disaster risk assessment result. According to the method, the structural relationship among the risk factors of the urban inland inundation disaster is displayed in a visual form of a graphic network, and a systematic and objective assessment method is provided for assessing the risk of the urban inland inundation disaster.

Description

Technical Field

[0001] The present application relates to the technical field of risk assessment, and in particular to a method, device, equipment and medium for assessing urban waterlogging disaster risk. Background Art

[0002] Due to climate change, extreme rainfall events have increased and the risk of rain and flood disasters has also risen sharply; at the same time, with the expansion of urban scale and the development of underground space, high-intensity and continuous precipitation can easily cause urban waterlogging, which poses a serious threat to transportation and residents' safety.

[0003] When conducting urban waterlogging disaster risk assessment, due to the wide range of urban waterlogging disasters, numerous influencing factors and complex disaster mechanisms, urban waterlogging disaster risk assessment work mainly relies on urban waterlogging disaster events that have occurred and the subjective experience of experts. There is still a lack of an effective research method to assess the risk of urban waterlogging disasters as a whole, which can not only intuitively and vividly display the risk factors of urban waterlogging disasters and their relationship with disasters, but also systematically and objectively carry out risk assessment work such as urban waterlogging disaster risk factor identification, risk category classification and risk degree calculation. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and medium for evaluating urban waterlogging disaster risk, which are used to display the relationship between urban waterlogging disaster risk factors in a visual form and evaluate urban waterlogging disaster risk in a systematic and objective manner.

[0005] In a first aspect, an embodiment of the present application provides a method for evaluating urban waterlogging disasters, the method comprising:

[0006] Acquire multi-source data on urban waterlogging disaster risk to be assessed, extract knowledge from the multi-source data, and obtain a waterlogging disaster risk data set, wherein the waterlogging disaster risk data set includes: multiple risk factors and their representation dimensions and quantitative indicators;

[0007] Classify the waterlogging disaster risk dataset according to multiple risk impact sources to obtain a classification result, and construct an urban waterlogging disaster risk knowledge graph based on the classification result and the waterlogging disaster risk dataset;

[0008] Based on the knowledge graph, the waterlogging disaster risk of the city to be assessed is quantitatively calculated to obtain a waterlogging disaster risk assessment result.

[0009] In a possible implementation, knowledge is extracted from multi-source data to obtain a waterlogging disaster risk dataset, including:

[0010] Performing entity extraction on the multi-source data to obtain a plurality of risk factor entities contained in the multi-source data;

[0011] Based on multiple risk factors, extracting the representation relationship of risk factors from the multi-source data to obtain representation dimensions corresponding to the multiple risk factors;

[0012] Based on the representation dimensions of multiple risk factors, extract the indicator attributes of the risk factor representation dimensions from the multi-source data to obtain the quantitative indicators corresponding to the multiple risk factor entities and their representation dimensions;

[0013] The risk factors and their related data are integrated and processed to obtain an urban waterlogging disaster risk data set.

[0014] In a possible implementation, the risk factors and their related data are integrated to obtain an urban waterlogging disaster risk dataset, including:

[0015] Screening the risk factors and related data thereof, and performing synonym recognition on the risk factors and related data after the screening process to obtain recognition results, wherein the recognition results are used to indicate whether there are synonym entities for the risk factors and related data thereof;

[0016] In the case where the identification result indicates that the risk factor and its related data have synonym entities, determining high-frequency entities in the synonym entities, and replacing other synonym entities in the synonym entities with the high-frequency entities to obtain the urban waterlogging disaster risk dataset;

[0017] When the identification result indicates that there are no synonym entities for the risk factor and its related data, the risk factor and its related data are used as the urban waterlogging disaster risk dataset.

[0018] In a possible implementation, the risk factors are classified according to multiple influencing sources to obtain classification results, including:

[0019] Input the multiple risk impact sources and the multiple risk factor names into the corpus analysis model respectively, and obtain the output result of the corpus analysis model, wherein the output result is used to indicate the source word vector corresponding to each risk impact source and the element word vector corresponding to each risk factor;

[0020] For all risk factors, determining a distance parameter between the factor word vector corresponding to the risk factor and the multiple source word vectors one by one, wherein the distance parameter is used to indicate a matching degree between the factor word vector and the source word vector;

[0021] The risk impact source corresponding to the distance parameter with the smallest risk factor distance is taken as the category of the risk factor, and the risk factors are classified into the corresponding risk impact sources to obtain the classification results.

[0022] In a possible implementation, the knowledge graph is centered on urban waterlogging disaster risk, including risk impact sources, risk factors, representation dimensions, and quantitative indicators, including:

[0023] The knowledge relationship of urban waterlogging disaster risk is expressed as a four-layer structure of urban waterlogging disaster risk-risk impact source-risk factor-representation dimension-quantitative indicator, namely, urban waterlogging disaster risk-risk impact source, risk impact source-risk factor, risk factor-representation dimension, representation dimension-quantitative indicator;

[0024] A graph database is used for storage and mapping. The first and last entity parts of each layer of the structure are stored and expressed as nodes, and the intermediate relationship parts are stored and expressed as edges, thus forming a graphical network structure and visual display of urban waterlogging disaster risk knowledge.

[0025] In a possible implementation, knowledge reasoning is performed on the knowledge graph, and waterlogging disaster risk assessment is performed on the city to be assessed to obtain a waterlogging disaster risk assessment result, including:

[0026] Normalizing the quantitative indicator data in the knowledge graph to obtain normalized data;

[0027] Performing hierarchical analysis on the knowledge graph, dividing it into a target layer, a criterion layer and an indicator layer, and obtaining the indicator weight corresponding to each layer;

[0028] According to the normalized data and the corresponding indicator weights of the multiple layers, a waterlogging disaster risk assessment is performed on the city to be assessed to obtain a waterlogging disaster risk assessment result.

