CN109800961A - A kind of fire rescue decision-making technique, device, storage medium and terminal device - Google Patents
A kind of fire rescue decision-making technique, device, storage medium and terminal device Download PDFInfo
- Publication number
- CN109800961A CN109800961A CN201811611894.2A CN201811611894A CN109800961A CN 109800961 A CN109800961 A CN 109800961A CN 201811611894 A CN201811611894 A CN 201811611894A CN 109800961 A CN109800961 A CN 109800961A
- Authority
- CN
- China
- Prior art keywords
- fire
- decision
- grade
- rescue
- information
- 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
Landscapes
- Fire Alarms (AREA)
Abstract
The present invention relates to fire rescue technical field more particularly to a kind of fire rescue decision-making technique, device, storage medium and terminal devices.The described method includes: obtaining place occurs for fire environmental information and fire protection patrol information；Environmental information is input in the machine learning model after training, the fire behavior grade of machine learning model output is obtained；The architecture information that place occurs for fire is obtained, and determines that the fire hazard rating in place occurs for fire according to architecture information；Determine the fire-fighting grade of skill that the rescue personnel within the scope of the pre-determined distance of place occurs apart from fire；By fire behavior grade, fire hazard rating, fire-fighting grade of skill and fire protection patrol information input into preset decision model, obtain the result of decision of decision model output, to generate efficient, the correct result of decision by comprehensively considering fire behavior grade, fire hazard rating, fire-fighting grade of skill and fire protection patrol information, casualties and property loss caused by fire are reduced, fire hazard is reduced.
Description
Technical field
The present invention relates to fire rescue technical fields more particularly to a kind of fire rescue decision-making technique, device, computer can
Read storage medium and terminal device.
Background technique
After fire generation, if handling aptly, there will be larger chance to put out most fire, be made to reduce fire
At loss.However, existing fire monitoring system can only often provide simple warning information, it can only such as issue alarm bell and mention
Show, so that not knowing fire and rescue situations in policymaker's short time, it is difficult to accurately rescue decision is made, if pacified rashly
Arrange rescue personnel's fire extinguishing, it is possible to can be because the fire-fighting level of skill of rescue personnel is limited or the factors such as fire-fighting equipment is insufficient cause
Casualties, and if rescue personnel is not arranged to put out a fire, wait fire department to come to put out a fire, then may cause originally can be by fire
The fire that rescue personnel near scene puts out is unable to get timely control, causes meaningless property loss.
To sum up, how aid decision making person, which formulates efficient, correct rescue decision scheme, becomes those skilled in the art urgently
Problem to be solved.
Summary of the invention
The embodiment of the invention provides a kind of fire rescue decision-making technique, device, computer readable storage medium and terminals
Equipment, can aid decision making person formulate efficiently, correctly rescue decision scheme, to reduce casualties and property caused by fire
Loss reduces fire hazard.
The embodiment of the present invention in a first aspect, providing a kind of fire rescue decision-making technique, comprising:
Obtain place occurs for fire environmental information and fire protection patrol information；
The environmental information is input in the machine learning model after training, the machine learning mould after obtaining the training
The fire behavior grade of type output；
The architecture information that place occurs for the fire is obtained, and determines that place occurs for the fire according to the architecture information
Fire hazard rating；
Determine the fire-fighting grade of skill that the rescue personnel within the scope of the pre-determined distance of place occurs apart from the fire；
The fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information is defeated
Enter into preset decision model, obtain the result of decision of the decision model output, the result of decision is used to indicate whether
It needs to take rescue measure, and indicates corresponding rescue plan when needing and taking rescue measure.
Further, the machine learning model is obtained by following step training:
The first training sample of the first preset quantity is obtained, each first training sample includes one group of corresponding environment letter
Breath；
Mark the corresponding standard fire behavior grade of each first training sample；
Each first training sample is input in initial machine learning model, the initial machine learning is obtained
The training fire behavior grade of model output；
Calculate the error between the trained fire behavior grade and the standard fire behavior grade；
If the error is unsatisfactory for preset condition, the model parameter of the machine learning model is adjusted, and model is joined
Number machine learning model adjusted is returned and is executed each first training sample input as initial machine learning model
Step and subsequent step into initial machine learning model；
If the error meets the preset condition, it is determined that the machine learning model training is completed.
Preferably, the decision model is obtained by following step training:
The second training sample of the second preset quantity is obtained, each second training sample includes fire behavior grade, one
A fire hazard rating, a fire-fighting grade of skill, a fire protection patrol information and a criteria decision result；
Each second training sample is converted into corresponding trained numerical value vector according to default corresponding relationship；
Each trained numerical value vector is input in initial decision model and is trained, trained decision is obtained
Model.
Optionally, described by the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire-fighting
Inspection information input obtains the result of decision of the decision model output into preset decision model, comprising:
According to the default corresponding relationship, the fire behavior grade, the fire hazard rating, the fire-fighting skill are determined respectively
It can grade and the corresponding numerical value of the fire protection patrol information；
Each numerical value is formed into corresponding numerical value vector, and the numerical value vector is input to preset decision model
In, obtain the result of decision of the decision model output.
Further, the decision model includes decision table；
By the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information
It is input to before preset decision model, comprising:
The sample record of third preset quantity is obtained, each sample record includes a fire behavior grade, a fire danger
Dangerous grade, a fire-fighting grade of skill and a fire protection patrol information；
Determine the corresponding default result of decision of each sample record, and by the default result of decision and corresponding sample
Record is saved into the decision table of the decision model.
Preferably, described by the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire-fighting
Inspection information input obtains the result of decision of the decision model output into preset decision model, comprising:
The fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information is defeated
Enter into preset decision model, to search corresponding sample record in the decision table of the decision model；
The found corresponding default result of decision of sample record is obtained, and the acquired default result of decision is determined
For the result of decision of decision model output.
Optionally, the determining fire-fighting technical ability that the rescue personnel within the scope of the pre-determined distance of place occurs apart from the fire
Grade, comprising:
Obtain the location information that place occurs for the fire；
The rescue personnel occurred within the scope of the pre-determined distance of place apart from the fire is determined according to the positional information；
The administration of the prevention and control information of the rescue personnel is obtained, and the rescue personnel is determined according to the administration of the prevention and control information
Fire-fighting grade of skill.
