CN110309961A - Fire alarm method and apparatus - Google Patents
Fire alarm method and apparatus Download PDFInfo
- Publication number
- CN110309961A CN110309961A CN201910537983.5A CN201910537983A CN110309961A CN 110309961 A CN110309961 A CN 110309961A CN 201910537983 A CN201910537983 A CN 201910537983A CN 110309961 A CN110309961 A CN 110309961A
- Authority
- CN
- China
- Prior art keywords
- fire
- plot
- prediction
- occurs
- space characteristics
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Abstract
The invention discloses a kind of fire alarm method and apparatus, are related to field of computer technology.Wherein, this method comprises: target area is divided into multiple plot；Space characteristics data to same plot in multiple historical time sections merge, to obtain fused characteristic；Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple；The fused characteristic and the plot are inputted into fire prediction device in the Fire Data of the multiple historical time section, the probability value of fire occurs in predicted time section with the determination plot.By above method, the dynamic early-warning of fire can not only be realized, and can be improved the accuracy of fire prediction, reduce the complexity of fire prediction.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of fire alarm method and apparatus.
Background technique
In modern city, the influence factor of Urban Fire Risk becomes to become increasingly complex, the personnel such as house compact district
Fire hazard investigation work also become more and more arduous.In the limited situation of fire-fighting resource, it is pre- how accurately to carry out fire
Survey the key for having become and fire department being helped to carry out the deployment of fire-fighting emphasis, utmostly reduce fire risk.
In the prior art, fire prediction mainly is carried out using following methods: being based on analytic hierarchy process (AHP) and fuzzy synthesis
The fire prediction method of judge method.This method mainly includes following below scheme: firstly the need of the professional knowledge in related fire-salvage specialist
Under guidance, the system of the Urban Fires evaluation index of a set of comparatively perfect is established；Then each comment is determined according to analytic hierarchy process (AHP)
The weight of valence index and the risk class for determining each evaluation index；Finally using fuzzy synthetic evaluation model to fire risk
Carry out comprehensive assessment.
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery:
The first, existing fire prediction method excessively relies on the participation of fire-salvage specialist and entire treatment process is excessively complicated, consumption
Take a large amount of manpower and material resources.The second, along with the variation of the factors such as the development in city, the activity of the mankind, weather in time, fire
Risk is not unalterable, but constantly change.However, existing fire prediction method does not account for the time for fire
The influence of calamity risk can not carry out dynamic early-warning for fire, and the prediction effect of existing fire prediction method is often not satisfactory.
Summary of the invention
In view of this, the present invention provides a kind of fire alarm method and apparatus, the dynamic early-warning of fire can not only be realized,
And can be improved the accuracy of fire prediction, reduce the complexity of fire prediction.
To achieve the above object, according to an aspect of the invention, there is provided a kind of fire alarm method.
Fire alarm method of the invention includes: that target area is divided into multiple plot；Same plot is gone through multiple
The space characteristics data of history period are merged, to obtain fused characteristic；Wherein, the space characteristics data are
Influential plot feature construction is occurred on fire based on multiple；The fused characteristic and the plot are existed
The Fire Data of the multiple historical time section inputs fire prediction device, is sent out in predicted time section with the determination plot
The probability value for calamity of lighting a fire.
Optionally, the space characteristics data to same plot in multiple historical time sections merge, to be melted
The step of characteristic after conjunction includes: to same plot based on preparatory trained recurrent neural networks model in multiple history
The space characteristics data of period are merged, to obtain fused characteristic.
Optionally, the fire prediction device is by being trained in advance to Time series forecasting model；Wherein, described
Time series forecasting model includes: conditional random field models, Markov-chain model, Hidden Markov chain model or LSTM model.
Optionally, the method also includes: according to plot each in target area occur fire probability value building first
Fire prediction figure is visualized with the fire prediction situation to plot each in target area；And/or filter out fire
The maximum K plot of calamity probability of happening constructs the second fire prediction figure according to the probability value that fire occurs for the K plot, with
The fire prediction situation in the K plot is visualized.
Optionally, the method also includes: the influence degree that fire occurs for the multiple ground block feature is ranked up,
And third fire prediction figure is constructed according to ranking results, to be visualized to the multiple ground block feature；Wherein, described
Multiple ground block feature to the influence degree that fire occurs is determined according to the parameter value in the Time series forecasting model after training.
Optionally, the ground block feature influential on fire generation includes at least one of the following: temperature, humidity, plot
The frequency, the intramassif order volume of fire occur for the classification number of interior point of interest, adjacent plot.
To achieve the above object, according to another aspect of the present invention, a kind of fire disaster alarming device is provided.
Fire disaster alarming device of the invention includes: division module, for target area to be divided into multiple plot；Merge mould
Block is merged for the space characteristics data to same plot in multiple historical time sections, to obtain fused characteristic
According to；Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple；Determining module,
For the fused characteristic and the plot to be inputted in the Fire Data of the multiple historical time section
The probability value of fire occurs in predicted time section with the determination plot for fire prediction device.
Optionally, space characteristics data of the Fusion Module to same plot in multiple historical time sections merge,
It include: that the Fusion Module is based on preparatory trained recurrent neural networks model to same to obtain fused characteristic
Plot is merged in the space characteristics data of multiple historical time sections, to obtain fused characteristic.
Optionally, the fire prediction device is by being trained in advance to Time series forecasting model；Wherein, described
Time series forecasting model includes: conditional random field models, Markov-chain model, Hidden Markov chain model or LSTM model.
