CN110675587B - Fire early warning method, device, terminal and readable storage medium - Google Patents
Fire early warning method, device, terminal and readable storage medium Download PDFInfo
- Publication number
- CN110675587B CN110675587B CN201910912978.8A CN201910912978A CN110675587B CN 110675587 B CN110675587 B CN 110675587B CN 201910912978 A CN201910912978 A CN 201910912978A CN 110675587 B CN110675587 B CN 110675587B
- Authority
- CN
- China
- Prior art keywords
- early warning
- parameters
- fire
- network model
- node
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/04—Hydraulic or pneumatic actuation of the alarm, e.g. by change of fluid pressure
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
- G08B17/117—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means by using a detection device for specific gases, e.g. combustion products, produced by the fire
Abstract
The embodiment of the invention provides a fire early warning method, a fire early warning device, a fire early warning terminal and a readable storage medium. The fire early warning method comprises the following steps: constructing an early warning parameter of an early warning node and an environment parameter intergraph data structure in a target area where the early warning node is located; training and constructing a target graph neural network model according to a graph data structure; acquiring actual environment parameters of a target area, and performing data preprocessing on the actual environment parameters; determining early warning parameters of early warning nodes according to the preprocessed actual environment parameters and the target graph neural network model; and carrying out fire hazard early warning according to the early warning parameters. And constructing a graph data structure according to the early warning parameters of the early warning nodes and the environmental parameters in the target area, wherein the graph data structure can contain the environmental parameters with a plurality of dimensional data. A target graph neural network model is trained and constructed based on the graph data structure, so that accurate fire early warning can be made for a target area in a targeted mode, and the reliability of the fire early warning is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of emergency management, in particular to a fire early warning method, a fire early warning device, a fire early warning terminal and a readable storage medium.
Background
At present, a fire early warning system is mainly used for monitoring based on a single sensor parameter, and early warning is carried out when the monitored parameter reaches a preset threshold value. However, the method of monitoring by using a single sensor can lead to unreliable fire early warning, untimely fire discovery and higher fire false alarm rate and missing report rate.
Disclosure of Invention
The embodiment of the invention aims to provide a fire early warning method, a fire early warning device, a fire early warning terminal and a readable storage medium, which can solve the technical problem that fire early warning in a fire early warning system in the prior art is unreliable.
In order to solve the above technical problem, an embodiment of the present invention provides a fire early warning method, including:
constructing an early warning parameter of an early warning node and an environment parameter intergraph data structure in a target area where the early warning node is located;
training and constructing a target graph neural network model according to the graph data structure;
acquiring actual environment parameters of the target area, and performing data preprocessing on the actual environment parameters;
determining early warning parameters of the early warning nodes according to the preprocessed actual environment parameters and the preprocessed target graph neural network model;
and carrying out fire early warning according to the early warning parameters.
Optionally, the step of constructing a data structure of a graph between the early warning parameters of the early warning node and the environmental parameters in the target area where the early warning node is located includes:
establishing connection for parameters with direct dependency relationship in the environment parameters;
and establishing connection between the environmental parameters which have direct dependence relationship with the early warning parameters and the early warning parameters, thereby forming the graph data structure.
Optionally, the environmental parameters include carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity, barometric pressure intensity, and illumination intensity.
Optionally, the step of training and constructing a target graph neural network model according to the graph data structure includes:
acquiring training parameters matched with the early warning parameters according to the early warning parameters of the early warning nodes;
and training a preset network model by combining the graph data structure according to the early warning parameters and the training parameters so as to obtain the target graph neural network model.
Optionally, the step of acquiring actual environment parameters of the target region and performing data preprocessing on the actual environment parameters includes;
acquiring actual environmental parameters in the target area through a sensor arranged in the target area;
and carrying out non-dimensionalization processing on the actual environment parameters.
Optionally, the step of determining the early warning parameters of the early warning node according to the preprocessed actual environment parameters and the target graph neural network model includes:
inputting the actual environment parameters into the target graph neural network model as an input set of the target graph neural network model;
and calculating the early warning parameters of the early warning nodes by the target graph neural network model.
Optionally, the step of performing fire early warning according to the early warning parameter includes:
identifying the early warning grade of the early warning parameter;
and executing corresponding text early warning and/or acousto-optic early warning according to the early warning grade of the early warning parameter.
