CN112801473A - Disaster prediction method and system based on natural disaster chain - Google Patents

Disaster prediction method and system based on natural disaster chain Download PDF

Info

Publication number
CN112801473A
CN112801473A CN202110055885.5A CN202110055885A CN112801473A CN 112801473 A CN112801473 A CN 112801473A CN 202110055885 A CN202110055885 A CN 202110055885A CN 112801473 A CN112801473 A CN 112801473A
Authority
CN
China
Prior art keywords
disaster
natural disaster
natural
risk
event
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110055885.5A
Other languages
Chinese (zh)
Inventor
刘梦婷
朱伟
郑建春
王晶晶
尹萌萌
杨艳英
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BEIJING RESEARCH CENTER OF URBAN SYSTEM ENGINEERING
Original Assignee
BEIJING RESEARCH CENTER OF URBAN SYSTEM ENGINEERING
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by BEIJING RESEARCH CENTER OF URBAN SYSTEM ENGINEERING filed Critical BEIJING RESEARCH CENTER OF URBAN SYSTEM ENGINEERING
Priority to CN202110055885.5A priority Critical patent/CN112801473A/en
Publication of CN112801473A publication Critical patent/CN112801473A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Alarm Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a disaster prediction method and a system based on a natural disaster chain, wherein the method comprises the following steps: acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range; establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network; and acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurrence and condition probability table in the risk assessment area. According to the embodiment of the invention, the natural disaster chain of the area is found out through the historical natural disaster recording text and the disaster-bearing body event, then the risk event incidence relation matrix is established, the conditional probability table of the Bayesian network is calculated, then the probability of risk occurrence is predicted according to the natural disaster which has occurred, the risk is quantitatively analyzed and predicted, and the risk is favorably evaluated, prevented and controlled.