[0029] In a possible implementation, based on the normalized data and the corresponding indicator weights of multiple layers, a waterlogging disaster risk assessment is performed on the city to be assessed, and a waterlogging disaster risk assessment result is obtained, including:

[0030] The waterlogging disaster risk assessment result A is determined using the following formula:

[0031]

[0032] Among them, A is the waterlogging disaster risk index of the city to be evaluated, Wi is the indicator weight corresponding to the criterion layer, ωij is the indicator weight corresponding to the indicator layer, Dij is the normalized data, m is the number of indicators corresponding to the criterion layer, and n is the number of indicators corresponding to the indicator layer.

[0033] In a second aspect, an embodiment of the present application provides an assessment device for urban waterlogging disaster risk, comprising:

[0034] The acquisition module is used to obtain multi-source data on urban waterlogging disaster risks to be assessed;

[0035] A processing module is used to extract knowledge from the multi-source data to obtain a waterlogging disaster risk data set, wherein the waterlogging disaster risk data set includes: multiple risk factors and their representation dimensions and quantitative indicators;

[0036] The processing module is further used to classify the waterlogging disaster risk data set according to multiple risk impact sources to obtain a classification result, and to construct an urban waterlogging disaster risk knowledge graph based on the classification result and the waterlogging disaster risk data set;

[0037] The evaluation module is used to quantitatively calculate the waterlogging disaster risk of the city to be evaluated based on the knowledge graph to obtain a waterlogging disaster risk evaluation result.

[0038] In a possible implementation, the device further includes: an extraction module;

[0039] The extraction module performs entity extraction on the multi-source data to obtain multiple risk factor entities contained in the multi-source data; based on multiple risk factors, extracts the representation relationship of risk factors on the multi-source data to obtain the representation dimensions corresponding to the multiple risk factors; based on the representation dimensions of multiple risk factors, extracts the indicator attributes of the risk factor representation dimensions on the multi-source data to obtain the quantitative indicators corresponding to the multiple risk factor entities and their representation dimensions;

[0040] The processing module is also used to integrate the risk factors and their related data to obtain an urban waterlogging disaster risk data set.

[0041] In a possible implementation, the processing module is used to screen the risk factors and their related data, and perform synonym recognition on the risk factors and their related data after the screening process to obtain a recognition result, and the recognition result is used to indicate whether there are synonym entities in the risk factors and their related data;

[0042] When the identification results indicate that there are synonym entities in the risk factors and their related data, the high-frequency entities in the synonym entities are determined, and other synonym entities in the synonym entities are replaced with high-frequency entities to obtain the target city waterlogging disaster risk dataset.

[0043] When the identification results indicate that there are no synonym entities for the risk factors and their related data, the risk factors and their related data are used as the target city waterlogging disaster risk dataset.

[0044] In a possible implementation, the processing module is used to input the multiple risk impact sources and the multiple risk factor names into a corpus analysis model respectively, and obtain an output result of the corpus analysis model, wherein the output result is used to indicate a source word vector corresponding to each risk impact source and an element word vector corresponding to each risk factor;

[0045] For any one of all the risk factors, determining a distance parameter between the factor word vector corresponding to the risk factor and the plurality of source word vectors, wherein the distance parameter is used to indicate a matching degree between the factor word vector and the source word vector;

[0046] The risk impact source corresponding to the distance parameter with the smallest risk factor distance is taken as the category of the risk factor, and the risk factors are classified into the corresponding risk impact sources to obtain the classification results.

[0047] In a possible implementation, the knowledge graph is centered on urban waterlogging disaster risk, including risk impact sources, risk factors, representation dimensions, and quantitative indicators, including:

[0048] The knowledge relationship of urban waterlogging disaster risk is expressed as a four-layer structure of urban waterlogging disaster risk-risk impact source-risk factor-representation dimension-quantitative indicator, namely, urban waterlogging disaster risk-risk impact source, risk impact source-risk factor, risk factor-representation dimension, representation dimension-quantitative indicator;

[0049] A graph database is used for storage and mapping expression. The first and last entity parts of each layer of the structure are stored and expressed as nodes, and the intermediate relationship part is stored and expressed as edges, thereby forming a graphical network structure and visual display of urban waterlogging disaster risk knowledge.

[0050] The evaluation module is used to normalize the quantitative indicator data in the knowledge graph to obtain normalized data; perform hierarchical analysis on the knowledge graph to divide it into a target layer, a criterion layer and an indicator layer to obtain the indicator weight corresponding to each layer; and perform an urban waterlogging disaster risk assessment on the city to be evaluated based on the normalized data and the indicator weights corresponding to the multiple layers to obtain an urban waterlogging disaster risk assessment result.

[0051] In a possible implementation, the assessment module is used to determine the waterlogging disaster risk assessment result A using the following formula:

[0052]

[0053] Among them, A is the waterlogging disaster risk index of the city to be evaluated, Wi is the indicator weight corresponding to the criterion layer, ωij is the indicator weight corresponding to the indicator layer, Dij is the normalized data, m is the number of indicators corresponding to the criterion layer, and n is the number of indicators corresponding to the indicator layer.

[0054] In a third aspect, an embodiment of the present application provides a device for urban waterlogging disaster risk assessment, including: a memory and a processor;

[0055] Wherein, the memory stores computer-executable instructions;

[0056] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for assessing urban waterlogging disaster risk as described in the first aspect and various possible implementations of the first aspect.

[0057] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method for assessing the urban waterlogging disaster risk as described in the first aspect and various possible implementation methods of the first aspect.

[0058] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for assessing urban waterlogging disaster risks as described in the first aspect and various possible implementations of the first aspect.