Additionally, an embodiment of the present invention further provides a fire early warning device, including:
the early warning system comprises a first construction module, a second construction module and a third construction module, wherein the first construction module is used for constructing an early warning parameter of an early warning node and an environment parameter map data structure in a target area where the early warning node is located;
the second construction module is used for training and constructing a target graph neural network model according to the graph data structure;
the data processing module is used for acquiring the actual environment parameters of the target area and carrying out data preprocessing on the actual environment parameters;
the determining module is used for determining early warning parameters of the early warning nodes according to the preprocessed actual environment parameters and the target graph neural network model;
and the early warning module is used for carrying out fire early warning according to the early warning parameters.
Additionally, an embodiment of the present invention further provides a terminal, where the terminal includes: a memory, a processor and a program stored in the memory and executable on the processor, the program, when executed by the processor, implementing the steps of the fire early warning method as described above.
Additionally, an embodiment of the present invention further provides a readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the fire early warning method as described above.
Compared with the prior art, in the fire early warning method provided by the embodiment of the invention, the graph data structure is constructed together according to the early warning parameters of the early warning nodes and the environmental parameters in the target area, the graph data structure can contain the environmental parameters with a plurality of dimensional data, so that the plurality of dimensional data can be collected to comprehensively and accurately represent the environmental information in the target area, and the environmental parameters and the early warning parameters of the plurality of dimensional data are connected according to the mutual relation to construct the graph data structure. A target graph neural network model is trained and constructed based on the graph data structure, so that accurate fire early warning can be made for a target area in a targeted mode, and the reliability of the fire early warning is improved.
Drawings
FIG. 1 is a schematic diagram of an application scenario of the fire early warning method of the present invention;
FIG. 2 is a flow chart of a fire warning method according to an embodiment of the present invention;
fig. 3 is a detailed flowchart of step S10 shown in fig. 2;
fig. 4 is a block diagram of a fire early warning apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a hardware structure of a terminal according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of the fire warning method according to the present invention. Here, an example of performing fire early warning for a target area is described. A plurality of dimensional parameters may be included within the target region, such as carbon monoxide concentration, rate of change of carbon dioxide concentration, smoke concentration, and temperature, among others. The terminal 100 acquires a plurality of dimensional parameters in the target area and performs data processing and analysis, thereby achieving the technical purpose of performing fire early warning based on multi-dimensional data.
Based on the application scenario and the hardware structure, the fire early warning method provided by the invention has the following embodiments:
referring to fig. 2, an embodiment of the present invention provides a fire early warning method, including the following steps:
and step S10, constructing a data structure of an early warning parameter of the early warning node and an environment parameter in a target area where the early warning node is located.
The terminal 100 constructs a data structure of an early warning parameter of an early warning node and an environment parameter in a target area where the early warning node is located. The graph data structure comprises nodes and edges for representing the interrelation among the nodes. Two nodes having a direct relationship to each other may be connected by edges, such that each node and edge constitutes a graph data structure. The target area is used for monitoring whether a fire condition exists or not, the target area is a certain space such as a room or a channel, and by the fire early warning method, whether the fire condition exists in the target area or not is monitored, and grading early warning can be carried out according to various conditions. The environmental parameters are various data features for characterizing environmental information in a target area, for example, the environmental parameters include dimensional data: carbon monoxide concentration, carbon dioxide concentration rate of change, smoke concentration, temperature, oxygen concentration, humidity, air pressure intensity, and illumination intensity. Of course, the environmental parameters may also include other dimensional data, which is not listed here. The early warning nodes are characterized by early warning parameters, wherein the early warning parameters can be divided into a plurality of early warning levels, for example, the early warning parameters can be divided into three early warning levels: normal grade, high risk grade and open fire burning grade, namely the normal grade is used for representing that no fire condition exists in the regional environment; the high risk grade is used for representing that the regional environment has fire hazard and has a high risk situation; the open flame burning grade is used for indicating that open flame burning exists in the regional environment and a fire disaster is formed. Of course, the warning parameters may also be divided into other numbers of warning levels, which are not listed here.
In this embodiment, a graph data structure is constructed according to the early warning parameters of the early warning nodes and the environmental parameters in the target area, wherein one node represents one dimension data in the environmental parameters, and each node having a relationship with each other is connected through edges to construct the graph data structure.