Optionally, described device further include: the first building module, for fire to occur according to plot each in target area
Probability value construct the first fire prediction figure, visualization exhibition is carried out with the fire prediction situation to plot each in target area
Show；And/or second building module, for filtering out the maximum K plot of fire probability, according to the K plot generation
The probability value of fire constructs the second fire prediction figure, is visualized with the fire prediction situation to the K plot.
Optionally, described device further include: third constructs module, for what fire occurred for the multiple ground block feature
Influence degree is ranked up, and according to ranking results construct third fire prediction figure, with to the multiple ground block feature carry out can
It is shown depending on changing；Wherein, the multiple ground block feature is according to the Time series forecasting model after training to the influence degree that fire occurs
In parameter value determine.
Optionally, the ground block feature influential on fire generation includes at least one of the following: temperature, humidity, plot
The frequency, the intramassif order volume of fire occur for the classification number of interior point of interest, adjacent plot.
To achieve the above object, according to a further aspect of the invention, a kind of electronic equipment is provided.
Electronic equipment of the invention, comprising: one or more processors；And storage device, for storing one or more
A program；When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes fire alarm method of the invention.
To achieve the above object, according to a further aspect of the invention, a kind of computer-readable medium is provided.
Computer-readable medium of the invention is stored thereon with computer program, real when described program is executed by processor
Existing fire alarm method of the invention.
One embodiment in foregoing invention has the following advantages that or the utility model has the advantages that multiple by the way that target area to be divided into
Plot, and fire prediction is carried out to each plot, it can reduce influence of the randomness of fire generation to prediction result, improve fire
The accuracy of calamity prediction result；It is merged by the space characteristics data to same plot in multiple historical time sections, and will
Fused characteristic and the plot input fire prediction device in the Fire Data of the multiple historical time section,
It not only allows for different spaces dimension, the influence that fire occurs for the ground block feature of different time dimension, and considers history
Fires Occurred in period can be realized the dynamic early-warning of fire to the influence in predicted time section, improve fire
The accuracy of calamity prediction；In addition, compared with prior art, since prediction technique of the invention is without relying on related fire-salvage specialist structure
Fire assessment indicator system is built, determines evaluation criterion weight without according to analytic hierarchy process (AHP), reduces the complexity of fire alarm
Property.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the main flow schematic diagram of fire alarm method according to an embodiment of the invention；
Fig. 2 is the main flow schematic diagram of fire alarm method in accordance with another embodiment of the present invention；
Fig. 3 is the main modular schematic diagram of fire disaster alarming device according to an embodiment of the invention；
Fig. 4 is the main modular schematic diagram of fire disaster alarming device in accordance with another embodiment of the present invention；
Fig. 5 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein；
Fig. 6 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present invention.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
It should be pointed out that in the absence of conflict, the feature in embodiment and embodiment in the present invention can be with
It is combined with each other.
Fig. 1 is the main flow schematic diagram of fire alarm method according to an embodiment of the invention.As shown in Figure 1, this
The fire alarm method of inventive embodiments includes:
Step S101, target area is divided into multiple plot.
In this step, target area can be evenly divided into the ground of multiple regular edges based on latitude and longitude information
Block；Target area can also be divided into the irregular plot in multiple edges based on administrative division information.Wherein, the target area
Domain can be a city (such as Beijing, Zhengzhou City etc.) or an administrative area (such as Chaoyang District, Beijing City) in city
Deng.For example, it is assumed that target area is Beijing, a rectangle can be constructed based on the latitude and longitude information of Beijing, and be arranged every
A grid size (assuming that the size in practical plot corresponding to each grid be 1km*1km, and then can by the rectangular partition at
Multiple grids, that is, Beijing to be divided into the plot of multiple 1km*1km.
In embodiments of the present invention, by the way that target area is divided into multiple plot, and it is pre- to carry out fire to each plot
It surveys, can reduce influence of the randomness of fire generation to prediction result, improve the accuracy of fire prediction result.
Step S102, the space characteristics data to same plot in multiple historical time sections merge, to be merged
Characteristic afterwards.
Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple.Into one
Step, the ground block feature influential on fire generation may include at least one of following: temperature, humidity, intramassif point of interest
(POI) frequency, the intramassif order volume of fire occur for classification number, adjacent plot.Wherein, the intramassif point of interest
Classification number can be regarded as the classification number of the intramassif landmark.For example, the plot dining room Nei You, gymnasium, reading room
These three points of interest, then the classification number of intramassif point of interest is 3.
Wherein, the historical time section can be regarded as the period before predicted time section.When it is implemented, can basis
The size of a period is arranged in business demand, for example can enable a period is one month.Assuming that predicted time section is May
Part, the plot multiple historical time sections space characteristics data can for the plot March space characteristics data, with
And the plot is in the space characteristics data in April.
In embodiments of the present invention, melted by the space characteristics data by same plot in multiple historical time sections
It closes, can effectively solve the problem that has caused by retardance the influence that fire occurs certain ground block feature (such as order volume)
The true problem of forecasting inaccuracy；In addition, fire occurs for the ground block feature for not only allowing for different spaces dimension by step S102
Influence, and the influence that fire occurs for the ground block feature for considering different time dimension, and then can be realized the dynamic of fire
State early warning improves the accuracy of fire prediction.
Step S103, by the fused characteristic and the plot the multiple historical time section fire
Statistical data inputs fire prediction device, and the probability value of fire occurs in predicted time section with the determination plot.