Description

Disaster prediction method and system based on natural disaster chain
Technical Field
The invention relates to the technical field of meteorological monitoring and forecasting, in particular to a disaster prediction method and system based on a natural disaster chain.
Background
Natural disasters bring many hazards to production and survival of human beings all the time, once the natural disasters are hidden, irreparable loss is easily caused, and therefore, the disaster early warning has epoch-crossing significance to human life.
At present, the risk assessment of a multi-disaster chain can only perform qualitative analysis, for example, after a cold tide occurs, a disaster that a strong wind or a strong snow may occur can be predicted, but quantitative calculation cannot be performed, so that a disaster prediction method and a disaster prediction system based on a natural disaster chain are urgently needed.
Disclosure of Invention
The invention provides a disaster prediction method based on a natural disaster chain, which is used for solving the defect that the disaster cannot be quantitatively predicted in the prior art and realizing the quantitative prediction of the disaster.
The invention provides a disaster prediction method based on a natural disaster chain, which comprises the following steps:
acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network;
and acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, wherein the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur form a natural disaster chain.
According to the disaster prediction method based on the natural disaster chain, the method for acquiring the incidence relation matrix of the risk event based on the historical natural disaster record text and the disaster-bearing body event corresponding to the risk assessment area within the assessment period range comprises the following steps:
acquiring keywords corresponding to natural disasters and keywords corresponding to disaster-bearing body events;
screening the historical natural disaster record text based on the keywords corresponding to the natural disaster and the keywords corresponding to the disaster-bearing body event to obtain an optimal natural disaster record text;
acquiring the relation between the natural disasters and disaster bearing body events according to the preferable natural disaster record text;
and acquiring a risk event incidence relation matrix according to the relation between the natural disasters and disaster-bearing body events.
According to the disaster prediction method based on the natural disaster chain, provided by the invention, the historical natural disaster record text is screened based on the keywords corresponding to the natural disaster and the keywords corresponding to the disaster-bearing body event to obtain the preferred natural disaster record text, and the method comprises the following steps:
if the historical natural disaster record text at least comprises a keyword corresponding to the natural disaster or a keyword corresponding to the disaster-bearing body event, taking the historical natural disaster record text as an alternative natural disaster record text;
and if the alternative natural disaster record text at least comprises two keywords with different risk types, taking the alternative natural disaster record text as the preferred natural disaster record text.
According to the disaster prediction method based on the natural disaster chain provided by the invention, the acquiring of the risk event incidence relation matrix according to the relation between the natural disasters and disaster-bearing body events comprises the following steps:
Figure BDA0002900899630000031
wherein, it is toIn the nth preferred natural disaster recording text SnWhen present, when present
Figure BDA0002900899630000032
When the temperature of the water is higher than the set temperature,
Figure BDA0002900899630000033
if not, then,
Figure BDA0002900899630000034
and (3) representing the elements in the ith row and the jth column in the risk event incidence relation matrix.
According to the disaster prediction method based on the natural disaster chain provided by the invention, the establishing of the bayesian network based on the risk event incidence relation matrix and the obtaining of the conditional probability table corresponding to the bayesian network comprise:
converting the risk event incidence relation matrix into a Bayesian network form to form a disaster chain diagram;
based on the correlation strength between two nodes connected with each other in the disaster chain graph, deleting a connecting line between the two nodes with the correlation strength smaller than a preset threshold value to obtain a final Bayesian network;
and calculating the parameters of the final Bayesian network by adopting a maximum likelihood estimation method to form a conditional probability table.
According to the disaster prediction method based on the natural disaster chain, provided by the invention, the correlation strength between two nodes connected with each other in the disaster chain graph is the condition mutual information of the two nodes.
According to the disaster prediction method based on the natural disaster chain, provided by the invention, the condition mutual information is obtained by applying the following formula:
Figure BDA0002900899630000035
Figure BDA0002900899630000041
wherein, I (X)i,XjY) represents two nodes XiAnd XjConditional mutual information between, p (X)i,XjY) is Xi、XjAnd the joint probability of Y, p (X)i|Y)、p(Xj| Y) and p (X)i,XjY) is a conditional probability,
