CN114819525A - Fire risk assessment method, system, terminal device and medium - Google Patents
Fire risk assessment method, system, terminal device and medium Download PDFInfo
- Publication number
- CN114819525A CN114819525A CN202210333809.0A CN202210333809A CN114819525A CN 114819525 A CN114819525 A CN 114819525A CN 202210333809 A CN202210333809 A CN 202210333809A CN 114819525 A CN114819525 A CN 114819525A
- Authority
- CN
- China
- Prior art keywords
- fire
- dynamic
- assessment
- model
- fire risk
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000012502 risk assessment Methods 0.000 title claims abstract description 71
- 238000011161 development Methods 0.000 claims abstract description 78
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000012360 testing method Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 20
- 238000010276 construction Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008676 import Effects 0.000 description 5
- 239000000779 smoke Substances 0.000 description 4
- 238000004088 simulation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic 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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Optimization (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a fire risk assessment method, a fire risk assessment system, terminal equipment and a computer readable storage medium, wherein the fire risk assessment method comprises the following steps: constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters; acquiring dynamic fire development influence parameters, and determining fire development trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients; and obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network. The invention can improve the evaluation efficiency when carrying out risk evaluation aiming at dynamic fire.
Description
Technical Field
The present invention relates to the field of data management technologies, and in particular, to a fire risk assessment method, system, terminal device, and computer-readable storage medium.
Background
The existing fire risk assessment model is mainly assessed by methods such as a fuzzy comprehensive assessment method, an analytic hierarchy process, a quotient method and the like, but the methods cannot represent the mutual influence relationship among indexes at the same level or across levels; the existing evaluation model mainly depends on experts to score characteristic variables; in addition, the conditional probability of the existing bayesian network model is mainly set by an analytic hierarchy process or expert experience, and is not accurate enough.
In conclusion, the conventional fire risk assessment model is high in artificial participation degree, low in assessment precision and limited in application scenarios.
Disclosure of Invention
The invention mainly aims to provide a fire risk assessment method, a fire risk assessment system, a terminal device and a computer readable storage medium, and aims to improve assessment efficiency when risk assessment is carried out on dynamic fire.
The fire risk assessment method comprises the following steps:
constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
acquiring dynamic fire development influence parameters, and determining fire development trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients;
and obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
Optionally, the step of displaying the model output parameter through a knowledge graph includes:
according to a preset fire risk characteristic variable, a middle variable corresponding to the fire risk characteristic variable and a preset fire parameter, constructing an ontology in a knowledge graph and a relation between the ontologies;
and displaying the model output parameters through a knowledge graph according to the relation between the ontology and the ontology.
Optionally, the step of determining a dynamic fire development impact parameter, and obtaining a fire development trend probability through a dynamic bayesian network based on the dynamic fire development impact parameter and the path coefficient includes:
determining dynamic fire development influence parameters, and determining the conditional probability of the dynamic fire development influence parameters according to the path coefficients;
and obtaining the fire evolution trend probability through a dynamic Bayesian network based on the fire development stage main frame of the dynamic fire development influence parameters and the conditional probability.
Optionally, the step of constructing a fire risk structural equation model includes:
and constructing a fire risk structural equation model based on the fire risk characteristic variables.
Optionally, after the step of constructing the fire risk structural equation model and before the step of training the fire risk structural equation model to obtain the model output parameters, the method further includes:
importing preset multi-source heterogeneous data into the fire risk structural equation model to score the fire risk characteristic variables according to the multi-source heterogeneous data, wherein the multi-source heterogeneous data comprise: numeric, picture, video, excel, pdf, and word.
Optionally, after the step of obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, the method further includes:
and evaluating the dynamic fire evaluation network through preset test data, and displaying the evaluated dynamic fire evaluation network through a knowledge graph.
Optionally, the step of training the fire risk structural equation model to obtain a model output parameter includes:
and carrying out model identification, model estimation and model evaluation on the fire risk structure equation model to obtain model output parameters so as to complete the training of the fire risk structure equation model.
In order to achieve the above object, the present invention also provides a fire risk assessment system, including:
the acquisition module is used for constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
the determining module is used for acquiring dynamic fire development influence parameters and determining fire evolution trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients;
and the obtaining module is used for obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
The functional modules of the fire risk assessment system realize the steps of the fire risk assessment method when running.
In order to achieve the above object, the present invention further provides a terminal device, where the terminal device includes: a memory, a processor and a fire risk assessment program stored on the memory and executable on the processor, the fire risk assessment program when executed by the processor implementing the steps of the fire risk assessment method as described above.
Furthermore, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a fire risk assessment program, which when executed by a processor, implements the steps of the fire risk assessment method as described above.
Furthermore, to achieve the above object, the present invention also provides a computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the fire risk assessment method as described above.