For example, the environmental parameters include a plurality of dimensional data: carbon monoxide concentration, rate of change of carbon dioxide concentration, smoke concentration, temperature, oxygen concentration, humidity, barometric pressure intensity, and illumination intensity, and thus can be formulated as: carbon monoxide concentration node, carbon dioxide concentration change rate node, smoke concentration node, temperature node, oxygen concentration node, humidity node, atmospheric pressure intensity node and illumination intensity node. The mutual relation among all the nodes is established through the early warning node, the carbon monoxide concentration node, the carbon dioxide concentration change rate node, the smoke concentration node, the temperature node, the oxygen concentration node, the humidity node, the air pressure intensity node and the illumination intensity node, and therefore a graph data structure is constructed.
And step S20, training and constructing a target graph neural network model according to the graph data structure.
And the terminal 100 trains and constructs a target graph neural network model according to the graph data structure. The target graph neural network model is a graph neural network model obtained by training data in a graph data structure based on the graph data structure.
For example, a target graph neural network model is obtained based on the constructed graph data structure and trained through data in the graph data structure. Alternatively, the data in the graph data structure may be based on historical environmental data within a region, or obtained through scene simulation.
And step S30, acquiring the actual environment parameters of the target area, and performing data preprocessing on the actual environment parameters.
The terminal 100 collects the actual environment parameters of the target area and performs data preprocessing on the actual environment parameters. The terminal 100 may include a sensor for acquiring an actual environment parameter, for example, the terminal 100 may include a carbon monoxide concentration sensor, a carbon dioxide concentration change rate sensor, a smoke concentration sensor, a temperature sensor, an oxygen concentration sensor, a humidity sensor, an air pressure intensity sensor, an illumination intensity sensor, and a data processor, and the plurality of actual environment parameters are acquired by the plurality of sensors and fed back to the data processor, and the data processor performs data preprocessing on the plurality of actual environment parameters. Optionally, a carbon monoxide concentration sensor, a carbon dioxide concentration change rate sensor, a smoke concentration sensor, a temperature sensor, an oxygen concentration sensor, a humidity sensor, an air pressure intensity sensor, and an illumination intensity sensor are disposed in the target area.
For example, a carbon monoxide concentration sensor is taken as an example to illustrate, the carbon monoxide concentration sensor collects the carbon monoxide concentration in the target area and feeds the carbon monoxide concentration back to the data processor, and the data processor performs a de-unitization process on the carbon monoxide concentration, that is, a non-dimensionalization process on the carbon monoxide concentration.
And step S40, determining early warning parameters of the early warning nodes according to the preprocessed actual environment parameters and the target graph neural network model.
And the terminal 100 determines the early warning parameters of the early warning nodes according to the preprocessed actual environment parameters and the target graph neural network model. The real environment parameters are used as an input set of the target graph neural network model, and the target graph neural network model is used for analyzing and processing, so that early warning parameters matched with the real environment parameters in the early warning nodes are determined.
For example, the early warning parameters are classified into a normal level, a high risk level, and an open flame combustion level. And inputting the actual environment parameters into the trained target graph neural network model so as to determine early warning parameters matched with the actual environment parameters, wherein the early warning parameters are one of normal grade, high risk grade or open flame combustion parameters.
And step S50, carrying out fire early warning according to the early warning parameters.
And the terminal 100 carries out fire early warning according to the early warning parameters. When the terminal 100 determines the early warning parameters matched with the actual environmental parameters, the terminal 100 performs fire early warning according to the early warning parameters. For example, the early warning parameters are divided into a normal level, a high risk level and an open fire burning level, and when the early warning parameters are the normal level, the terminal 100 correspondingly makes a fire early warning according to the signal of the normal level: the area has no fire hazard and the condition is normal; when the early warning parameter is a high risk level, the terminal 100 correspondingly makes a fire early warning according to the signal of the high risk level: the area has fire hazard and belongs to a high risk situation; when the early warning parameter is the open fire combustion level, the terminal 100 correspondingly makes a fire early warning according to the signal of the open fire combustion level: this area already constitutes a fire.