Wherein, the plot can be gone through for the plot multiple in the Fire Data of the multiple historical time section
The frequency occurs for the fire of history period.For example, it is assumed that predicted time section is May, then the plot is in the multiple history
Between the Fire Data of section can specifically: the frequency and the plot occur for fire of the plot in March in the fire in April
The frequency occurs for calamity.
Wherein, the fire prediction device can be by being trained to obtain to Time series forecasting model in advance.It is exemplary
Ground, the Time series forecasting model can include: conditional random field models, Markov-chain model, Hidden Markov chain model or
LSTM (shot and long term memory network) model.
In embodiments of the present invention, by step S103, the ground of different spaces dimension, different time dimension is not only allowed for
The influence that fire occurs for block feature, and the Fires Occurred in historical time section is considered to the shadow in predicted time section
It rings, the accuracy of fire prediction can be further increased.
In embodiments of the present invention, it by above step, can not only realize the dynamic early-warning of fire, and can be improved
The accuracy of fire prediction.In addition, compared with prior art, since prediction technique of the invention is without relying on related fire-salvage specialist
Fire assessment indicator system is constructed, evaluation criterion weight is determined without according to analytic hierarchy process (AHP), reduces answering for fire alarm
Polygamy.
Fig. 2 is the main flow schematic diagram of fire alarm method in accordance with another embodiment of the present invention.As shown in Fig. 2,
The fire alarm method of the embodiment of the present invention includes:
Step S201, target area is divided into multiple plot.
In this step, target area can be evenly divided into the ground of multiple regular edges based on latitude and longitude information
Block；Target area can also be divided into the irregular plot in multiple edges based on administrative division information.Wherein, the target area
Domain can be a city (such as Beijing, Zhengzhou City etc.) or an administrative area (such as Chaoyang District, Beijing City) in city
Deng.For example, it is assumed that target area is Beijing, a rectangle can be constructed based on the latitude and longitude information of Beijing, and be arranged every
A grid size (assuming that the size in practical plot corresponding to each grid be 1km*1km, and then can by the rectangular partition at
Multiple grids, that is, Beijing to be divided into the plot of multiple 1km*1km.
In embodiments of the present invention, by the way that target area is divided into multiple plot, and it is pre- to carry out fire to each plot
It surveys, can reduce influence of the randomness of fire generation to prediction result, improve the accuracy of fire prediction result.
Step S202, based on preparatory trained recurrent neural networks model to same plot in multiple historical time sections
Space characteristics data are merged, to obtain fused characteristic.
Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple.Into one
Step, the ground block feature influential on fire generation may include at least one of following: temperature, humidity, intramassif point of interest
(POI) frequency, the intramassif order volume of fire occur for classification number, adjacent plot.Wherein, the intramassif point of interest
Classification number can be regarded as the classification number of the intramassif landmark.For example, the plot dining room Nei You, gymnasium, reading room
These three points of interest, then the classification number of intramassif point of interest is 3.
Wherein, the historical time section can be regarded as the period before predicted time section.When it is implemented, can basis
The size of a period is arranged in business demand, for example can enable a period is one month.Assuming that predicted time section is May
Part, the plot multiple historical time sections space characteristics data can for the plot March space characteristics data, with
And the plot is in the space characteristics data in April.
In one example, can be occurred based on temperature, humidity, the classification number of intramassif point of interest (POI), adjacent plot
This five plot feature constructions, one plot of the frequency of fire, intramassif order volume is in a period (such as one month)
Space characteristics data, can be expressed as: xi,t={ tempi,t,humi,t,poii,t,suri,t,orderi,t}.Wherein, xi,tTable
Show space characteristics data of i-th of plot within t-th of period, specifically includes the plot characteristic statistics value of five dimensions；
tempi,t(for example it can be the plot in one month to the temperature statistics value for indicating in i-th of plot within t-th of period
Temperature averages)；humi,tIndicate that (for example it can be the ground to humidity statistical value of i-th of plot within t-th of period
Humidity average value of the block in one month)；poii,tIndicate the classification number of point of interest of i-th of plot within t-th of period；
suri,tIndicate that the frequency of fire occurs within t-th of period for the adjacent plot in i-th of plot；orderi,tIndicate i-th of ground
Quantity on order (such as its quantity for can be plot electric type order one month in) of the block within t-th of period.
Recurrent neural networks model (RNN) is that one kind has tree-shaped hierarchical structure and network node by its order of connection to defeated
Enter information and carries out recursive artificial neural network.In embodiments of the present invention, trained recurrent neural networks model can be based on
Space characteristics data to same plot in multiple historical time sections merge.For example, based on the RNN after training to same
When the space characteristics data of two historical time sections are merged, calculating process can be approximately represented as in plot:
hi,t-2=f (Uxi,t-2+b)；
hi,t-1=f (Uxi,t-1+Whi,t-2+b)；
Fi=sigmoid (Vhi,t-1+c)；
Wherein, U, W, V, b and c be RNN model in can training parameter, xi,t-2Indicate i-th of plot in historical time
Space characteristics data in section t-2, xi,t-1Indicate space characteristics data of i-th of plot in historical time section t-1, hi,t-2
Indicate input xi,t-2When RNN model hidden state, hi,t-1Indicate input xi,t-1When RNN model hidden state, FiExpression is melted
Characteristic after conjunction, f () and sigmoid () are nonlinear function used in RNN model.