The second aspect of the embodiment of the present invention provides a kind of fire rescue decision making device, comprising:
The environmental information and fire protection patrol information in place occur for obtaining fire for data obtaining module；
Fire behavior level determination module is obtained for the environmental information to be input in the machine learning model after training
The fire behavior grade of machine learning model output after the training；
Fire hazard rating determining module occurs the architecture information in place for obtaining the fire, and is built according to described
It builds information and determines that the fire hazard rating in place occurs for the fire；
Grade of skill determining module, for determining the rescue personnel occurred within the scope of the pre-determined distance of place apart from the fire
Fire-fighting grade of skill；
Result of decision generation module is used for the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill
With the fire protection patrol information input into preset decision model, the result of decision of the decision model output is obtained, it is described
The result of decision is used to indicate whether to need to take rescue measure, and corresponding rescue meter is indicated when needing to take rescue measure
It draws.
The third aspect of the embodiment of the present invention, provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
It realizes as described in aforementioned first aspect the step of fire rescue decision-making technique.
The fourth aspect of the embodiment of the present invention, provides a kind of computer readable storage medium, described computer-readable to deposit
Storage media is stored with computer program, and the fire as described in aforementioned first aspect is realized when the computer program is executed by processor
The step of rescuing decision-making technique.
As can be seen from the above technical solutions, the embodiment of the present invention has the advantage that
In the embodiment of the present invention, the machine after training is input to by the way that collected environmental information in place is occurred for fire
In learning model, the fire behavior grade of fire development can be quickly and accurately determined, while obtaining the fire protection patrol that place occurs for fire
Information, and the architecture information in place is occurred to determine that the fire hazard rating in place, Yi Jiji occur for fire by acquisition fire
When determine the fire-fighting grade of skill that the rescue personnel within the scope of the pre-determined distance of place occurs apart from fire, and by fire behavior grade, fire
Calamity danger classes, fire-fighting grade of skill and fire protection patrol information input are into preset decision model, by comprehensively considering fire
Feelings grade, fire hazard rating, fire-fighting grade of skill and fire protection patrol information generate efficient, the correct result of decision, thus
Facilitate policymaker to formulate and efficiently, correctly rescues decision scheme fire is effectively treated, to reduce casualties caused by fire
And property loss, reduce fire hazard.
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 a kind of one embodiment flow chart of fire rescue decision-making technique in the embodiment of the present invention；
Fig. 2 is a kind of fire rescue decision-making technique training machine study mould under an application scenarios in the embodiment of the present invention
The flow diagram of type；
Fig. 3 is a kind of fire rescue decision-making technique determining fire-fighting technical ability etc. under an application scenarios in the embodiment of the present invention
The flow diagram of grade；
Fig. 4 is a kind of fire rescue decision-making technique training decision model under an application scenarios in the embodiment of the present invention
Flow diagram；
Fig. 5 is a kind of one embodiment structure chart of fire rescue decision making device in the embodiment of the present invention；
Fig. 6 is a kind of schematic diagram for terminal device that one embodiment of the invention provides.
Specific embodiment
The embodiment of the invention provides a kind of fire rescue decision-making technique, device, computer readable storage medium and terminals
Equipment, be used to help policymaker formulate efficiently, correctly rescue decision scheme, to reduce casualties and property caused by fire
Loss reduces fire hazard.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, the embodiment of the invention provides a kind of fire rescue decision-making technique, the fire rescue decision-making party
Method, comprising:
Step S101, place occurs for fire environmental information and fire protection patrol information are obtained；
It is understood that the environmental information may include the information such as smokescope, temperature and concentration of toxic gases.
In the embodiment of the present invention, occur can to detect by various sensors after fire fire occur the smokescope in place, temperature with
And the environmental informations such as concentration of toxic gases.
The fire protection patrol in place can occur by fire in inquiry management information system of fire fighting for the fire protection patrol information
Data acquisition.Specifically, the fire fighting device assessment indicator system and the corresponding weight of index in each place can be pre-established.Refer to
Mark may include whether fire fighting device is complete, whether fire fighting hydraulic pressure is normal, whether fire fighting device function is normal etc..By professional people
Member periodically carries out inspection according to These parameters, and gives a mark to each index, is then asked according to index weights index marking and is added
Weigh and obtain fire protection patrol information.
Step S102, the environmental information is input in the machine learning model after training, after obtaining the training
The fire behavior grade of machine learning model output；
In the embodiment of the present invention, the training that training sample carries out machine learning model, and the machine after training can be first passed through in advance
Device learning model can then determine fire behavior grade according to the environmental information of input, that is, determine fire developing stage locating at present, such as
It is in which of initial stage, developing stage, the fierce combustion phases and decaying extinguishing stage stage.
Wherein, machine learning model can be the machine learning model based on BP neural network, such as can choose three layers
BP neural network is as machine learning model, and correspondingly, BP neural network is settable, and there are three corresponding input layers, can
The toxic gases such as smokescope data, temperature data and carbonomonoxide concentration data are defeated as the input data of BP neural network
Enter to input layer, meanwhile, also settable five output layer neurons of BP neural network, can by each fire development stage,
Such as initial stage, developing stage, fierce combustion phases, decaying extinguishing stage corresponding probability are as output.In addition, can be BP
Neural network selects the parameters such as suitable hidden layer neuron number, Learning Step, the number of iterations.
Specifically, as shown in Fig. 2, the machine learning model can be obtained by following step training:
Step S201, the first training sample of the first preset quantity is obtained, each first training sample includes one group pair
The environmental information answered；
Step S202, the corresponding standard fire behavior grade of each first training sample is marked；
Step S203, each first training sample is input in initial machine learning model, is obtained described initial
Machine learning model output training fire behavior grade；
Step S204, the error between the trained fire behavior grade and the standard fire behavior grade is calculated；
Step S205, judge whether the error meets preset condition；
If step S206, the described error meets the preset condition, it is determined that the machine learning model training is completed；
If step S207, the described error is unsatisfactory for the preset condition, the model ginseng of the machine learning model is adjusted
Number, and using model parameter machine learning model adjusted as initial machine learning model is returned and is executed each described the
One training sample is input to step and subsequent step in initial machine learning model.
