自然灾害综合风险评估方法、装置、计算机设备及存储介质

Natural disaster comprehensive risk assessment method and device, computer equipment and storage medium

文档序号：8919 发布日期：2021-09-17 浏览：28次中文

1. The natural disaster comprehensive risk assessment method is characterized by comprising the following steps:

extracting characteristics of each evaluation index based on an artificial intelligence algorithm to obtain evaluation characteristics;

performing model training through a machine learning algorithm according to the evaluation characteristics to obtain an evaluation model;

comprehensively considering the connectivity among single disaster species and the vulnerability of a disaster bearing body according to the evaluation model to obtain a comprehensive risk evaluation result;

and carrying out risk zoning according to the comprehensive risk assessment result.

2. The method for comprehensive risk assessment of natural disasters according to claim 1, wherein the model training by machine learning algorithm according to the evaluation features to obtain an assessment model comprises:

training a convolutional neural network, a cyclic neural network, a tree model and an ensemble learning model by using the evaluation features to obtain a plurality of trained models;

calculating evaluation indexes of the trained multiple models to obtain an evaluation result;

and fusing the plurality of models after training in a decision-making level by using the evaluation result to obtain an evaluation model.

3. The method for comprehensive risk assessment of natural disasters according to claim 2, wherein the extracting features for each evaluation index based on artificial intelligence algorithm to obtain evaluation features comprises:

determining the relation of multiple disaster types according to the extracted information, and taking the determined relation of the multiple disaster types as an attribute;

the extracted information and attributes are combined to form an evaluation feature.

4. The method for evaluating the comprehensive risk of natural disasters according to claim 3, wherein the obtaining of the information about single-disaster risk, vulnerability of disaster-bearing body, and disaster prevention and reduction capability based on the artificial intelligence algorithm to obtain the extracted information comprises:

comprehensively analyzing vulnerability and disaster prevention and reduction capability of a disaster bearing body, classifying and sorting according to different data formats, and extracting and mining characteristics of the sorted data with different formats;

wherein, the extracted information comprises the risk levels of all the geographic units and the characteristics of the disaster-bearing body; the disaster-bearing body characteristics comprise a disaster-bearing body exposure characteristic, a vulnerability characteristic and a disaster prevention and reduction capability characteristic.

5. The method for comprehensive risk assessment of natural disasters according to claim 4, wherein the comprehensive analysis of vulnerability and disaster prevention and reduction capability of a disaster-bearing body, classification and arrangement according to different data formats, and feature extraction and mining of the well-organized data with different formats comprises:

respectively obtaining the exposure characteristics of the disaster-bearing body according to population density, infrastructure density and arable area occupation ratio in the research unit;

respectively obtaining vulnerability characteristics according to the population attribute distribution condition, the infrastructure firmness degree and the cultivated land area gradient in the research unit;

and determining the disaster prevention and reduction capability characteristics based on an expert scoring method according to the medical level, the per capita income and the traffic facilities in the research unit.

6. The method according to claim 4, wherein the disaster-bearing body includes population, infrastructure, and cultivated land.

7. The method according to claim 3, wherein the multiple disaster relations include at least one of a causal relation and an antagonistic relation.

8. Natural disasters synthesizes risk assessment device, its characterized in that includes:

the characteristic extraction unit is used for extracting characteristics of each evaluation index based on an artificial intelligence algorithm so as to obtain evaluation characteristics;

the model training unit is used for carrying out model training through a machine learning algorithm according to the evaluation characteristics so as to obtain an evaluation model;

the evaluation unit is used for comprehensively considering the connectivity among the single disaster species and the vulnerability of the disaster bearing body according to the evaluation model so as to obtain a comprehensive risk evaluation result;

and the risk zoning unit is used for carrying out risk zoning according to the comprehensive risk assessment result.

9. A computer device, characterized in that the computer device comprises a memory, on which a computer program is stored, and a processor, which when executing the computer program implements the method according to any of claims 1 to 7.

10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Background

The natural disaster comprehensive risk assessment refers to the comprehensive assessment of the total risk under the influence of various disaster-causing factors in an area by adopting a certain theory and method. The natural disaster comprehensive risk assessment mainly aims to master the overall risk condition of an area for interest correlators or decision makers, make the area, utilize planning and arrange services such as disaster prevention and reduction funds, and the like, so as to achieve the purpose of effectively reducing the disaster risk. The natural disaster comprehensive risk assessment is based on single disaster risk research, but the assessment mode is more complex due to the problems of multiple disaster factors and multiple fragility.