The invention provides a fire risk assessment method, a fire risk assessment system, a terminal device, a computer readable storage medium and a computer program product, wherein a fire risk structural equation model is constructed, the fire risk structural equation model is trained to obtain model output parameters, the model output parameters are displayed through a knowledge graph, and path coefficients in the model output parameters are obtained; acquiring dynamic fire development influence parameters, and determining fire development trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients; and obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
According to the method, a fire risk structural equation model is constructed, meanwhile, the conditional probability of each dynamic fire development influence parameter is determined based on the path coefficient output by the fire risk structural equation model, so that the fire evolution trend probability is obtained through a dynamic Bayesian network based on the conditional probability and the dynamic fire development influence parameters, and finally a dynamic fire evaluation network is obtained, therefore, the method utilizes a knowledge graph to display the structural equation model analysis result, the display effect is enriched, and the influence relation among characteristic variables can be more visually seen; the path coefficient of the fire risk structural equation model is used for supporting the conditional probability of the dynamic Bayesian network, so that the relation among characteristic variables can be more accurately reflected, and the difficulty in adjusting the subsequent model is reduced. Furthermore, the invention realizes high-efficiency fire risk quantitative evaluation.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for evaluating fire risk according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a fire risk assessment model according to an embodiment of the fire risk assessment method of the present invention;
FIG. 4 is a schematic diagram illustrating an output result of a structural equation model according to an embodiment of the fire risk assessment method of the present invention;
FIG. 5 is a schematic view of a knowledge graph of an output result of a structural equation model according to an embodiment of the fire risk assessment method of the present invention;
FIG. 5-1 is a schematic view of a local knowledge map of the output result of the structural equation model according to an embodiment of the fire risk assessment method of the present invention;
FIG. 5-2 is a schematic diagram illustrating a local simulation of a knowledge graph of an output result of a structural equation model according to an embodiment of the fire risk assessment method of the present invention;
FIG. 6 is a schematic diagram of a main frame in a fire development stage according to an embodiment of the method for evaluating a fire risk of the present invention;
FIG. 7 is a schematic diagram of a dynamic fire assessment indicator system according to an embodiment of the fire risk assessment method of the present invention;
FIG. 8 is a schematic diagram of a dynamic fire assessment network according to an embodiment of the fire risk assessment method of the present invention;
FIG. 8-1 is a partial schematic view of a dynamic fire assessment network according to an embodiment of the fire risk assessment method of the present invention;
FIG. 9 is a schematic diagram of a conditional probability of a dynamic fire assessment network according to an embodiment of the fire risk assessment method of the present invention;
FIG. 10 is a schematic view of a structural equation model according to an embodiment of the fire risk assessment method of the present invention;
FIG. 11 is a schematic diagram of structural equation model training in an embodiment of a fire risk assessment method of the present invention;
FIG. 12 is a schematic diagram illustrating a structural equation model training code according to an embodiment of the fire risk assessment method of the present invention;
FIG. 13 is a schematic diagram of test data of a dynamic fire assessment network according to an embodiment of the fire risk assessment method of the present invention;
FIG. 14 is a diagram illustrating test results of a dynamic fire assessment network according to an embodiment of the fire risk assessment method of the present invention;
FIG. 15 is a schematic diagram of fire factor nodes of a dynamic fire assessment network according to an embodiment of the fire risk assessment method of the present invention;
FIG. 16 is a schematic diagram illustrating a fire factor relationship of a dynamic fire assessment network according to an embodiment of a fire risk assessment method of the present invention;
FIG. 17 is a schematic diagram illustrating a fire factor node relationship of a dynamic fire evaluation network according to an embodiment of a fire risk evaluation method of the present invention;
FIG. 18 is a schematic overall view of a dynamic fire assessment network import knowledge graph display platform according to an embodiment of the fire risk assessment method of the present invention;
FIG. 18-1 is a first schematic view of a portion of a dynamic fire assessment network import knowledge graph display platform according to an embodiment of the fire risk assessment method of the present invention;
FIG. 18-2 is a second schematic view of a portion of a dynamic fire assessment network import knowledge graph display platform according to an embodiment of the fire risk assessment method of the present invention;
FIG. 19 is a functional block diagram of an embodiment of a fire risk assessment system according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
It should be noted that, the terminal device in the embodiment of the present invention may be a terminal device for extracting data from multiple types of data sources, and the terminal device may specifically be a smart phone, a personal computer, a server, and the like.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration of the apparatus shown in fig. 1 is not intended to be limiting of the apparatus and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a fire risk assessment program. The operating system is a program that manages and controls the hardware and software resources of the device, supporting the operation of the fire risk assessment program as well as other software or programs. In the device shown in fig. 1, the user interface 1003 is mainly used for data communication with a client; the network interface 1004 is mainly used for establishing communication connection with a server; and the processor 1001 may be configured to call the fire risk assessment program stored in the memory 1005 and perform the following operations:
constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
acquiring dynamic fire development influence parameters, and determining fire development trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients;
and obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
Further, the processor 1001 may be further configured to call a fire risk assessment program stored in the memory 1005, and further perform the following operations:
according to a preset fire risk characteristic variable, a middle variable corresponding to the fire risk characteristic variable and a preset fire parameter, constructing an ontology in a knowledge graph and a relation between the ontologies;
and displaying the model output parameters through a knowledge graph according to the relation between the ontology and the ontology.