For above-mentioned steps S201, before training machine learning model, need to obtain first for training in advance
Training sample.Standard fire experiment can be carried out in monitored place, then utilize smokescope sensor, temperature sensing
The sensors such as device, carbon monoxide transducer are obtained the measurement data of environmental information by certain time interval, and by survey obtained
Data are measured as the first training sample.Wherein, each first training sample includes one group of corresponding environmental information, i.e., each
A first training sample includes a smokescope, a temperature and a concentration of toxic gases, and these environmental informations
It is collected in fire test place or fire occurs in place.It is understood that the data volume of these the first training samples
It is bigger, it is better to the training effect of machine learning model, thus, in the embodiment of the present invention, the first more instructions can be obtained as far as possible
Practice sample.
For above-mentioned steps S202, after the first training sample for getting training, it is also necessary to mark these training
Standard fire behavior grade corresponding to sample, the fire development stage as corresponding to when can be acquired according to the first training sample mark
Standard fire behavior grade corresponding to each first training sample, if such as first the first training sample is to be collected in the generation of A fire
It then can be initial stage by the corresponding standard fire behavior grade mark of first the first training sample when the initial stage in place.
It can after having marked standard fire behavior grade corresponding to these first training samples for above-mentioned steps S203
These first training samples are input in initial machine learning model, to obtain initial training fire behavior grade, due to first
Machine learning model not yet training is completed when the beginning, therefore, the standard fire behavior grade of the training fire behavior grade and label exported at this time
Between can have certain deviation, error.
For above-mentioned steps S204 and step S205, after obtaining training fire behavior grade, the training fire can be calculated
Error between feelings grade and corresponding standard fire behavior grade, and judge whether the error meets preset condition, such as error in judgement
Whether less than 5%.Here, the preset condition can be determined in the specific machine learning model of training, such as can set pre-
If condition is that error is less than specific threshold, which can be a percentages, wherein specific threshold is smaller, then
The machine learning model that finally training completion obtains is more stable, and identification accuracy is higher.
For above-mentioned steps S206, it is to be understood that when the trained fire behavior grade and the standard fire behavior grade it
Between error when meeting the preset condition, the error such as between the trained fire behavior grade and the standard fire behavior grade is less than
When 5%, then it can determine that the machine learning model training is completed.
For above-mentioned steps S207, when the error between the trained fire behavior grade and the standard fire behavior grade is unsatisfactory for
It is when the error such as between the trained fire behavior grade and the standard fire behavior grade is 10%, then adjustable when the preset condition
The model parameter of the whole machine learning model, and using model parameter machine learning model adjusted as initial engineering
Model is practised, the training of the first training sample is then re-started, to pass through the model parameter for adjusting machine learning model repeatedly, and
The training for carrying out multiple first training sample comes so that between the training fire behavior grade and standard fire behavior grade of subsequent training output
Minimize the error, until the error between final training fire behavior grade and standard fire behavior grade meets the preset condition.
Step S103, it obtains the fire and the architecture information in place occurs, and the fire is determined according to the architecture information
The fire hazard rating in calamity generation place；
In the embodiment of the present invention, the architecture information that place occurs for the fire can be obtained when fire occurs, such as by disappearing
Anti- information management system obtains the fire and the architecture informations such as building occupancy and the building height in place occurs, according to for building
Determine that the fire hazard rating in place occurs for the fire with building height on the way.Here, the fire hazard rating can wrap
Light danger classes, middle danger classes, grave danger grade and warehouse danger classes are included, the fire hazard rating can be according to existing
Classification standard divided, for example, it is 24 meters of hotels below, office building, middle danger that light danger classes, which can be building height,
Dangerous grade can be high-rise civil building (hotel, office building, complex building, postal building, financial telecommunications building, command scheduling building, broadcast
TV building, tower etc.), grave danger grade can be the stock and vehicle of the factories such as printing house, alcohol product, flammable liquid product
Between, warehouse danger classes can for food, tobacco and wine, wooden case, the non-ignitable fire retardant article of packed in cases, warehouse style market shelf area
Deng.
Step S104, the fire-fighting technical ability of rescue personnel etc. occurred within the scope of the pre-determined distance of place apart from the fire is determined
Grade；
Specifically, as shown in figure 3, the determining rescue personnel occurred within the scope of the pre-determined distance of place apart from the fire
Fire-fighting grade of skill, may include:
Step S301, the location information that place occurs for the fire is obtained；
Step S302, the rescue occurred within the scope of the pre-determined distance of place apart from the fire is determined according to the positional information
Personnel；
Step S303, the administration of the prevention and control information of the rescue personnel is obtained, and institute is determined according to the administration of the prevention and control information
State the fire-fighting grade of skill of rescue personnel.
For above-mentioned steps S301 to step S303, when fire occurs, the location information that place occurs for fire can be obtained,
Such as fire can be obtained by inquiry Fire-fighting Information System or electronic map and the GPS coordinate built where place occurs, with determination
The generation position of fire, and after the generation position of fire has been determined, then it can further determine that the rescue personnel near the position,
And the administration of the prevention and control information of rescue personnel is obtained, to obtain the fire-fighting grade of skill of rescue personnel according to the administration of the prevention and control information,
Wherein, the fire-fighting grade of skill may include high (fire-fighting Skill is excellent, and fire-fighting technical ability is skilled), in (participated in
Fire drill and training, without examination) and low (not participating in fire drill and training) three grades.
Step S105, the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire-fighting are patrolled
Information input is examined into preset decision model, obtains the result of decision of the decision model output, the result of decision is used for
Indicate whether to need to take rescue measure, and indicates corresponding rescue plan when needing and taking rescue measure.
In the embodiment of the present invention, the building of decision model can be carried out in advance, and the decision model built then can be according to defeated
Fire behavior grade, fire hazard rating, fire-fighting grade of skill and the fire protection patrol information entered generates the result of decision, it is generated certainly
Plan result may be used to indicate whether need to take current fire rescue measure, and the instruction when needing to take rescue measure
Corresponding rescue plan.The rescue plan may include several emergency plans pre-established, such as may include fire fighting meter
Draw and evacuation plan, such as first carry out fire fighting plan and execute evacuation plan again, or first carry out evacuation plan and execute fire fighting plan again.
