CN109389795A - Dynamic Fire risk assessment method, device, server and storage medium - Google Patents
Dynamic Fire risk assessment method, device, server and storage medium Download PDFInfo
- Publication number
- CN109389795A CN109389795A CN201811033980.XA CN201811033980A CN109389795A CN 109389795 A CN109389795 A CN 109389795A CN 201811033980 A CN201811033980 A CN 201811033980A CN 109389795 A CN109389795 A CN 109389795A
- Authority
- CN
- China
- Prior art keywords
- model
- risk assessment
- fire
- machine learning
- index
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is suitable for fire-fighting risk assessment technology field, provides a kind of dynamic Fire risk assessment method, device, server and storage medium, wherein described method includes following steps: establishing Zone Risk Assessment model using expert survey；Training sample set is obtained using Zone Risk Assessment model；Machine learning model is established, is trained using training sample the set pair analysis model；Model set-up procedure is executed when there is abnormal alarm to be adjusted machine learning model；Fire risk assessment is carried out using the machine learning model being adjusted；Wherein, model set-up procedure includes: to generate exceptional sample according to abnormal alarm, and training sample set is added in exceptional sample；Re -training is carried out to machine learning model using training sample set.The present invention can make dynamic adjustment to model according to practical fire behavior while learning expertise.
Description
Technical field
The invention belongs to fire-fighting risk assessment technology field more particularly to a kind of dynamic Fire risk assessment method, device,
Server and storage medium.
Background technique
Fire risk assessment is suitable only for assessing social unit in existing wisdom fire-fighting system, and city integrated
There are the social units of different function in vivo, and therefore, this method is not applied for City complex fire risk assessment.In addition,
Expertise is relied primarily in existing evaluation process carries out index weights setting, risk class judgement and risk stratification,
Cause subjectivity very strong, objectivity is insufficient, and These parameters weight is fixed, and is not directed to the monitoring problem of Internet of Things equipment, is ignored
The fire fighting state moment changes this dynamic characteristic, so that assessment result is inaccurate.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of dynamic fire risk assessment sides suitable for City complex
Method, device, server and storage medium are fixed with solving existing assessment models index weights, cannot be adjusted with actual conditions
Whole problem.
The first aspect of the embodiment of the present invention provides a kind of dynamic Fire risk assessment method, comprising:
Zone Risk Assessment model is established using expert survey；
Training sample set is obtained using Zone Risk Assessment model；
Machine learning model is established, is trained using training sample the set pair analysis model；
Model set-up procedure is executed when there is abnormal alarm to be adjusted machine learning model；
Fire risk assessment is carried out using the machine learning model being adjusted；
Wherein, model set-up procedure includes:
Exceptional sample is generated according to abnormal alarm, training sample set is added in exceptional sample；
Re -training is carried out to machine learning model using training sample set.
Preferably, described the step of generating exceptional sample according to abnormal alarm, includes: and obtains when abnormal alarm occurs respectively to refer to
Target score value and the corresponding security level of abnormal alarm, the score value and abnormal alarm of each index are corresponding when being occurred with abnormal alarm
Security level is as exceptional sample.
Preferably, the machine learning model is multiple linear regression model.
Preferably, the step of establishing Zone Risk Assessment model using expert survey include:
City complex is divided into different function subregion, establishes the fire Safety Assessment model of every a kind of function division；
The each function division of City complex is obtained in conjunction with expert survey according to the region parameter of City complex
Weight, the region parameter include fire risk, density of personnel, Division area and different degree；
According to the weight of function division each in City complex, Zone Risk Assessment model is established.
Preferably, described that City complex is divided into different function subregion, establish the fire-fighting peace of every a kind of function division
Assessment models include: entirely
Analysis of Fire Hazard is carried out by the different function subregion to City complex, setting different function subregion disappears
Anti- Safety Influence Factors, the function division include market region, supermarket region, food and drink region, movie theatre region, recreational area,
Administrative office region and apartment and flats region；
According to the security against fire influence factor of different function subregion, the index system of different function subregion is constructed；
Using expert survey, the weight of each index in the index system of different function subregion is determined；
Establish the fire Safety Assessment model of every a kind of function division.
Preferably, it is each to obtain City complex in conjunction with expert survey for the region parameter according to City complex
The weight of function division includes:
Judged by each level index relative importance of index system of the expert survey to every kind of function division
Assignment obtains the fuzzy judgment matrix of every kind of function division；
The fuzzy judgment matrix of every kind of function division is converted, Fuzzy consistent matrix is obtained；
According to Fuzzy consistent matrix, evaluation index initial weight vector is calculated by root method；
By evaluation index initial weight vector, power method iterative method is introduced as iterative initial value and is iterated calculating, obtain every
The weight of a function division.