In embodiments of the present invention, melted by the space characteristics data by same plot in multiple historical time sections
It closes, can effectively solve the problem that has caused by retardance the influence that fire occurs certain ground block feature (such as order volume)
The true problem of forecasting inaccuracy；In addition, fire occurs for the ground block feature for not only allowing for different spaces dimension by step S202
Influence, and the influence that fire occurs for the ground block feature for considering different time dimension, and then can be realized the dynamic of fire
State early warning improves the accuracy of fire prediction.
Step S203, by the fused characteristic and the plot the multiple historical time section fire
Statistical data inputs fire prediction device, and the probability value of fire occurs in predicted time section with the determination plot.
Wherein, the plot can be gone through for the plot multiple in the Fire Data of the multiple historical time section
The frequency occurs for the fire of history period, is represented by { yi,t-n,…yi,t-1}.Wherein, yi,t-nIndicate i-th of plot in history
The frequency of fire, y occur in time period t-ni,t-1Indicate that the frequency of fire occurs in historical time section t-1 for i-th of plot.Example
Such as, it is assumed that predicted time section is May, and the plot can in the Fire Data of multiple historical time sections specifically: the ground
Fire of the block in March occurs the frequency and the plot and the frequency occurs in the fire in April.In addition, in the specific implementation, institute
State plot the Fire Data of the multiple historical time section can be with are as follows: to the plot in multiple historical time sections
The data that the frequency is normalized occur for fire.
It in this step, can be by the fused characteristic in the plot (such as Fi) and the plot gone through the multiple
Fire Data (such as { the y of history periodi,t-n,…yi,t-1) input fire prediction device.Wherein, the fire prediction device
By being trained to obtain to conditional random field models (CRF) in advance.
Further, the process for carrying out fire prediction based on the CRF model after training can be approximately represented as:
Wherein,The probability value of fire occurs in predicted time section t for i-th of plot；For fusion
Characteristic F afterwardsiPredicted time section t occurs the influence function of fire；When for multiple history
Between section Fire Data to predicted time section t occur fire influence function；αpf(yi,t,Fi,p) it is Fi,p(due to space
Characteristic includes the plot characteristic statistics value of multiple dimensions, therefore FiIt also include multiple components, Fi,pFor FiIn p-th of component
Value) to predicted time section t occur fire influence；For the fire statistics of a historical time section
Data subsequent time period occur the influence of fire；αpAnd βqFor in conditional random field models can training parameter；There are four types of take q
Value, every kind of value corresponds to a kind of Fires Occurred, and (specifically include: fire, k+1 time occur for k+1 period and k period
Fire does not occur for Duan Fasheng fire and k period, fire does not occur for the k+1 period and fire, k+1 period occur for the k period
Fire does not occur with the k period), and then βqgq(yi,k+1,yi,k) indicate the influence of Fires Occurred a kind of.
In embodiments of the present invention, by step S203, the ground of different spaces dimension, different time dimension is not only allowed for
The influence that fire occurs for block feature, and the Fires Occurred in historical time section is considered to the shadow in predicted time section
It rings, the accuracy of fire prediction can be further increased.
Further, before executing step S201, the method for the embodiment of the present invention be can comprise the further steps of: to recurrence mind
It is trained through network model and conditional random field models.In training pattern, it is pre- to measure to need to define a loss function
Error between measured value and true value, and then can be reduced between predicted value and true value by continuing to optimize the parameter in model
Error.
Step S204, the first fire prediction figure is constructed according to the probability value that fire occurs for plot each in target area, with
The fire prediction situation in plot each in target area is visualized.
Illustratively, when constructing the first fire prediction figure, fire can be occurred according to plot each in target area
The display color in the plot is arranged in probability value.For example, can enable the display color that the big plot of fire probability value occurs is red, enable
The display color that the small plot of fire probability value occurs is yellow.Plot generation fire probability value is bigger, and display color is redder；
Plot generation fire probability value is smaller, and display color is more yellow.
Step S205, the maximum K plot of fire probability is filtered out, the general of fire is occurred according to the K plot
Rate value constructs the second fire prediction figure, is visualized with the fire prediction situation to the K plot.
Wherein, the value of K can be preset, and setting in real time can also be inputted according to user.
Step S206, the influence degree that fire occurs for multiple ground block feature is ranked up, and according to ranking results structure
Third fire prediction figure is built, to visualize to the multiple ground block feature.
In embodiments of the present invention, determining modules fire can occur in predicted time section for fire disaster alarming device
After probability value, automatic at least one step executed in step S204, step S205 and step S206；Fire alarm dress
Set can also receive terminal sending building the first fire prediction figure request, construct the second fire prediction figure request or
The request that person constructs third fire prediction figure executes step S204, step S205 or step S206 later.
It in embodiments of the present invention, can be to fire prediction result by step S204 and step S205 and step S206
And the influence degree that fire occurs for multiple ground block feature visualizes, and then can provide more for related personnel
Intuitively, scientific fire alarm information carries out emphasis deployment for the high area of fire risk convenient for related personnel.
In embodiments of the present invention, the dynamic early-warning of fire can not only be realized by above step, and can be improved
The accuracy of fire prediction reduces the complexity of fire prediction.
Fig. 3 is the main modular schematic diagram of fire disaster alarming device according to an embodiment of the invention.As shown in figure 3, this
The fire disaster alarming device 300 of inventive embodiments includes: division module 301, Fusion Module 302 and determining module 303.
Division module 301, for target area to be divided into multiple plot.