[0059] The risk assessment method, device, equipment and storage medium for urban waterlogging disasters provided in the embodiments of the present application obtain multi-source data on the urban waterlogging disaster risks to be assessed, and obtain multiple risk factors for urban waterlogging disasters and their representation dimensions and quantitative indicators through knowledge extraction, and classify the risk factors according to the sources of influence, and construct an urban waterlogging knowledge graph according to the four-layer structure of urban waterlogging disaster risk-risk influence source-risk factor-representation dimension-quantitative indicator, and then analyze the knowledge graph, perform calculations based on the analysis results, objectively and systematically assess the urban waterlogging disaster risks, and provide strong support for urban waterlogging management. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0061] Figure 1 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 1 ;

[0062] Figure 2 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 2 ;

[0063] Figure 3 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 3 ;

[0064] Figure 4 A schematic diagram of a knowledge graph of urban waterlogging disaster risk provided in an embodiment of the present application;

[0065] Figure 5 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 4 ;

[0066] Figure 6 A hierarchical structure diagram of urban waterlogging disaster risk assessment provided in an embodiment of the present application;

[0067] Figure 7 A schematic diagram of the structure of a device for assessing urban waterlogging disaster risk provided in this application;

[0068] Figure 8 A schematic diagram of the structure of an urban waterlogging disaster risk assessment device provided in this application.

[0069] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] "Multiple" means two or more, and other quantifiers are similar. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0072] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0073] On the one hand, with climate change, the frequency of extreme rainfall events has increased, leading to a sharp increase in the risk of rain and flood disasters; on the other hand, with the expansion of urban scale and the increase in underground space development, high-intensity and continuous rainfall can easily cause urban flooding, bringing serious impacts on transportation and residents' safety.

[0074] A knowledge graph is a series of diverse graphics that display the interconnections and structural relationships of knowledge. It uses visualization technology to present knowledge resources and their relationships, and to mine, analyze, construct, draw and display knowledge and their interconnections.

[0075] At present, when conducting urban waterlogging disaster risk assessment, due to the wide range of urban waterlogging disasters, numerous influencing factors and complex disaster mechanisms, the urban waterlogging disaster risk assessment work mainly relies on urban waterlogging disaster events that have occurred and the subjective experience of experts. There is still a lack of an effective research method to assess the risk of urban waterlogging disasters as a whole, which can not only intuitively and vividly display the risk factors of urban waterlogging disasters and their relationship with disasters, but also systematically and objectively carry out risk assessment work such as urban waterlogging disaster risk factor identification, risk category classification and risk degree calculation.

[0076] In response to the above problems, this application provides an assessment method for urban waterlogging disaster risk. This method extracts multi-source data on urban waterlogging disaster risk, and constructs a knowledge graph based on the logical relationship between waterlogging disaster risk data, visually displaying the urban waterlogging disaster risk factors and their relationship with waterlogging disasters. Based on the knowledge graph and analytic hierarchy process, the indicator weights of each risk factor and influencing source are quantitatively calculated, and a comprehensive, systematic and quantitative assessment of urban waterlogging risk is conducted, providing a reliable basis for urban waterlogging control planning and defense arrangements, and reducing disaster losses.

[0077] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0078] Figure 1 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 1 .like Figure 1 As shown, the method includes:

[0079] S101. Obtain multi-source data on urban waterlogging disaster risks to be assessed, extract knowledge from the multi-source data, and obtain a waterlogging disaster risk data set.

[0080] Among them, the multi-source data can be, for example, literature data related to the urban waterlogging disaster to be assessed, including, for example, relevant literature data such as the hydrological and meteorological conditions, geographical and geomorphological characteristics, social and economic conditions, and the construction of waterlogging prevention and control systems in the area where the city is located. The waterlogging disaster risk dataset includes multiple risk factors and their representation dimensions and quantitative indicators.

[0081] The process of knowledge extraction may be, for example: the first step is to extract entities from the multi-source data to obtain multiple risk factor entities contained in the multi-source data, such as heavy rain; the second step is to extract the representation relationship of risk factors from the multi-source data based on multiple risk factors to obtain the representation dimensions corresponding to the multiple risk factor entities, such as heavy rain-heavy rain intensity; the third step is to extract the indicator attributes of the risk factor representation dimensions from the multi-source data based on the representation dimensions of multiple risk factors to obtain the quantitative indicators corresponding to the multiple risk factor entities and their representation dimensions, such as heavy rain-heavy rain intensity-24-hour rainfall;

[0082] For example, multi-source data can be data obtained through multiple channels based on keywords such as "urban waterlogging disaster risk". Multiple channels can be, for example, the Internet, journals, etc. Through knowledge extraction, the representation dimensions and quantitative indicators corresponding to multiple risk factors are obtained from multi-source data to obtain a waterlogging disaster risk data set.

[0083] S102. Classify the risk factors according to multiple influencing sources to obtain classification results, and construct an urban waterlogging disaster risk knowledge map based on the classification results and the waterlogging disaster risk data set.

[0084] Among them, the sources of impact include the occurrence and development process of urban waterlogging disasters, disaster losses and disaster reduction measures. The sources of impact may include: disaster-causing factors, disaster-prone environment, disaster-bearing objects and disaster reduction system.

[0085] Classification processing is to classify risk factors according to multiple sources of influence, providing a basis for the subsequent construction of a knowledge graph.

[0086] The specific process of classification processing may include, for example:

[0087] 1. Input multiple sources of influence and multiple risk factors into the corpus analysis model to classify the risk factors.

[0088] Among them, the corpus analysis model is a pre-trained language model, which can obtain word vectors and measure the similarity of influencing sources and risk factors by calculating the distance of word vectors.

[0089] 2. Determine the impact types of multiple impact sources, and based on the multiple impact types, determine the corresponding risk factor data, and then classify the risk factors.

[0090] Among them, the impact types of multiple impact sources are first determined, and then the risk factors are classified and processed based on the impact types.

[0091] Knowledge graphs can use visualization technology to display each knowledge node and the connections between them.