Further, the processor 1001 may be further configured to call a fire risk assessment program stored in the memory 1005, and further perform the following operations:
determining dynamic fire development influence parameters, and determining the conditional probability of the dynamic fire development influence parameters according to the path coefficients;
and obtaining the fire evolution trend probability through a dynamic Bayesian network based on the fire development stage main frame of the dynamic fire development influence parameters and the conditional probability.
Further, the processor 1001 may be further configured to call a fire risk assessment program stored in the memory 1005, and further perform the following operations:
and constructing a fire risk structural equation model based on the fire risk characteristic variables.
Further, after the step of constructing the fire risk structural equation model and before the step of training the fire risk structural equation model to obtain the model output parameters, the processor 1001 may be further configured to call a fire risk assessment program stored in the memory 1005, and further perform the following operations:
importing preset multi-source heterogeneous data into the fire risk structural equation model to score the fire risk characteristic variables according to the multi-source heterogeneous data, wherein the multi-source heterogeneous data comprise: numeric, picture, video, excel, pdf, and word.
Further, after the step of obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and a preset expert knowledge, the processor 1001 may be further configured to call a fire risk assessment program stored in the memory 1005, and further perform the following operations:
and evaluating the dynamic fire evaluation network through preset test data, and displaying the evaluated dynamic fire evaluation network through a knowledge graph.
Further, the processor 1001 may be further configured to call a fire risk assessment program stored in the memory 1005, and further perform the following operations:
and carrying out model identification, model estimation and model evaluation on the fire risk structure equation model to obtain model output parameters so as to complete the training of the fire risk structure equation model.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the fire risk assessment method according to the present invention.
In the present embodiment, an embodiment of a fire risk assessment method is provided, it being noted that although a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different than here.
In the present embodiment, a fire risk assessment model architecture is constructed, and as shown in fig. 3, the fire risk assessment model architecture includes a structural equation model and a dynamic bayesian network model. The model architecture is a modeling idea of the model, and the modeling idea includes three contents of model entering data, calculation logic and output results in the embodiment. When a structural equation model is constructed, 45 basic characteristic variables and 8 intermediate characteristic variables are used as characteristic variables to be modeled, and then mutual influence among the characteristic variables and influence of each characteristic variable on casualties, fire numbers and property loss are obtained based on the calculation logic of the structural equation model. Meanwhile, the conditional probability among the characteristic variables obtained according to the structural equation model is input into the dynamic Bayesian network model, and the fire occurrence probability is finally output through 93 characteristic variables in the dynamic Bayesian network model.
Step S10, constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
the method comprises the steps that the terminal equipment firstly constructs a fire risk structure equation model, further trains the fire risk structure equation model, obtains a model output result, displays the model output result through a knowledge graph in order to increase the visualization degree, and simultaneously obtains a path coefficient from a model output parameter so as to determine the conditional probability of the dynamic Bayesian network based on the path coefficient.
Specifically, for example, as shown in fig. 4, the output results of the structural equation model are displayed in a tabular manner in fig. 4. Wherein, the independent variable represents the 'cause' of a pair of relations, the dependent variable represents the 'effect' of a pair of relations, each variable can be either the cause (effect) or the effect (cause) of another pair of relations, for example, in the 'building fire-proof interval-firewall/door/valve' pair relation, the influence of the building fire-proof interval on the firewall/door/valve is 0; in the pair relationship of 'fire capital investment-firewall/door/valve', the influence coefficient of the fire capital investment on the firewall/door/valve is 0.9, which means that the more the fire capital investment is, the higher the security of the firewall/door/valve is; in the pair relationship of the fire safety general knowledge education and the electric appliance fault hidden danger, the influence coefficient of the fire safety general knowledge education on the electric appliance fault hidden danger is-0.9, which means that the more the fire safety education is, the less the electric appliance fault hidden danger is.
Further, in the step S10, the displaying the model output parameter through the knowledge graph may include:
step S101, constructing an ontology in a knowledge graph and a relation between the ontology according to a preset fire risk characteristic variable, an intermediate variable corresponding to the fire risk characteristic variable and a preset fire parameter;
and S102, obtaining knowledge graph data based on the relation between the ontology and the ontology, and displaying the model output parameters through a knowledge graph based on the knowledge graph data.