Illustratively, target area can be evenly divided into multiple edges based on latitude and longitude information by division module 301
The plot of rule；It is irregular that target area can also be divided into multiple edges based on administrative division information by division module 301
Plot.Wherein, the target area can be an administration in a city (such as Beijing, Zhengzhou City etc.) or city
Area (such as Chaoyang District, Beijing City) etc..For example, it is assumed that target area is Beijing, division module 301 can be based on Beijing
Latitude and longitude information constructs a rectangle, and the size of each grid is arranged (assuming that practical plot corresponding to each grid is big
Small is 1km*1km, and then can be by the rectangular partition at multiple grids, that is, Beijing is divided into multiple 1km*1km's
Plot.
In embodiments of the present invention, target area is divided by multiple plot by division module 301, and to each plot
Fire prediction is carried out, influence of the randomness of fire generation to prediction result is can reduce, improves the accurate of fire prediction result
Property.
Fusion Module 302 is merged for the space characteristics data to same plot in multiple historical time sections, with
To fused characteristic.Wherein, the space characteristics data are based on multiple ground block features influential on fire generation
Building.
Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple.Into one
Step, the ground block feature influential on fire generation may include at least one of following: temperature, humidity, intramassif point of interest
(POI) frequency, the intramassif order volume of fire occur for classification number, adjacent plot.Wherein, the intramassif point of interest
Classification number can be regarded as the classification number of the intramassif landmark.For example, the plot dining room Nei You, gymnasium, reading room
These three points of interest, then the classification number of intramassif point of interest is 3.
Wherein, the historical time section can be regarded as the period before predicted time section.When it is implemented, can basis
The size of a period is arranged in business demand, for example can enable a period is one month.Assuming that predicted time section is May
Part, the plot multiple historical time sections space characteristics data can for the plot March space characteristics data, with
And the plot is in the space characteristics data in April.
In embodiments of the present invention, by Fusion Module 302 by same plot multiple historical time sections space characteristics
Data are merged, and can effectively solve the problem that has delay to the influence that fire occurs due to certain ground block feature (such as order volume)
The true problem of forecasting inaccuracy caused by property；In addition, by Fusion Module 302 by same plot multiple historical time sections sky
Between characteristic merged, not only allow for the influence that fire occurs for the ground block feature of different spaces dimension, and consider
The influence that fire occurs for the ground block feature of different time dimension, and then can be realized the dynamic early-warning of fire, improve fire
The accuracy of prediction.
Determining module 303 is used for the fused characteristic and the plot in the multiple historical time
The Fire Data of section inputs fire prediction device, and the probability value of fire occurs in predicted time section with the determination plot.
Wherein, the plot can be gone through for the plot multiple in the Fire Data of the multiple historical time section
The frequency occurs for the fire of history period.For example, it is assumed that predicted time section is May, the plot is in multiple historical time sections
Fire Data can specifically: fire of the plot in March occurs the frequency and the plot and occur in the fire in April
The frequency.
Wherein, the fire prediction device can be by being trained to obtain to Time series forecasting model in advance.It is exemplary
Ground, the Time series forecasting model can include: conditional random field models, Markov-chain model, Hidden Markov chain model or
LSTM (shot and long term memory network) model.
In embodiments of the present invention, the fused characteristic and the plot are existed by determining module 303
The Fire Data input fire prediction device of the multiple historical time section carries out fire prediction, not only allows for different spaces
The ground block feature influence that fire is occurred of dimension, different time dimension, and consider the generation of the fire in historical time section
Situation can further increase the accuracy of fire prediction to the influence in predicted time section.
The device of the embodiment of the present invention can not only realize the dynamic early-warning of fire, and can be improved the standard of fire prediction
True property, reduces the complexity of fire alarm.
Fig. 4 is the main modular schematic diagram of fire disaster alarming device in accordance with another embodiment of the present invention.As shown in figure 4,
The fire disaster alarming device 400 of the embodiment of the present invention includes: division module 401, Fusion Module 402, determining module 403, the first structure
It models block 404, second and constructs module 405, third building module 406.
Division module 401, for target area to be divided into multiple plot.
Illustratively, target area can be evenly divided into multiple edges based on latitude and longitude information by division module 401
The plot of rule；It is irregular that target area can also be divided into multiple edges based on administrative division information by division module 401
Plot.Wherein, the target area can be an administration in a city (such as Beijing, Zhengzhou City etc.) or city
Area (such as Chaoyang District, Beijing City) etc..For example, it is assumed that target area is Beijing, division module 401 can be based on Beijing
Latitude and longitude information constructs a rectangle, and the size of each grid is arranged (assuming that practical plot corresponding to each grid is big
Small is 1km*1km, and then can be by the rectangular partition at multiple grids, that is, Beijing is divided into multiple 1km*1km's
Plot.
In embodiments of the present invention, target area is divided by multiple plot by division module 401, and to each plot
Fire prediction is carried out, influence of the randomness of fire generation to prediction result is can reduce, improves the accurate of fire prediction result
Property.
Fusion Module 402, for being based on preparatory trained recurrent neural networks model to same plot in multiple history
The space characteristics data of period are merged, to obtain fused characteristic.
Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple.Into one
Step, the ground block feature influential on fire generation may include at least one of following: temperature, humidity, intramassif point of interest
(POI) frequency, the intramassif order volume of fire occur for classification number, adjacent plot.Wherein, the intramassif point of interest
Classification number can be regarded as the classification number of the intramassif landmark.For example, the plot dining room Nei You, gymnasium, reading room
These three points of interest, then the classification number of intramassif point of interest is 3.