[0092] Based on the factors that affect the occurrence and development of urban waterlogging disasters and the disaster losses, the risk factors are classified and processed, and the classification results are obtained by identifying the relationship between the risk factors and the factors that affect the occurrence and development of urban waterlogging disasters and the disaster losses. Through the classification results, the influencing sources and risk factors and their representation dimensions and quantitative indicator data are associated to construct a knowledge graph.

[0093] Exemplarily, the sources of impact may include: disaster-causing factors, disaster-prone environment, disaster-bearing objects, disaster reduction system, etc.; risk factors may include: heavy rain, underlying surface, personnel, property, infrastructure, engineering system, non-engineering system, etc.

[0094] By identifying the relationship between the sources of influence: disaster-causing factors, disaster-prone environment, disaster-bearing objects, and disaster reduction systems, and the risk factors: heavy rain, underlying surface, personnel, property, infrastructure, engineering systems, and non-engineering systems, the classification results are as follows:

[0095] Disaster factors: heavy rain;

[0096] Disaster-prone environment: underlying surface;

[0097] Disaster-affected objects: people, property, infrastructure;

[0098] Disaster reduction system: engineering system, non-engineering system;

[0099] According to the classification results, we associate disaster-causing factors with heavy rain, disaster-prone environment with underlying surface, disaster-bearing objects with personnel, property, and infrastructure, and disaster reduction system with engineering system and non-engineering system, improve the relationship between these knowledge nodes, and then construct a knowledge graph.

[0100] S103. Based on the knowledge graph, quantitatively calculate the waterlogging disaster risk of the city to be assessed to obtain a waterlogging disaster risk assessment result.

[0101] Among them, risk assessment is the process of quantitatively evaluating the possible risks of urban flooding disasters in the city to be assessed before the urban flooding disaster event occurs in the city to be assessed.

[0102] Based on the constructed knowledge graph, by analyzing the relationship between each knowledge node, a quantitative assessment is made on the impact of possible urban waterlogging disasters in the assessed city, and the results of the urban waterlogging disaster risk assessment are obtained.

[0103] The embodiment of the present application provides an assessment method for urban waterlogging disasters. By acquiring multi-source data on the risk of urban waterlogging disasters to be assessed, knowledge extraction is performed on risk factors and their representation dimensions and quantitative indicators, and the results of knowledge extraction are classified and processed. A knowledge graph is constructed based on the classification results, and then based on the analysis of the knowledge graph, an assessment of waterlogging disaster risk is performed on the city to be assessed, and an assessment result of waterlogging disaster risk is obtained. This method visualizes the connection and structural relationship between urban waterlogging disasters and their risk factors in the form of a knowledge graph, providing a systematic and intuitive assessment method for urban waterlogging disaster risk assessment. Based on the assessment results, the improvement of important urban infrastructure is guided, and the urban waterlogging problem is effectively addressed, thereby improving the city's sustainable development capacity.

[0104] Figure 2 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 2 .like Figure 2 As shown, in this embodiment Figure 1 Based on the embodiment, a possible implementation method of extracting knowledge from multi-source literature to obtain multiple risk factors and their representation dimensions and quantitative indicators is described in detail. The method includes:

[0105] S201. Perform entity extraction on the multi-source data to obtain a plurality of risk factor entities contained in the multi-source data.

[0106] Among them, multi-source literature materials are literature materials obtained through various channels, such as technical reports, papers, bulletins, etc.

[0107] Entity extraction is performed on the literature data to extract the risk factors, representation dimensions and quantitative indicators related to urban waterlogging disasters, and other invalid content and invalid data are filtered out to determine multiple data related to waterlogging disaster risks and obtain multiple risk factor entities contained in multi-source data.

[0108] S202: Based on multiple risk factors, extract the representation relationship of risk factors from the multi-source data to obtain representation dimensions corresponding to the multiple risk factors.

[0109] Based on multiple risk factors, knowledge is extracted from multi-source data obtained from literature obtained through various channels, and the representation dimensions corresponding to multiple risk factors are obtained according to the representation relationship of risk factors.

[0110] For example: heavy rain-heavy rain frequency, heavy rain-heavy rain intensity.

[0111] S203. Based on the representation dimensions of multiple risk factors, extract indicator attributes of the risk factor representation dimensions from the multi-source data to obtain quantitative indicators corresponding to multiple risk factor entities and their representation dimensions.

[0112] Indicator attributes are extracted based on the representation relationship of risk factors to obtain quantitative indicators corresponding to multiple risk factor entities and their representation dimensions.

[0113] For example: heavy rain-rainstorm intensity-maximum 24-hour rainfall (224.6 mm), heavy rain-rainstorm frequency-average number of heavy rain days per year (5 days), etc.

[0114] S204: Integrate the risk factors and their related data to obtain an urban waterlogging disaster risk data set.

[0115] Among them, the risk factor entities and the quantitative indicators corresponding to their representation dimensions are expressed and stored in the form of a triple data set <risk factor, representation dimension, quantitative indicator>, which is the waterlogging disaster risk dataset.

[0116] For example, the average number of rainstorm days per year is 5 days, which is used to measure the rainstorm frequency, and the maximum 24-hour rainfall of 224.6 mm is used to measure the rainstorm intensity. The above multiple risk factors, representation dimensions, and quantitative indicators are expressed and stored in the form of ternary data sets to obtain waterlogging disaster risk data such as <rainstorm, rainstorm frequency, average number of rainstorm days per year is 5 days>; <rainstorm, rainstorm intensity, maximum 24-hour rainfall of 224.6 mm>.

[0117] In a possible implementation, the above-mentioned integration and processing of waterlogging disaster risk data to obtain a waterlogging disaster risk data set is specifically implemented as follows:

[0118] The <risk factor, representation dimension, quantitative indicator> is screened, and synonym recognition is performed on the screened <risk factor, representation dimension, quantitative indicator> data to obtain a recognition result, which is used to indicate whether there is a synonym entity for <risk factor, representation dimension, quantitative indicator>.

