A multi-region multi-disaster fusion early warning method, device, equipment and storage medium

Abstract

The application discloses a multi-region multi-disaster type fusion early warning method, comprising the following steps: dividing a target region into multiple region types according to disaster-pregnant space characteristics, configuring a corresponding disaster type importance priority for each region type, and constructing a fuzzy judgment matrix based on the disaster type importance priority; calculating the fuzzy judgment matrix by using a fuzzy analytic hierarchy process to obtain disaster type weights adapted to each region type; obtaining discrete early warning levels of each disaster type, converting the discrete early warning levels into a fuzzy vector by using a membership function, and constructing a membership matrix based on the fuzzy vector; performing fuzzy synthesis operation on the disaster type weights and the membership matrix to obtain a comprehensive membership vector, and determining a comprehensive early warning level of the target region and a membership degree distribution of each early warning level based on the comprehensive membership vector. The application can realize adaptive weight distribution and early warning level boundary fuzziness, quantize a multi-disaster type synergistic effect, and significantly improve the practicability of multi-disaster type early warning fusion.

Description

Technical Field

[0001] This invention relates to the field of disaster early warning technology, and in particular to a multi-regional, multi-hazard integrated early warning method, device, equipment, and storage medium. Background Technology

[0002] As a country frequently hit by natural disasters, my country often experiences the simultaneous occurrence of six major disasters—earthquakes, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires—in the same region and at the same time. These disasters often form a chain through a "trigger-amplification" mechanism, resulting in a non-linear increase in comprehensive risk, far exceeding the simple superposition of risks from a single disaster. Currently, the relevant authorities in various industries only issue single early warning information for the disasters under their jurisdiction. Due to the lack of uniformity in disaster-causing mechanisms, assessment models, and spatial units, the early warning information exhibits obvious fragmentation and heterogeneity, failing to accurately reflect the comprehensive risk intensity after multiple disasters occur simultaneously. This can easily lead to misjudgments in emergency decision-making and chaotic resource allocation. Meanwhile, the disaster-prone environments in different regions of my country, such as coastal areas, mountainous areas, plains, and seismic zones, vary significantly, and the dominant disaster types and risk patterns differ. Existing technologies have failed to deeply integrate regional disaster-prone characteristics with weight allocation, lacking a regionally adaptive weight system, resulting in insufficient regional adaptability of fusion early warning. Although the demand for multi-hazard fusion early warning is urgent, it is limited by issues such as inconsistent cross-industry standards, difficulty in quantifying disaster superposition mechanisms, and the dual constraints of regional differences and grade ambiguity. Mature multi-hazard early warning level fusion technology solutions have not yet been formed domestically and internationally. Currently, similar technologies are mainly simple weighted synthesis method, traditional hierarchical analysis method, and fuzzy comprehensive evaluation method, none of which have achieved an effective combination of fuzzy comprehensive evaluation and regionally differentiated weight system in multi-hazard early warning fusion.

[0003] Existing multi-hazard early warning fusion technologies suffer from three prominent shortcomings when applied to scenarios involving the fusion of multi-hazard early warning levels that consider spatial differences in hazard occurrence: First, they lack a regional adaptive weight allocation mechanism, generally employing uniform fixed weights without differentiated design based on the hazard-causing environment and dominant hazard types in different regions. This results in a mismatch between the fusion results and the actual risk pattern in the region, failing to meet the needs of regional prevention and control. Second, they fail to address the ambiguity of early warning levels, directly treating discrete levels as rigid values ​​in calculations. This leads to the loss of crucial risk information regarding the gradual transition between levels, making it difficult to accurately characterize the true risk intensity after the superposition of multiple hazards. Third, the fusion logic is simplistic, and the weight calculation method is rigid. Simple weighting cannot quantify the synergistic amplification effect between disasters. The traditional analytic hierarchy process is rigid and cannot express uncertainty. The fuzzy comprehensive evaluation rule is disconnected from the weight calculation process. The overall technical system is not designed for the concurrent characteristics of multiple hazards, making it difficult to achieve effective fusion of cross-domain, multi-hazard early warning information and unified comprehensive early warning level output. Summary of the Invention

[0004] This invention provides a multi-regional, multi-hazard fusion early warning method that can achieve adaptive weight allocation and ambiguity of early warning level boundaries, and quantify the synergistic effect of multiple hazards, significantly improving the practicality of multi-hazard early warning fusion.

[0005] In a first aspect, embodiments of the present invention provide a multi-regional, multi-hazard integrated early warning method, comprising: Based on the spatial characteristics of disaster-prone areas, the target area is divided into multiple area types, and a corresponding disaster importance priority is assigned to each area type. A fuzzy judgment matrix is ​​then constructed based on the disaster importance priority. The fuzzy judgment matrix is ​​calculated using the fuzzy hierarchical analysis method to obtain the disaster type weights adapted to each region type; The discrete warning levels for each type of disaster are obtained, and the discrete warning levels are converted into fuzzy vectors through a membership function. A membership matrix is ​​then constructed based on the fuzzy vectors. The disaster type weights and the membership degree matrix are combined using a fuzzy synthesis operation to obtain a comprehensive membership degree vector. Based on the comprehensive membership degree vector, the comprehensive early warning level of the target area and the membership degree distribution of each early warning level are determined.