Figure BDA0002900899630000042
representation and node variable XiThe set of nodes that are directly connected to each other,
Figure BDA0002900899630000043
representation and node variable XjA set of directly connected nodes.
The invention also provides a disaster prediction system based on the natural disaster chain, which comprises:
the incidence matrix module is used for acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
the conditional probability calculation module is used for establishing a Bayesian network based on the risk event incidence relation matrix and acquiring a conditional probability table corresponding to the Bayesian network;
and the risk prediction module is used for acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, and forming a natural disaster chain by the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur.
The present invention also provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for disaster prediction based on natural disaster chain as described in any one of the above.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for natural disaster chain based disaster prediction as defined in any of the above.
The embodiment of the invention provides a disaster prediction method and a disaster prediction system based on a natural disaster chain.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a flowchart of a disaster prediction method based on a natural disaster chain according to the present invention;
FIG. 2 is a schematic diagram of a natural disaster chain according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a disaster prediction system based on a natural disaster chain according to the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but 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.
An embodiment of the present invention provides a disaster prediction method based on a natural disaster chain, as shown in fig. 1, the method includes:
in the embodiment of the invention, aiming at a natural disaster chain consisting of natural disasters and disaster-bearing body events in the natural world, in one natural disaster chain, when a certain natural disaster occurs, other natural disasters or other disaster-bearing body events in the natural disaster chain can be caused.
110, acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
the risk assessment area is a target area needing risk prediction, the assessment period is a period of time needing risk assessment, for example, a specific season, month or day in a year, natural disasters occurring in the risk assessment area in the period of time are acquired, generally, in a city, whenever a natural disaster occurs, a corresponding natural disaster recording text is generated, and the time, place, reason, consequence, disaster damage and other situations of the occurrence of the current natural disaster are recorded in the natural disaster recording text.
The disaster-bearing event refers to life line engineering accidents such as electric power, water conservancy, gas and heat supply, and the natural disasters can affect the engineering.
Therefore, based on the historical natural disaster recording text, the mutual influence relationship between the natural disaster and the mutual influence relationship between the natural disaster and the disaster-bearing body event are found out, and thus a risk event incidence relationship matrix is established.
120, establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network;
and establishing a Bayesian network on the basis of the risk event incidence relation matrix, wherein elements corresponding to two connected disaster events in the risk event incidence relation matrix are set to be 1, and otherwise, the elements are set to be 0.
When a node event triggers another node event, the previous node is the parent node of the next node. The conditional probability table lists the probability of occurrence or non-occurrence of any node in the bayesian network given the values of all its parents (i.e., all occurrences of all its parents are known to occur or not occur, etc.).
And 130, acquiring the probability that the natural disaster will occur and/or the disaster object event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, wherein the natural disaster occurring, the natural disaster to occur and the disaster object event to occur form a natural disaster chain.
And inputting the natural disaster occurring in the risk assessment area into a condition probability table as a known condition to obtain the probability of the natural disaster or the disaster-bearing body event about to occur in the risk assessment area.
The embodiment of the invention provides a natural disaster chain-based disaster prediction method, which comprises the steps of finding out a natural disaster chain of a region through a historical natural disaster recording text and a disaster-bearing body event, then establishing a risk event incidence relation matrix, calculating a conditional probability table of a Bayesian network, predicting the probability of risk occurrence according to the natural disaster, quantitatively predicting the risk, and facilitating prevention and control of the risk.
On the basis of the foregoing embodiment, preferably, the acquiring a risk event incidence relation matrix based on the historical natural disaster record text and the disaster-bearing body event corresponding to the risk assessment area within the assessment period range includes:
acquiring keywords corresponding to natural disasters and keywords corresponding to disaster-bearing body events;