[0119] When the identification results indicate that the <risk factor, representation dimension, quantitative indicator> data has synonym entities, the high-frequency entities in the synonym entities are determined, and other synonym entities in the synonym entities are replaced with high-frequency entities to obtain the waterlogging disaster risk dataset.

[0120] When the identification result indicates that there is no synonym entity in the <risk factor, representation dimension, quantitative indicator> data, the waterlogging disaster risk data is used as the target waterlogging disaster risk data set.

[0121] Among them, the screening process is to remove noise data. The noise data that may exist in the data is removed, and then synonym recognition is performed on the data after the screening process.

[0122] When the recognition result indicates that the data has synonym entities, the synonym entities may be, for example, heavy rainfall, heavy precipitation, rainstorm, etc. A high-frequency entity in the synonym is determined, for example, rainstorm, and then heavy rainfall and heavy rainfall in the synonym entities are replaced with rainstorm until there are no synonym entities in the recognition result, and the waterlogging disaster risk data is used as the target waterlogging disaster risk data set.

[0123] The urban waterlogging assessment method provided in the embodiment of the present application extracts quantitative indicators corresponding to urban waterlogging disaster risk factors and their representation dimensions through knowledge extraction, and screens the extracted data to improve the accuracy of the data, performs synonym replacement processing on the extracted data to make the data more accurate and refined, provides data support for constructing a knowledge graph, and improves the accuracy and reliability of urban waterlogging risk assessment.

[0124] Figure 3 A schematic diagram of a process for evaluating the risk of urban waterlogging disasters provided in an embodiment of the present application Figure 3 .like Figure 3 As shown, in this embodiment Figure 1 Example or Figure 2 Based on the embodiment, a possible implementation method of classifying risk factors according to multiple influencing sources to obtain classification results is described in detail. The method includes:

[0125] S301. Input multiple impact sources and multiple risk factors into a corpus analysis model to obtain an output result of the corpus analysis model, where the output result is used to indicate a source word vector corresponding to each impact source and an element word vector corresponding to each risk factor.

[0126] Among them, through the corpus analysis model, the word vector corresponding to the input into the corpus analysis model can be obtained.

[0127] Multiple impact source phrases and multiple risk factor phrases are taken as input and input into the corpus analysis model. The output result is obtained through the corpus analysis model. The output result is used to indicate the source word vector corresponding to each impact source and the element word vector corresponding to each risk factor.

[0128] S302. For any one of all risk factors, determine a distance parameter between the factor word vector corresponding to the risk factor and the multiple source word vectors.

[0129] Among them, the distance parameter is used to indicate the degree of match between the feature word vector and the source word vector.

[0130] S303: Taking the risk impact source corresponding to the distance parameter with the smallest risk factor distance as the category of the risk factor, classify the risk factor into the corresponding risk impact source to obtain a classification result.

[0131] For any one of the multiple risk factors, a distance parameter between the factor word vector corresponding to the risk factor and the multiple source word vectors is determined, where the distance parameter is used to indicate the degree of matching between the factor word vector and the source word vector.

[0132] A matching influence source corresponding to a distance parameter with the smallest distance is determined from multiple distance parameters.

[0133] Among them, the distance parameter is the Euclidean distance, and the distance between two vectors is determined by calculating the square root of the sum of the squares of the numerical differences in each dimension of the two vectors.

[0134] For example: there are three source word vectors A, B, C, and an element word vector O. The Euclidean distances between the source word vectors A, B, C and the element word vector O are d1, d2, and d3 respectively.

[0135] If d2 is the smallest, it is determined that the matching degree between the source word vector B and the element word vector O is the highest, and the risk factor o corresponding to the element word vector O is classified into the risk source b corresponding to the source word vector B, thereby achieving classification.

[0136] For example, Figure 4 This is a schematic diagram of the urban flooding knowledge graph provided in the embodiment of the present application. Figure 4 shown.

[0137] The influencing source 1 may include, for example, a disaster-prone environment; the risk factor 2 may include, for example, an underlying surface; the characterization dimension 3 may include, for example, a surface slope; and the quantitative indicator 4 may include, for example, a slope coefficient.

[0138] It can be understood that when the impact source 1 is a disaster-prone environment, the corresponding risk factor 2 is the underlying surface. Since the underlying surface is an influencing factor of the disaster-prone environment, the line between the two can indicate that there is an influencing factor relationship between the two.

[0139] When risk factor 2 is the underlying surface, its corresponding representation dimension 3 is the surface slope. Since the underlying surface can be measured from the dimension of the surface slope, the line between the two can indicate that there is a representation dimension relationship between the two.

[0140] When the representation dimension 3 is the surface slope, the corresponding quantitative index 4 is the slope coefficient. Since the slope coefficient is a quantitative index of the surface slope, the line between the two can indicate that there is a quantitative relationship between the two.

[0141] It can be understood that when risk factor 2 is the underlying surface, representation dimension 3 is the surface slope, and quantitative indicator 4 is the slope coefficient, the quantitative indicator 4 slope coefficient measures the underlying surface of risk factor 2 by using the representation dimension 3 surface slope.

[0142] In one possible implementation, the knowledge graph is centered on urban waterlogging disaster risk, including risk impact sources, risk factors, representation dimensions, and quantitative indicators, and a detailed description is given of the construction of the urban waterlogging disaster risk knowledge graph based on the classification results and the waterlogging disaster risk data set.

[0143] Based on the classification results, the knowledge relationship of urban waterlogging disaster risk is expressed as a four-layer structure of urban waterlogging disaster risk-risk impact source-risk factor-representation dimension-quantitative indicator, namely, urban waterlogging disaster risk-risk impact source, risk impact source-risk factor, risk factor-representation dimension, and representation dimension-quantitative indicator.