[0006] Furthermore, the regional types include at least coastal areas, mountainous and hilly areas, plains, and earthquake zones; the disaster types include at least earthquake disasters, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires.

[0007] Furthermore, the fuzzy judgment matrix is ​​a triangular fuzzy reciprocal matrix, and each element in the matrix is ​​a triangular fuzzy number, which is composed of three values ​​in sequence: lower limit, median, and upper limit; wherein, the median is a 1-9 scale value determined based on the priority of the importance of the disaster type.

[0008] Furthermore, the fuzzy judgment matrix is ​​calculated using the fuzzy hierarchical analysis method to obtain disaster weights suitable for each regional type, including: Perform a fuzzy geometric mean operation on each row element of the fuzzy judgment matrix to obtain the fuzzy geometric mean of the corresponding row; The fuzzy geometric mean is converted into initial weights using the mean method; The initial weights are normalized to obtain disaster weights that are adapted to each region type.

[0009] Furthermore, the step of converting the discrete warning level into a fuzzy vector using a membership function includes: A Gaussian membership function is used, with the coded value of the warning level as input and the center value of the warning level as the function center, to transform the five-level discrete warning levels into a five-dimensional fuzzy vector; wherein, the five-level discrete warning levels include no warning, blue warning, yellow warning, orange warning and red warning.

[0010] Furthermore, the step of performing a fuzzy synthesis operation on the disaster type weights and the membership matrix includes: Perform a matrix composition operation between the weight vector and the membership matrix; The synthesis results are normalized to obtain the comprehensive membership vector.

[0011] Furthermore, determining the comprehensive early warning level of the target area based on the comprehensive membership vector includes: Based on the principle of maximum membership degree, the warning level corresponding to the maximum membership degree value in the comprehensive membership degree vector is determined as the comprehensive warning level.

[0012] Secondly, embodiments of the present invention provide a multi-regional, multi-hazard integrated early warning device, comprising: The fuzzy matrix construction module is used to divide the target area into multiple area types according to the spatial characteristics of disaster-prone areas, configure the corresponding disaster type importance priority for each area type, and construct a fuzzy judgment matrix based on the disaster type importance priority. The disaster type weight calculation module is used to calculate the fuzzy judgment matrix using the fuzzy hierarchical analysis method to obtain disaster type weights that are suitable for each region type. The early warning fuzzification processing module is used to obtain the discrete early warning level of each disaster type, convert the discrete early warning level into a fuzzy vector through a membership function, and construct a membership matrix based on the fuzzy vector; The integrated early warning determination module is used to perform fuzzy synthesis operation on the disaster type weight and the membership degree matrix to obtain a comprehensive membership degree vector, and to determine the comprehensive early warning level of the target area and the membership degree distribution of each early warning level based on the comprehensive membership degree vector.

[0013] Thirdly, embodiments of the present invention provide an electronic device, comprising: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the multi-regional multi-hazard fusion early warning method described in any of the first aspects above.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed, implements the multi-regional, multi-hazard fusion early warning method described in any of the first aspects above.

[0015] Compared with existing technologies, the multi-regional, multi-hazard fusion early warning method provided by this invention has the following advantages: The target area is divided into multiple regional types based on the spatial characteristics of disaster-prone areas; a corresponding disaster importance priority is assigned to each regional type; a fuzzy judgment matrix is ​​constructed based on the disaster importance priority; the fuzzy hierarchical analysis method is used to calculate the fuzzy judgment matrix to obtain disaster weights suitable for each regional type; the discrete early warning levels of each disaster type are obtained, and the discrete early warning levels are converted into fuzzy vectors using a membership function; a membership matrix is ​​constructed based on the fuzzy vectors; the disaster weights and the membership matrix are fuzzily synthesized to obtain a comprehensive membership vector; and the comprehensive early warning level of the target area and the membership distribution of each early warning level are determined based on the comprehensive membership vector. This invention achieves precise matching between weights and regional disaster characteristics by constructing a region-specific fuzzy matrix, fully preserves the fuzziness of the early warning level boundaries using a Gaussian membership function, and simultaneously outputs the comprehensive early warning level and the membership distribution of each level. This quantifies the possibility of risk transitions and significantly improves the scientific rigor, accuracy, and emergency decision support capabilities of multi-hazard fusion early warning. Attached Figure Description

[0016] To more clearly illustrate the technical features of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a multi-regional, multi-hazard integrated early warning method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the membership curve in one embodiment of a multi-regional, multi-hazard fusion early warning method provided by the present invention; Figure 3 This is a schematic diagram of the structure of a multi-regional, multi-hazard integrated early warning device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0021] Firstly, embodiments of the present invention provide a multi-regional, multi-hazard integrated early warning method, see [link to relevant documentation]. Figure 1 This is a flowchart illustrating an embodiment of a multi-regional, multi-hazard fusion early warning method provided by the present invention.