At present, there are many methods for comprehensive risk assessment of natural disasters, wherein the methods have the following influences: DRI (natural Disaster Risk Index, Disaster Risk Index) multi-Disaster Risk assessment, hotspot multi-Disaster Risk assessment, ESPON comprehensive Risk assessment, JRC comprehensive Risk assessment, level weighting model, namely, hierarchical analysis and other assessments, transcendental probability comprehensive assessment model assessment and the like, wherein the models are different in the aspects of application area, assessment unit, assessment of Disaster seeds, Risk indexes, method characteristics and the like, and have different scales in the world, country, city and the like in the area; seen from the evaluation unit, there are cities, counties, minimum administrative units and grid units with different scales; the risk indexes include population, agriculture, construction, direct economy and comprehensive indexes; from the disaster perspective, there are multiple disaster-causing factors such as geological disasters and meteorological disasters. However, most of these models have poor interpretability, do not consider vulnerability and exposure of disaster-bearing objects, have insufficient input information, and do not consider relationships and interactions between disaster-causing factors.

Therefore, it is necessary to design a new method, which has strong interpretability of risk assessment, considers vulnerability and exposition of disaster-bearing bodies, has sufficient input information of models, and considers the relationship and interaction between disaster-causing factors.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provides a natural disaster comprehensive risk assessment method, a natural disaster comprehensive risk assessment device, computer equipment and a storage medium.

In order to achieve the purpose, the invention adopts the following technical scheme: the natural disaster comprehensive risk assessment method comprises the following steps:

extracting characteristics of each evaluation index based on an artificial intelligence algorithm to obtain evaluation characteristics;

performing model training through a machine learning algorithm according to the evaluation characteristics to obtain an evaluation model;

and carrying out risk zoning according to the comprehensive risk assessment result.

The further technical scheme is as follows: the model training is performed through a machine learning algorithm according to the evaluation features to obtain an evaluation model, and the method comprises the following steps:

training a convolutional neural network, a cyclic neural network, a tree model and an ensemble learning model by using the evaluation features to obtain a plurality of trained models;

calculating evaluation indexes of the trained multiple models to obtain an evaluation result;

and fusing the plurality of models after training in a decision-making level by using the evaluation result to obtain an evaluation model.

The further technical scheme is as follows: the method for extracting characteristics of each evaluation index based on the artificial intelligence algorithm to obtain the evaluation characteristics comprises the following steps:

determining the relation of multiple disaster types according to the extracted information, and taking the determined relation of the multiple disaster types as an attribute;

the extracted information and attributes are combined to form an evaluation feature.

The further technical scheme is as follows: the method for acquiring the information of single disaster type dangerousness, the vulnerability of a disaster bearing body and the disaster prevention and reduction capacity based on the artificial intelligence algorithm to obtain the extracted information comprises the following steps:

The further technical scheme is as follows: the comprehensive analysis of vulnerability and disaster prevention and reduction capability of a disaster-bearing body, the classification and the arrangement according to different data formats and the feature extraction and mining of the well-arranged data with different formats comprise the following steps:

respectively obtaining the exposure characteristics of the disaster-bearing body according to population density, infrastructure density and arable area occupation ratio in the research unit;

The further technical scheme is as follows: the disaster-bearing body comprises population, infrastructure and cultivated land.

The further technical scheme is as follows: the multiple disaster relations comprise at least one of a causal relation and an antagonistic relation.

The invention also provides a natural disaster comprehensive risk assessment device, which comprises:

the characteristic extraction unit is used for extracting characteristics of each evaluation index based on an artificial intelligence algorithm so as to obtain evaluation characteristics;

the model training unit is used for carrying out model training through a machine learning algorithm according to the evaluation characteristics so as to obtain an evaluation model;

and the risk zoning unit is used for carrying out risk zoning according to the comprehensive risk assessment result.

The invention also provides computer equipment which comprises a memory and a processor, wherein the memory is stored with a computer program, and the processor realizes the method when executing the computer program.

The invention also provides a storage medium storing a computer program which, when executed by a processor, is operable to carry out the method as described above.