Preferably, described to pass through each relatively important journey of level index of index system of the expert survey to every kind of function division
Degree carries out judging that assignment is specific:
It is quasi- to rule layer-destination layer, sub- rule layer-rule layer and indicator layer-son of the index system of every kind of function division
Then index relative importance in layer carries out assignment with Fuzzy Scale method.
Preferably, described the step of obtaining training sample set using Zone Risk Assessment model includes: to obtain index score value；
Corresponding security level is calculated according to index score value using Zone Risk Assessment model.
The second aspect of the embodiment of the present invention provides a kind of dynamic fire risk assessment device, comprising:
Regional model establishes module, for establishing Zone Risk Assessment model using expert survey；
Sample acquisition module, for obtaining training sample set using Zone Risk Assessment model；
Training module, for being trained using training sample set to machine learning model；
For generating exceptional sample when there is abnormal alarm training sample is added in exceptional sample by dynamic adjustment module
Collection, and re -training is carried out to machine learning model using training sample set；
Evaluation module carries out regional fire risk assessment using the machine learning model being adjusted.
Further, the regional model establishes module and includes:
Subregion risk assessment unit establishes every a kind of function point for City complex to be divided into different function subregion
The fire Safety Assessment model in area；
Region weight acquiring unit obtains city in conjunction with expert survey for the region parameter according to City complex
The weight of each function division of synthesis, the region parameter include fire risk, density of personnel, Division area and important
Degree；
Zone Risk Assessment unit establishes Regional Risk for the weight according to function division each in City complex
Assessment models.
The third aspect of the embodiment of the present invention provides a kind of server, including memory, processor and is stored in institute
The computer program that can be run in memory and on the processor is stated, the processor executes real when the computer program
Now such as the step of any one dynamic Fire risk assessment method of first aspect.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and any one dynamic fire such as first aspect is realized when the computer program is executed by processor
The step of calamity methods of risk assessment.
The beneficial effects of the present invention are: on the one hand, the embodiment of the present invention using expert survey foundation by being exclusively used in
The Zone Risk Assessment model of City complex obtains training sample set using Zone Risk Assessment model, establishes machine learning
Model, and be trained using training sample the set pair analysis model, model set-up procedure is executed when there is abnormal alarm, to obtain
The machine learning model being adjusted, since training sample set remains the Zone Risk Assessment model established by expert survey
The training sample of generation, therefore Fire risk assessment method of the invention can be while learning expertise according to practical fire
Feelings make dynamic adjustment to assessment models, more accurately to assess the fire risk of City complex.It is another
Aspect, the present invention proposes index system and weighing computation method for City complex, so that the fire wind of City complex
Danger assessment is more scientific and accurate.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram for the dynamic Fire risk assessment method that the embodiment of the present invention one provides；
Fig. 2 is the flow chart that Zone Risk Assessment model is established using expert survey；
Fig. 3 is the structural block diagram of dynamic fire risk assessment device provided by Embodiment 2 of the present invention；
Fig. 4 is that a kind of regional model of embodiment according to the invention establishes the structural block diagram of module；
Fig. 5 is the schematic diagram for the server that the embodiment of the present invention three provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one
Fig. 1 shows the implementation process schematic diagram of the dynamic Fire risk assessment method of the offer of the embodiment of the present invention one.Such as
Shown in Fig. 1, which specifically may include following steps:
Step S1: Zone Risk Assessment model is established using expert survey；
Step S2: training sample set is obtained using Zone Risk Assessment model；
Step S3: establishing machine learning model, is trained using training sample the set pair analysis model；
Step S4: model set-up procedure is executed when there is abnormal alarm, machine learning model is adjusted；
Step S5: fire risk assessment is carried out using the machine learning model being adjusted.
Specifically, step S2 specifically includes following two steps:
Step S21: obtaining index score value, specifically, can be in different zones (such as different cities synthesis) by certain
Time interval (such as one month, a season) acquires multiple groups index score value by Fire-fighting Information System, and specific targets system will
It is described in detail below.
Step S22: calculating corresponding security level according to index score value using Zone Risk Assessment model, specifically, instruction
The sample practiced in sample set includes sample characteristics and sample label, can will be corresponded to using the score value of each index as sample characteristics
Security level as sample label, multiple groups sample characteristics and sample label form training sample set.