[0022] like Figure 1 As shown, the method includes the following steps: S1: Divide the target area into multiple area types according to the spatial characteristics of disaster-prone areas, configure the corresponding disaster type importance priority for each area type, and construct a fuzzy judgment matrix based on the disaster type importance priority; Specifically, based on the disaster-prone spatial characteristics of the target area, such as its inherent geographical, climatic, and geological features, it is divided into several regional types with different disaster risk patterns. A corresponding disaster importance priority is then assigned to each regional type. For example, see Table 1 below, which shows an example of prioritizing disaster importance for the four regional types: Table 1. Priority Ranking of the Importance of Four Types of Regional Disasters

[0023] Based on this priority, a fuzzy judgment matrix is ​​constructed for the corresponding region, so that the matrix can reflect the difference in contribution between the dominant and secondary disaster types in different regions, providing a basis for regional adaptive weight allocation.

[0024] S2: The fuzzy judgment matrix is ​​calculated using the fuzzy hierarchical analysis method to obtain the disaster type weights that are suitable for each region type; By processing the regionally differentiated fuzzy judgment matrix through fuzzy hierarchical analysis, the fuzzy judgment is quantitatively calculated, and the disaster weights that are adapted to the disaster patterns of each region are output. This results in higher weights for dominant disasters and correspondingly lower weights for secondary disasters, thereby achieving regional self-adaptation of the weights.

[0025] S3: Obtain the discrete warning level of each disaster type, convert the discrete warning level into a fuzzy vector through the membership function, and construct a membership matrix based on the fuzzy vector; By taking the discrete warning levels output by each type of disaster as input, the rigid discrete levels are converted into fuzzy vectors that can reflect the gradual change characteristics of risk using the membership function. Then, a membership matrix with a unified dimension is constructed using the fuzzy vectors of each type of disaster as elements, so as to realize the standardized and fuzzy expression of multi-hazard warning information.

[0026] S4: Perform a fuzzy synthesis operation on the disaster type weights and the membership degree matrix to obtain a comprehensive membership degree vector. Based on the comprehensive membership degree vector, determine the comprehensive early warning level of the target area and the membership degree distribution of each early warning level.

[0027] The regional adaptive disaster type weights are fused with the membership degree matrix to obtain a comprehensive membership degree vector. The comprehensive early warning level is determined based on the comprehensive membership degree vector, and the membership degree distribution of each early warning level is output simultaneously, thus fully reflecting the comprehensive risk level and level transition trend after the superposition of multiple disasters.

[0028] In summary, this invention constructs a region-specific fuzzy judgment matrix for different disaster-prone spaces, achieving precise matching between disaster weights and regional dominant disaster characteristics, effectively solving the problems of uniform weights and poor regional adaptability in traditional methods. By employing a membership function to transform discrete warning levels into fuzzy vectors, it can fully capture the boundary ambiguity and gradual transition characteristics between warning levels, making the comprehensive risk assessment results after multi-hazard superposition more consistent with the actual occurrence and development patterns of disasters. Simultaneously, it innovatively adopts a dual-dimensional result mode that simultaneously outputs the comprehensive warning level and the membership distribution of each level. This not only clarifies the current comprehensive risk level but also quantifies the possibility of risk transitioning to higher or lower levels, providing a more comprehensive and refined decision-making basis for emergency resource scheduling, tiered prevention and control, risk assessment, and early response, significantly enhancing the practicality, scientific value, and engineering application value of multi-hazard early warning fusion.

[0029] In one optional implementation, the region type includes at least coastal areas, mountainous and hilly areas, plains, and earthquake zones; the disaster type includes at least earthquake disasters, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires.

[0030] Specifically, based on the differences in regional disaster-prone environment, topography, and dominant disaster types, the geographic space of the target assessment is divided into four typical sub-regions. The regional types include at least: coastal areas, mountainous and hilly areas, plains, and seismic areas. These four types of regions can cover the disaster-prone spatial characteristics of major natural disaster-prone areas in my country and can adapt to the multi-hazard risk assessment needs under different geographic scenarios.

[0031] Meanwhile, based on the major types of natural disasters, six core disaster categories were selected, including at least earthquake disasters, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires. For ease of quantitative expression and calculation, these disaster categories are uniformly numbered, namely: earthquake Geology meteorological Floods and droughts ocean Forest fire ; This embodiment divides four typical regions and clarifies the composition of six core disaster types, which can accurately match the disaster-prone environment and dominant disaster risks in different regions, making the subsequent weight allocation and early warning integration more in line with the actual disaster occurrence patterns.