Specifically, as shown in figure 4, the decision model can be instructed by following step in a concrete application scene
It gets:
Step S401, the second training sample of the second preset quantity is obtained, each second training sample includes a fire
Feelings grade, a fire hazard rating, a fire-fighting grade of skill, a fire protection patrol information and a criteria decision result；
Step S402, according to preset corresponding relationship by each second training sample be converted into corresponding trained numerical value to
Amount；
Step S403, each trained numerical value vector is input in initial decision model and is trained, obtain by
Trained decision model.
For above-mentioned steps S401, before the training decision model, need to obtain second for training in advance
Training sample, wherein each second training sample may each comprise a fire behavior grade, a fire hazard rating, one disappear
Anti- grade of skill, a fire protection patrol information and a criteria decision are as a result, here, the criteria decision result can be by expert
Personnel carry out comprehensive descision to these information and obtain, such as when determining fire behavior grade is light danger classes, fire hazard rating is just
Stage phase, fire-fighting grade of skill be in and fire protection patrol information scoring it is high when, it may be determined that criteria decision result be need take
The rescue plan first put out a fire.It is understood that the data volume of these the second training samples is bigger, to the instruction of the decision model
It is better to practice effect, thus in the embodiment of the present invention, the second more training samples can be obtained as far as possible.
Here, the fire protection patrol information may include, scoring is high, scoring neutralization scoring is three kinds low, such as can be preset three
A score value section, wherein the first score value section and corresponding and third in high corresponding, the second score value section of scoring and scoring
Score value section and scoring are low corresponding, thus, if if the appraisal result of a certain fire protection patrol information is located at the first score value section,
It then can determine that the fire protection patrol information is high for scoring；If can determine this and if the appraisal result is located at the second score value section
Fire protection patrol information is in scoring；If if the appraisal result is located at third score value section, can determine the fire protection patrol information
It is low to score.
It, can be according to default corresponding relationship after obtaining these second training samples for above-mentioned steps S402 and step S403
Each second training sample is converted into corresponding trained numerical value vector, the default corresponding relationship can be with are as follows: in fire behavior grade
The correspondence numerical value of initial stage is 2, the correspondence numerical value of developing stage is 5, the correspondence numerical value of fierce combustion phases is 8 and decaying
The correspondence numerical value in extinguishing stage is 9；The correspondence numerical value of light danger classes in fire hazard rating is pair of 1, middle danger classes
Answering numerical value is 4, the correspondence numerical value of grave danger grade is 7 and the correspondence numerical value of warehouse danger classes is 9；Fire-fighting grade of skill
Inferior grade correspondence numerical value be 3, the correspondence numerical value of middle grade is 6 and high-grade corresponding data is 9；And fire protection patrol is believed
The low correspondence numerical value that scores in breath is 1, the correspondence numerical value 2 in scoring and the high correspondence numerical value that scores are 3.
That is, can be determined first according to the default corresponding relationship each after getting these second training samples
The corresponding numerical value of each information in second training sample, the input sequence then required according to the decision model is by these numerical value groups
It is input in initial decision model and is trained at training numerical value vector, to obtain trained decision model, as worked as
-- fire-fighting grade of skill -- fire protection patrol information -- fire behavior etc. of stating input sequence required by decision model are as follows: fire hazard rating
Grade, then the trained numerical value vector is that (the corresponding numerical value of fire hazard rating, the corresponding numerical value of fire-fighting grade of skill, fire-fighting are patrolled
Examine the corresponding numerical value of information, the corresponding numerical value of fire behavior grade).
Therefore, described by the fire behavior grade, the fire hazard rating, the fire-fighting technical ability in the embodiment of the present invention
Grade and the fire protection patrol information input obtain the result of decision of the decision model output into preset decision model,
It may include: step a, according to the default corresponding relationship, determine the fire behavior grade, the fire hazard rating, institute respectively
State fire-fighting grade of skill and the corresponding numerical value of the fire protection patrol information；Step b, by each numerical value form corresponding numerical value to
Amount, and the numerical value vector is input in preset decision model, obtain the result of decision of the decision model output.
Further, in another concrete application scene, the decision model may include a decision table；And by institute
Fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information input is stated to determine to preset
Before plan model, may include:
Step c, the sample record of third preset quantity is obtained, each sample record includes a fire behavior grade, one
Fire hazard rating, a fire-fighting grade of skill and a fire protection patrol information；
Step d, determine the corresponding default result of decision of each sample record, and by the default result of decision with it is corresponding
Sample record save into the decision table of the decision model.
Correspondingly, described by the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire-fighting
Inspection information input obtains the result of decision of the decision model output, may include: into preset decision model
Step e, by the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol
Information input is into preset decision model, to search corresponding sample record in the decision table of the decision model；
Step f, the found corresponding default result of decision of sample record is obtained, and by acquired default decision knot
Fruit is determined as the result of decision of the decision model output.
For above-mentioned steps c to step f, it is to be understood that in the application scenarios, can first obtain third preset quantity
Sample record, the historical record that the building of fire occurred can be read in Fire-fighting Information System, when obtaining fire and occurring
Fire behavior grade (fire development stage), fire hazard rating, fire-fighting grade of skill and fire protection patrol information, it is then true by expert
Determine the corresponding default result of decision of each sample record, wherein the default result of decision is corresponding emergency plan, by expert according to tool
Body fire condition constructs, and can save the constructed default result of decision to the decision model with corresponding sample record
Decision table in, when need generate be directed to a certain fire the result of decision when, can by the corresponding fire behavior grade of the fire, fire endanger
Dangerous grade, fire-fighting grade of skill and fire protection patrol information are separately input into preset decision model, and the decision model then may be used
Fire behavior grade corresponding with the fire, fire hazard rating, fire-fighting grade of skill and fire protection patrol information are searched in decision table
The sample record to match, and the default result of decision corresponding to the sample record found is determined as the decision model
The result of decision of output, and shown or be sent in the application terminal of corresponding policymaker, it is formulated with aid decision person high
Effect correctly rescues decision scheme.
