CN109190943A - Dynamic Fire risk assessment method, device and server based on machine learning - Google Patents
Dynamic Fire risk assessment method, device and server based on machine learning Download PDFInfo
- Publication number
- CN109190943A CN109190943A CN201810947241.5A CN201810947241A CN109190943A CN 109190943 A CN109190943 A CN 109190943A CN 201810947241 A CN201810947241 A CN 201810947241A CN 109190943 A CN109190943 A CN 109190943A
- Authority
- CN
- China
- Prior art keywords
- risk assessment
- model
- fire
- abnormal alarm
- 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
- 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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The present invention is suitable for fire-fighting risk assessment technology field, provide a kind of dynamic Fire risk assessment method, device, server and storage medium based on machine learning, wherein, described method includes following steps: establishing Zone Risk Assessment model using expert graded；Training sample set is obtained using Zone Risk Assessment model；Softmax regression 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 softmax regression model；Fire risk assessment is carried out using the softmax regression 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 softmax regression 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 risks based on machine learning
Appraisal procedure, device and server.
Background technique
Fire risk assessment is suitable only for social unit and is assessed in existing wisdom fire-fighting system, and City complex
Inside there is the social unit of different function, therefore, this method is not applied for City complex fire risk assessment.In addition, commenting
Expertise is relied primarily on during estimating and carries out index weights setting, risk class judgement and risk stratification, leads to 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 had ignored fire fighting state
Moment changes this dynamic characteristic, so that assessment result is inaccurate.
Summary of the invention
In view of this, the dynamic Fire risk assessment method that the embodiment of the invention provides a kind of based on machine learning, dress
It sets, server and storage medium, is fixed with solving existing assessment models index weights, what cannot be adjusted with actual conditions asks
Topic.
The first aspect of the embodiment of the present invention provides a kind of dynamic Fire risk assessment method based on machine learning, packet
It includes:
Zone Risk Assessment model is established using expert graded；
Training sample set is obtained using Zone Risk Assessment model；
Softmax regression 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 softmax regression model；
Fire risk assessment is carried out using the softmax regression 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 softmax regression model using training sample set.
Further, described the step of generating exceptional sample according to abnormal alarm includes: each when obtaining abnormal alarm generation
The corresponding security level of score value and abnormal alarm of index, the score value and abnormal alarm of each index are corresponding when being occurred with abnormal alarm
Security level as exceptional sample.
Further, described the step of establishing Zone Risk Assessment model using expert graded, specifically includes:
By carrying out Analysis of Fire Hazard, the security against fire influence factor of setting regions to region；
Index system is constructed according to security against fire influence factor；
The weight of each index in index system is determined using expert graded.
The second aspect of the embodiment of the present invention provides a kind of dynamic fire risk assessment device based on machine learning, packet
It includes:
Regional model establishes module, for establishing Zone Risk Assessment model using expert graded；
Sample acquisition module, for obtaining training sample set using Zone Risk Assessment model；
Training module, for establishing softmax regression model, and using training sample set to softmax regression model into
Row training；
For generating exceptional sample when there is abnormal alarm training sample is added in exceptional sample by dynamic adjustment module
Collection carries out re -training to softmax regression model using training sample set；
Evaluation module carries out regional fire risk assessment using the softmax regression model being adjusted.
Further, the dynamic adjustment module is specifically used for obtaining the score value and exception of each index when abnormal alarm occurs
It alarms corresponding security level, the corresponding security level of score value and abnormal alarm of each index is as different when being occurred using abnormal alarm
Normal sample.
Further, the regional model is established module and is specifically included:
Factor determines submodule, for by carrying out Analysis of Fire Hazard, the security against fire shadow of setting regions to region
The factor of sound；
Establishing submodule, for constructing index system according to security against fire influence factor；
Weight Acquisition submodule, for determining the weight of each index in index system using expert graded.
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
The step of now such as any one of first aspect based on the dynamic Fire risk assessment method of machine learning.
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, realizes that any one such as first aspect is based on machine when the computer program is executed by processor
The step of dynamic Fire risk assessment method of device study.