Specifically, the model set-up procedure in step S4 specifically includes following two steps:
Step S41: exceptional sample is generated according to abnormal alarm, training sample set is added in exceptional sample；
Step S42: re -training is carried out to machine learning model using training sample set.
Wherein, described the step of generating exceptional sample according to abnormal alarm in step S41, specifically includes following two sons
Step:
Step S411: the score value and the corresponding security level of abnormal alarm of each index when abnormal alarm occurs are obtained；Specifically
The score value on ground, index can be obtained by inquiry Fire-fighting Information System, and security level can be carried out by expert according to practical fire behavior
Assessment obtains, such as when a fire, security level can be preferably minimized, and the score value of index is constant.
Step S412: the corresponding security level of score value and abnormal alarm of each index is as extremely when being occurred using abnormal alarm
Sample.
In some embodiments, the machine learning model can be one of following model or combination: multiple linear
Regression model, softmax regression model, supporting vector machine model, Random Forest model.Preferably, the machine learning model
Including multiple linear regression model.When using the score value of each index as characteristic value (independent variable) and using corresponding security level as
It after label (dependent variable) is trained multiple linear regression model, is readily apparent that, the regression coefficient of multiple linear regression model
Corresponding index will be leveled off to weight.When a fire, trigger model set-up procedure utilizes abnormal sample when fire behavior occurs
This is trained multiple linear regression model, so that the regression coefficient of multiple linear regression model changes, realizes
The dynamic adjustment of model, can generate new index weights according to regression coefficient.
Sample due to training sample set comprising expertise formation and the exceptional sample according to the generation of practical fire behavior, sample
Capacity constantly expands, and multiple linear regression model is constantly iterated according to training sample set, realizes to the whole samples newly formed
This fitting, so as to make dynamic adjustment according to practical fire behavior while learning expertise.
It should be noted that when establishing multiple linear regression model, in order to guarantee that regression model has excellent interpretability
And prediction effect, answer the selection it is first noted that independent variable, criterion is: (1) independent variable must have significant impact to dependent variable,
It and is in close linear correlation；(2) linear correlation between independent variable and dependent variable must be true, rather than in form
's；(3) there should be certain alternative between independent variable, i.e. degree of correlation between independent variable should not be greater than independent variable and because becoming
Amount because degree of correlation；(4) independent variable should have complete statistical data, and predicted value is easy to determine.Multiple linear regression mould
The parameter Estimation of type, it is the same with unary linear regression equation, and under the premise of it is the smallest for requiring error sum of squares, with minimum
Square law solves parameter.
Fig. 2 is the flow chart that Zone Risk Assessment model is established using expert survey.As shown in Fig. 2, in some implementations
In example, the step of step S1 establishes Zone Risk Assessment model using expert survey includes following three sub-step:
Step S11: being divided into different function subregion for City complex, and the security against fire for establishing every a kind of function division is commented
Estimate model.
Specifically, step S11 includes following four steps:
Step S111: Analysis of Fire Hazard is carried out by the different function subregion to City complex, sets different function
Can subregion security against fire influence factor, the function division include market region, supermarket region, food and drink region, movie theatre region,
Recreational area, administrative office region and apartment and flats region；
Wherein, security against fire influence factor includes convention security influence factor and Special Influence factor, each function division
Special Influence factor it is as follows:
Step S112: according to the security against fire influence factor of different function subregion, the index body of different function subregion is constructed
System；Specifically, to rule layer-destination layer of the index system of every kind of function division, sub- rule layer-rule layer and indicator layer-son
Index relative importance in rule layer carries out assignment with 1-9 Fuzzy Scale method.Such as City complex market region disappears
Anti- index of security assessment system is as follows:
Step S113: expert survey is used, determines the weight of each index in the index system of different function subregion；Its
The index weights in middle market region are as follows:
Step S114: the fire Safety Assessment model of every a kind of function division is established.
Step S12: each function of City complex is obtained in conjunction with expert survey according to the region parameter of City complex
The weight of energy subregion, the region parameter includes fire risk, density of personnel, Division area and different degree.
Specifically, step S12 includes following four steps:
Step S121: pass through each level index relative importance of index system of the expert survey to every kind of function division
Judgement assignment is carried out, obtains the fuzzy judgment matrix of every kind of function division；
Step S122: converting the fuzzy judgment matrix of every kind of function division, obtains Fuzzy consistent matrix；
Step S123: according to Fuzzy consistent matrix, evaluation index initial weight vector is calculated by root method；
Step S124: by evaluation index initial weight vector, power method iterative method is introduced as iterative initial value and is iterated meter
It calculates, obtains the weight of each function division.