In this embodiment, a graph data structure is constructed according to the early warning parameters of the early warning nodes and the environmental parameters in the target area, and the graph data structure may include environmental parameters with a plurality of dimensional data, so that the plurality of dimensional data may be collected to comprehensively and accurately represent the environmental information in the target area, and the environmental parameters and the early warning parameters of the plurality of dimensional data are connected according to the mutual relationship to construct the graph data structure. A target graph neural network model is trained and constructed based on the graph data structure, so that accurate fire early warning can be made for a target area in a targeted mode, and the reliability of the fire early warning is improved.
Referring to fig. 3, based on the above embodiment, another embodiment of the fire warning method according to the present invention is further provided, which is different from the above embodiment in that:
step S10, constructing a data structure of an early warning parameter of an early warning node and an environment parameter map between the early warning node and the environment parameter in the target area, wherein the data structure specifically comprises the following steps:
step S11, establishing connection for parameters with direct dependency relationship in the environment parameters;
and step S12, connecting the environmental parameters having direct dependency relationship with the early warning parameters, thereby forming the graph data structure.
Environmental information in the target area is represented by the dimensional data, so that fire early warning can be performed on the target area. For example, the environmental parameters include a plurality of dimensional data: carbon monoxide concentration, carbon dioxide concentration rate of change, smog concentration, temperature, oxygen concentration, humidity, atmospheric pressure intensity and illumination intensity, can gather the data message of carbon monoxide concentration, carbon dioxide concentration rate of change, smog concentration, temperature, oxygen concentration, humidity, atmospheric pressure intensity and illumination intensity respectively through setting up a plurality of sensors in the target area. Based on the environmental parameters, the following can be planned: carbon monoxide concentration node, carbon dioxide concentration change rate node, smoke concentration node, temperature node, oxygen concentration node, humidity node, atmospheric pressure intensity node and illumination intensity node.
According to the direct dependency relationship among the nodes, the following graph data structure is constructed:
the adjacent nodes of the early warning node are a carbon monoxide concentration node, a carbon dioxide concentration change rate node, a smoke concentration node and a temperature node;
the adjacent nodes of the carbon monoxide concentration node are provided with an oxygen concentration node and an early warning node;
the adjacent nodes of the carbon dioxide concentration change rate node are a temperature node, an oxygen concentration node and an early warning node;
the adjacent nodes of the smoke concentration node are provided with an illumination intensity node and an early warning node;
the adjacent nodes of the temperature node are a carbon dioxide concentration change rate node, an air pressure intensity node, a humidity node and an early warning node.
In the present embodiment, when constructing the graph data structure, the graph data structure is constructed in consideration of the mutual influence between the respective nodes. For example, the four-dimensional data of carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration and temperature are directly related to the fire situation, and the adjacent nodes of the early warning node comprise a carbon monoxide concentration node, a carbon dioxide concentration change rate node, a smoke concentration node and a temperature node.
In addition, in the process of judging whether a fire disaster exists, the concentration of the carbon monoxide is related to the concentration of the oxygen, and then the adjacent nodes of the carbon monoxide concentration node comprise an oxygen concentration node and an early warning node; the carbon dioxide concentration change rate is related to the temperature and the oxygen concentration, and the adjacent nodes of the carbon dioxide concentration change rate node comprise a temperature node, an oxygen concentration node and an early warning node; if the smoke concentration is related to the illumination intensity, the illumination intensity node and the early warning node are arranged at the adjacent nodes of the smoke concentration node; the temperature is related to the carbon dioxide concentration change rate, the air pressure intensity and the humidity, and the adjacent nodes of the temperature node comprise a carbon dioxide concentration change rate node, an air pressure intensity node, a humidity node and an early warning node.
Of course, the above only provides a method for constructing a graph data structure in consideration of direct dependency relationships between nodes, and in other embodiments, there are still multiple methods for constructing a graph data structure, and constructing a graph data structure conforming to a scene for a specific application scene can enhance the judgment capability of the scene.
In this embodiment, some environmental parameters may be abnormal, such as an increase in carbon monoxide concentration, a sudden increase in temperature, and the like, at the time of or during the latent period of the fire. And constructing an appropriate graph data structure based on a plurality of dimensional data in the target area, so that the fire early warning capability of the target area can be enhanced.
In other embodiments, in step S20, the step of training and constructing the target graph neural network model according to the graph data structure specifically includes:
step S21, acquiring training parameters matched with the early warning parameters according to the early warning parameters of the early warning nodes;
and step S22, training a preset network model according to the early warning parameters and the training parameters and by combining the graph data structure, thereby obtaining the target graph neural network model.