[0032] In one optional implementation, the fuzzy judgment matrix is ​​a triangular fuzzy reciprocal matrix, where each element is a triangular fuzzy number, consisting of a lower limit, a median, and an upper limit value in sequence; wherein the median is a 1-9 scale value determined based on the priority of the disaster type importance.

[0033] Specifically, the fuzzy judgment matrix is ​​implemented using a triangular fuzzy reciprocal matrix to adapt to the needs of regionally differentiated weight allocation and the fuzzy expression of expert judgment. For four types of regions—coastal areas, mountainous and hilly areas, plains, and seismic zones—sixth-order triangular fuzzy reciprocal matrices are constructed, denoted as: ; in, It is a triangular fuzzy reciprocal matrix, with six rows and six columns, corresponding one-to-one with the six types of disasters. Let be the element in the i-th row and j-th column of the matrix, representing the fuzzy quantization value of the importance of the i-th disaster type relative to the j-th disaster type.

[0034] Each matrix element Represented using triangular fuzzy numbers, in the form of: ; in, This represents the lower limit of the triangular fuzzy number, signifying the minimum possible value for the importance level. The median represents the most likely value for importance, determined by a 1-9 scale corresponding to the disaster importance priority. This is the upper limit value, representing the maximum possible value for the importance level.

[0035] By using triangular fuzzy numbers, we can retain the quantitative logic of the 1-9 scale while also reflecting the fuzziness and uncertainty of expert judgment.

[0036] It should be noted that the triangular fuzzy reciprocal matrix strictly follows the rules of reflexivity and reciprocity: the diagonal elements of the matrix satisfy... This indicates that elements of the same type are considered equally important, and off-diagonal elements satisfy a reciprocal mapping relationship, i.e. ,For example ,but This ensures that the logic for comparing the importance of different disaster types remains consistent.

[0037] At the same time, the 1-9 scale is mapped to triangular fuzzy numbers according to preset rules: the median is determined by disaster type priority. ,when Lower limit ,when Lower limit ;when Time limit ,when Time limit For example, in coastal areas, marine disasters are slightly more important than meteorological disasters, with a scale of 3 and corresponding fuzzy numbers (2,3,4); in mountainous areas, geological disasters are significantly more important than forest fires, with a scale of 5 and corresponding fuzzy numbers (4,5,6); in earthquake-prone areas, earthquake disasters are extremely important than marine disasters, with a scale of 9 and corresponding fuzzy numbers (8,9,9).

[0038] Each regional matrix is ​​designed differently based on regional priority, with higher scaling values ​​for the rows containing the dominant disaster type, so that the weight distribution matches the regional disaster characteristics.

[0039] For example, taking the inland plain as a typical assessment area, the construction process of the triangular fuzzy reciprocal matrix is ​​explained in detail. The core risk characteristics of the inland plain are that floods and droughts are the most prevalent, followed by meteorological disasters, and marine disasters have the least impact. In this embodiment, based on the priority of disaster importance and the 1-9 scale rule, a 6×6 triangular fuzzy reciprocal matrix matching the disaster-prone characteristics of the region is constructed. Each row of the matrix corresponds to six types of disasters: the first row is earthquake disaster B1, the second row is geological disaster B2, the third row is meteorological disaster B3, the fourth row is floods and droughts B4, the fifth row is marine disaster B5, and the sixth row is forest and grassland fire B6. The constructed triangular fuzzy reciprocal matrix is ​​as follows: ; Among them, flood and drought disaster B4, which is the dominant disaster type, is located in the fourth row. This row has a significantly higher scale than other disaster types. For example, flood and drought disaster is extremely important to marine disaster B5, with a corresponding triangular fuzzy number of (6,8,9). Flood and drought disaster is slightly important to meteorological disaster B3, with a corresponding triangular fuzzy number of (1,2,3). Marine disaster B5, which is the least important disaster type, is located in the fifth row. This row takes the minimum scale interval for all other disaster types. For example, the triangular fuzzy number of marine disaster is (1 / 9,1 / 8,1 / 6) relative to flood and drought disaster B4. The overall matrix satisfies the constraints of reflexivity, reciprocity, and regional priority. The weight allocation logic is completely matched with the disaster characteristics of inland plains.

[0040] This embodiment constructs a region-specific triangular fuzzy reciprocal matrix, which can achieve fuzzification and differentiated quantification of the importance of disaster types, taking into account the uncertainty of expert judgment and regional risk characteristics, improving the rationality and adaptability of weight calculation, and providing a reliable matrix foundation for the accurate solution of subsequent regional adaptive disaster weights.

[0041] In one optional implementation, the step of using fuzzy hierarchical analysis to calculate the fuzzy judgment matrix to obtain disaster type weights suitable for each region type includes: Perform a fuzzy geometric mean operation on each row element of the fuzzy judgment matrix to obtain the fuzzy geometric mean of the corresponding row; The fuzzy geometric mean is converted into initial weights using the mean method; The initial weights are normalized to obtain disaster weights that are adapted to each region type.