The beneficial effects of the present invention are: on the one hand, the embodiment of the present invention is by establishing region wind using expert graded
Dangerous assessment models obtain training sample set using Zone Risk Assessment model, establish softmax regression model, and utilize training
Sample the set pair analysis model is trained, and model set-up procedure is executed when there is abnormal alarm, thus what acquisition was adjusted
Softmax regression model, since training sample set remains the Zone Risk Assessment model generation established by expert graded
Training sample, thus Fire risk assessment method of the invention can while learning expertise according to practical fire behavior to commenting
Estimate model and make dynamic adjustment, more accurately to predict fire risk.On the other hand, the present invention is directed to city
Region proposes index system and weighing computation method, so that fire risk 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 for the dynamic Fire risk assessment method based on machine learning that the embodiment of the present invention one provides
Schematic diagram；
Fig. 2 is the flow chart that Zone Risk Assessment model is established using expert graded；
Fig. 3 is the structural block diagram of dynamic fire risk assessment device provided by Embodiment 2 of the present invention；
Fig. 4 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 realization of the dynamic Fire risk assessment method based on machine learning of the offer of the embodiment of the present invention one
Flow diagram.As shown in Figure 1, being somebody's turn to do the dynamic Fire risk assessment method based on machine learning specifically may include following steps:
Step S1: Zone Risk Assessment model is established using expert graded；
Step S2: training sample set is obtained using Zone Risk Assessment model；
Step S3: establishing softmax regression model, is trained using training sample the set pair analysis model；
Step S4: model set-up procedure is executed when there is abnormal alarm, softmax regression model is adjusted；
Step S5: fire risk assessment is carried out using the softmax regression model being adjusted.
Specifically, step S2 specifically includes following two steps:
Step S21: obtaining index score value can specifically be looked by certain time interval (such as one month, a season)
The database for asking the Fire-fighting Information System in region acquires multiple groups index score value, and every group of index score value includes all fingers in index system
Target score value.Specific targets system will be described below in detail.
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 softmax regression 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 inquiring the database of Fire-fighting Information System, and security level can be by expert according to reality
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.
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.
When a fire, trigger model set-up procedure returns softmax using exceptional sample when fire behavior occurs
Model is trained, so that softmax regression model changes.
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 softmax regression model is constantly iterated according to training sample set, realizes to the whole samples newly formed
Fitting, so as to make dynamic adjustment according to practical fire behavior while learning expertise.
Fig. 2 is the flow chart that Zone Risk Assessment model is established using expert graded.As shown in Fig. 2, in some implementations
In example, the step of step S1 establishes Zone Risk Assessment model using expert graded, specifically includes following three sub-step:
Step S11: by carrying out Analysis of Fire Hazard, the security against fire influence factor of setting regions to region；
Step S12: index system is constructed according to security against fire influence factor；
Step S13: the weight of each index in index system is determined using expert graded.
Specifically, the security against fire influence factor and corresponding index system of expert investigation setting regions can be passed through；So
Afterwards to the relatively important journey of index in rule layer-destination layer of index system, sub- rule layer-rule layer and the sub- rule layer of indicator layer-
Degree carries out assignment with 1-9 Fuzzy Scale method.Such as the fire Safety Assessment index system in City complex market region is such as
Under:
Using expert graded, the weight of each index in the index system of different function subregion is determined；Such as market area
The index weights in domain are as follows:
Specifically, step S13 includes following four steps:
Step S131: carrying out judgement assignment to each level index relative importance of index system by expert graded,
Obtain fuzzy judgment matrix；
Step S132: converting fuzzy judgment matrix, obtains Fuzzy consistent matrix；
Step S133: according to Fuzzy consistent matrix, evaluation index initial weight vector is calculated by root method；
Step S134: 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.
The score value of the index of Zone Risk Assessment model and weight, which are done weighted sum operation, can be obtained safe scoring.According to
The corresponding risk class of safety scoring can be obtained in the corresponding quantizing range of risk class.Such as below be a kind of risk class with
The table of comparisons of the quantizing range to score safely:
It should be noted that the score value of index can specifically obtain by the following method: by fire-fighting supervisor according to peace
Full evaluation item checks target area, and inspection result (selection type result) is inputted Fire-fighting Information System, and foundation refers to
Scalarization scoring criteria converts the selection type result that fire-fighting supervisor inputs to the score value of corresponding index (A11, A12 ...).