screening the historical natural disaster record text based on the keywords corresponding to the natural disaster and the keywords corresponding to the disaster-bearing body event to obtain an optimal natural disaster record text;
acquiring the relation between the natural disasters and disaster bearing body events according to the preferable natural disaster record text;
and acquiring a risk event incidence relation matrix according to the relation between the natural disasters and disaster-bearing body events.
Based on historical natural disaster record texts in risk assessment areas and assessment period ranges, table 1 is a keyword meaning table corresponding to natural disaster risk types and different natural disaster risk types in the embodiment of the present invention, natural disasters in table 1 are arranged in sequence, and table 2 is a keyword meaning table corresponding to life line engineering function interruption risk types in the embodiment of the present invention, as shown in tables 1 and 2, retrieval and comparison are performed by using keywords of urban natural disasters and disaster-bearing body events, and a risk event incidence relation matrix is established for representing incidence relations between natural disasters and between natural disasters and disaster-bearing body events.
TABLE 1
Figure BDA0002900899630000081
Figure BDA0002900899630000091
(1) A keyword list of risk events (including natural disasters and disaster recovery events) is established. For example, the risk types and keywords of natural disasters and life line engineering accidents are listed as shown in tables 1 and 2. The natural disaster risk type set is a1 ═ X1, X2, …, X22}, the corresponding natural disaster keyword set is a2, the life line function interruption risk type set is B1 ═ X23, X24, …, X29}, and the corresponding life line function interruption keyword set is B2.
Wherein, X has two values of 1 and 0, which respectively represent that the risk event occurs and does not occur.
(2) And screening out preferable natural disaster record text samples.
And (3) screening for the first time, comparing all historical natural disaster record texts with the keywords, screening out texts containing the natural disaster keywords as alternative natural disaster record texts, and supposing that M texts are screened out.
And (3) performing secondary screening, comparing the M alternative natural disaster record texts with the keywords, recording as an optimal natural disaster record text when two or more keyword vocabularies appear in the mth text and belong to the set A2 at the same time or part of the M alternative natural disaster record text belongs to the set A2 and part of the M alternative natural disaster record text belongs to the set B2, and the keywords do not belong to the same risk type, wherein the text sample is marked as SmI.e. SmWherein the number of X values of 1 is greater than or equal to 2.
Assume that N preferred natural disaster record texts are screened out.
For example, the m-th preferred natural disaster record text shows "cold tide", "strong wind" and "power", and records:
Sm＝{X1＝1,X2＝0,X3＝0,X4＝1,…,X23＝1,…}
(3) and establishing a risk event incidence relation matrix as prior knowledge of the Bayesian network structure.
Analyzing { X between two risk events in a preferred natural disaster record texti,XjThe incidence relation of the risk event matrix is established, and an element C in the risk event incidence relation matrix is establishedijThe value is 1 or 0, which indicates both the case of association and the case of no association.
The value taking method comprises the following steps:
Figure BDA0002900899630000101
wherein, for the nth preferred natural disaster recording text SnWhen present, when present
Figure BDA0002900899630000102
When the temperature of the water is higher than the set temperature,
Figure BDA0002900899630000103
if not, then,
Figure BDA0002900899630000104
Cijand (3) representing the elements in the ith row and the jth column in the risk event incidence relation matrix.
For example, table 3 is a schematic diagram of an incidence relation matrix of risk events of natural disasters and life line engineering function interruptions in the embodiment of the present invention, and the incidence matrix established by taking a cold tide disaster as an example is shown in table 3. This approach can be applied to more risk types and more chain levels.
TABLE 3
Figure BDA0002900899630000111
On the basis of the foregoing embodiment, preferably, the establishing a bayesian network based on the risk event association relation matrix, and acquiring a conditional probability table corresponding to the bayesian network includes:
converting the risk event incidence relation matrix into a Bayesian network form to form a disaster chain diagram;
based on the correlation strength between two nodes connected with each other in the disaster chain graph, deleting a connecting line between the two nodes with the correlation strength smaller than a preset threshold value to obtain a final Bayesian network;
and calculating the parameters of the final Bayesian network by adopting a maximum likelihood estimation method to form a conditional probability table.
(1) Converting the risk event incidence relation matrix into a network form to form a disaster chain diagram,
each node is a risk event, and two nodes with matrix element values of 1 are connected by edges. For example, all node variables in the disaster chain graph network have two values Xi0 and 1 represent the states in which the event does not occur and occurs, respectively.