[0042] Specifically, firstly, a fuzzy geometric mean operation is performed on the i-th row of the triangular fuzzy reciprocal matrix to aggregate the comprehensive judgments of experts on the relative importance of the i-th disaster type, thereby obtaining the fuzzy geometric mean corresponding to that row. The calculation formula is: ; in, , respectively, are the lower limit, median, and upper limit of the element in the i-th row and j-th column of the matrix, where j is the disaster type number, ranging from 1 to 6.

[0043] Secondly, defuzzification and normalization are performed, and the mean method is used to calculate the fuzzy geometric mean. The corresponding triangular fuzzy numbers are converted into definite initial weights, and the calculation formula is as follows: ; in, Let be the lower limit, median, and upper limit of the fuzzy geometric mean of the i-th row, respectively. Let be the initial weight of the i-th disaster type.

[0044] The initial weights are then normalized so that the sum of the weights of all disaster types is 1, thus obtaining the final weight of the i-th disaster type in the current region. The calculation formula is: ; in, This is the sum of the initial weights for the six types of disasters.

[0045] To ensure that the weighting judgments are logically consistent, this embodiment adds a strict consistency check step: first, the triangular fuzzy matrix is ​​converted into a normal analytic hierarchy process (AHP) matrix A (matrix elements...). Then calculate the largest eigenvalue of the matrix. The consistency index (CI) and the consistency ratio (CR) are calculated using the following formulas: ; ; Where n is the matrix order, in this embodiment n=6, and RI is the random consistency index (takes a value of 1.24 when n=6), when the following conditions are met... If the consistency check passes, the adaptive disaster type weight vector for the region is output. If the conditions are not met, the triangular fuzzy reciprocal matrix is ​​readjusted until the test passes.

[0046] For example, based on the aforementioned regional adaptive disaster weighting solution method, using the 6×6 triangular fuzzy reciprocal matrix of the inland plain region in the example as input, the process sequentially undergoes three core operations: fuzzy geometric mean operation to aggregate expert judgments, mean method defuzzification to determine initial weights, and normalization processing to make the sum of weights equal to 1. The final weight obtained is W=[0.185,0.114,0.210,0.373,0.032,0.087]. This weight calculation result aligns with the inland plain's pattern of "dominantly flood and drought disasters, with marine disasters being the weakest." The disaster-prone characteristics are highly consistent, and the consistency test yielded a CR of 0.0714, satisfying the logical constraint requirement of CR≤0.1, ensuring that the weight judgment is consistent. From the weight matrix distribution, flood and drought disasters have the highest weight (0.373), fully highlighting their dominant disaster status; marine disasters have the lowest weight (0.032), which is consistent with the geographical attributes of inland areas; the weights of other disaster types are distributed in a reasonable gradient according to the actual risk impact, accurately matching the regional disaster characteristics, effectively verifying the effectiveness and adaptability of this method in solving regional multi-hazard weights.

[0047] This embodiment, through a complete process of fuzzy geometric averaging, defuzzification, normalization, and consistency verification, can reliably transform the fuzzy judgment matrix into adaptive disaster weights that match the regional disaster-prone characteristics. It retains the fuzzy characteristics of expert judgment while ensuring that the weight results are rigorous, reasonable, and free of logical contradictions, providing an accurate and stable weight foundation for subsequent multi-disaster early warning fuzzy fusion calculations.

[0048] In one optional implementation, the step of converting the discrete warning level into a fuzzy vector using a membership function includes: A Gaussian membership function is used, with the coded value of the warning level as input and the center value of the warning level as the function center, to transform the five-level discrete warning levels into a five-dimensional fuzzy vector; wherein, the five-level discrete warning levels include no warning, blue warning, yellow warning, orange warning and red warning.

[0049] Specifically, a set of warning levels is defined, with the five warning levels sequentially coded as 0, 1, 2, 3, and 4, corresponding to no warning, blue warning, yellow warning, orange warning, and red warning, respectively. Discrete warning level data for six types of disasters are obtained within each assessment unit. Using the level code value as input, the degree of membership to each standard warning level is calculated using a Gaussian membership function. The function expression is as follows: ; Where x represents the original discrete early warning level for a single disaster, with a value ranging from 0 to 4. This is the center value for the v-th warning level, and it is consistent with the warning level code value. The width coefficient of the Gaussian function is taken in this embodiment. , Let x be the membership degree of discrete level x relative to the v-th warning level.

[0050] Using the Gaussian membership function described above, any original discrete warning level can be converted into a fuzzy vector containing five components, which correspond to its membership degree to the five warning levels: no warning, blue, yellow, orange, and red, respectively, thus realizing the transformation from rigid discrete numerical values ​​to flexible fuzzy probabilities.