In the embodiment of the present invention, by the way that the fire generation collected environmental information in place to be input to the engineering after training
It practises in model, can quickly and accurately determine the fire behavior grade of fire development, while obtaining the fire protection patrol letter that place occurs for fire
Breath, and the architecture information in place is occurred to determine that the fire hazard rating in place occurs for fire, and in time by acquisition fire
Determine the fire-fighting grade of skill that the rescue personnel within the scope of the pre-determined distance of place occurs apart from fire, and by fire behavior grade, fire
Danger classes, fire-fighting grade of skill and fire protection patrol information input are into preset decision model, by comprehensively considering fire behavior
Grade, fire hazard rating, fire-fighting grade of skill and fire protection patrol information generate efficient, the correct result of decision, thus side
Just policymaker formulates efficiently, correctly that fire is effectively treated in rescue decision scheme, with reduce casualties caused by fire and
Property loss reduces fire hazard.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
A kind of fire rescue decision-making technique is essentially described above, a kind of fire rescue decision making device will be carried out below detailed
Thin description.
As shown in figure 5, the embodiment of the invention provides a kind of fire rescue decision making device, the fire rescue decision dress
It sets, comprising:
The environmental information and fire protection patrol information in place occur for obtaining fire for data obtaining module 501；
Fire behavior level determination module 502 is obtained for the environmental information to be input in the machine learning model after training
The fire behavior grade of machine learning model output after to the training；
The architecture information in place occurs for obtaining the fire for fire hazard rating determining module 503, and according to described
Architecture information determines that the fire hazard rating in place occurs for the fire；
Grade of skill determining module 504, for determining the rescue occurred within the scope of the pre-determined distance of place apart from the fire
The fire-fighting grade of skill of personnel；
Result of decision generation module 505 is used for the fire behavior grade, the fire hazard rating, the fire-fighting technical ability
Grade and the fire protection patrol information input obtain the result of decision of the decision model output into preset decision model,
The result of decision is used to indicate whether to need to take rescue measure, and indicates to rescue accordingly when needing to take rescue measure
The plan of helping.
Further, the fire rescue decision making device, further includes:
First training sample obtains module, for obtaining the first training sample of the first preset quantity, each first instruction
Practicing sample includes one group of corresponding environmental information；
Standard fire behavior grade mark module, for marking the corresponding standard fire behavior grade of each first training sample；
Training fire behavior grade obtains module, for each first training sample to be input to initial machine learning model
In, obtain the training fire behavior grade of the initial machine learning model output；
Error calculating module, for calculating the error between the trained fire behavior grade and the standard fire behavior grade；
Model parameter adjusts module and adjusts the machine learning model if being unsatisfactory for preset condition for the error
Model parameter, and using model parameter machine learning model adjusted as initial machine learning model, return execute general
Each first training sample is input to step and subsequent step in initial machine learning model；
Determining module is completed in training, if meeting the preset condition for the error, it is determined that the machine learning mould
Type training is completed.
Preferably, the fire rescue decision making device, further includes:
Second training sample obtains module, for obtaining the second training sample of the second preset quantity, each second instruction
Practicing sample includes a fire behavior grade, a fire hazard rating, a fire-fighting grade of skill, a fire protection patrol information and one
A criteria decision result；
Training vector conversion module, it is corresponding for being converted into each second training sample according to default corresponding relationship
Training numerical value vector；
Decision model training module is instructed for each trained numerical value vector to be input in initial decision model
Practice, obtains trained decision model.
Optionally, the result of decision generation module 505, comprising:
Numerical value determination unit, for determining the fire behavior grade, fire danger respectively according to the default corresponding relationship
Dangerous grade, the fire-fighting grade of skill and the corresponding numerical value of the fire protection patrol information；
First result of decision generation unit, for will the corresponding numerical value vector of each numerical value composition, and by the numerical value
Vector is input in preset decision model, obtains the result of decision of the decision model output.
Further, the decision model includes decision table；
The fire rescue decision making device, further includes:
Sample record obtains module, and for obtaining the sample record of third preset quantity, each sample record includes one
A fire behavior grade, a fire hazard rating, a fire-fighting grade of skill and a fire protection patrol information；
Default result of decision memory module, for determining the corresponding default result of decision of each sample record, and by institute
The default result of decision is stated to save with corresponding sample record into the decision table of the decision model.
Preferably, the result of decision generation module 505, further includes:
Sample record searching unit is used for the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill
It is corresponding to be searched in the decision table of the decision model with the fire protection patrol information input into preset decision model
Sample record；
Second result of decision generation unit, for obtaining the corresponding default result of decision of found sample record, and
The acquired default result of decision is determined as to the result of decision of the decision model output.
Optionally, the grade of skill determining module 504, comprising:
The location information in place occurs for obtaining the fire for location information acquiring unit；
Apart from the fire place pre-determined distance occurs for rescue personnel's determination unit for determining according to the positional information
Rescue personnel in range；
Grade of skill determination unit, for obtaining the administration of the prevention and control information of the rescue personnel, and according to the extinguishing pipe
Reason information determines the fire-fighting grade of skill of the rescue personnel.
Fig. 6 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in fig. 6, the terminal of the embodiment is set
Standby 6 include: processor 60, memory 61 and are stored in the meter that can be run in the memory 61 and on the processor 60
Calculation machine program 62, such as fire rescue decision-making process.The processor 60 is realized above-mentioned each when executing the computer program 62
Step in a fire rescue decision-making technique embodiment, such as step S101 shown in FIG. 1 to step S105.Alternatively, the place
Reason device 60 realizes the function of each module/unit in above-mentioned each Installation practice, such as Fig. 5 institute when executing the computer program 62
The function for the module 501 to 505 shown.