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 based on machine learning, comprising: regional model establishes mould
Block 101, sample acquisition module 102, training module 103, dynamic adjustment module 104 and evaluation module 105.Wherein, regional model
Module 101 is established for establishing Zone Risk Assessment model using expert graded；Sample acquisition module 102 is used to utilize region
Risk evaluation model obtains training sample set；Training module 103 utilizes training sample for establishing softmax regression model
Collection is trained softmax regression model；Dynamic adjustment module 104 is used to generate exceptional sample when there is abnormal alarm,
Training sample set is added in exceptional sample, and re -training is carried out to softmax regression model using training sample set；Assess mould
Block 105 carries out regional fire risk assessment using the softmax regression model by dynamic adjustment 104 re -training of module.
In the present embodiment, module 101 is established by regional model first and establishes Zone Risk Assessment using expert graded
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 softmax regression model；When there is abnormal alarm, dynamic adjustment module 104 generates exceptional sample,
Training sample set is added in exceptional sample, and re -training is carried out to softmax regression model using training sample set, assesses mould
Block 105 carries out regional fire risk assessment using the softmax regression model by dynamic adjustment 104 re -training of module, from
And obtain regional fire risk evaluation result.
Further, the dynamic adjustment module is specifically used for obtaining the score value and exception of each index when abnormal alarm occurs
It alarms corresponding security level, the corresponding security level of score value and abnormal alarm of each index is as different when being occurred using abnormal alarm
Normal sample.
Further, the regional model is established module and is specifically included:
Factor determines submodule, for by carrying out Analysis of Fire Hazard, the security against fire shadow of setting regions to region
The factor of sound；
Establishing submodule, for constructing index system according to security against fire influence factor；
Weight Acquisition submodule, for determining the weight of each index in index system using expert graded.
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 press in the zone certain time interval (such as
One month, a season) multiple groups index score value acquired by the database of inquiry Fire-fighting Information System, specific targets system is the
There is similar description in one embodiment, which is not described herein again；Security level computing unit is using Zone Risk Assessment model according to finger
It marks score value and calculates corresponding security level, specifically, the sample that training sample is concentrated includes sample characteristics and sample label, can be with
Using the score value of each index as sample characteristics, using corresponding security level as sample label, multiple groups sample characteristics and sample mark
Label form 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 be obtained by inquiring the database of Fire-fighting Information System, and security level can be by
Expert is assessed to obtain according to practical fire behavior, such as when a fire, security level can be preferably minimized, point of index
It is worth constant.Exceptional sample generates the score value of each index and abnormal alarm corresponding security level when unit is occurred with abnormal alarm and makees
For exceptional sample.Repetitive exercise unit carries out again softmax regression model using the training sample set that exceptional sample is added
Training.
Embodiment three
Fig. 4 is the schematic diagram for the server that the embodiment of the present invention three provides.As shown in figure 4, 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 based on machine learning, 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. 4 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, is realized when the computer program is executed by processor such as the above-mentioned respectively dynamic fire based on machine learning
Calamity methods of risk assessment, such as step S1 to S5 shown in FIG. 1.The computer readable storage medium can be memory, grafting
Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..
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 (8)
1. a kind of dynamic Fire risk assessment method based on machine learning characterized by comprising
Zone Risk Assessment model is established using expert graded；
Training sample set is obtained using Zone Risk Assessment model；
Softmax regression 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 softmax regression model；
Fire risk assessment is carried out using the softmax regression 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 softmax regression model using training sample set.
2. the dynamic Fire risk assessment method according to claim 1 based on machine learning, which is characterized in that described
The step of generating exceptional sample according to abnormal alarm includes: that the score value and abnormal alarm of each index when obtaining abnormal alarm generation are corresponding
Security level, the corresponding security level of score value and abnormal alarm of each index is as exceptional sample when being occurred using abnormal alarm.