Compared with the prior art, the invention has the beneficial effects that: the method extracts the characteristics of the single disaster danger, the vulnerability of the disaster bearing body and the disaster bearing capacity based on the artificial intelligence algorithm, determines the relationship of multiple disaster types, trains the model by using the extracted information, comprehensively considers the relationship between the single disaster types and the risk assessment of the vulnerability of the disaster bearing body by using the trained model, divides the risk, realizes strong interpretability of the risk assessment, considers the vulnerability and the exposure of the disaster bearing body, inputs of the model comprise the single disaster danger, the vulnerability of the disaster bearing body, the disaster bearing capacity and the relationship between the multiple disaster types, has sufficient input information of the model, and considers the relationship and the interaction between disaster causing factors to be more comprehensive.

The invention is further described below with reference to the accompanying drawings and specific embodiments.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention;

fig. 3 is a sub-flow diagram of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention;

fig. 4 is a sub-flow diagram of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention;

fig. 5 is a sub-flow diagram of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention;

fig. 6 is a sub-flow diagram of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention;

fig. 7 is a schematic diagram of a multi-disaster relationship provided in an embodiment of the present invention;

fig. 8 is a schematic block diagram of a natural disaster comprehensive risk assessment device according to an embodiment of the present invention;

fig. 9 is a schematic block diagram of a feature extraction unit of a natural disaster comprehensive risk assessment apparatus according to an embodiment of the present invention;

fig. 10 is a schematic block diagram of an information extraction subunit of the natural disaster comprehensive risk assessment apparatus according to the embodiment of the present invention;

fig. 11 is a schematic block diagram of an excavation module of the natural disaster comprehensive risk assessment apparatus according to the embodiment of the present invention;

fig. 12 is a schematic block diagram of a model training unit of a natural disaster comprehensive risk assessment device according to an embodiment of the present invention;

FIG. 13 is a schematic block diagram of a computer device provided by an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention. Fig. 2 is a schematic flowchart of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention. The natural disaster comprehensive risk assessment method is applied to a server. The server performs data interaction with the sensor, the sensor can be used for collecting each evaluation index, the server performs feature extraction, model training and evaluation, and finally the result of the risk division can be sent to the terminal.

Fig. 2 is a schematic flow chart of a natural disaster comprehensive risk assessment method according to an embodiment of the present invention. As shown in fig. 2, the method includes the following steps S110 to S140.

And S110, extracting characteristics of each evaluation index based on an artificial intelligence algorithm to obtain evaluation characteristics.

In this embodiment, the evaluation features include the risk, vulnerability of the disaster-bearing body, information of disaster prevention and reduction capability, and the relationship of multiple kinds of disasters. Wherein the danger information comprises meteorological disasters, geological disasters, flood and drought disasters, earthquake disasters and forest fires; the vulnerability information of the disaster-bearing body comprises exposure characteristics and vulnerability characteristics, wherein the exposure characteristics comprise population density, road network density, building density and land reclamation rate, and the vulnerability characteristics comprise sex proportion, age structure and old crisis; the information of the disaster prevention and reduction capability comprises the per-capita income, traffic facilities and medical level.

In an embodiment, referring to fig. 3, the step S110 may include steps S111 to S113.

And S111, acquiring information of single disaster danger, vulnerability of a disaster bearing body and disaster prevention and reduction capacity based on an artificial intelligence algorithm to obtain extracted information.

In this embodiment, the extracted information refers to information about the risk, vulnerability of the disaster-bearing body, and disaster prevention and reduction capability.

In an embodiment, referring to fig. 4, the step S111 may include steps S1111 to S1112.

S1111, performing risk grading on all geographic units in the research area according to the evaluation results of meteorological disasters, geological disasters, flood and drought disasters and forest fires in the single disaster danger based on an artificial intelligence algorithm.

And sorting and analyzing the single disaster risk assessment results, wherein the sorting, checking and analyzing of the results are included, the risk distribution condition of each single disaster in the research area is preliminarily mastered, the spatial law of the single disaster distribution is analyzed and researched, and support is provided for the construction and feature extraction of a subsequent model.