It should be noted that, in this embodiment, the professional knowledge map display tool deep finder is used to display the results of the structural equation model. The deepFinder tool supports the import of various knowledge graphs and supports the import of multi-element heterogeneous data. The construction of the knowledge graph is divided into three steps, namely, the construction of an ontology, the construction of a relation and the introduction of data.
Specifically, for example, an ontology is constructed, where the ontology includes an original characteristic variable, an intermediate variable corresponding to the original characteristic variable, and a preset fire parameter, where the preset fire parameter includes: number of fires, casualties and property loss; the relation among all nodes of the knowledge graph based on the structural equation model is single, and in the embodiment, the relation among the nodes is a causal relation, namely 'cause', and further, the ontology and the relation jointly form knowledge graph data; finally, displaying the model output parameters through the knowledge graph based on knowledge graph data, wherein the knowledge graph of the structural equation model is shown in fig. 5, in order to more clearly display the model conclusion, the output result of the structural equation model in fig. 4 is displayed by using knowledge graph simulation, fig. 5-1 is a local display graph of fig. 5, in order to more clearly display the knowledge graph model conclusion, the knowledge graph is displayed in a simulation mode, as shown in fig. 5-2, wherein in the pair relationship of 'building fire prevention distance-firewall/door/valve', the influence of the building fire prevention distance on the firewall/door/valve is 0; in the pair relationship of 'fire capital investment-firewall/door/valve', the influence coefficient of the fire capital investment on the firewall/door/valve is 0.9, which means that the more the fire capital investment is, the higher the security of the firewall/door/valve is; in the pair relationship of the fire safety general knowledge education and the electric appliance fault hidden danger, the influence coefficient of the fire safety general knowledge education on the electric appliance fault hidden danger is-0.9, which means that the more the fire safety education is, the less the electric appliance fault hidden danger is.
Further, the fire risk assessment method further includes:
step S20, determining dynamic fire development influence parameters, and obtaining fire evolution trend probability through a dynamic Bayesian network based on the state of the dynamic fire development influence parameters and the path coefficients;
the terminal equipment determines different stages of fire dynamic evolution and dynamic fire development influence parameters thereof by combining business expert knowledge and fire professional knowledge in advance, and determines fire evolution trend probability through a dynamic Bayesian network by combining path coefficients in model output parameters of a fire risk structural equation model.
Further, in the step S20, the "determining a dynamic fire development influence parameter and obtaining a fire development trend probability through a dynamic bayesian network based on the dynamic fire development influence parameter and the path coefficient" may include:
step S201, determining dynamic fire development influence parameters, and determining the conditional probability of the dynamic fire development influence parameters according to the path coefficients;
and S202, acquiring the fire evolution trend probability through a dynamic Bayesian network based on the fire development stage main frame of the dynamic fire development influence parameters and the conditional probability.
Determining dynamic fire development influence parameters including parameters such as fire, fire growth, fire spread, smoke propagation, spread to adjacent buildings, personnel evacuation caused by fire, property loss and the like in different stages of fire dynamic evolution and influence factors thereof by combining business expert knowledge and fire professional knowledge, determining the conditional probability of each dynamic fire development influence parameter according to the path coefficient output by the fire risk structural equation model, simultaneously constructing a fire development framework including each dynamic fire development influence parameter, and obtaining the fire development trend probability through a dynamic Bayesian network according to the fire development framework and the conditional probability of each dynamic fire development influence parameter.
Specifically, for example, after determining dynamic fire development influence parameters including parameters of fire, fire growth, fire spread and smoke propagation, spread to adjacent buildings, personnel evacuation due to fire, property loss, and the like, a fire development stage main frame is constructed by continuously iterating, as shown in fig. 6, arrows represent main influence parameters of each stage, and directions are directed from "cause" to "effect" so as to further determine a fire development trend probability based on the fire development stage main frame.
It should be noted that, in this embodiment, the conditional probability of the dynamic bayesian network is determined by the path coefficient in the model output parameter of the fire risk structural equation model, and compared with the method in the prior art in which the conditional probability is set by an analytic hierarchy process or expert experience, the method in the present invention uses the path coefficient of the structural equation to support the conditional probability of the dynamic bayesian network, so that the relationship between characteristic variables can be more accurately reflected, and the difficulty in tuning the subsequent model is reduced.
And step S30, obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, and performing risk quantitative assessment on the fire through the dynamic fire assessment network.
It should be noted that, in this embodiment, before constructing a dynamic fire assessment network based on a dynamic fire assessment index system, a dynamic fire assessment index system needs to be constructed in advance, as shown in fig. 7, in the dynamic fire assessment index system, a large number of basic characteristic variables and intermediate characteristic variables related to fire development are included, a dynamic fire assessment index system is constructed based on the basic characteristic variables, the intermediate characteristic variables and relationships among the characteristic variables, and the obtained dynamic fire assessment network is shown in fig. 8.