Step S13: according to the weight of function division each in City complex, Zone Risk Assessment model is established.For example,
Each function division weight is as follows:
The score value of index and weight, which are done weighted sum, can be obtained security level.It should be noted that the score value of index has
Body can obtain by the following method: be checked according to security evaluation project target area by fire-fighting supervisor, and will
Inspection result (selection type result) inputs Fire-fighting Information System, inputs fire-fighting supervisor according to quantification of targets scoring criteria
Selection type result is converted into the score value of corresponding index (A11, A12 ...).Using Zone Risk Assessment model according to index score value meter
Calculate corresponding security level can specifically comprise the following steps: according to each function division in region index score value and weight by
It is weighted summation according to the level of index and can calculate the safe score of each function division, further according to the weight and peace of function division
The weighted sum of full score value can be obtained the security level in region.Index weights can be made more smart by optimizing Weight algorithm model
Really, to guarantee the accuracy of assessment result.
It should be noted that can establish multiple polynary correspondingly with function division when establishing machine learning model
Then linear regression model (LRM) obtains the training sample set of function division using the fire Safety Assessment model of corresponding function subregion,
Corresponding multiple linear regression model is trained using the sample set of function division.By the index score value of corresponding function subregion
The fire risk assessment that function division can be obtained is input in trained multiple linear regression model as a result, function division
Fire risk assessment result be weighted summation operation in conjunction with the weight of function division, the fire risk in region can be obtained
Assessment result.The independent variable quantity of model can be reduced by establishing multiple linear regression model for function division, to reduce model
Trained computational complexity.
Embodiment two
Fig. 3 is the structural block diagram of dynamic fire risk assessment device provided by Embodiment 2 of the present invention.As shown in figure 3, this
Inventive embodiments two provide a kind of dynamic fire risk assessment device, comprising: regional model establishes module 101, sample acquisition
Module 102, training module 103, dynamic adjustment module 104 and evaluation module 105.Wherein, regional model is established module 101 and is used for
Zone Risk Assessment model is established using expert survey；Sample acquisition module 102 using Zone Risk Assessment model for being obtained
Take training sample set；Training module 103 for establishing machine learning model, and using training sample set to machine learning model into
Row training；For generating exceptional sample when there is abnormal alarm training sample is added in exceptional sample by dynamic adjustment module 104
Collection, and re -training is carried out to machine learning model using training sample set；Evaluation module 105 is using by dynamic adjustment module
The machine learning model of 104 re -trainings carries out regional fire risk assessment.
In the present embodiment, module 101 is established by regional model first and establishes Zone Risk Assessment using expert survey
Model；Training sample set is obtained using Zone Risk Assessment model by sample acquisition module 102；Training module 103 utilizes training
Sample set is trained machine learning model；When there is abnormal alarm, dynamic adjustment module 104 generates exceptional sample, will be different
Training sample set is added in normal sample, and carries out re -training, 105 benefit of evaluation module to machine learning model using training sample set
Regional fire risk assessment is carried out with the machine learning model by dynamic adjustment 104 re -training of module, to obtain region
Fire risk assessment result.
Specifically, sample acquisition module 102 may include score value acquiring unit (not shown) and security level computing unit
(not shown).Score value acquiring unit is for obtaining index score value, specifically, can (such as different cities are comprehensive in different zones
Body) certain time interval (such as one month, a season) is pressed by Fire-fighting Information System acquisition multiple groups index score value, it refers specifically to
Mark system has similar description in the first embodiment, and which is not described herein again；Security level computing unit utilizes Zone Risk Assessment
Model calculates corresponding security level according to index score value, and specifically, the sample that training sample is concentrated includes sample characteristics and sample
This label, can be using the score value of each index as sample characteristics, and using corresponding security level as sample label, multiple groups sample is special
Sample label of seeking peace forms training sample set.
Dynamic adjustment module 104 may include that exceptional sample generation unit (not shown) and repetitive exercise unit (do not show
Out).Exceptional sample generates unit and generates exceptional sample according to abnormal alarm, and training sample set is added in exceptional sample.Work as generation
When abnormal alarm, the score value and abnormal alarm that exceptional sample generates each index when the available abnormal alarm of unit occurs are corresponding
Security level；Specifically, the score value of index can by inquiry Fire-fighting Information System obtain, security level can by expert according to
Practical fire behavior is assessed to obtain, such as when a fire, security level can be preferably minimized, and the score value of index is constant.