The single disaster type refers to a single natural disaster, and comprises a meteorological disaster, a geological disaster, a flood and drought disaster and a forest fire. And (4) carrying out risk grading on all geographic units in the research area based on the four single disaster risk assessment results. And is divided into an absolute risk and a relative risk, wherein the absolute risk means that the risk value in a specific research unit is between 0 and 1, the relative risk is the risk grade in the research unit, and the absolute risk is divided into 4 grades: low, medium, high and high. The absolute risk is used for later machine learning input, and the relative risk is only used for macroscopic comprehensive evaluation. The risk of meteorological disasters is recorded as Fqx, the risk of geological disasters is recorded as Fdz, the risk of flood and drought is recorded as Fsh, and the risk of forest fires is recorded as Fhz.

S1112, comprehensively analyzing vulnerability and disaster prevention and reduction capacity of a disaster bearing body, classifying and sorting according to different data formats, and extracting and mining characteristics of the sorted data with different formats;

Specifically, the disaster-bearing body is comprehensively analyzed from the exposure, the vulnerability and the disaster prevention and reduction capability, and is classified and sorted according to different data formats, such as points, lines, planes and the like. And performing feature extraction and mining on the sorted data with different formats, and fully considering different influence degrees of different disaster types on the same area and the difference of the bearing capacity of different disaster-bearing bodies on different disaster types.

In an embodiment, referring to fig. 5, the step S1112 may include steps S11121 to S11123.

S11121, respectively obtaining exposure characteristics of disaster-bearing bodies according to population density, infrastructure density and cultivated area ratio in the research unit;

s11122, respectively obtaining vulnerability characteristics according to population attribute distribution conditions, infrastructure firmness and farmland region gradient in the research unit;

s11123, determining the disaster prevention and reduction capability characteristics according to the medical level, the per capita income and the traffic facilities in the research unit based on an expert scoring method.

The disaster-bearing body to be considered comprises three categories of population, infrastructure such as roads and buildings and arable land. Respectively obtaining the exposure characteristics of the bearing body according to population density, infrastructure density and arable land area ratio in the research unit, wherein the population exposure is recorded as Ep, the infrastructure exposure is recorded as Eb, and the arable land exposure is recorded as Ec; respectively obtaining the vulnerability of the bearing body according to the population attribute distribution condition, the infrastructure firmness degree and the farmland region gradient in the research unit, wherein the population vulnerability is recorded as Vp, the infrastructure vulnerability is recorded as Vb and the farmland vulnerability is recorded as Vc; and determining the disaster prevention and reduction capacity according to the medical level, the per capita income and the traffic facilities in the research unit based on an expert scoring method, and recording as A.

And S112, determining the relation of the multiple disaster types according to the extracted information, and taking the determined relation of the multiple disaster types as an attribute.

In this embodiment, the attribute refers to a relationship between two single disaster species.

How to clear the interaction relation among various disaster types and reflect the interaction relation in the multi-disaster risk assessment method is very critical to the comprehensive research of the multi-disaster. As shown in fig. 7, the thick lines indicate that disaster events occur almost simultaneously in time; the thin lines indicate that a disaster event occurs for a certain time interval. The relationship between multiple disaster species is divided into a causal relationship and an antagonistic relationship. Namely, the multiple disaster relationship includes at least one of a causal relationship and an antagonistic relationship.

Wherein, extreme rainfall in meteorological disasters may induce geological disasters and waterlogging, and the occurrence of geological disasters may further aggravate the severity of waterlogging and small-watershed torrential floods; extreme high temperatures in meteorological disasters can increase drought risks and forest fire risk levels; lightning in a meteorological disaster may induce a forest fire; the above situations belong to the causal relationship existing among multiple disaster species. On the other hand, extreme precipitation in meteorological disasters can relieve drought and reduce the fire danger level of forests, and the condition belongs to the confrontation relation among multiple kinds of disasters. And (3) clearly marking the correlation between every two disaster species as a causal relationship and an antagonistic relationship, and inputting the correlation as an attribute into a model for training.

And S113, combining the extracted information and the attributes to form the evaluation features.

The evaluation features include the extracted information and attributes. Sorting and analyzing the single disaster danger results to determine the space-time distribution condition of the single disaster natural disasters in the research area; and screening, cleaning and processing disaster bearing body data, and performing characteristic extraction to form evaluation characteristics.

And S120, performing model training through a machine learning algorithm according to the evaluation features to obtain an evaluation model.

In this embodiment, the evaluation model refers to a model for risk evaluation that can comprehensively consider the connectivity between single disaster sources and the vulnerability of the disaster carrier.