Wherein, the historical time section can be regarded as the period before predicted time section.When it is implemented, can basis
The size of a period is arranged in business demand, for example can enable a period is one month.Assuming that predicted time section is May
Part, the plot multiple historical time sections space characteristics data can for the plot March space characteristics data, with
And the plot is in the space characteristics data in April.
In one example, can be occurred based on temperature, humidity, the classification number of intramassif point of interest (POI), adjacent plot
This five plot feature constructions, one plot of the frequency of fire, intramassif order volume is in a period (such as one month)
Space characteristics data, can be expressed as: xi,t={ tempi,t,humi,t,poii,t,suri,t,orderi,t}.Wherein, xi,tTable
Show space characteristics data of i-th of plot within t-th of period, specifically includes the plot characteristic statistics value of five dimensions；
tempi,t(for example it can be the plot in one month to the temperature statistics value for indicating in i-th of plot within t-th of period
Temperature averages)；humi,tIndicate that (for example it can be the ground to humidity statistical value of i-th of plot within t-th of period
Humidity average value of the block in one month)；poii,tIndicate the classification number of point of interest of i-th of plot within t-th of period；
suri,tIndicate that the frequency of fire occurs within t-th of period for the adjacent plot in i-th of plot；orderi,tIndicate i-th of ground
Quantity on order (such as its quantity for can be plot electric type order one month in) of the block within t-th of period.
Recurrent neural networks model (RNN) is that one kind has tree-shaped hierarchical structure and network node by its order of connection to defeated
Enter information and carries out recursive artificial neural network.In embodiments of the present invention, Fusion Module 402 can be based on trained recurrence mind
Space characteristics data through network model to same plot in multiple historical time sections merge.
In embodiments of the present invention, by Fusion Module 402 by same plot multiple historical time sections space characteristics
Data are merged, and can effectively solve the problem that has delay to the influence that fire occurs due to certain ground block feature (such as order volume)
The true problem of forecasting inaccuracy caused by property；In addition, by Fusion Module 402 by same plot multiple historical time sections sky
Between characteristic carry out fusion and not only allow for the influence that fire occurs for the ground block feature of different spaces dimension, and consider
The influence that fire occurs for the ground block feature of different time dimension, and then can be realized the dynamic early-warning of fire, it is pre- to improve fire
The accuracy of survey.
Determining module 403 is used for the fused characteristic and the plot in the multiple historical time
The Fire Data of section inputs fire prediction device, and the probability value of fire occurs in predicted time section with the determination plot.
Wherein, the fire prediction device to conditional random field models (CRF) by being trained to obtain in advance.
Wherein, the plot can be gone through for the plot multiple in the Fire Data of the multiple historical time section
The frequency occurs for the fire of history period, is represented by { yi,t-n,…yi,t-1}.Wherein, yi,t-nIndicate i-th of plot in history
The frequency of fire, y occur in time period t-ni,t-1Indicate that the frequency of fire occurs in historical time section t-1 for i-th of plot.Example
Such as, it is assumed that predicted time section is May, and the plot can in the Fire Data of multiple historical time sections specifically: the ground
Fire of the block in March occurs the frequency and the plot and the frequency occurs in the fire in April.In addition, in the specific implementation, institute
State plot the Fire Data of the multiple historical time section can be with are as follows: to the plot in multiple historical time sections
The data that the frequency is normalized occur for fire.
In embodiments of the present invention, by by the fused characteristic and the plot in the multiple history
The Fire Data of period inputs fire prediction device, not only allows for the plot of different spaces dimension, different time dimension
The influence that fire occurs for feature, and the Fires Occurred in historical time section is considered to the shadow in predicted time section
It rings, the accuracy of fire prediction can be further increased.
First building module 404, for the first fire of probability value building of fire to occur according to plot each in target area
Calamity prognostic chart is visualized with the fire prediction situation to plot each in target area.
Illustratively, the first building module 404, can be according to each in target area when constructing the first fire prediction figure
The display color in the plot is arranged in the probability value that fire occurs for plot.The aobvious of the big plot of fire probability value occurs for example, can enable
Show color for red, enabling the display color that the small plot of fire probability value occurs is yellow.Plot generation fire probability value is bigger,
Its display color is redder；Plot generation fire probability value is smaller, and display color is more yellow.
Second building module 405 is sent out for filtering out the maximum K plot of fire probability according to the K plot
The probability value for calamity of lighting a fire constructs the second fire prediction figure, is visualized with the fire prediction situation to the K plot.Its
In, the value of K can be preset, and setting in real time can also be inputted according to user.
Third constructs module 406, and the influence degree for fire to occur for multiple ground block feature is ranked up, and according to
Ranking results construct third fire prediction figure, to visualize to the multiple ground block feature.
In embodiments of the present invention, it can determine that fire occurs in predicted time section for each plot in determining module 403
It is automatic to call at least one of the first building module, the second building module and third building module after probability value is completed；?
It can be in the request for building the first fire prediction figure for receiving terminal sending, the request of the second fire prediction figure of building or structure
The first building of calling module, the second building module or third construct module after building the request of third fire prediction figure.
In embodiments of the present invention, module is constructed by the first building of setting module, the second building module and third, be convenient for
The influence degree that fire occurs for fire prediction result and multiple ground block feature visualizes, and then can be phase
Pass personnel provide more intuitive, science fire alarm information, carry out weight for the high area of fire risk convenient for related personnel
Point deployment.