Exceptional sample generate unit when being occurred using abnormal alarm the score value of each index and the corresponding security level of abnormal alarm as extremely
Sample.Repetitive exercise unit carries out re -training to machine learning model using the training sample set that exceptional sample is added.
Fig. 4 is that a kind of regional model of embodiment according to the invention establishes the structural block diagram of module.As shown in figure 4,
In some embodiments, regional model is established module 101 and be may further include: subregion risk assessment unit 1011, region power
Weight acquiring unit 1012 and Zone Risk Assessment unit 1013.Subregion risk assessment unit 1011 is for dividing City complex
For different function subregion, the fire Safety Assessment model of every a kind of function division is established；Region weight acquiring unit 1012 is used for
The weight of each function division of City complex is obtained in conjunction with expert survey according to the region parameter of City complex, it is described
Region parameter includes fire risk, density of personnel, Division area and different degree；Zone Risk Assessment unit 1013 is used for basis
The weight of each function division in City complex, establishes Zone Risk Assessment model.
In some embodiments, subregion risk assessment unit 1011 can pass through the different function subregion to City complex
Analysis of Fire Hazard is carried out, sets the security against fire influence factor of different function subregion, the function division includes market area
Domain, supermarket region, food and drink region, movie theatre region, recreational area, administrative office region and apartment and flats region, wherein fire-fighting peace
Full influence factor includes convention security influence factor and Special Influence factor, and the Special Influence factor of each function division can join
Examine embodiment one.Then subregion risk assessment unit 1011 can be according to the security against fire influence factor of different function subregion, structure
Build the index system of different function subregion；Specifically, quasi- to rule layer-destination layer of the index system of every kind of function division, son
Then layer-rule layer and index relative importance in the sub- rule layer of indicator layer-, carry out assignment with 1-9 Fuzzy Scale method；Then
Using expert survey, the weight of each index in the index system of different function subregion is determined；The wherein index in market region
Weight can be with reference implementation example one.Subregion risk assessment unit 1011 can establish the fire Safety Assessment of every a kind of function division
Model.
In some embodiments, region weight acquiring unit 1012 is according to the region parameter of City complex, in conjunction with expert
Investigation method, obtain each function division of City complex weight, the region parameter include fire risk, density of personnel,
Division area and different degree.In some embodiments, region weight acquiring unit 1012 can be by expert survey to every kind
Each level index relative importance of the index system of function division carries out judgement assignment, show that the fuzzy of every kind of function division is sentenced
Disconnected matrix；The fuzzy judgment matrix of every kind of function division is converted, Fuzzy consistent matrix is obtained；According to fuzzy consensus square
Battle array calculates evaluation index initial weight vector by root method；By evaluation index initial weight vector, introduced as iterative initial value
Power method iterative method is iterated calculating, obtains the weight of each function division.
Embodiment three
Fig. 5 is the schematic diagram for the server that the embodiment of the present invention three provides.As shown in figure 5, the server packet of the embodiment
It includes: processor 33, memory 31 and being stored in the computer that can be run in the memory 31 and on the processor 33
Program 32, such as dynamic Fire risk assessment method.The processor 33 is realized when executing the computer program as above-mentioned each
Dynamic Fire risk assessment method, such as step S1 to S5 shown in FIG. 1.
The server can be computer and cloud server etc. and calculate equipment.The server may include, but not only
It is limited to, processor 33, memory 31.It will be understood by those skilled in the art that Fig. 3 is only the example of server, do not constitute
Restriction to server may include perhaps combining certain components or different portions than illustrating more or fewer components
Part, such as the server can also include input-output equipment, network access equipment, bus etc..
Alleged processor 33 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 31 can be the internal storage unit of the server, such as the hard disk or memory of server.Institute
The plug-in type hard disk being equipped on the External memory equipment that memory 31 is also possible to the server, such as the server is stated,
Intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash
Card) etc..Further, the memory 31 can also both include the internal storage unit of the server or deposit including outside
Store up equipment.The memory 31 is for other programs and data needed for storing the computer program and the server.
The memory 31 can be also used for temporarily storing the data that has exported or will export.