[0051] For example, see Figure 2 The diagram shows a membership function curve. The horizontal axis represents the warning level code value (0-4), and the vertical axis represents the membership value (0-1). The five Gaussian curves are symmetrically distributed around the values ​​0, 1, 2, 3, and 4. Figure 2The following characteristics can be observed: First, each membership function curve is bell-shaped, centered on the corresponding warning level code value. The membership degree at the center is 1.000, and it decreases exponentially with the increase of the level interval on both sides, which is consistent with the typical distribution characteristics of Gaussian function. Second, there is a significant overlap between adjacent levels. For example, at code value 1 (blue warning), it is simultaneously affected by the no warning curve and the yellow warning curve. The membership degrees of the three at code value 1 are 0.707, 1.000, and 0.707, respectively, indicating that the blue warning has a fuzzy characteristic of bidirectional transition to no warning and yellow warning. Third, the membership degree between levels with an interval of two or more levels decreases rapidly. For example, the membership degree of blue warning (code 1) to orange warning (code 3) is only 0.249, and the membership degree to red warning (code 4) is only 0.044, which is close to zero. This shows that the Gaussian membership function effectively suppresses the cross interference of distant levels while retaining the transition information between adjacent levels, taking into account both fuzziness and distinguishability. Taking a blue alert (level code 1) as an example, a complete calculation yields a fuzzy vector of [0.707, 1.000, 0.707, 0.249, 0.044]. This vector clearly shows that although the blue alert is primarily associated with the blue level (membership degree 1.000), it also has a high membership degree to the adjacent no alert and yellow alert (both 0.707), while its membership degree to orange and red alerts is extremely low (0.249 and 0.044, respectively), thus fully characterizing the gradual transition features of the blue alert level boundary. Similarly, taking a yellow alert (level code 2) as an example, its fuzzy vector is [0.249, 0.707, 1.000, 0.707, 0.249], which is symmetrically distributed, reflecting the characteristic of yellow alert as an intermediate level transitioning evenly to both sides; taking a red alert (level code 4) as an example, its fuzzy vector is [0.004, 0.044, 0.249, 0.707, 1.000], with the membership degree decreasing sequentially towards lower levels, reflecting the focusing and unidirectional decay characteristics of high-risk levels.

[0052] This embodiment uses Gaussian membership functions to fuzzify discrete early warning levels, which can completely preserve the fuzzy transition information of the early warning level boundaries, avoid the loss of risk details caused by traditional rigid numerical calculations, and make the risk assessment after multiple disasters superimposed more in line with the actual disaster evolution law, significantly improving the accuracy and reliability of the comprehensive early warning results.

[0053] In one optional implementation, the step of performing a fuzzy synthesis operation between the disaster type weights and the membership matrix includes: Perform a matrix composition operation between the weight vector and the membership matrix; The synthesis results are normalized to obtain the comprehensive membership vector.

[0054] Specifically, the five-dimensional fuzzy vectors corresponding to the six types of disasters are arranged in rows to form a 6-row, 5-column membership matrix M. Each row corresponds to a type of disaster, and each column corresponds to one of the following levels: no warning, blue warning, yellow warning, orange warning, and red warning. Each element in the matrix represents the degree of membership of the corresponding disaster type under that warning level.

[0055] For example, the membership matrix takes the following form: ; The first to sixth rows of the matrix correspond to fuzzy vectors for earthquake disasters, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires, respectively. Each vector fully preserves the fuzzy transition characteristics between warning levels, which can truly reflect the gradual distribution of single-disaster risks between different levels.

[0056] Next, fuzzy synthesis is performed, multiplying the disaster weight vector W with the membership matrix M to obtain the preliminary integrated membership vector S. The calculation formula is as follows: ; Where W is a 1×6 regional adaptive disaster type weight vector, M is a 6×5 membership matrix, and S is a 1×5 preliminary comprehensive membership vector.

[0057] To make the comprehensive risk results quantifiable and comparable, the composite results are normalized, unifying the comprehensive membership vector to the 0-1 interval and ensuring that the sum of all components is 1. The normalization formula is as follows: ; in, To initially synthesize the components corresponding to the v-th level in the membership vector, This represents the sum of the initial membership degrees corresponding to the five warning levels. The final comprehensive membership degree of the v-th level after normalization is determined by all... This constitutes the final comprehensive membership vector.

[0058] This embodiment achieves the organic integration of multi-hazard weights and fuzzy early warning information through matrix synthesis operations, and uses normalization processing to ensure the standardization and comparability of the results. It can scientifically quantify the comprehensive risk distribution after the superposition of multiple hazards, and fully retain the transitional correlation characteristics between each level, providing stable and reliable data support for the accurate determination of the comprehensive early warning level.

[0059] In one optional implementation, determining the comprehensive early warning level of the target area based on the comprehensive membership vector includes: Based on the principle of maximum membership degree, the warning level corresponding to the maximum membership degree value in the comprehensive membership degree vector is determined as the comprehensive warning level.

[0060] Specifically, based on the normalized comprehensive membership vector, the level is determined according to the principle of maximum membership. The calculation formula is as follows: ; in, The final comprehensive early warning level code, This is a warning level code, with values ​​of 0, 1, 2, 3, and 4, corresponding to no warning, blue warning, yellow warning, orange warning, and red warning, respectively. This represents the comprehensive membership degree corresponding to the v-th warning level after normalization.