In an embodiment, referring to fig. 6, the step S120 may include steps S121 to S123.

And S121, training a convolutional neural network, a cyclic neural network, a tree model and an ensemble learning model by utilizing the evaluation characteristics to obtain various trained models.

The specific process of training various models by using the evaluation features belongs to the prior art, and is not described herein again.

The result output by the trained model is a natural disaster comprehensive risk assessment result, and taking a research unit as an example, a single natural disaster has a risk value on the research unit. The natural disaster comprehensive risk result is that the risk value is between 0 and 1 under the condition of considering the common influence, the superposition influence and the influence of the disaster chain of a plurality of single natural disasters.

And S122, calculating evaluation indexes of the trained multiple models to obtain an evaluation result.

In this embodiment, a plurality of evaluation indexes such as a subject working characteristic curve, a mausis correlation coefficient, and overall accuracy are adopted, and model fusion is performed in a decision level by using an evaluation result.

And S123, fusing the multiple models after training in a decision-making level by using the evaluation result to obtain an evaluation model.

And training by using a plurality of models, comparing the obtained results, and selecting the optimal result to obtain the evaluation model.

And automatically adjusting model parameters by establishing an evaluation index of model accuracy, and preferentially selecting the most suitable model parameters for application. The evaluation model based on artificial intelligence comprehensively considers factors such as the dangerousness of various disaster-causing factors, the vulnerability and the exposure of disaster-bearing bodies, automatically analyzes the weight of each factor to form a comprehensive risk analysis result, improves the precision of the risk evaluation result to a certain extent, and can reasonably explain the space difference reasons of the comprehensive disaster risk and the constituent factors thereof; in the present embodiment, the model parameters are adjusted by using bayesian parameters.

S130, comprehensively considering the connectivity among the single disaster species and the vulnerability of the disaster-bearing body according to the evaluation model to obtain a comprehensive risk evaluation result.

In this embodiment, the integrated risk assessment result refers to a natural disaster integrated risk assessment result, and taking a research unit as an example, a single natural disaster may have a risk value on the research unit. The natural disaster comprehensive risk result is that the risk value is between 0 and 1 under the condition of considering the common influence, the superposition influence and the influence of the disaster chain of a plurality of single natural disasters.

And S140, carrying out risk zoning according to the comprehensive risk assessment result.

In this embodiment, the risk zones include a single disaster-bearing body comprehensive risk zone and a multiple disaster-bearing body comprehensive risk zone, where the single disaster-bearing body comprehensive risk zone is a comprehensive risk zone of a single disaster species, and the multiple disaster-bearing body comprehensive risk zone is a comprehensive risk zone formed by combining at least two single disaster species.

The method comprises the steps of carrying out data characteristic engineering analysis by acquiring information such as single disaster dangerousness, vulnerability of a disaster bearing body, disaster bearing capacity and the like based on an artificial intelligence comprehensive risk assessment technology, constructing a comprehensive risk assessment model by using an artificial intelligence algorithm, training the model, assessing and zoning regional natural disaster comprehensive risks, and outputting a risk zoning grade drawing and a risk prevention zoning drawing.

According to the natural disaster comprehensive risk assessment method, the characteristics of single disaster dangerousness, the vulnerability of a disaster bearing body and the disaster bearing capacity are extracted based on an artificial intelligence algorithm, the relation of multiple kinds of disasters is determined, the extracted information is used for training the model, the trained model can be used for comprehensively considering the relation among the single kinds of disasters and the risk assessment of the vulnerability of the disaster bearing body, the risk division is carried out, the interpretability of the risk assessment is high, the vulnerability and the exposure of the disaster bearing body are considered, the input information of the model comprises the single disaster dangerousness, the vulnerability of the disaster bearing body, the disaster bearing capacity and the relation among the multiple kinds of disasters, the input information of the model is sufficient, and the relation and the interaction among disaster causing factors are considered to be comprehensive.

Fig. 8 is a schematic block diagram of a natural disaster comprehensive risk assessment apparatus 300 according to an embodiment of the present invention. As shown in fig. 8, the present invention further provides a natural disaster comprehensive risk assessment apparatus 300 corresponding to the above natural disaster comprehensive risk assessment method. The natural disaster integrated risk assessment apparatus 300 includes a unit for performing the above-described natural disaster integrated risk assessment method, and may be configured in a server. Specifically, referring to fig. 8, the natural disaster integrated risk assessment apparatus 300 includes a feature extraction unit 301, a model training unit 302, an assessment unit 303, and a risk zoning unit 304.