Specifically, for example, as shown in fig. 8-1, a dynamic fire assessment network is parametrically designed by taking an a32 (fire effectiveness) node as an example, in fig. 8-1, a conditional probability of a node a32 (fire effectiveness) is shown in fig. 9, a26 has two states, high represents that the quantity of fire-fighting power is large, and low represents that the quality of fire-fighting power is good; the corresponding meanings of the A40 node and the A32 node can be obtained in the same way. P (A32/A26, A40) represents the probability of the occurrence of the A32 node under the condition that A26 and A40 occur simultaneously. The summed probability sums per row for the P (A32/A26, A40) probabilities in the table are 1.
In this embodiment, the terminal device first constructs a fire risk structural equation model, further trains the fire risk structural equation model, and obtains a model output result, and in order to increase the visualization degree, displays the model output result through a knowledge graph, and simultaneously obtains a path coefficient from a model output parameter. Determining dynamic fire development influence parameters including parameters such as fire, fire growth, fire spread, smoke propagation, spread to adjacent buildings, personnel evacuation caused by fire, property loss and the like in different stages of fire dynamic evolution and influence factors thereof by combining business expert knowledge and fire professional knowledge, determining the conditional probability of each dynamic fire development influence parameter according to the path coefficient output by the fire risk structural equation model, simultaneously constructing a fire development framework including each dynamic fire development influence parameter, and obtaining the fire development trend probability through a dynamic Bayesian network according to the fire development framework and the conditional probability of each dynamic fire development influence parameter. And obtaining a dynamic fire assessment network based on the fire evolution trend probability, a dynamic fire assessment index system and preset expert knowledge, so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
According to the method, the fire risk characteristic variables are scored by adopting multi-source heterogeneous data, a fire risk structural equation model is established based on the fire risk characteristic variables, meanwhile, the condition probability of each dynamic fire development influence parameter is determined based on the path coefficient output by the fire risk structural equation model, the fire evolution trend probability is obtained through a dynamic Bayesian network based on the condition probability and the dynamic fire development influence parameters, and finally a dynamic fire evaluation network is obtained, so that the method can more comprehensively establish a numerical information base of the characteristic variables based on the multi-source heterogeneous data, and the accuracy of model evaluation results is improved; the knowledge graph is used for displaying the analysis result of the structural equation model, the display effect is enriched, and the influence relation among characteristic variables can be more visually seen; the path coefficient of the fire risk structural equation model is used for supporting the conditional probability of the dynamic Bayesian network, so that the relation among characteristic variables can be more accurately reflected, and the difficulty in adjusting the subsequent model is reduced. Furthermore, the invention realizes high-efficiency fire risk quantitative evaluation.
Further, based on the above first embodiment of the fire risk assessment method of the present invention, a second embodiment of the fire risk assessment method is proposed.
In this embodiment, the step S10 of "constructing a fire risk structural equation model" may include:
and S103, constructing a fire risk structural equation model based on the fire risk characteristic variables.
It should be noted that, in this embodiment, a fire risk structural equation model is constructed based on fire risk characteristic variables by means of consulting experts and consulting documents. In the fire risk structural equation model, the relationship between the fire risk characteristic variables and the intermediate characteristic variables, the relationship between the fire risk characteristic variables and the influence of the fire risk characteristic variables on the quantity of fire, casualties and economic loss are displayed.
Specifically, for example, as shown in fig. 10, after determining the fire risk characteristic variables and the intermediate characteristic variables, the terminal device obtains the mutual influence between the characteristic variables and the influence of each characteristic variable on casualties, the number of fires and property loss based on the fire risk characteristic variables and the intermediate characteristic variables, and completes the construction of the fire risk structural equation model.
In addition, in this embodiment, the computational logic of the structural equation model core algorithm is:
x＝Λx·ξ+δ
y＝Λy·η+ε
wherein x represents a vector consisting of exogenous indicators and y represents a vector consisting of endogenous indicators; Λ x represents the relationship between exogenous indexes and exogenous latent variables; lambda y represents the relation between endogenous indexes and endogenous latent variables; δ represents an error term representing the exogenous index x; epsilon represents an error term of the endogenous index y; eta represents an intrinsic variable; ξ represents the extrinsic latent variable.
Further, after the step S10 of "building the fire risk structural equation model" and before the step S10 of "training the fire risk structural equation model to obtain the model output parameters", the method further includes:
step S40, importing preset multi-source heterogeneous data into the fire risk structural equation model to score the fire risk characteristic variables according to the multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises: numeric, picture, video, excel, pdf, and word.
It should be noted that, in this embodiment, the multivariate heterogeneous data is extracted to serve as one of the basis for scoring the characteristic variables, so as to establish a more comprehensive numerical information base of the fire risk characteristic variables based on the multisource heterogeneous data, thereby improving the accuracy of the model evaluation result.