[0144] A graph database is used for storage and mapping. The first and last entity parts of each layer of the structure are stored and expressed as nodes, and the intermediate relationship parts are stored and expressed as edges, thus forming a graphical network structure and visual display of urban waterlogging disaster risk knowledge.

[0145] The urban waterlogging assessment method provided in the embodiment of the present application, through data classification processing, classifies the risk factors according to the degree of match between them and the source of influence. By measuring the Euclidean distance between the factor word vector and the source word vector, the degree of match between the risk factor and the source of influence is determined, and the system objectively divides the risk factor categories to achieve data classification. According to the classification structure, a knowledge graph is constructed to intuitively and vividly display the relationship between urban waterlogging disaster risk factors and waterlogging disasters, so as to further evaluate urban waterlogging.

[0146] Figure 5 A schematic diagram of a method for evaluating urban waterlogging disasters provided in an embodiment of the present application Figure 4 .like Figure 5 As shown, the knowledge graph in this embodiment includes: a target layer, a criterion layer, and an indicator layer. Figure 1-3 On the basis of any embodiment, a possible implementation method of performing waterlogging disaster risk assessment on a city to be assessed based on a knowledge graph to obtain a waterlogging disaster risk assessment result is described in detail, and the method includes:

[0147] S501. Normalize multiple quantitative indicator data in the knowledge graph to obtain normalized data.

[0148] Normalize multiple quantitative indicator data to eliminate the dimensional impact between different indicators and make the importance of each feature in the model more equal, thereby improving the evaluation accuracy.

[0149] For example, the maximum 24-hour rainfall in the city to be evaluated is 224.6 mm, and the average number of rainstorm days per year is 5 days. Then the normalized data of the maximum 24-hour rainfall in the city to be evaluated is 0.45, and the normalized data of the average number of rainstorm days per year is 0.3.

[0150] S502. Perform hierarchical analysis on the knowledge graph to obtain the indicator weight corresponding to each layer, wherein the criterion layer is used to indicate the impact source, and the indicator layer is used to indicate the risk factor.

[0151] The indicator weights corresponding to different levels can be the same or different, which is subject to actual conditions.

[0152] For example, Figure 6 A hierarchical structure diagram of urban waterlogging risk assessment provided in the embodiment of the present application. A hierarchical analysis is performed based on the knowledge graph to construct a hierarchical structure diagram of urban waterlogging risk assessment. Figure 6 The hierarchy diagram shown.

[0153] Among them, the target layer elements are: assessing the risk of urban waterlogging; the criterion layer elements are: disaster-prone environment, disaster-causing factors, disaster-bearing objects, and disaster reduction system; the indicator layer elements are: underlying surface, heavy rain, infrastructure, property, personnel, engineering system, and non-engineering system.

[0154] The elements at the same level are compared pairwise based on the elements at the next higher level.

[0155] It can be understood that the elements of the criterion layer are: disaster-prone environment, disaster-causing factors, disaster reduction system, and disaster-affected objects. The lines between them indicate that the disaster-prone environment, disaster-causing factors, disaster reduction system, and disaster-affected objects all have an impact on the assessment of urban waterlogging disasters. Therefore, based on the assessment of urban waterlogging risk, the disaster-prone environment, disaster-causing factors, disaster reduction system, and disaster-affected objects are compared in pairs.

[0156] For the index layer elements, such as infrastructure, property, and personnel, the lines between them and the disaster-prone objects indicate that the infrastructure, property, and personnel have an impact on the disaster-prone objects. Therefore, the infrastructure, property, and personnel are compared in pairs based on the disaster-prone objects.

[0157] The relative importance is determined according to the evaluation scale, and then the judgment matrix is ​​constructed. The evaluation scale is: the 1-9 ratio scale method is introduced, and 1, 3, 5, 7, and 9 are respectively used to represent the same importance, slightly important, relatively important, strongly important, and absolutely important of factor i compared with factor j according to experience, while 2, 4, 6, and 8 represent the compromise value between the above two judgment levels.

[0158] The indicator weights of each layer of indicators are determined by calculating the eigenvectors of the judgment matrix constructed by the above method.

[0159] S503. Based on the normalized data and the corresponding indicator weights of the multiple layers, an urban waterlogging disaster risk assessment is conducted on the city to be assessed, and an urban waterlogging disaster assessment result is obtained.

[0160] Among them, the importance of the indicator can be determined by firstly determining at least one normalized data corresponding to each indicator in the indicator layer and the indicator weight corresponding to the indicator; then the importance of the criterion can be determined by determining at least one indicator corresponding to each criterion in the criterion layer and the importance corresponding to the indicator; and then the corresponding evaluation results can be determined according to the importance of multiple criteria.

[0161] In a possible implementation, for example, the waterlogging disaster risk assessment result A may be determined by using the following formula:

[0162]

[0163] Among them, A is the waterlogging disaster risk index of the city to be evaluated, Wi is the indicator weight corresponding to the criterion layer, ωij is the indicator weight corresponding to the indicator layer, Dij is the normalized data, m is the number of indicators corresponding to the criterion layer, and n is the number of indicators corresponding to the indicator layer.

[0164] Substitute the indicator weights obtained in the above steps, that is, the indicator weights corresponding to the criterion layer and the indicator weights corresponding to the indicator layer, and the normalized data into the above formula for calculation to obtain the calculation result of the risk index of the city to be evaluated. The higher the calculation result, the greater the risk of urban waterlogging disasters.

[0165] The urban waterlogging assessment method provided in the embodiment of the present application, by normalizing multiple quantitative indicator data, systematically and objectively quantifies the impact of multiple risk factors in assessing the risk level of urban waterlogging disasters, eliminates the dimensional impact between different characteristics, analyzes the knowledge graph through the hierarchical analysis method, calculates the indicator weights of each layer, and objectively and quantitatively calculates the waterlogging disaster risk index of the city to be assessed, thereby objectively assessing the urban waterlogging disaster risk, providing a new research method for urban waterlogging disaster risk assessment, helping to fully understand the urban waterlogging disaster risk, facilitating the management of the construction of the urban waterlogging governance system, and providing effective support for disaster prevention and mitigation.