[0061] This invention outputs a comprehensive early warning level, and also provides complete output... The membership distribution vector formed by this structure allows decision-makers not only to know the current dominant risk level, but also to intuitively judge the trend and possibility of risk transitioning to adjacent levels.

[0062] For example, the comprehensive membership vector of the unit to be evaluated is [0.070, 0.195, 0.297, 0.270, 0.168]. Based on the principle of maximum membership, it is determined to be a yellow warning. At the same time, the distribution of membership values ​​can be used to determine that the risk of this unit is close to the critical state of transitioning from yellow to orange warning, and the risk situation is operating at a high level.

[0063] This embodiment adopts the maximum membership principle to ensure the objectivity and uniqueness of the early warning level determination. At the same time, it retains complete risk distribution information through a dual-dimensional output mode, which can effectively support emergency command personnel to identify the gradual trend of risk changes and predict the possibility of level jumps, so as to achieve more refined and forward-looking disaster risk assessment and emergency decision-making.

[0064] Secondly, embodiments of the present invention provide a multi-regional, multi-hazard integrated early warning device, see [link to relevant documentation]. Figure 3 This is a schematic diagram of the structure of an embodiment of a multi-regional, multi-hazard integrated early warning device provided by the present invention.

[0065] like Figure 3 As shown, the device includes: The fuzzy matrix construction module 21 is used to divide the target area into multiple area types according to the disaster-prone spatial characteristics, configure the corresponding disaster type importance priority for each area type, and construct a fuzzy judgment matrix based on the disaster type importance priority. The disaster type weight calculation module 22 is used to calculate the fuzzy judgment matrix using the fuzzy hierarchical analysis method to obtain the disaster type weights adapted to each region type. The early warning fuzzification processing module 23 is used to obtain the discrete early warning level of each disaster type, convert the discrete early warning level into a fuzzy vector through a membership function, and construct a membership matrix based on the fuzzy vector; The fusion early warning determination module 24 is used to perform fuzzy synthesis operation on the disaster type weight and the membership degree matrix to obtain a comprehensive membership degree vector, and determine the comprehensive early warning level of the target area and the membership degree distribution of each early warning level based on the comprehensive membership degree vector.

[0066] In one optional implementation, the region type includes at least coastal areas, mountainous and hilly areas, plains, and earthquake zones; the disaster type includes at least earthquake disasters, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires.

[0067] In one optional implementation, the fuzzy judgment matrix is ​​a triangular fuzzy reciprocal matrix, where each element is a triangular fuzzy number, consisting of a lower limit, a median, and an upper limit value in sequence; wherein the median is a 1-9 scale value determined based on the priority of the disaster type importance.

[0068] In one optional implementation, the step of using fuzzy hierarchical analysis to calculate the fuzzy judgment matrix to obtain disaster type weights suitable for each region type includes: Perform a fuzzy geometric mean operation on each row element of the fuzzy judgment matrix to obtain the fuzzy geometric mean of the corresponding row; The fuzzy geometric mean is converted into initial weights using the mean method; The initial weights are normalized to obtain disaster weights that are adapted to each region type.

[0069] In one optional implementation, the step of converting the discrete warning level into a fuzzy vector using a membership function includes: A Gaussian membership function is used, with the coded value of the warning level as input and the center value of the warning level as the function center, to transform the five-level discrete warning levels into a five-dimensional fuzzy vector; wherein, the five-level discrete warning levels include no warning, blue warning, yellow warning, orange warning and red warning.

[0070] In one optional implementation, the step of performing a fuzzy synthesis operation between the disaster type weights and the membership matrix includes: Perform a matrix composition operation between the weight vector and the membership matrix; The synthesis results are normalized to obtain the comprehensive membership vector.

[0071] In one optional implementation, determining the comprehensive early warning level of the target area based on the comprehensive membership vector includes: Based on the principle of maximum membership degree, the warning level corresponding to the maximum membership degree value in the comprehensive membership degree vector is determined as the comprehensive warning level.

[0072] It should be noted that the multi-regional multi-hazard fusion early warning device provided in this embodiment of the invention is used to execute all the process steps of the multi-regional multi-hazard fusion early warning method in the above embodiment. The working principle and beneficial effects of the two are one-to-one, so they will not be described again.

[0073] Thirdly, embodiments of the present invention provide an electronic device, see [link to previous document]. Figure 4 The diagram shown is a structural schematic of an electronic device provided in an embodiment of the present invention.

[0074] like Figure 4 As shown, the device includes: Memory 31 is used to store computer programs; Processor 32 is used to execute the computer program; When the processor 32 executes the computer program, it implements the multi-regional, multi-hazard fusion early warning method as described in any of the above embodiments.