A feature extraction unit 301, configured to extract features of each evaluation index based on an artificial intelligence algorithm to obtain evaluation features; a model training unit 302, configured to perform model training through a machine learning algorithm according to the evaluation features to obtain an evaluation model; the evaluation unit 303 is configured to comprehensively consider the connectivity between the single disaster species and the vulnerability of the disaster carrier according to the evaluation model to obtain a comprehensive risk evaluation result; and a risk zoning unit 304, configured to perform risk zoning according to the comprehensive risk assessment result.

In one embodiment, as shown in fig. 9, the feature extraction unit 301 includes an information extraction subunit 3011, a relationship confirmation subunit 3012, and a combination subunit 3013.

The information extraction subunit 3011 is configured to obtain information about single disaster risk, vulnerability of a disaster-bearing body, and disaster prevention and reduction capability based on an artificial intelligence algorithm, so as to obtain extracted information; a relation confirming subunit 3012, configured to specify a relation of the multiple disaster types according to the extracted information, and use the specified relation of the multiple disaster types as an attribute; a combining subunit 3013, configured to combine the extracted information and the attributes to form an evaluation feature.

In one embodiment, as shown in fig. 10, the information extraction subunit 3011 includes a grading module 30111 and a mining module 30112.

The grading module 30111 is configured to grade risks of all geographic units in the area under study based on an artificial intelligence algorithm according to evaluation results of meteorological disasters, geological disasters, flood and drought disasters, and forest fires within a single disaster risk; the mining module 30112 is configured to perform comprehensive analysis on vulnerability and disaster prevention and reduction capability of a disaster-bearing body, perform classification and arrangement according to different data formats, and perform feature extraction and mining on the well-arranged data in different formats; wherein, the extracted information comprises the risk levels of all the geographic units and the characteristics of the disaster-bearing body; the disaster-bearing body characteristics comprise a disaster-bearing body exposure characteristic, a vulnerability characteristic and a disaster prevention and reduction capability characteristic.

In one embodiment, as shown in FIG. 11, the mining module 30112 includes a first determination submodule 301121, a second determination submodule 301122, and a third determination submodule 301123.

The first determining submodule 301121 is used for respectively obtaining the exposure characteristics of the disaster-bearing body according to population density, infrastructure density and arable area occupation ratio in the research unit; the second determining submodule 301122 is used for respectively obtaining vulnerability characteristics according to the population attribute distribution condition, the infrastructure firmness degree and the cultivated land area gradient in the research unit; and a third determining submodule 301123 for determining the disaster prevention and reduction capability characteristics based on the expert scoring method according to the medical level, the per-capita income and the transportation facilities in the research unit.

In one embodiment, as shown in fig. 12, the model training unit 302 includes a training subunit 3021, a calculating subunit 3022, and a fusion subunit 3023.

A training subunit 3021, configured to train a convolutional neural network, a cyclic neural network, a tree model, and an ensemble learning model using the evaluation features to obtain multiple trained models; a calculating subunit 3022, configured to perform evaluation index calculation on the trained multiple models to obtain an evaluation result; and the fusion subunit 3023 is configured to fuse the multiple models trained in the decision level according to the evaluation result to obtain an evaluation model.

It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation processes of the natural disaster comprehensive risk assessment apparatus 300 and each unit may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.

The natural disaster integrated risk assessment apparatus 300 may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 13.

Referring to fig. 13, fig. 13 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of a plurality of servers.

Referring to fig. 13, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer programs 5032 include program instructions that, when executed, cause the processor 502 to perform a natural disaster integrated risk assessment method.

The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.

The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be enabled to perform a natural disaster comprehensive risk assessment method.

The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the architecture shown in fig. 13 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing device 500 to which the disclosed aspects apply, as a particular computing device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps:

extracting characteristics of each evaluation index based on an artificial intelligence algorithm to obtain evaluation characteristics; performing model training through a machine learning algorithm according to the evaluation characteristics to obtain an evaluation model; comprehensively considering the connectivity among single disaster species and the vulnerability of a disaster bearing body according to the evaluation model to obtain a comprehensive risk evaluation result; and carrying out risk zoning according to the comprehensive risk assessment result.