[0166] Figure 7 A schematic diagram of a structure of an urban waterlogging disaster assessment device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, this embodiment provides an urban waterlogging disaster risk assessment device 70, comprising:

[0167] An acquisition module 701 is used to acquire multi-source data of urban waterlogging disaster risk to be assessed;

[0168] The processing module 702 is used to extract knowledge from multi-source data to obtain a waterlogging disaster risk data set, which includes: multiple risk factors and their representation dimensions and quantitative indicators;

[0169] The processing module 702 is also used to classify the waterlogging disaster risk data set according to multiple risk impact sources to obtain a classification result, and to construct an urban waterlogging disaster risk knowledge graph based on the classification result and the waterlogging disaster risk data set;

[0170] The evaluation module 703 is used to perform quantitative calculation of the waterlogging disaster risk of the city to be evaluated based on the knowledge graph to obtain the waterlogging disaster risk assessment result.

[0171] In a possible implementation, the device further includes: an extraction module 704;

[0172] The extraction module 704 performs entity extraction on the multi-source data to obtain multiple risk factor entities contained in the multi-source data; based on the multiple risk factors, extracts the representation relationship of the risk factors on the multi-source data to obtain the representation dimensions corresponding to the multiple risk factors; based on the representation dimensions of the multiple risk factors, extracts the indicator attributes of the risk factor representation dimensions on the multi-source data to obtain the quantitative indicators corresponding to the multiple risk factor entities and their representation dimensions;

[0173] The processing module 702 is also used to integrate the risk factors and their related data to obtain an urban waterlogging disaster risk data set.

[0174] In a possible implementation, the processing module 702 is used to screen the risk factors and their related data, and perform synonym recognition on the risk factors and their related data after the screening process to obtain a recognition result, and the recognition result is used to indicate whether there are synonym entities in the risk factors and their related data;

[0175] When the identification results indicate that there are synonym entities in the risk factors and their related data, the high-frequency entities in the synonym entities are determined, and other synonym entities in the synonym entities are replaced with high-frequency entities to obtain the target city waterlogging disaster risk dataset.

[0176] When the identification results indicate that there are no synonym entities for the risk factors and their related data, the risk factors and their related data are used as the target city waterlogging disaster risk dataset.

[0177] In a possible implementation, the processing module 702 is used to input multiple risk impact sources and multiple risk factor names into the corpus analysis model respectively, and obtain an output result of the corpus analysis model, where the output result is used to indicate a source word vector corresponding to each risk impact source and an element word vector corresponding to each risk factor;

[0178] For all risk factors, determine the distance parameter between the factor word vector corresponding to the risk factor and multiple source word vectors one by one, and the distance parameter is used to indicate the matching degree between the factor word vector and the source word vector;

[0179] The risk impact source corresponding to the distance parameter with the smallest risk factor distance is taken as the category of the risk factor, and the risk factors are classified into the corresponding risk impact sources to obtain the classification results.

[0180] In a possible implementation, the knowledge graph is centered on urban waterlogging disaster risk, including risk impact sources, risk factors, representation dimensions, and quantitative indicators, including:

[0181] The knowledge relationship of urban waterlogging disaster risk is expressed as a four-layer structure of urban waterlogging disaster risk-risk impact source-risk factor-representation dimension-quantitative indicator, namely, urban waterlogging disaster risk-risk impact source, risk impact source-risk factor, risk factor-representation dimension, representation dimension-quantitative indicator;

[0182] A graph database is used for storage and mapping. The first and last entity parts of each layer of the structure are stored and expressed as nodes, and the intermediate relationship parts are stored and expressed as edges, thus forming a graphical network structure and visual display of urban waterlogging disaster risk knowledge.

[0183] The evaluation module 703 is used to normalize the quantitative indicator data in the knowledge graph to obtain normalized data; perform hierarchical analysis on the knowledge graph to divide it into a target layer, a criterion layer and an indicator layer to obtain the indicator weight corresponding to each layer; and perform an urban waterlogging disaster risk assessment on the city to be evaluated based on the normalized data and the indicator weights corresponding to the multiple layers to obtain an urban waterlogging disaster risk assessment result.

[0184] In a possible implementation, the assessment module 703 is used to determine the waterlogging disaster risk assessment result A using the following formula:

[0185]

[0186] Among them, A is the waterlogging disaster risk index of the city to be assessed, W i is the indicator weight corresponding to the criterion layer, ω ij is the indicator weight corresponding to the indicator layer, D ij is the normalized data, m is the number of indicators corresponding to the criterion layer, and n is the number of indicators corresponding to the indicator layer.

[0187] Figure 8 This is a schematic diagram of a structure of an urban waterlogging disaster risk assessment device provided in an embodiment of the present application. Figure 8As shown, the urban waterlogging disaster risk assessment device 80 provided in this embodiment includes: at least one processor 801 and a memory 802. Optionally, the device 80 also includes a communication component 803. The processor 801, the memory 802 and the communication component 803 are connected via a bus 804.

[0188] In a specific implementation process, at least one processor 801 executes the computer execution instructions stored in the memory 802, so that at least one processor 801 executes the urban waterlogging disaster risk assessment method shown in the above embodiment.

[0189] The specific implementation process of the processor 801 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0190] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0191] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0192] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0193] The embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for assessing the urban waterlogging disaster risk shown in the above embodiment.

[0194] The embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method for assessing the urban waterlogging disaster risk shown in the above embodiment is implemented.