Illustratively, the computer program 62 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 61, and are executed by the processor 60, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 62 in the terminal device 6 is described.For example, the computer program 62 can be divided
It is cut into data obtaining module, fire behavior level determination module, fire hazard rating determining module, grade of skill determining module, decision
Result-generation module, each module concrete function are as follows:
The environmental information and fire protection patrol information in place occur for obtaining fire for data obtaining module；
Fire behavior level determination module is obtained for the environmental information to be input in the machine learning model after training
The fire behavior grade of machine learning model output after the training；
Fire hazard rating determining module occurs the architecture information in place for obtaining the fire, and is built according to described
It builds information and determines that the fire hazard rating in place occurs for the fire；
Grade of skill determining module, for determining the rescue personnel occurred within the scope of the pre-determined distance of place apart from the fire
Fire-fighting grade of skill；
Result of decision generation module is used for the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill
With the fire protection patrol information input into preset decision model, the result of decision of the decision model output is obtained, it is described
The result of decision is used to indicate whether to need to take rescue measure, and corresponding rescue meter is indicated when needing to take rescue measure
It draws.
The terminal device 6 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 60, memory 61.It will be understood by those skilled in the art that Fig. 6
The only example of terminal device 6 does not constitute the restriction to terminal device 6, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input-output equipment, net
Network access device, bus etc..
The processor 60 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 61 can be the internal storage unit of the terminal device 6, such as the hard disk or interior of terminal device 6
It deposits.The memory 61 is also possible to the External memory equipment of the terminal device 6, such as be equipped on the terminal device 6
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 61 can also both include the storage inside list of the terminal device 6
Member also includes External memory equipment.The memory 61 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 61 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, 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 each embodiment described in conjunction with the examples disclosed in this document
Module, unit and/or method and step can be realized with the combination of electronic hardware or computer software and electronic hardware.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, 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 unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-described embodiment side
All or part of the process in method can also instruct relevant hardware to complete, the computer by computer program
Program can be stored in a computer readable storage medium, and the computer program is when being executed by processor, it can be achieved that above-mentioned each
The step of a embodiment of the method.Wherein, the computer program includes computer program code, and the computer program code can
Think source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium can be with
It include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, light that can carry the computer program code
Disk, 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 the computer
The content that readable medium includes can carry out increase and decrease appropriate according to the requirement made laws in jurisdiction with patent practice, such as
It does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium in certain jurisdictions.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, 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.
Claims (10)
1. a kind of fire rescue decision-making technique characterized by comprising
Obtain place occurs for fire environmental information and fire protection patrol information；
The environmental information is input in the machine learning model after training, the machine learning model after obtaining the training is defeated
Fire behavior grade out；
The architecture information that place occurs for the fire is obtained, and determines that the fire in place occurs for the fire according to the architecture information
Calamity danger classes；
Determine the fire-fighting grade of skill that the rescue personnel within the scope of the pre-determined distance of place occurs apart from the fire；
Extremely by the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information input
In preset decision model, the result of decision of the decision model output is obtained, the result of decision is used to indicate whether to need
Rescue measure is taken, and indicates corresponding rescue plan when needing and taking rescue measure.
2. fire rescue decision-making technique according to claim 1, which is characterized in that the machine learning model passes through following
Step training obtains:
The first training sample of the first preset quantity is obtained, each first training sample includes one group of corresponding environmental information；
Mark the corresponding standard fire behavior grade of each first training sample；
Each first training sample is input in initial machine learning model, the initial machine learning model is obtained
The training fire behavior grade of output；
Calculate the error between the trained fire behavior grade and the standard fire behavior grade；
If the error is unsatisfactory for preset condition, the model parameter of the machine learning model is adjusted, and by model parameter tune
Machine learning model after whole returns to execution and is input to each first training sample just as initial machine learning model
Step and subsequent step in the machine learning model of beginning；
If the error meets the preset condition, it is determined that the machine learning model training is completed.
3. fire rescue decision-making technique according to claim 1, which is characterized in that the decision model passes through following step
Training obtains:
The second training sample of the second preset quantity is obtained, each second training sample includes a fire behavior grade, a fire
Calamity danger classes, a fire-fighting grade of skill, a fire protection patrol information and a criteria decision result；
Each second training sample is converted into corresponding trained numerical value vector according to default corresponding relationship；
Each trained numerical value vector is input in initial decision model and is trained, trained decision model is obtained
Type.
4. fire rescue decision-making technique according to claim 3, which is characterized in that it is described by the fire behavior grade, it is described
Fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information input obtain institute into preset decision model
State the result of decision of decision model output, comprising:
According to the default corresponding relationship, the fire behavior grade, the fire hazard rating, described fire-fighting technical ability etc. are determined respectively
Grade numerical value corresponding with the fire protection patrol information；
Each numerical value is formed into corresponding numerical value vector, and the numerical value vector is input in preset decision model, is obtained
The result of decision exported to the decision model.
5. fire rescue decision-making technique according to claim 1, which is characterized in that the decision model includes decision table；
By the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information input
Before to preset decision model, comprising:
The sample record of third preset quantity is obtained, each sample record includes a fire behavior grade, a fire hazard etc.
Grade, a fire-fighting grade of skill and a fire protection patrol information；
Determine the corresponding default result of decision of each sample record, and by the default result of decision and corresponding sample record
It saves into the decision table of the decision model.
6. fire rescue decision-making technique according to claim 5, which is characterized in that it is described by the fire behavior grade, it is described
Fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information input obtain institute into preset decision model
State the result of decision of decision model output, comprising:
Extremely by the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and the fire protection patrol information input
In preset decision model, to search corresponding sample record in the decision table of the decision model；
The found corresponding default result of decision of sample record is obtained, and the acquired default result of decision is determined as institute
State the result of decision of decision model output.
7. fire rescue decision-making technique according to any one of claim 1 to 6, which is characterized in that the determination distance
The fire-fighting grade of skill of rescue personnel within the scope of the pre-determined distance of place occurs for the fire, comprising:
Obtain the location information that place occurs for the fire；
The rescue personnel occurred within the scope of the pre-determined distance of place apart from the fire is determined according to the positional information；
The administration of the prevention and control information of the rescue personnel is obtained, and disappearing for the rescue personnel is determined according to the administration of the prevention and control information
Anti- grade of skill.