3. the dynamic Fire risk assessment method according to claim 2 based on machine learning, which is characterized in that the benefit
The step of establishing Zone Risk Assessment model with expert graded specifically includes:
By carrying out Analysis of Fire Hazard, the security against fire influence factor of setting regions to region；
Index system is constructed according to security against fire influence factor；
The weight of each index in index system is determined using expert graded.
4. a kind of dynamic fire risk assessment device based on machine learning characterized by comprising
Regional model establishes module, for establishing Zone Risk Assessment model using expert graded；
Sample acquisition module, for obtaining training sample set using Zone Risk Assessment model；
Training module instructs softmax regression model for establishing softmax regression model, and using training sample set
Practice；
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 softmax regression model with training sample set；
Evaluation module carries out regional fire risk assessment using the softmax regression model being adjusted.
5. the dynamic fire risk assessment device according to claim 4 based on machine learning, which is characterized in that described dynamic
State adjusts module and is specifically used for obtaining the score value and the corresponding security level of abnormal alarm of each index when abnormal alarm occurs, with different
The score value of each index and the corresponding security level of abnormal alarm are as exceptional sample when often alarm occurs.
6. the dynamic fire risk assessment device according to claim 5 based on machine learning, which is characterized in that the area
Domain model is established module and is specifically included:
Factor determines submodule, for by carrying out Analysis of Fire Hazard to region, the security against fire of setting regions influence because
Element；
Establishing submodule, for constructing index system according to security against fire influence factor；
Weight Acquisition submodule, for determining the weight of each index in index system using expert graded.
7. 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 that claims 1 to 3 such as is appointed when executing the computer program
The step of one the method.
8. 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 claims 1 to 3 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810947241.5A CN109190943A (en) | 2018-08-20 | 2018-08-20 | Dynamic Fire risk assessment method, device and server based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810947241.5A CN109190943A (en) | 2018-08-20 | 2018-08-20 | Dynamic Fire risk assessment method, device and server based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190943A true CN109190943A (en) | 2019-01-11 |
Family
ID=64918859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810947241.5A Pending CN109190943A (en) | 2018-08-20 | 2018-08-20 | Dynamic Fire risk assessment method, device and server based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190943A (en) |
Cited By (9)
| 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 |
| CN110348684A (en) * | 2019-06-06 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Service call risk model generation method, prediction technique and respective device |
| CN111353386A (en) * | 2020-02-04 | 2020-06-30 | 重庆特斯联智慧科技股份有限公司 | Fire-fighting risk intelligent evaluation method and system based on deep learning |
| 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 |
| CN113033391A (en) * | 2021-03-24 | 2021-06-25 | 浙江中辰城市应急服务管理有限公司 | Fire risk early warning research and judgment method and system |
| 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 |
| CN114399816A (en) * | 2021-12-28 | 2022-04-26 | 北方工业大学 | Community fire risk sensing method and device |
| CN117367435A (en) * | 2023-12-06 | 2024-01-09 | 深圳大学 | Evacuation path planning method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913604A (en) * | 2016-05-18 | 2016-08-31 | 中国计量大学 | Fire occurrence determining method and device based on unmanned aerial vehicle |
| 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 |
| CN106886858A (en) * | 2017-02-23 | 2017-06-23 | 深圳凯达通光电科技有限公司 | A kind of building fire Risk Evaluating 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 |
| 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
- 2018-08-20 CN CN201810947241.5A patent/CN109190943A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913604A (en) * | 2016-05-18 | 2016-08-31 | 中国计量大学 | Fire occurrence determining method and device based on unmanned aerial vehicle |
| 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 |