Example IV
The fourth embodiment of the present invention provides a kind of computer readable storage medium, the computer readable storage medium
It is stored with computer program, such as above-mentioned each dynamic fire risk assessment side is realized when the computer program is executed by processor
Method, such as step S1 to S5 shown in FIG. 1.The computer readable storage medium can be memory, and plug-in type hard disk is intelligently deposited
Card storage (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card)
Deng.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/server and method, Ke Yitong
Other modes are crossed to realize.For example, device/server example described above is only schematical, for example, the mould
The division of block or unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple
Unit or assembly can be combined or can be integrated into another system, or some features can be ignored or not executed.It is another
Point, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device or
The INDIRECT COUPLING or communication connection of unit can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of dynamic Fire risk assessment method characterized by comprising
Zone Risk Assessment model is established using expert survey；
Training sample set is obtained using Zone Risk Assessment model；
Machine learning model is established, is trained using training sample the set pair analysis model；
Model set-up procedure is executed when there is abnormal alarm to be adjusted machine learning model；
Fire risk assessment is carried out using the machine learning model being adjusted；
Wherein, model set-up procedure includes:
Exceptional sample is generated according to abnormal alarm, training sample set is added in exceptional sample；
Re -training is carried out to machine learning model using training sample set.
2. dynamic Fire risk assessment method according to claim 1, which is characterized in that described to be generated according to abnormal alarm
The step of exceptional sample includes: the score value and the corresponding security level of abnormal alarm for obtaining each index when abnormal alarm occurs, with
The score value of each index and the corresponding security level of abnormal alarm are as exceptional sample when abnormal alarm generation.
3. dynamic Fire risk assessment method according to claim 1, which is characterized in that the machine learning model is more
First linear regression model (LRM).
4. dynamic Fire risk assessment method according to claim 1, which is characterized in that establish area using expert survey
The step of domain risk evaluation model includes:
City complex is divided into different function subregion, establishes the fire Safety Assessment model of every a kind of function division；
The weight of each function division of City complex is obtained in conjunction with expert survey according to the region parameter of City complex,
The region parameter includes fire risk, density of personnel, Division area and different degree；
According to the weight of function division each in City complex, Zone Risk Assessment model is established.
5. dynamic Fire risk assessment method according to claim 4, which is characterized in that described to divide City complex
For different function subregion, the fire Safety Assessment model for establishing every a kind of function division includes:
Analysis of Fire Hazard, the fire-fighting peace of setting different function subregion are carried out by the different function subregion to City complex
Full influence factor, the function division include market region, supermarket region, food and drink region, movie theatre region, recreational area, administration
Administrative Area and apartment and flats region；
According to the security against fire influence factor of different function subregion, the index system of different function subregion is constructed；
Using expert survey, the weight of each index in the index system of different function subregion is determined；
Establish the fire Safety Assessment model of every a kind of function division.
6. dynamic Fire risk assessment method according to claim 5, which is characterized in that described according to City complex
Region parameter, in conjunction with expert survey, the weight for obtaining each function division of City complex includes:
Judgement assignment is carried out by each level index relative importance of index system of the expert survey to every kind of function division,
Obtain the fuzzy judgment matrix of every kind of function division；
The fuzzy judgment matrix of every kind of function division is converted, Fuzzy consistent matrix is obtained；
According to Fuzzy consistent matrix, evaluation index initial weight vector is calculated by root method；
By evaluation index initial weight vector, power method iterative method is introduced as iterative initial value and is iterated calculating, obtains each function
The weight of energy subregion.
7. a kind of dynamic fire risk assessment device characterized by comprising
Regional model establishes module, for establishing Zone Risk Assessment model using expert survey；
Sample acquisition module obtains training sample set using Zone Risk Assessment model；
Training module is trained machine learning model using training sample set；
For generating exceptional sample when there is abnormal alarm training sample set is added in exceptional sample by dynamic adjustment module, benefit
Re -training is carried out to machine learning model with training sample set；
Evaluation module carries out regional fire risk assessment using the machine learning model being adjusted.
8. dynamic fire risk assessment device according to claim 7, which is characterized in that the regional model establishes module
Include:
Subregion risk assessment unit establishes every a kind of function division for City complex to be divided into different function subregion
Fire Safety Assessment model；
Region weight acquiring unit obtains city integrated for the region parameter according to City complex in conjunction with expert survey
The weight of each function division of body, the region parameter include fire risk, density of personnel, Division area and different degree；
Zone Risk Assessment unit establishes Zone Risk Assessment model according to the weight of function division each in City complex.