Specifically, for example, the multi-source heterogeneous data used by the structural equation model in the present embodiment includes six types, i.e., a numerical value, a picture, a video, an excel, a pdf, and a word. For the processing of numerical data, two technologies of data cleaning and characteristic engineering are mainly used and are included into a structural equation model; directly extracting information for the excel data and incorporating the information into a structural equation model; for picture, pdf and video data, firstly, converting original information into numerical data by adopting an Optical Character Recognition (OCR) technology, then carrying out denoising and characteristic engineering technologies on the numerical data, and arranging the numerical data into standard clean data to be incorporated into a structural equation model; and (3) for word data, a natural semantic processing (NLP) technology is mainly used, and relevant information of fire accident investigation is extracted and is included in a structural equation model.
Further, in step S10, the training of the fire risk structural equation model to obtain the model output parameters may include:
step S103, carrying out model identification, model estimation and model evaluation on the fire risk structure equation model to obtain a model output parameter so as to complete the training of the fire risk structure equation model.
The model training process includes 7 steps of model setting, model identification, measurement, parameter estimation, model modification, goodness-of-fit evaluation and model evaluation, as shown in fig. 11, in this embodiment Python3 is used to train the structural equation model, part of the codes of the training process are shown in fig. 12, and after the training is completed, the output result of the structural equation model is obtained,
further, in step S30, after "obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system, and a preset expert knowledge", the method further includes:
and step S50, evaluating the dynamic fire evaluation network through preset test data, and displaying the evaluated dynamic fire evaluation network through a knowledge graph.
After the dynamic fire assessment network is obtained through the fire evolution trend probability, the dynamic fire assessment index system and the preset expert knowledge, the dynamic fire assessment network is further evaluated according to the preset test data, so that whether the dynamic fire assessment network can be applied to actual fire assessment or not is determined.
Specifically, for example, the model results were tested using the 179 old cell residences of Shenzhen city in the present embodiment. As shown in FIG. 13, the test data is derived from 179 old cell houses in Shenzhen city for manual filling of the evaluation scores of the relevant characteristic variables, and each cell takes on a value of 1-10. Dynamically accessing the test data into the first 54 characteristic libraries of the cell to predict the fire probability of the related nodes of the dynamic fire evaluation network; the fire, fire growth, fire spread and smoke propagation, evacuation of people caused by fire, spread to adjacent buildings, property loss, casualties and other nodes can be dynamically deduced by running a bayesian network python program, the test result is shown in fig. 14, the actual fire cell is [0,2,27,38,86,87,118,119,123,126,129,140,141,153,166,167], and the predicted fire cell is [0,2,27,56,86,87,118,119,123,126,129,141,153,166,178], and the predicted fire cell with correct result includes: [0,2,27,86,118,119,123,126,129,141,153,167], where the accuracy of this evaluation is 0.8125, the recall rate is 0.8125, the F1 score is 0.8125, and the AUC (evaluation index for the two-classification model, AUC is the area under the ROC curve) is 0.9225460122699387, it can be seen that the dynamic fire assessment network constructed in this embodiment can accurately predict the fire.
And then, displaying the evaluated dynamic fire assessment network through a knowledge graph, wherein the displaying comprises the steps of constructing a body, constructing a relation and importing the knowledge graph platform. As shown in fig. 15, the body includes fire factor nodes such as power consumption, short-circuit hidden trouble, poor contact, leakage hidden trouble, poor contact and the like, and the initial value of the occurrence probability of each node is defaulted to 0.5; for the simple relation in fire, it is a simple "cause" relation, as shown in fig. 16, the relation of fire factors in the knowledge graph display platform is "cause", the constructed fire factor relation is as shown in fig. 17, and the relation of fire factor nodes includes: the relations of the faults of the consumers, the short-circuit hidden trouble, the faults of the consumers and the contact failure of the consumers are established; the dynamic fire assessment network established in the above process is led into a knowledge graph display platform, as shown in fig. 18, fig. 18 is an overall schematic diagram of the dynamic fire assessment network led into the knowledge graph display platform, fig. 18-1 and fig. 18-2 are partial schematic diagrams, it can be seen that, when the node 'combustible' probability is increased from 0.2 to 0.6, the node probability of 'firing' is increased from 0.2 to 0.3, and the whole knowledge graph based on the dynamic fire assessment network supports the probability of dynamically assessing each node in the fire development.
In the embodiment, a fire risk structural equation model is constructed based on the fire risk characteristic variables by means of consulting experts, consulting documents and the like. And extracting the multi-element heterogeneous data to serve as one of characteristic variable scoring bases, and establishing a more comprehensive numerical information base of the fire risk characteristic variable based on the multi-source heterogeneous data, so that the accuracy of the model evaluation result is improved. After a dynamic fire assessment network is obtained through the fire evolution trend probability, the dynamic fire assessment index system and the preset expert knowledge, the dynamic fire assessment network is further evaluated according to preset test data to determine whether the dynamic fire assessment network can be applied to actual fire assessment or not, and the evaluated dynamic fire assessment network is displayed through a knowledge graph.