(2) And calculating the correlation strength, and performing Bayesian network structure learning.
Type of Risk event { Xi,XjConsidering the S samples as two discrete random variables, according to the information theory, calculating the conditions of the two variables by using the S samplesAnd (4) information.
The method comprises the following steps:
Figure BDA0002900899630000121
Y＝(ΦXi∪ΦXj)|{Xi,Xj}，
wherein, I (X)i,XjY) represents two nodes XiAnd XjConditional mutual information between, p (X)i,XjY) is Xi、XjAnd the joint probability of Y, p (X)i|Y)、p(Xj| Y) and p (X)i,XjY) is a conditional probability,
Figure BDA0002900899630000122
representation and node variable XiThe set of nodes that are directly connected to each other,
Figure BDA0002900899630000123
representation and node variable XjA set of directly connected nodes.
On the basis of a disaster chain graph obtained by prior knowledge, as shown in figure 2, calculating condition mutual information between every two node variables with association relation, setting a preset threshold value epsilon, and obtaining a disaster chain graph when I (X)i,XjIf Y) is less than or equal to epsilon, then X is equal to or less than epsilon under the condition of given YiConditions independent of XjThereby X can be deletediAnd XjTo be connected to each other.
(3) And (3) carrying out Bayesian network parameter learning on the network (namely the optimal Bayesian network) which completes the structure learning.
Using S samples, calculating parameters of the bayesian network by using a Maximum Likelihood Estimation (MLE) method to form a conditional probability table.
The parameter is any node variable XiConditional probability p (X) given its parent nodei|πXi)，πXiIs node XiIs selected.
For example, the conditional probability table of fig. 2 is shown in table 4.
TABLE 4
Figure BDA0002900899630000131
(4) And calculating the possibility of occurrence of the risk event in the natural disaster chain by using a Bayesian network inference method. Knowing the evidence (E) of occurrence of one or more risk events, the probability p (V ═ V | E ═ E) of occurrence of other risk events can be calculated using a junction tree (junctionaltree) inference method of the bayesian network:
Figure BDA0002900899630000132
for example, when cold tides occur, X1The probability of other risks occurring is 1:
p(X2＝1,…,X14＝1|X1＝1)＝(0.6,0.3,0.037,0.333,0.163,0.021,0.163,0.017,0.021)。
as shown in fig. 3, a disaster prediction system based on a natural disaster chain according to an embodiment of the present invention includes: a correlation matrix module 301, a conditional probability calculation module 302, and a risk prediction module 303, wherein:
the incidence matrix module 301 is configured to obtain a risk event incidence relation matrix based on a history natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
the conditional probability calculation module 302 is configured to establish a bayesian network based on the risk event incidence relation matrix, and obtain a conditional probability table corresponding to the bayesian network;
the risk prediction module 303 is configured to obtain a probability that a natural disaster will occur and/or a disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the conditional probability table, and form a natural disaster chain by the natural disaster occurring, the natural disaster to occur, and the disaster-bearing event to occur.
The present embodiment is a system embodiment corresponding to the above method, and please refer to the above method embodiment for details, which is not described herein again.
An embodiment of the present invention provides an electronic device, as shown in fig. 4, the electronic device may include: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. Processor 410 may invoke logic instructions in memory 430 to perform a method of natural disaster chain based disaster prediction, the method comprising:
acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network;
and acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, wherein the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur form a natural disaster chain.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may 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 server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform a natural disaster chain-based disaster prediction method provided by the above methods, the method comprising:
acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network;
and acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, wherein the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur form a natural disaster chain.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the method for natural disaster chain-based disaster prediction provided above, the method comprising:
acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network;
and acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, wherein the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur form a natural disaster chain.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A disaster prediction method based on a natural disaster chain is characterized by comprising the following steps:
acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
establishing a Bayesian network based on the risk event incidence relation matrix, and acquiring a conditional probability table corresponding to the Bayesian network;
and acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, wherein the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur form a natural disaster chain.