9. a kind of server, including memory, processor and storage can transport in the memory and on the processor
Capable computer program, which is characterized in that the processor realizes such as claim 1 to 6 times when executing the computer program
The step of one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811033980.XA CN109389795A (en) | 2018-09-05 | 2018-09-05 | Dynamic Fire risk assessment method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811033980.XA CN109389795A (en) | 2018-09-05 | 2018-09-05 | Dynamic Fire risk assessment method, device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109389795A true CN109389795A (en) | 2019-02-26 |
Family
ID=65418492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811033980.XA Pending CN109389795A (en) | 2018-09-05 | 2018-09-05 | Dynamic Fire risk assessment method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109389795A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163251A (en) * | 2019-04-15 | 2019-08-23 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of Optimum Identification Method of fire hazard rating, device and terminal device |
| CN110555617A (en) * | 2019-09-05 | 2019-12-10 | 消检通（深圳）科技有限公司 | Real-time dynamic quantitative assessment method for building fire risk based on Internet of things |
| CN111178756A (en) * | 2019-12-29 | 2020-05-19 | 杭州拓深科技有限公司 | Multiple linear regression fire risk assessment method based on environmental big data |
| CN111614938A (en) * | 2020-05-14 | 2020-09-01 | 杭州海康威视系统技术有限公司 | Risk identification method and device |
| CN111815177A (en) * | 2020-07-10 | 2020-10-23 | 杭州海康消防科技有限公司 | Fire safety assessment method, server, system and storage medium |
| CN112215446A (en) * | 2019-07-10 | 2021-01-12 | 小蜜蜂互联（北京）消防信息技术有限公司 | Neural network-based unit dynamic fire risk assessment method |
| CN112801556A (en) * | 2021-04-06 | 2021-05-14 | 深圳市维度数据科技股份有限公司 | Regional influence degree evaluation method and system for pollution discharge behaviors of industrial enterprise |
| CN113856077A (en) * | 2021-10-14 | 2021-12-31 | 赵兵 | Fire rescue measure generation method, device, equipment and storage medium |
| CN113902963A (en) * | 2021-12-10 | 2022-01-07 | 交通运输部公路科学研究所 | Method and device for evaluating fire detection capability of tunnel |
| CN115330177A (en) * | 2022-08-10 | 2022-11-11 | 北京市科学技术研究院 | Urban public facility safety risk assessment method based on causal learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096838A (en) * | 2016-06-14 | 2016-11-09 | 广州市恒迅技防系统有限公司 | Building fire safety evaluation method based on model of fuzzy synthetic evaluation and system |
| CN107909283A (en) * | 2017-11-17 | 2018-04-13 | 武汉科技大学 | A kind of Urban Fire Risk appraisal procedure based on a reference value |
| CN107958274A (en) * | 2017-12-18 | 2018-04-24 | 广东广业开元科技有限公司 | A kind of structural fire protection safety index computational methods based on big data sorting algorithm |
| CN108062392A (en) * | 2017-12-18 | 2018-05-22 | 广东广业开元科技有限公司 | A kind of protection of consumers' rights index calculation method based on big data sorting algorithm |
| CN108376310A (en) * | 2018-02-06 | 2018-08-07 | 深圳前海大观信息技术有限公司 | Building fire risk class appraisal procedure |
-
2018
- 2018-09-05 CN CN201811033980.XA patent/CN109389795A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096838A (en) * | 2016-06-14 | 2016-11-09 | 广州市恒迅技防系统有限公司 | Building fire safety evaluation method based on model of fuzzy synthetic evaluation and system |
| CN107909283A (en) * | 2017-11-17 | 2018-04-13 | 武汉科技大学 | A kind of Urban Fire Risk appraisal procedure based on a reference value |
| CN107958274A (en) * | 2017-12-18 | 2018-04-24 | 广东广业开元科技有限公司 | A kind of structural fire protection safety index computational methods based on big data sorting algorithm |
| CN108062392A (en) * | 2017-12-18 | 2018-05-22 | 广东广业开元科技有限公司 | A kind of protection of consumers' rights index calculation method based on big data sorting algorithm |
| CN108376310A (en) * | 2018-02-06 | 2018-08-07 | 深圳前海大观信息技术有限公司 | Building fire risk class appraisal procedure |
Non-Patent Citations (1)
| Title |
|---|
| 张立宁: "高层建筑火灾风险评价及智能报警系统研究", 《北京理工大学博士学位论文》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163251A (en) * | 2019-04-15 | 2019-08-23 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of Optimum Identification Method of fire hazard rating, device and terminal device |
| CN112215446A (en) * | 2019-07-10 | 2021-01-12 | 小蜜蜂互联（北京）消防信息技术有限公司 | Neural network-based unit dynamic fire risk assessment method |
| CN110555617A (en) * | 2019-09-05 | 2019-12-10 | 消检通（深圳）科技有限公司 | Real-time dynamic quantitative assessment method for building fire risk based on Internet of things |