According to the invention, the fire risk is quantitatively evaluated through model reasoning, so that the risk can be quantitatively evaluated, the requirement on fire dynamic risk evaluation is met, and an important model support is provided for the current fire-fighting construction.
In addition, an embodiment of the present invention further provides a fire risk assessment system, referring to fig. 19, and fig. 19 is a functional module schematic diagram of an embodiment of the fire risk assessment system according to the present invention. As shown in fig. 19, the fire risk assessment system of the present invention includes:
the acquisition module is used for constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
the determining module is used for acquiring dynamic fire development influence parameters and determining fire evolution trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients;
and the obtaining module is used for obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
Further, the obtaining module includes:
the first construction unit is used for constructing an ontology in a knowledge graph and a relation between the ontology according to a preset fire risk characteristic variable, an intermediate variable corresponding to the fire risk characteristic variable and a preset fire parameter;
and the display unit is used for displaying the model output parameters through a knowledge graph according to the body and the relation between the bodies.
Further, the determining module includes:
the determining unit is used for determining dynamic fire development influence parameters and determining the conditional probability of the dynamic fire development influence parameters according to the path coefficients;
and the obtaining unit is used for obtaining the fire evolution trend probability through a dynamic Bayesian network based on the fire development stage main frame of the dynamic fire development influence parameters and the conditional probability.
Further, the obtaining module further includes:
and the second construction unit is used for constructing a fire risk structural equation model based on the fire risk characteristic variables.
Further, the fire risk assessment system further includes:
the scoring module is used for importing preset multi-source heterogeneous data into the fire risk structural equation model so as to score the fire risk characteristic variable according to the multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises: numeric, picture, video, excel, pdf, and word.
Further, the fire risk assessment system further includes:
and the evaluation unit is used for evaluating the dynamic fire evaluation network through preset test data and displaying the evaluated dynamic fire evaluation network through a knowledge graph.
Further, the obtaining module further includes:
and the training module is used for carrying out model identification, model estimation and model evaluation on the fire risk structure equation model to obtain model output parameters so as to complete the training of the fire risk structure equation model.
The specific implementation of each functional module of the fire risk assessment system of the present invention is basically the same as that of each embodiment of the fire risk assessment method, and is not described herein again.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, on which a fire risk assessment program is stored, where the fire risk assessment program, when executed by a processor, implements the steps of the fire risk assessment method as described above.
For the embodiments of the fire risk assessment system and the computer-readable storage medium of the present invention, reference may be made to the embodiments of the fire risk assessment method of the present invention, and details are not repeated herein.
Furthermore, embodiments of the present invention also provide a computer program product, which includes a computer program that, when being executed by a processor, implements the steps of the fire risk assessment method according to any one of the above embodiments of the fire risk assessment method.
The specific embodiment of the computer program product of the present invention is substantially the same as the embodiments of the fire risk assessment method, and will not be described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A fire risk assessment method, characterized by comprising the steps of:
constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
acquiring dynamic fire development influence parameters, and determining fire development trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients;
and obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge, so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
2. A fire risk assessment method according to claim 1, wherein prior to said step of displaying said model output parameters by means of a knowledge map, further comprising:
according to a preset fire risk characteristic variable, a middle variable corresponding to the fire risk characteristic variable and a preset fire parameter, constructing an ontology in the knowledge graph and a relation between the ontologies;
the step of displaying the model output parameters through a knowledge graph comprises the following steps:
and displaying the model output parameters through the knowledge graph according to the relation between the ontology and the ontology.
3. A fire risk assessment method according to claim 1, wherein said step of determining a dynamic fire development impact parameter and deriving a fire development trend probability through a dynamic bayesian network based on said dynamic fire development impact parameter and said path coefficient comprises:
determining dynamic fire development influence parameters, and determining the conditional probability of the dynamic fire development influence parameters according to the path coefficients;
and acquiring the fire evolution trend probability through a dynamic Bayesian network based on the fire development stage main frame of the dynamic fire development influence parameters and the conditional probability.
4. A fire risk assessment method according to claim 2, wherein said step of constructing a fire risk structural equation model comprises:
and constructing a fire risk structural equation model based on the fire risk characteristic variables.
5. The fire risk assessment method of claim 2, wherein after the step of constructing a fire risk structural equation model and before the step of training the fire risk structural equation model to obtain model output parameters, further comprising:
importing preset multi-source heterogeneous data into the fire risk structural equation model to score the fire risk characteristic variables according to the multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises the following components: numerical values, pictures, videos, excel files, pdf files, and word files.
6. The fire risk assessment method according to claim 1, wherein after the step of deriving a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and a preset expert knowledge, further comprising:
and evaluating the dynamic fire evaluation network through preset test data, and displaying the evaluated dynamic fire evaluation network through a knowledge graph.