The device of the embodiment of the present invention can not only realize the dynamic early-warning of fire, and can be improved the standard of fire prediction
True property, reduces the complexity of fire prediction.
Fig. 5 is shown can be using the fire alarm method of the embodiment of the present invention or the exemplary system of fire disaster alarming device
Framework 500.
As shown in figure 5, system architecture 500 may include terminal device 501,502,503, network 504 and server 505.
Network 504 between terminal device 501,502,503 and server 505 to provide the medium of communication link.Network 504 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 501,502,503 and be interacted by network 504 with server 505, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 501,502,503
The application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 501,502,503 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 505 can be to provide the server of various services, such as utilize terminal device 501,502,503 to user
The website browsed provides the back-stage management server supported.Back-stage management server can request the fire alarm received
Etc. data carry out the processing such as analyzing, and processing result (such as fire alarm result) is fed back into terminal device.
It should be noted that fire alarm method provided by the embodiment of the present invention is generally executed by server 505, accordingly
Ground, fire disaster alarming device are generally positioned in server 505.
It should be understood that the number of terminal device, network and server in Fig. 5 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Below with reference to Fig. 6, it illustrates the computer systems 600 for the electronic equipment for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.Computer system shown in Fig. 6 is only an example, should not function and use to the embodiment of the present invention
Range band carrys out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communications portion 609, and/or from can
Medium 611 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 601, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
Include division module, Fusion Module and determining module.Wherein, the title of these modules is not constituted under certain conditions to the module
The restriction of itself, for example, division module is also described as " target area is divided into the module in multiple plot ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
It obtains the equipment and executes following below scheme: target area is divided into multiple plot；To same plot multiple historical time sections sky
Between characteristic merged, to obtain fused characteristic；Wherein, the space characteristics data are based on multiple pairs of fire
Influential plot feature construction occurs for calamity；By the fused characteristic and the plot in the multiple history
The Fire Data of period inputs fire prediction device, and the probability of fire occurs in predicted time section with the determination plot
Value.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (10)
1. a kind of fire alarm method, which is characterized in that the described method includes:
Target area is divided into multiple plot；
Space characteristics data to same plot in multiple historical time sections merge, to obtain fused characteristic；
Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple；
The fused characteristic and the plot are inputted in the Fire Data of the multiple historical time section
The probability value of fire occurs in predicted time section with the determination plot for fire prediction device.
2. the method according to claim 1, wherein it is described to same plot in the space of multiple historical time sections
Characteristic is merged, and to obtain fused characteristic the step of includes:
Based on preparatory trained recurrent neural networks model to same plot multiple historical time sections space characteristics data
It is merged, to obtain fused characteristic.
3. the method according to claim 1, wherein the fire prediction device is by advance to time series forecasting mould
What type was trained；Wherein, the Time series forecasting model includes: conditional random field models, Markov-chain model, hidden horse
Er Kefu chain model or LSTM model.
4. the method according to claim 1, wherein the method also includes:
The first fire prediction figure is constructed according to the probability value that fire occurs for plot each in target area, to each in target area
The fire prediction situation in a plot is visualized；And/or
The maximum K plot of fire probability is filtered out, the probability value building the of fire then occurs according to the K plot
Two fire prediction figures are visualized with the fire prediction situation to the K plot.
5. according to the method described in claim 3, it is characterized in that, the method also includes:
The influence degree that fire occurs for the multiple ground block feature is ranked up, and constructs third fire according to ranking results
Prognostic chart, to be visualized to the multiple ground block feature；Wherein, the shadow that fire occurs for the multiple ground block feature
The degree of sound is determined according to the parameter value in the Time series forecasting model after training.
6. the method according to claim 1, wherein it is described it is influential on fire generation ground block feature include with
At least one of lower: temperature, humidity, the classification number of intramassif point of interest, adjacent plot occur the frequency of fire, intramassif order
Dan Liang.
7. a kind of fire disaster alarming device, which is characterized in that described device includes:
Division module, for target area to be divided into multiple plot；
Fusion Module is merged for the space characteristics data to same plot in multiple historical time sections, to be merged
Characteristic afterwards；Wherein, the space characteristics data are that influential plot feature construction occurs on fire based on multiple；
Determining module, for by the fused characteristic and the plot the multiple historical time section fire
Statistical data inputs fire prediction device, and the probability value of fire occurs in predicted time section with the determination plot.
8. device according to claim 7, which is characterized in that the Fusion Module is to same plot in multiple historical times
The space characteristics data of section are merged, and include: to obtain fused characteristic
The Fusion Module is based on preparatory trained recurrent neural networks model to same plot in multiple historical time sections
Space characteristics data are merged, to obtain fused characteristic.
9. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1 to 6.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1 to 6 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910537983.5A CN110309961A (en) | 2019-06-20 | 2019-06-20 | Fire alarm method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910537983.5A CN110309961A (en) | 2019-06-20 | 2019-06-20 | Fire alarm method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110309961A true CN110309961A (en) | 2019-10-08 |
Family
ID=68077457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910537983.5A Pending CN110309961A (en) | 2019-06-20 | 2019-06-20 | Fire alarm method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110309961A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942259A (en) * | 2019-12-10 | 2020-03-31 | 北方工业大学 | Community gas equipment risk assessment method and device |
| CN110956409A (en) * | 2019-12-10 | 2020-04-03 | 北方工业大学 | Community gas equipment risk control method and device |
| CN112634572A (en) * | 2020-12-07 | 2021-04-09 | 北京中电飞华通信有限公司 | Fire prediction method and device based on smoke temperature sensing and electronic equipment |
| CN112950880A (en) * | 2021-01-26 | 2021-06-11 | 特斯联科技集团有限公司 | Fire early warning method and system based on big data |
| CN114792163A (en) * | 2022-04-24 | 2022-07-26 | 山东强力消防工程有限公司 | Fire prediction system under multi-dimensional data integration |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870891A (en) * | 2014-03-25 | 2014-06-18 | 安徽大学 | Electric transmission line fire spreading predicating method and system based on grid flow |
| CN104658170A (en) * | 2013-11-25 | 2015-05-27 | 青岛嘉和兴制粉有限公司 | Efficient fire early-warning method |
| CN105678419A (en) * | 2016-01-05 | 2016-06-15 | 天津大学 | Fine grit-based forest fire hazard probability forecasting system |
| CN108648124A (en) * | 2018-04-03 | 2018-10-12 | 成都恒华光讯科技有限公司 | A kind of smart city fire-fighting Internet of Things big data management system |
| CN109615064A (en) * | 2018-12-07 | 2019-04-12 | 电子科技大学 | A kind of end-to-end decision-making technique of intelligent vehicle based on space-time characteristic fusion recurrent neural network |
-
2019
- 2019-06-20 CN CN201910537983.5A patent/CN110309961A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104658170A (en) * | 2013-11-25 | 2015-05-27 | 青岛嘉和兴制粉有限公司 | Efficient fire early-warning method |
| CN103870891A (en) * | 2014-03-25 | 2014-06-18 | 安徽大学 | Electric transmission line fire spreading predicating method and system based on grid flow |
| CN105678419A (en) * | 2016-01-05 | 2016-06-15 | 天津大学 | Fine grit-based forest fire hazard probability forecasting system |
| CN108648124A (en) * | 2018-04-03 | 2018-10-12 | 成都恒华光讯科技有限公司 | A kind of smart city fire-fighting Internet of Things big data management system |
| CN109615064A (en) * | 2018-12-07 | 2019-04-12 | 电子科技大学 | A kind of end-to-end decision-making technique of intelligent vehicle based on space-time characteristic fusion recurrent neural network |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942259A (en) * | 2019-12-10 | 2020-03-31 | 北方工业大学 | Community gas equipment risk assessment method and device |
| CN110956409A (en) * | 2019-12-10 | 2020-04-03 | 北方工业大学 | Community gas equipment risk control method and device |
| CN112634572A (en) * | 2020-12-07 | 2021-04-09 | 北京中电飞华通信有限公司 | Fire prediction method and device based on smoke temperature sensing and electronic equipment |
| CN112950880A (en) * | 2021-01-26 | 2021-06-11 | 特斯联科技集团有限公司 | Fire early warning method and system based on big data |
| CN114792163A (en) * | 2022-04-24 | 2022-07-26 | 山东强力消防工程有限公司 | Fire prediction system under multi-dimensional data integration |
| CN114792163B (en) * | 2022-04-24 | 2024-01-02 | 火眼消防技术有限公司 | Fire prediction system under multidimensional data integration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110309961A (en) | Fire alarm method and apparatus | |
| Blondel et al. | A survey of results on mobile phone datasets analysis | |
| Zheng et al. | Detecting collective anomalies from multiple spatio-temporal datasets across different domains | |
| US10474974B2 (en) | Reciprocal models for resource allocation | |
| CN110647522B (en) | Data mining method, device and system | |
| CN108280685A (en) | Information acquisition method and device | |
| WO2013062237A1 (en) | System and method for managing social relationship information | |
| CN109886699A (en) | Activity recognition method and device, electronic equipment, storage medium | |
| CN109949063A (en) | A kind of address determines method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| Sim et al. | Great cities look small | |
| CN109831532A (en) | Data sharing method, device, equipment and medium | |
| CN109993638A (en) | Method, apparatus, medium and the electronic equipment of Products Show | |
| Zhang et al. | Simulation optimization of police patrol districting plans using response surfaces | |
| CN111311193B (en) | Method and device for configuring public service resources | |
| CN109034957A (en) | A kind of Products Show method, server and system for sharing articles | |
| US10157356B2 (en) | Activity based resource allocation modeling | |
| CN109903079A (en) | Information processing method, equipment and storage medium | |
| CN109002925A (en) | Traffic prediction method and apparatus | |
| CN108875032A (en) | Area type determines method and device | |
| WO2024051146A1 (en) | Methods, systems, and computer-readable media for recommending downstream operator | |
| CN108270929A (en) | Network traffic Forecasting Methodology and device | |
| CN110457607A (en) | A kind of partial journey information recommendation method, device, medium and electronic equipment | |
| Feng et al. | An empirical study on evolution of the connectivity for VANETs based on taxi GPS traces | |
| Ma et al. | A new assessment model for evacuation vulnerability in urban areas | |
| CN106157127A (en) | The framework of the online auction platform of wireless frequency spectrum and implementation method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200728 Address after: Room 806, 8 / F, Zhongguancun International Innovation Building, Haidian District, Beijing 100080 Applicant after: Beijing Jingdong intelligent city big data research institute Address before: 100086 No.76 Zhichun Road, Haidian District, Beijing, Building No.1, Building No.9, Floor 1-7-5 Applicant before: Jingdong City (Beijing) Digital Technology Co.,Ltd. |