In an embodiment, when implementing the step of performing model training by a machine learning algorithm according to the evaluation features to obtain an evaluation model, the processor 502 specifically implements the following steps:

training a convolutional neural network, a cyclic neural network, a tree model and an ensemble learning model by using the evaluation features to obtain a plurality of trained models; calculating evaluation indexes of the trained multiple models to obtain an evaluation result; and fusing the plurality of models after training in a decision-making level by using the evaluation result to obtain an evaluation model.

In an embodiment, when implementing the step of extracting features from each evaluation index based on the artificial intelligence algorithm to obtain the evaluation features, the processor 502 specifically implements the following steps:

acquiring single disaster danger, vulnerability of a disaster bearing body and disaster prevention and reduction capacity information based on an artificial intelligence algorithm to obtain extracted information; determining the relation of multiple disaster types according to the extracted information, and taking the determined relation of the multiple disaster types as an attribute; the extracted information and attributes are combined to form an evaluation feature.

Wherein the multiple disaster relations comprise at least one of a causal relation and an antagonistic relation.

In an embodiment, when the step of obtaining the information about the single disaster risk, the vulnerability of the disaster-bearing body, and the disaster prevention and reduction capability based on the artificial intelligence algorithm is implemented by the processor 502 to obtain the extracted information, the following steps are specifically implemented:

performing risk grading on all geographic units in the researched area according to the evaluation results of meteorological disasters, geological disasters, flood and drought disasters and forest fires in single disaster dangers based on an artificial intelligence algorithm; comprehensively analyzing vulnerability and disaster prevention and reduction capability of a disaster bearing body, classifying and sorting according to different data formats, and extracting and mining characteristics of the sorted data with different formats; wherein, the extracted information comprises the risk levels of all the geographic units and the characteristics of the disaster-bearing body; the disaster-bearing body characteristics comprise a disaster-bearing body exposure characteristic, a vulnerability characteristic and a disaster prevention and reduction capability characteristic.

Wherein, the disaster-bearing body comprises population, infrastructure and cultivated land.

In an embodiment, when the processor 502 performs the comprehensive analysis of the vulnerability and the disaster prevention and reduction capability of the disaster-bearing body, performs classification and arrangement according to different data formats, and performs the steps of feature extraction and mining on the well-arranged data with different formats, the following steps are specifically implemented:

respectively obtaining the exposure characteristics of the disaster-bearing body according to population density, infrastructure density and arable area occupation ratio in the research unit; respectively obtaining vulnerability characteristics according to the population attribute distribution condition, the infrastructure firmness degree and the cultivated land area gradient in the research unit; and determining the disaster prevention and reduction capability characteristics based on an expert scoring method according to the medical level, the per capita income and the traffic facilities in the research unit.

It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be 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, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.

Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the steps of:

In an embodiment, when the processor executes the computer program to implement the step of performing model training by a machine learning algorithm according to the evaluation features to obtain an evaluation model, the processor specifically implements the following steps:

In an embodiment, when the processor executes the computer program to implement the step of extracting features from each evaluation index based on the artificial intelligence algorithm to obtain the evaluation features, the following steps are specifically implemented:

Wherein, the disaster-bearing body comprises population, infrastructure and cultivated land.

The multiple disaster relations comprise at least one of a causal relation and an antagonistic relation.

In an embodiment, when the processor executes the computer program to realize the step of obtaining the information of the single disaster risk, the vulnerability of the disaster-bearing body and the disaster prevention and reduction capability based on the artificial intelligence algorithm to obtain the extracted information, the following steps are specifically realized:

In an embodiment, when the processor executes the computer program to implement the comprehensive analysis of vulnerability and disaster prevention and reduction capability of the disaster-bearing body, and performs classification and arrangement according to different data formats, and performs the steps of feature extraction and mining on the well-arranged data with different formats, the following steps are specifically implemented:

The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.

The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.

While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

完整详细技术资料下载

上一篇：石墨接头机器人自动装卡簧、装栓机

下一篇：基于多时相遥感分析的村镇垃圾降尺度时空分布反演方法

Natural disaster comprehensive risk assessment method and device, computer equipment and storage medium

相关技术

网友询问留言