| CN110555617B (en) * | 2019-09-05 | 2024-03-15 | 消检通（深圳）科技有限公司 | Real-time dynamic quantitative assessment method for building fire risk based on Internet of things |
| CN111178756B (en) * | 2019-12-29 | 2024-02-27 | 杭州拓深科技有限公司 | Multiple linear regression fire risk assessment method based on environmental big data |
| CN111178756A (en) * | 2019-12-29 | 2020-05-19 | 杭州拓深科技有限公司 | Multiple linear regression fire risk assessment method based on environmental big data |
| CN111614938A (en) * | 2020-05-14 | 2020-09-01 | 杭州海康威视系统技术有限公司 | Risk identification method and device |
| CN111614938B (en) * | 2020-05-14 | 2021-11-02 | 杭州海康威视系统技术有限公司 | Risk identification method and device |
| CN111815177A (en) * | 2020-07-10 | 2020-10-23 | 杭州海康消防科技有限公司 | Fire safety assessment method, server, system and storage medium |
| CN112801556A (en) * | 2021-04-06 | 2021-05-14 | 深圳市维度数据科技股份有限公司 | Regional influence degree evaluation method and system for pollution discharge behaviors of industrial enterprise |
| CN113856077A (en) * | 2021-10-14 | 2021-12-31 | 赵兵 | Fire rescue measure generation method, device, equipment and storage medium |
| CN113902963B (en) * | 2021-12-10 | 2022-06-17 | 交通运输部公路科学研究所 | Method and device for evaluating fire detection capability of tunnel |
| CN113902963A (en) * | 2021-12-10 | 2022-01-07 | 交通运输部公路科学研究所 | Method and device for evaluating fire detection capability of tunnel |
| CN115330177A (en) * | 2022-08-10 | 2022-11-11 | 北京市科学技术研究院 | Urban public facility safety risk assessment method based on causal learning |
| CN115330177B (en) * | 2022-08-10 | 2024-02-13 | 北京市科学技术研究院 | Urban public facility security risk assessment method based on causal learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389795A (en) | Dynamic Fire risk assessment method, device, server and storage medium | |
| CN109190943A (en) | Dynamic Fire risk assessment method, device and server based on machine learning | |
| CN109118095A (en) | Dynamic Fire risk assessment method, device and server based on machine learning | |
| CN109102166A (en) | A kind of comprehensive Fire risk assessment method, device and server | |
| CN107506941A (en) | A kind of enterprise in charge of construction's credit assessment method and system based on big data technology | |
| CN108241964A (en) | Capital construction scene management and control mobile solution platform based on BP artificial nerve network model algorithms | |
| CN107454105A (en) | A kind of multidimensional network safety evaluation method based on AHP and grey correlation | |
| Behboudian et al. | A long-term prediction of domestic water demand using preprocessing in artificial neural network | |
| CN110069815A (en) | Index system construction method, system and terminal device | |
| Williams | Predicting completed project cost using bidding data | |
| Soares dos Santos et al. | Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America | |
| CN103577876A (en) | Credible and incredible user recognizing method based on feedforward neural network | |
| CN109858729A (en) | A kind of power distribution network methods of risk assessment and device | |
| CN109829627A (en) | A kind of safe confidence appraisal procedure of Electrical Power System Dynamic based on integrated study scheme | |
| CN110941933B (en) | Complex electromagnetic environment fidelity assessment model system and method based on similarity theory | |
| CN110889207B (en) | Deep learning-based intelligent assessment method for credibility of system combination model | |
| CN108492049A (en) | A kind of system for the P2P platform operation risk assessment that logic-based returns | |
| CN108459997A (en) | High skewness data value probability forecasting method based on deep learning and neural network | |
| Rogachev et al. | Fuzzy cognitive modeling of the integral level of regional food security | |
| CN110533109A (en) | A kind of storage spraying production monitoring data and characteristic analysis method and its device | |
| Wu et al. | Stochastic modeling of artificial neural networks for real-time hydrological forecasts based on uncertainties in transfer functions and ANN weights | |
| CN110866694A (en) | Power grid construction project financial evaluation system and method | |
| CN108711100A (en) | A kind of system of the P2P platform operation risk assessment based on neural network | |
| CN110363443A (en) | The operation situation evaluation method and device of power spot market | |
| CN116415836A (en) | Security evaluation method for intelligent power grid information system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190226 |