2. The method according to claim 1, wherein the acquiring a risk event incidence relation matrix based on the historical natural disaster record text and the disaster-bearing body event corresponding to the risk assessment area within the assessment period comprises:
acquiring keywords corresponding to natural disasters and keywords corresponding to disaster-bearing body events;
screening the historical natural disaster record text based on the keywords corresponding to the natural disaster and the keywords corresponding to the disaster-bearing body event to obtain an optimal natural disaster record text;
acquiring the relation between the natural disasters and disaster bearing body events according to the preferable natural disaster record text;
and acquiring a risk event incidence relation matrix according to the relation between the natural disasters and disaster-bearing body events.
3. The method according to claim 2, wherein the step of screening the historical natural disaster record text based on the keywords corresponding to the natural disaster and the keywords corresponding to the disaster-bearing body event to obtain a preferred natural disaster record text comprises:
if the historical natural disaster record text at least comprises a keyword corresponding to the natural disaster or a keyword corresponding to the disaster-bearing body event, taking the historical natural disaster record text as an alternative natural disaster record text;
and if the alternative natural disaster record text at least comprises two keywords with different risk types, taking the alternative natural disaster record text as the preferred natural disaster record text.
4. The method according to claim 2, wherein the obtaining a risk event incidence relation matrix according to the relation between the natural disasters and disaster carrier events comprises:
Figure FDA0002900899620000021
wherein, for the nth preferred natural disaster recording text SnWhen present, when present
Figure FDA0002900899620000022
When the temperature of the water is higher than the set temperature,
Figure FDA0002900899620000023
if not, then,
Figure FDA0002900899620000024
Cijand (3) representing the elements in the ith row and the jth column in the risk event incidence relation matrix.
5. The method according to any one of claims 1 to 4, wherein the establishing a Bayesian network based on the risk event correlation matrix and obtaining a conditional probability table corresponding to the Bayesian network comprises:
converting the risk event incidence relation matrix into a Bayesian network form to form a disaster chain diagram;
based on the correlation strength between two nodes connected with each other in the disaster chain graph, deleting a connecting line between the two nodes with the correlation strength smaller than a preset threshold value to obtain a final Bayesian network;
and calculating the parameters of the final Bayesian network by adopting a maximum likelihood estimation method to form a conditional probability table.
6. A natural disaster chain based disaster prediction method according to claim 5, characterized in that the strength of the association between two nodes connected to each other in said disaster chain graph is the conditional mutual information of the two nodes.
7. A natural disaster chain based disaster prediction method according to claim 6, wherein said conditional mutual information is obtained by applying the following formula:
Figure FDA0002900899620000031
Figure FDA0002900899620000032
wherein, I (X)i,XjY) represents two nodes XiAnd XjConditional mutual information between, p (X)i,XjY) is Xi、XjAnd the joint probability of Y, p (X)i|Y)、p(Xj| Y) and p (X)i,XjY) is a conditional probability,
Figure FDA0002900899620000033
representation and node variable XiThe set of nodes that are directly connected to each other,
Figure FDA0002900899620000034
representation and node variable XjA set of directly connected nodes.
8. A disaster prediction system based on a natural disaster chain, comprising:
the incidence matrix module is used for acquiring a risk event incidence relation matrix based on a historical natural disaster record text and a disaster-bearing body event corresponding to the risk assessment area within an assessment period range;
the conditional probability calculation module is used for establishing a Bayesian network based on the risk event incidence relation matrix and acquiring a conditional probability table corresponding to the Bayesian network;
and the risk prediction module is used for acquiring the probability that the natural disaster will occur and/or the disaster-bearing event will occur in the risk assessment area according to the natural disaster occurring in the risk assessment area and the condition probability table, and forming a natural disaster chain by the natural disaster occurring, the natural disaster to occur and the disaster-bearing event to occur.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for natural disaster chain based disaster prediction according to any of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program, when being executed by a processor, is adapted to carry out the steps of the method for natural disaster chain based disaster prediction according to any of the claims 1 to 7.
CN202110055885.5A 2021-01-15 2021-01-15 Disaster prediction method and system based on natural disaster chain Pending CN112801473A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110055885.5A CN112801473A (en) 2021-01-15 2021-01-15 Disaster prediction method and system based on natural disaster chain