8. a kind of fire rescue decision making device characterized by comprising
The environmental information and fire protection patrol information in place occur for obtaining fire for data obtaining module；
Fire behavior level determination module obtains described for the environmental information to be input in the machine learning model after training
The fire behavior grade of machine learning model output after training；
The architecture information in place occurs for obtaining the fire, and is believed according to the building for fire hazard rating determining module
Breath determines that the fire hazard rating in place occurs for the fire；
Grade of skill determining module, for determining disappearing for the rescue personnel occurred within the scope of the pre-determined distance of place apart from the fire
Anti- grade of skill；
Result of decision generation module is used for the fire behavior grade, the fire hazard rating, the fire-fighting grade of skill and institute
Fire protection patrol information input is stated into preset decision model, obtains the result of decision of the decision model output, the decision
As a result it is used to indicate whether to need to take rescue measure, and indicates corresponding rescue plan when needing and taking rescue measure.
9. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 7 when executing the computer program
Any one of described in fire rescue decision-making technique the step of.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization fire rescue decision-making technique as described in any one of claims 1 to 7 when the computer program is executed by processor
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811611894.2A CN109800961A (en) | 2018-12-27 | 2018-12-27 | A kind of fire rescue decision-making technique, device, storage medium and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811611894.2A CN109800961A (en) | 2018-12-27 | 2018-12-27 | A kind of fire rescue decision-making technique, device, storage medium and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109800961A true CN109800961A (en) | 2019-05-24 |
Family
ID=66557865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811611894.2A Pending CN109800961A (en) | 2018-12-27 | 2018-12-27 | A kind of fire rescue decision-making technique, device, storage medium and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800961A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111343598A (en) * | 2020-02-03 | 2020-06-26 | 重庆特斯联智慧科技股份有限公司 | Intelligent fire-fighting vehicle-mounted platform operation method and system with edge computing capability |
| CN111539634A (en) * | 2020-04-26 | 2020-08-14 | 众安仕（北京）科技有限公司 | Fire rescue aid decision scheme generation method |
| CN111832976A (en) * | 2020-07-29 | 2020-10-27 | 深圳市睿策者科技有限公司 | Resource configuration pushing method and device, computer equipment and storage medium |
| CN112036680A (en) * | 2020-07-08 | 2020-12-04 | 贵州电网有限责任公司 | Power grid disaster emergency drilling management system based on deep neural network |
| CN112657109A (en) * | 2020-12-28 | 2021-04-16 | 长沙中联消防机械有限公司 | Machine learning fire extinguishing system and method based on cloud computing and fire fighting equipment |
| CN112883089A (en) * | 2020-10-29 | 2021-06-01 | 北京华胜天成科技股份有限公司 | Fire information processing method, fire information processing device, computer equipment and storage medium |
| CN113487164A (en) * | 2021-06-30 | 2021-10-08 | 武汉理工光科股份有限公司 | Fire rescue force intelligent dispatching method and device and storage medium |
| CN113554369A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Method and device for allocating rescue teams for dangerous chemical transport accidents |
| CN113856077A (en) * | 2021-10-14 | 2021-12-31 | 赵兵 | Fire rescue measure generation method, device, equipment and storage medium |
| CN114036613A (en) * | 2021-11-09 | 2022-02-11 | 香港理工大学 | Building fire protection design evaluation method and device based on artificial intelligence |
| CN114494944A (en) * | 2021-12-29 | 2022-05-13 | 北京辰安科技股份有限公司 | Method, device, equipment and storage medium for determining fire hazard level |
| CN114748813A (en) * | 2022-04-24 | 2022-07-15 | 一方设计集团有限公司 | Quick fire extinguishing method, system, equipment and storage medium suitable for high-rise building |
| CN114792194A (en) * | 2022-03-16 | 2022-07-26 | 广东永耀消防机电工程有限公司 | Whole fire control safety intelligent system of building |
| CN116385754A (en) * | 2022-12-12 | 2023-07-04 | 力景(北京)系统技术有限公司 | Airport fire dynamic sensing processing system and method |
| CN116957484A (en) * | 2023-06-08 | 2023-10-27 | 中国消防救援学院 | Fire rescue plan method and system based on digital twinning |
| CN117151436A (en) * | 2023-10-31 | 2023-12-01 | 北京数易科技有限公司 | Emergency rescue exercise method, system and medium |
| CN117408447A (en) * | 2023-09-18 | 2024-01-16 | 中国消防救援学院 | Fire-extinguishing rescue auxiliary decision-making method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992293A (en) * | 2015-07-02 | 2015-10-21 | 上海迪爱斯通信设备有限公司 | Fire emergency response method and system |
| CN105046451A (en) * | 2015-08-31 | 2015-11-11 | 湖南汇博电子技术有限公司 | Fire truck scheduling method and system |
| CN105976116A (en) * | 2016-05-09 | 2016-09-28 | 重庆和航物联网技术研究院有限公司 | IoT based fire safety dynamic evaluation method and system |
| CN106975191A (en) * | 2017-04-18 | 2017-07-25 | 江苏省冶金设计院有限公司 | A kind of fire-fighting system and its rescue mode |
| CN108346253A (en) * | 2018-04-13 | 2018-07-31 | 中联永安智慧消防科技（成都）有限公司 | Wisdom fire-fighting management, emergency system and method |
| CN108763364A (en) * | 2018-05-17 | 2018-11-06 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire management system and method based on big data |
-
2018
- 2018-12-27 CN CN201811611894.2A patent/CN109800961A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992293A (en) * | 2015-07-02 | 2015-10-21 | 上海迪爱斯通信设备有限公司 | Fire emergency response method and system |
| CN105046451A (en) * | 2015-08-31 | 2015-11-11 | 湖南汇博电子技术有限公司 | Fire truck scheduling method and system |
| CN105976116A (en) * | 2016-05-09 | 2016-09-28 | 重庆和航物联网技术研究院有限公司 | IoT based fire safety dynamic evaluation method and system |
| CN106975191A (en) * | 2017-04-18 | 2017-07-25 | 江苏省冶金设计院有限公司 | A kind of fire-fighting system and its rescue mode |
| CN108346253A (en) * | 2018-04-13 | 2018-07-31 | 中联永安智慧消防科技（成都）有限公司 | Wisdom fire-fighting management, emergency system and method |