7. The fire risk assessment method of claim 1, wherein the step of training the fire risk structural equation model to obtain model output parameters comprises:
and carrying out model identification, model estimation and model evaluation on the fire risk structure equation model to obtain model output parameters so as to complete the training of the fire risk structure equation model.
8. A fire risk assessment system, comprising:
the acquisition module is used for constructing a fire risk structural equation model, training the fire risk structural equation model to obtain model output parameters, displaying the model output parameters through a knowledge graph, and acquiring path coefficients in the model output parameters;
the determining module is used for acquiring dynamic fire development influence parameters and determining fire evolution trend probability through a dynamic Bayesian network based on the dynamic fire development influence parameters and the path coefficients;
and the obtaining module is used for obtaining a dynamic fire assessment network based on the fire evolution trend probability, a preset dynamic fire assessment index system and preset expert knowledge so as to carry out risk quantitative assessment on the fire through the dynamic fire assessment network.
9. A terminal device, characterized in that the terminal device comprises a memory, a processor and a fire risk assessment program stored on the memory and executable on the processor, the fire risk assessment program, when executed by the processor, implementing the steps of the fire risk assessment method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having a fire risk assessment program stored thereon, which when executed by a processor, performs the steps of the fire risk assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210333809.0A CN114819525A (en) | 2022-03-31 | 2022-03-31 | Fire risk assessment method, system, terminal device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210333809.0A CN114819525A (en) | 2022-03-31 | 2022-03-31 | Fire risk assessment method, system, terminal device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114819525A true CN114819525A (en) | 2022-07-29 |
Family
ID=82533205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210333809.0A Pending CN114819525A (en) | 2022-03-31 | 2022-03-31 | Fire risk assessment method, system, terminal device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114819525A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118153972A (en) * | 2024-05-13 | 2024-06-07 | 成都鸿钰网络科技有限公司 | Method and equipment for predicting forest fire risk level based on machine learning |
-
2022
- 2022-03-31 CN CN202210333809.0A patent/CN114819525A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118153972A (en) * | 2024-05-13 | 2024-06-07 | 成都鸿钰网络科技有限公司 | Method and equipment for predicting forest fire risk level based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| El-Zein et al. | Assessment of vulnerability to climate change using a multi-criteria outranking approach with application to heat stress in Sydney | |
| Abdollahian et al. | Techno-social energy infrastructure siting: sustainable energy modeling programming (SEMPro) | |
| Fan et al. | Evaluating the performance of inclusive growth based on the BP neural network and machine learning approach | |
| Li et al. | A Bayesian networks-based risk identification approach for software process risk: the context of Chinese trustworthy software | |
| Shirley et al. | Development of a quantitative Bayesian network mapping objective factors to subjective performance shaping factor evaluations: An example using student operators in a digital nuclear power plant simulator | |
| Pupara et al. | An institution recommender system based on student context and educational institution in a mobile environment | |
| CN111198897A (en) | Scientific research hotspot topic analysis method and device and electronic equipment | |
| Xu et al. | Integrating an option-oriented attitude analysis into investigating the degree of stabilities in conflict resolution | |
| CN114819525A (en) | Fire risk assessment method, system, terminal device and medium | |
| Williams | An ontology based collaborative recommender system for security requirements elicitation | |
| Li et al. | Multi-neighborhood simulated annealing for personalized user project planning | |
| CN113919763A (en) | Power grid disaster analysis method and device based on fuzzy evaluation matrix | |
| JP2020160551A (en) | Analysis support device for personnel item, analysis support method, program, and recording medium | |
| Al-Roumi et al. | Exploring the rate of adoption and implementation depth of building information modeling (BIM): A case of Kuwait | |
| CN113723747A (en) | Analysis report generation method, electronic device and readable storage medium | |
| Ruan et al. | An ordered weighted averaging operator-based cumulative belief degree approach for energy policy evaluation | |
| KR101469081B1 (en) | Method for estimating the distribution and grade cut of exam results in real time | |
| Aryan | Knowledge graph for explainable cyber physical systems: a case study in smart energy grids | |
| Di Thommazo et al. | An automatic approach to detect traceability links using fuzzy logic | |
| Magnusson | Uncertainty Analysis: identification, quantification and propagation | |
| Savchenko-Synyakova et al. | The Tools for Intelligent Data Analysis, Modeling and Forecasting Of Social and Economic Processes | |
| WO2024098357A1 (en) | Power battery control strategy determining method and apparatus, and device control method and apparatus | |
| Gao et al. | Software Quality Evaluation Model based on Multiple Linear Regression and Fuzzy Comprehensive Evaluation Method | |
| US20230316210A1 (en) | Policy decision support apparatus and policy decision support method | |
| EP4276719A1 (en) | Social indicator quantification method and apparatus |
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 |