[0195] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0196] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0197] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0198] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0199] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0200] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can essentially or in other words contribute to the prior art or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0201] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0202] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for assessing urban waterlogging risk. It is characterized in that include: Acquire multi-source data on urban waterlogging disaster risk to be assessed, extract knowledge from the multi-source data, and obtain a waterlogging disaster risk data set, wherein the waterlogging disaster risk data set includes: multiple risk factors and their representation dimensions and quantitative indicators; Classify the waterlogging disaster risk dataset according to multiple risk impact sources to obtain a classification result, and construct an urban waterlogging disaster risk knowledge graph based on the classification result and the waterlogging disaster risk dataset; Based on the knowledge graph, the waterlogging disaster risk of the city to be assessed is quantitatively calculated to obtain a waterlogging disaster risk assessment result.

2. The method according to claim 1, It is characterized in that The knowledge extraction of the multi-source data is performed to obtain a waterlogging disaster risk data set, including: Performing entity extraction on the multi-source data to obtain a plurality of risk factor entities contained in the multi-source data; Based on multiple risk factors, extracting the representation relationship of risk factors from the multi-source data to obtain representation dimensions corresponding to the multiple risk factors; Based on the representation dimensions of multiple risk factors, extract the indicator attributes of the risk factor representation dimensions from the multi-source data to obtain the quantitative indicators corresponding to the multiple risk factor entities and their representation dimensions; The risk factors and their related data are integrated and processed to obtain an urban waterlogging disaster risk data set.

3. The method according to claim 2, It is characterized in that The risk factors and their related data are integrated to obtain an urban waterlogging disaster risk data set, including: Screening the risk factors and related data thereof, and performing synonym recognition on the risk factors and related data after the screening process to obtain recognition results, wherein the recognition results are used to indicate whether there are synonym entities for the risk factors and related data thereof; In the case where the identification result indicates that the risk factor and its related data have synonym entities, determining high-frequency entities in the synonym entities, and replacing other synonym entities in the synonym entities with the high-frequency entities to obtain the urban waterlogging disaster risk dataset; When the identification result indicates that there are no synonym entities for the risk factor and its related data, the risk factor and its related data are used as the urban waterlogging disaster risk dataset.

4. The method according to claim 1, It is characterized in that The risk factors and their related data are classified and processed according to multiple risk impact sources to obtain classification results, including: Input the multiple risk impact sources and the multiple risk factor names into the corpus analysis model respectively, and obtain the output result of the corpus analysis model, wherein the output result is used to indicate the source word vector corresponding to each risk impact source and the element word vector corresponding to each risk factor; For any one of all the risk factors, determining a distance parameter between the factor word vector corresponding to the risk factor and the plurality of source word vectors, wherein the distance parameter is used to indicate a matching degree between the factor word vector and the source word vector; The risk impact source corresponding to the minimum distance parameter of the risk factor is used as the category of the risk factor, and the risk factor is classified into the corresponding risk impact source to obtain the classification result.

5. The method according to claim 1, It is characterized in that The knowledge graph is centered on urban waterlogging disaster risk, including risk impact sources, risk factors, representation dimensions, and quantitative indicators. Based on the classification results and the waterlogging disaster risk data set, the urban waterlogging disaster risk knowledge graph is constructed, including: Based on the classification results, the knowledge relationship of urban waterlogging disaster risk is expressed as a four-layer structure of urban waterlogging disaster risk-risk impact source-risk factor-representation dimension-quantitative index, namely, urban waterlogging disaster risk-risk impact source, risk impact source-risk factor, risk factor-representation dimension, representation dimension-quantitative index; A graph database is used for storage and mapping expression. The first and last entity parts of each layer of the structure are stored and expressed as nodes, and the intermediate relationship parts are stored and expressed as edges, thus forming a graphical network structure and visual display of urban waterlogging disaster risk knowledge.

6. The method according to claim 1, It is characterized in that Perform knowledge reasoning on the knowledge graph, conduct waterlogging disaster risk assessment on the city to be assessed, and obtain the urban waterlogging disaster risk assessment result, including: Normalizing the quantitative indicator data in the knowledge graph to obtain normalized data; Performing hierarchical analysis on the knowledge graph, dividing it into a target layer, a criterion layer and an indicator layer, and obtaining the indicator weight corresponding to each layer; According to the normalized data and the corresponding indicator weights of the multiple layers, a waterlogging disaster risk assessment is performed on the city to be assessed to obtain a waterlogging disaster risk assessment result.

7. The method according to claim 6, It is characterized in that The waterlogging disaster risk assessment is performed on the city to be assessed based on the normalized data and the indicator weights corresponding to the multiple layers to obtain a waterlogging disaster risk assessment result, including: The waterlogging disaster risk assessment result A is determined using the following formula: Where A is the waterlogging disaster risk index of the city to be assessed, W i is the indicator weight corresponding to the criterion layer, ω ij is the indicator weight corresponding to the indicator layer, D ij is the normalized data, m is the number of indicators corresponding to the criterion layer, and n is the number of indicators corresponding to the indicator layer.

8. An assessment device for urban waterlogging disaster risk, It is characterized in that include: The acquisition module is used to obtain multi-source data on urban waterlogging disaster risks to be assessed; A processing module is used to extract knowledge from the multi-source data to obtain a waterlogging disaster risk data set, wherein the waterlogging disaster risk data set includes: multiple risk factors and their representation dimensions and quantitative indicators; The processing module is further used to classify the waterlogging disaster risk data set according to multiple risk impact sources to obtain a classification result, and construct a knowledge graph based on the classification result and the waterlogging disaster risk data set; An assessment module is used to conduct a waterlogging disaster risk assessment on the city to be assessed based on the knowledge graph to obtain a waterlogging disaster risk assessment result.

9. An urban waterlogging disaster risk assessment device, It is characterized in that include: Memory and processor; Wherein, the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for assessing urban waterlogging disaster risk as described in any one of claims 1-7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for assessing urban waterlogging disaster risk as described in any one of claims 1 to 7.

Images