[0075] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 32 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0076] The processor 32 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0077] The memory 31 can be used to store the computer programs and / or modules. The processor 32 implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory 31 and calling the data stored in the memory 31. The memory 31 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0078] It should be noted that the aforementioned electronic devices include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 4 The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device. It may include more components than shown in the diagram, or combine certain components, or use different components.

[0079] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed, implements the multi-regional, multi-hazard fusion early warning method described in any of the above embodiments.

[0080] It should be understood that the implementation of all or part of the processes in the above-mentioned multi-regional multi-hazard fusion early warning method can also be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above-mentioned multi-regional multi-hazard fusion early warning method. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0081] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. It should be noted that, for those skilled in the art, several equivalent obvious modifications and / or equivalent substitutions can be made without departing from the technical principles of the present invention, and these obvious modifications and / or equivalent substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A multi-regional, multi-hazard integrated early warning method, characterized in that, include: Based on the spatial characteristics of disaster-prone areas, the target area is divided into multiple area types, and a corresponding disaster importance priority is assigned to each area type. A fuzzy judgment matrix is ​​then constructed based on the disaster importance priority. The fuzzy judgment matrix is ​​calculated using the fuzzy hierarchical analysis method to obtain the disaster type weights adapted to each region type; The discrete warning levels for each type of disaster are obtained, and the discrete warning levels are converted into fuzzy vectors through a membership function. A membership matrix is ​​then constructed based on the fuzzy vectors. The disaster type weights and the membership degree matrix are combined using a fuzzy synthesis operation to obtain a comprehensive membership degree vector. Based on the comprehensive membership degree vector, the comprehensive early warning level of the target area and the membership degree distribution of each early warning level are determined.

2. The multi-regional, multi-hazard integrated early warning method as described in claim 1, characterized in that, The regional types include at least coastal areas, mountainous and hilly areas, plains, and earthquake zones; the disaster types include at least earthquake disasters, geological disasters, meteorological disasters, floods and droughts, marine disasters, and forest and grassland fires.

3. The multi-regional, multi-hazard integrated early warning method as described in claim 1, characterized in that, The fuzzy judgment matrix is ​​a triangular fuzzy reciprocal matrix, and each element in the matrix is ​​a triangular fuzzy number, which is composed of three values ​​in sequence: lower limit, median, and upper limit; wherein, the median is a 1-9 scale value determined based on the priority of the importance of the disaster type.

4. The multi-regional, multi-hazard integrated early warning method as described in claim 1, characterized in that, The fuzzy judgment matrix is ​​calculated using the fuzzy hierarchical analysis method to obtain disaster weights suitable for each regional type, including: Perform a fuzzy geometric mean operation on each row element of the fuzzy judgment matrix to obtain the fuzzy geometric mean of the corresponding row; The fuzzy geometric mean is converted into initial weights using the mean method; The initial weights are normalized to obtain disaster weights that are adapted to each region type.

5. The multi-regional, multi-hazard integrated early warning method as described in claim 1, characterized in that, The process of converting the discrete warning level into a fuzzy vector using a membership function includes: A Gaussian membership function is used, with the coded value of the warning level as input and the center value of the warning level as the function center, to transform the five-level discrete warning levels into a five-dimensional fuzzy vector; wherein, the five-level discrete warning levels include no warning, blue warning, yellow warning, orange warning and red warning.

6. The multi-regional, multi-hazard integrated early warning method as described in claim 1, characterized in that, The step of performing a fuzzy synthesis operation between the disaster type weights and the membership matrix includes: Perform a matrix composition operation between the weight vector and the membership matrix; The synthesis results are normalized to obtain the comprehensive membership vector.

7. The multi-regional, multi-hazard integrated early warning method as described in claim 1, characterized in that, The determination of the comprehensive early warning level of the target area based on the comprehensive membership vector includes: Based on the principle of maximum membership degree, the warning level corresponding to the maximum membership degree value in the comprehensive membership degree vector is determined as the comprehensive warning level.

8. A multi-regional, multi-hazard integrated early warning device, characterized in that, include: The fuzzy matrix construction module is used to divide the target area into multiple area types according to the spatial characteristics of disaster-prone areas, configure the corresponding disaster type importance priority for each area type, and construct a fuzzy judgment matrix based on the disaster type importance priority. The disaster type weight calculation module is used to calculate the fuzzy judgment matrix using the fuzzy hierarchical analysis method to obtain disaster type weights that are suitable for each region type. The early warning fuzzification processing module is used to obtain the discrete early warning level of each disaster type, convert the discrete early warning level into a fuzzy vector through a membership function, and construct a membership matrix based on the fuzzy vector; The integrated early warning determination module is used to perform fuzzy synthesis operation on the disaster type weight and the membership degree matrix to obtain a comprehensive membership degree vector, and to determine the comprehensive early warning level of the target area and the membership degree distribution of each early warning level based on the comprehensive membership degree vector.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the multi-regional multi-hazard fusion early warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the multi-regional, multi-hazard fusion early warning method as described in any one of claims 1 to 7.

Images