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110055885.5A CN112801473A (en) 2021-01-15 2021-01-15 Disaster prediction method and system based on natural disaster chain

Publications (1)

Publication Number Publication Date
CN112801473A true CN112801473A (en) 2021-05-14

Family

ID=75809717

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110055885.5A Pending CN112801473A (en) 2021-01-15 2021-01-15 Disaster prediction method and system based on natural disaster chain

Country Status (1)

Country Link
CN (1) CN112801473A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115630846A (en) * 2022-12-07 2023-01-20 速度时空信息科技股份有限公司 Processing method suitable for comprehensive monitoring data of natural disaster risks
CN115829336A (en) * 2023-02-17 2023-03-21 深圳市城市公共安全技术研究院有限公司 Risk assessment method and device for gas pipeline leakage, equipment and storage medium
CN116433032A (en) * 2023-04-26 2023-07-14 中国农业科学院农业环境与可持续发展研究所 Intelligent assessment method based on web crawler mode

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650985A (en) * 2016-09-12 2017-05-10 南京航空航天大学 Method for predicting the chain effect of abnormal flight derived event based on stochastic Petri nets
KR101797179B1 (en) * 2017-01-18 2017-11-13 주식회사 제이비티 Hazard potential evaluation method for complex disasters
CN108062638A (en) * 2018-02-09 2018-05-22 国通广达（北京）技术有限公司 Pipe gallery disaster chain methods of risk assessment
CN108615056A (en) * 2018-04-28 2018-10-02 南京理工大学 A kind of tree enhancing Naive Bayes Classification method based on decomposable asymmetric choice net score function
CN111223027A (en) * 2020-01-03 2020-06-02 清华大学合肥公共安全研究院 Urban earthquake disaster risk assessment method and system
CN111275951A (en) * 2019-12-25 2020-06-12 中国移动通信集团江苏有限公司 Information processing method, device and equipment and computer storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650985A (en) * 2016-09-12 2017-05-10 南京航空航天大学 Method for predicting the chain effect of abnormal flight derived event based on stochastic Petri nets
KR101797179B1 (en) * 2017-01-18 2017-11-13 주식회사 제이비티 Hazard potential evaluation method for complex disasters
CN108062638A (en) * 2018-02-09 2018-05-22 国通广达（北京）技术有限公司 Pipe gallery disaster chain methods of risk assessment
CN108615056A (en) * 2018-04-28 2018-10-02 南京理工大学 A kind of tree enhancing Naive Bayes Classification method based on decomposable asymmetric choice net score function
CN111275951A (en) * 2019-12-25 2020-06-12 中国移动通信集团江苏有限公司 Information processing method, device and equipment and computer storage medium
CN111223027A (en) * 2020-01-03 2020-06-02 清华大学合肥公共安全研究院 Urban earthquake disaster risk assessment method and system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115630846A (en) * 2022-12-07 2023-01-20 速度时空信息科技股份有限公司 Processing method suitable for comprehensive monitoring data of natural disaster risks
CN115829336A (en) * 2023-02-17 2023-03-21 深圳市城市公共安全技术研究院有限公司 Risk assessment method and device for gas pipeline leakage, equipment and storage medium
CN116433032A (en) * 2023-04-26 2023-07-14 中国农业科学院农业环境与可持续发展研究所 Intelligent assessment method based on web crawler mode
CN116433032B (en) * 2023-04-26 2024-04-09 中国农业科学院农业环境与可持续发展研究所 Intelligent assessment method based on web crawler mode

Similar Documents

Publication Publication Date Title
CN112801473A (en) Disaster prediction method and system based on natural disaster chain
Taleb-Berrouane et al. Bayesian Stochastic Petri Nets (BSPN)-A new modelling tool for dynamic safety and reliability analysis
Sarewitz et al. Vulnerability and risk: some thoughts from a political and policy perspective
McNeil Estimating the tails of loss severity distributions using extreme value theory
Khan et al. HEPI: A new tool for human error probability calculation for offshore operation
Fazeres-Ferradosa et al. Asymmetric copula–based distribution models for met-ocean data in offshore wind engineering applications
WO2019183371A1 (en) Networked computer-system management and control
CN110736968B (en) Radar abnormal state diagnosis method based on deep learning
KR20200052806A (en) Operating method of deep learning based climate change prediction system
TW201224812A (en) Probabilistic data mining model comparison engine
CN112835769A (en) Service data abnormity diagnosis method, device, equipment and storage medium
Zhang et al. Temporal data-driven failure prognostics using BiGRU for optical networks
CN113900844A (en) Service code level-based fault root cause positioning method, system and storage medium
CN117494292A (en) Engineering progress management method and system based on BIM and AI large model
Katebi et al. Economic and economic-statistical designs of the T2 control charts with SVSSI sampling scheme
Comert et al. Malaria outbreak detection with machine learning methods
Indra et al. Modeling of optimal deep learning based flood forecasting model using twitter data
CN117972355A (en) Time sequence data prediction method, system, equipment and medium
CN115169650B (en) Equipment health prediction method for big data analysis
Mohril et al. XGBoost based residual life prediction in the presence of human error in maintenance
Nateghi et al. The frontiers of uncertainty estimation in interdisciplinary disaster research and practice
CN114338351B (en) Network anomaly root cause determination method and device, computer equipment and storage medium
Pourtaheri Three-level control charts with variable sample size, sampling interval, and control limits
Mukhopadhyay et al. Predictive likelihood for coherent forecasting of count time series
WO2022109150A1 (en) Systems and methods for automated document review

Legal Events

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