| CN108763364A (en) * | 2018-05-17 | 2018-11-06 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire management system and method based on big data |
Non-Patent Citations (2)
| Title |
|---|
| 何南南: "多传感器信息融合技术在火灾探测中的应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 曾珏鑫: "基于灰色关联的案例推理在火灾应急系统中的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111343598A (en) * | 2020-02-03 | 2020-06-26 | 重庆特斯联智慧科技股份有限公司 | Intelligent fire-fighting vehicle-mounted platform operation method and system with edge computing capability |
| CN113554369A (en) * | 2020-04-23 | 2021-10-26 | 中国石油化工股份有限公司 | Method and device for allocating rescue teams for dangerous chemical transport accidents |
| CN111539634A (en) * | 2020-04-26 | 2020-08-14 | 众安仕（北京）科技有限公司 | Fire rescue aid decision scheme generation method |
| CN112036680A (en) * | 2020-07-08 | 2020-12-04 | 贵州电网有限责任公司 | Power grid disaster emergency drilling management system based on deep neural network |
| CN111832976A (en) * | 2020-07-29 | 2020-10-27 | 深圳市睿策者科技有限公司 | Resource configuration pushing method and device, computer equipment and storage medium |
| CN112883089A (en) * | 2020-10-29 | 2021-06-01 | 北京华胜天成科技股份有限公司 | Fire information processing method, fire information processing device, computer equipment and storage medium |
| CN112657109A (en) * | 2020-12-28 | 2021-04-16 | 长沙中联消防机械有限公司 | Machine learning fire extinguishing system and method based on cloud computing and fire fighting equipment |
| CN113487164A (en) * | 2021-06-30 | 2021-10-08 | 武汉理工光科股份有限公司 | Fire rescue force intelligent dispatching method and device and storage medium |
| CN113856077A (en) * | 2021-10-14 | 2021-12-31 | 赵兵 | Fire rescue measure generation method, device, equipment and storage medium |
| CN114036613A (en) * | 2021-11-09 | 2022-02-11 | 香港理工大学 | Building fire protection design evaluation method and device based on artificial intelligence |
| CN114494944A (en) * | 2021-12-29 | 2022-05-13 | 北京辰安科技股份有限公司 | Method, device, equipment and storage medium for determining fire hazard level |
| WO2023125588A1 (en) * | 2021-12-29 | 2023-07-06 | 北京辰安科技股份有限公司 | Fire danger level determination method and apparatus |
| CN114792194A (en) * | 2022-03-16 | 2022-07-26 | 广东永耀消防机电工程有限公司 | Whole fire control safety intelligent system of building |
| CN114792194B (en) * | 2022-03-16 | 2023-04-18 | 深圳森磊弘泰消防科技有限公司 | Whole fire control safety intelligent system of building |
| CN114748813A (en) * | 2022-04-24 | 2022-07-15 | 一方设计集团有限公司 | Quick fire extinguishing method, system, equipment and storage medium suitable for high-rise building |
| CN114748813B (en) * | 2022-04-24 | 2023-03-14 | 一方设计集团有限公司 | Quick fire extinguishing method, system, equipment and storage medium suitable for high-rise building |
| CN116385754A (en) * | 2022-12-12 | 2023-07-04 | 力景(北京)系统技术有限公司 | Airport fire dynamic sensing processing system and method |
| CN116957484A (en) * | 2023-06-08 | 2023-10-27 | 中国消防救援学院 | Fire rescue plan method and system based on digital twinning |
| CN117408447A (en) * | 2023-09-18 | 2024-01-16 | 中国消防救援学院 | Fire-extinguishing rescue auxiliary decision-making method and system |
| CN117151436A (en) * | 2023-10-31 | 2023-12-01 | 北京数易科技有限公司 | Emergency rescue exercise method, system and medium |
| CN117151436B (en) * | 2023-10-31 | 2024-02-02 | 北京数易科技有限公司 | Emergency rescue exercise method, system and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800961A (en) | A kind of fire rescue decision-making technique, device, storage medium and terminal device | |
| CN109686036B (en) | Fire monitoring method and device and edge computing device | |
| CN107563549B (en) | BIM (building information modeling) -based escape path generation method, device and equipment | |
| CN108490889B (en) | The safe big data data source method for generation of intelligent plant and device based on TE model | |
| CN113379267B (en) | Urban fire event processing method, system and storage medium based on risk classification prediction | |
| CN109978005A (en) | A kind of fire alarm method, device, storage medium and terminal device | |
| CN112070215B (en) | Processing method and processing device for dangerous situation analysis based on BP neural network | |
| CN107358344B (en) | Enterprise hidden danger management method and management system thereof, electronic equipment and storage medium | |
| US11906112B2 (en) | Methods for safety management of compressors in smart gas pipeline network and internet of things systems thereof | |
| CN115792505B (en) | Rail transit power supply management method and system | |
| US10930141B2 (en) | System and method for indicating building fire danger ratings | |
| CN111178828A (en) | Method and system for building fire safety early warning | |
| CN110703712A (en) | Industrial control system information security attack risk assessment method and system | |
| CN115660922A (en) | Intelligent safety and fire integrated early warning management system based on Internet of things | |
| CN111178756A (en) | Multiple linear regression fire risk assessment method based on environmental big data | |
| CN116363825B (en) | Method and device for displaying fire spreading trend, electronic equipment and medium | |
| CN117273504A (en) | Fault recovery method, device, equipment and storage medium for power communication network | |
| CN109543000B (en) | Intelligent evacuation system for shopping mall based on algorithm and mobile phone | |
| CN116975680A (en) | Method, device, system, electronic equipment and medium for processing fire alarm condition | |
| Andrade et al. | Wildfire Emergency Response Hazard Extraction and Analysis of Trends (HEAT) through Natural Language Processing and Time Series | |
| CN113449966B (en) | Gypsum board equipment inspection method and system | |
| CN114416814A (en) | Data processing method and device, electronic equipment and storage medium | |
| Ventikos et al. | A smart risk assessment tool for decision support during ship evacuation | |
| CN113850477A (en) | Method, device and terminal for judging hazard level of pollutant | |
| CN114519834A (en) | High-rise fire hazard early warning method, device and application |
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 |
Application publication date: 20190524 |
|
| RJ01 | Rejection of invention patent application after publication |