| CN106886858A (en) * | 2017-02-23 | 2017-06-23 | 深圳凯达通光电科技有限公司 | A kind of building fire Risk Evaluating 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 |
| 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 (5)
| Title |
|---|
| 丁承君，赵泽羽，朱雪宏，冯玉伯: "神经网络在智能火灾预警系统的应用", 《传感器与微系统》 * |
| 伍爱友: "基于神经网络和遗传算法的城市火灾风险评价模型", 《中国安全科学学报》 * |
| 刘胜: "《智能预报技术及其在船舶工程中的应用》", 30 November 2015 * |
| 吴芳: "AHP 法对提速线路能效综合评价的算法研究", 《兰州铁道学院学报 (自然科学版)》 * |
| 张立宁: "高层建筑火灾风险评价及智能报警系统研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (14)
| 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 |
| CN110348684A (en) * | 2019-06-06 | 2019-10-18 | 阿里巴巴集团控股有限公司 | Service call risk model generation method, prediction technique and respective device |
| CN111353386B (en) * | 2020-02-04 | 2023-01-17 | 重庆特斯联智慧科技股份有限公司 | Fire-fighting risk intelligent assessment method and system based on deep learning |
| CN111353386A (en) * | 2020-02-04 | 2020-06-30 | 重庆特斯联智慧科技股份有限公司 | Fire-fighting risk intelligent evaluation method and system based on deep learning |
| 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 |
| CN113033391A (en) * | 2021-03-24 | 2021-06-25 | 浙江中辰城市应急服务管理有限公司 | Fire risk early warning research and judgment method and system |
| CN113033391B (en) * | 2021-03-24 | 2022-03-08 | 浙江中辰城市应急服务管理有限公司 | Fire risk early warning research and judgment method and system |
| 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 |
| 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 |
| CN114399816A (en) * | 2021-12-28 | 2022-04-26 | 北方工业大学 | Community fire risk sensing method and device |
| CN114399816B (en) * | 2021-12-28 | 2023-04-07 | 北方工业大学 | Community fire risk sensing method and device |
| CN117367435A (en) * | 2023-12-06 | 2024-01-09 | 深圳大学 | Evacuation path planning method, device, equipment and storage medium |
| CN117367435B (en) * | 2023-12-06 | 2024-02-09 | 深圳大学 | Evacuation path planning method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| 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 | |
| CN109389795A (en) | Dynamic Fire risk assessment method, device, server and storage medium | |
| CN106779755A (en) | A kind of network electric business borrows or lends money methods of risk assessment and model | |
| Arshadi Khamseh et al. | A new fuzzy TOPSIS-TODIM hybrid method for green supplier selection using fuzzy time function | |
| CN107633323A (en) | Core protects method, apparatus, computer equipment and the storage medium of difficulty prediction | |
| CN109102166A (en) | A kind of comprehensive Fire risk assessment method, device and server | |
| CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
| CN108241964A (en) | Capital construction scene management and control mobile solution platform based on BP artificial nerve network model algorithms | |
| CN110298663A (en) | Based on the wide fraudulent trading detection method learnt deeply of sequence | |
| CN107944761A (en) | Early warning and monitoring analysis method is complained based on artificial intelligence protection of consumers' rights index enterprise | |
| CN109829627A (en) | A kind of safe confidence appraisal procedure of Electrical Power System Dynamic based on integrated study scheme | |
| CN109919608A (en) | A kind of recognition methods, device and the server of high-risk transaction agent | |
| CN113470475A (en) | Real-operation learning assessment method and system based on scene simulation and Internet of things | |
| Wanke et al. | Revisiting camels rating system and the performance of Asean banks: a comprehensive mcdm/z-numbers approach | |
| Jamshidi et al. | Using artificial neural networks and system identification methods for electricity price modeling | |
| Jauhar et al. | An approach to solve multi-criteria supplier selection while considering environmental aspects using differential evolution | |
| CN108711100A (en) | A kind of system of the P2P platform operation risk assessment based on neural network | |
| Telipenko et al. | Results of research on development of an intellectual information system of bankruptcy risk assessment of the enterprise | |
| CN110866694A (en) | Power grid construction project financial evaluation system and method | |
| Indriyanti et al. | The web-based estimation of motorcycles sales using linear regression method | |
| Pang et al. | Wt model & applications in loan platform customer default prediction based on decision tree algorithms | |
| CN110220727A (en) | A kind of method for detecting abnormality and device of electric machinery equipment | |
| CN111080046A (en) | Transmission technology maturity assessment method and device | |
| CN106886858A (en) | A kind of building fire Risk Evaluating 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 |