The early warning parameters are used for representing early warning nodes, wherein the early warning parameters can be divided into a plurality of early warning levels, for example, the early warning parameters can be divided into a normal level, a high risk level and an open fire combustion level. In this embodiment, when performing fire early warning for a target area, environmental parameters of multiple dimensions in the target area may be collected: carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity node, air pressure intensity and illumination intensity.
Therefore, when the early warning parameter is a normal level, each parameter of the carbon monoxide concentration, the carbon dioxide concentration change rate, the smoke concentration, the temperature, the oxygen concentration, the humidity node, the air pressure intensity and the illumination intensity under the normal level is acquired.
Similarly, when the early warning parameter is a high risk level, each parameter of carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity node, air pressure intensity and illumination intensity under the high risk level is collected. When the early warning parameter is the open flame combustion level, collecting each parameter of carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity node, air pressure intensity and illumination intensity under the open flame combustion level.
And taking the normal grade, the high risk grade and the open fire combustion grade of the early warning parameters and the environmental parameters respectively corresponding to the normal grade, the high risk grade and the open fire combustion grade as training parameters, thereby training and constructing a target graph neural network model. Optionally, migration learning is performed based on a preset network model, and a target graph neural network model is obtained through training.
Optionally, when the training parameters matched with the early warning parameters are obtained, the training parameters may be obtained based on historical environmental data in the target area, or in a computer simulation manner.
In other embodiments, in step S30, the step of acquiring an actual environmental parameter of the target area and performing data preprocessing on the actual environmental parameter specifically includes;
step S31, acquiring actual environmental parameters in the target area through a sensor arranged in the target area;
and step S32, carrying out non-dimensionalization processing on the actual environment parameters.
In this embodiment, the environmental parameters include carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity, barometric pressure intensity, and illumination intensity. Through carbon monoxide concentration sensor, carbon dioxide concentration rate of change sensor, smog concentration sensor, temperature sensor, oxygen concentration sensor, humidity transducer, atmospheric pressure intensity sensor and illumination intensity sensor, acquire the actual environmental parameter in the target area respectively: carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity, air pressure intensity and illumination intensity. The carbon monoxide concentration sensor, the carbon dioxide concentration change rate sensor, the smoke concentration sensor, the temperature sensor, the oxygen concentration sensor, the humidity sensor, the air pressure intensity sensor and the illumination intensity sensor are all arranged in the target area.
And carrying out non-dimensionalization processing on the acquired actual environment parameters. For example, a plurality of sensors are disposed in the target area, and the processor of the terminal 100 is disposed in the monitoring platform, the plurality of sensors correspondingly acquire a plurality of actual environment parameters and feed back the actual environment parameters to the monitoring platform, and the monitoring platform performs non-dimensionalization processing on the actual environment parameters, for example, through standardized non-dimensionalization calculation processing.
In other embodiments, in step S40, the step of determining the early warning parameters of the early warning node according to the preprocessed actual environment parameters and the target graph neural network model specifically includes:
step S41, the actual environment parameters are used as an input set of the target graph neural network model, and the target graph neural network model is input;
and step S42, calculating the early warning parameters of the early warning nodes by the target graph neural network model.
In this embodiment, the actual environment parameters may be used as an input set of the target graph neural network model after the dimensionless processing, and the early warning parameters matched with the actual environment parameters in the early warning nodes may be calculated under the analysis processing of the trained and constructed target graph neural network model.
In other embodiments, in step S50, the fire warning step according to the warning parameter includes:
step S51, identifying the early warning grade of the early warning parameter;
and step S52, executing corresponding text early warning and/or acousto-optic early warning according to the early warning level of the early warning parameter.
In the present exemplary embodiment, the warning variables are classified into a plurality of warning classes, for example, into a normal class, a high risk class and an open flame combustion class. When the early warning parameter is a normal level, the terminal 100 correspondingly makes a fire early warning according to the signal of the normal level: the area has no fire hazard and the condition is normal; when the early warning parameter is a high risk level, the terminal 100 correspondingly makes a fire early warning according to the signal of the high risk level: the area has fire hazard and belongs to a high risk situation; when the early warning parameter is the open fire combustion level, the terminal 100 correspondingly makes a fire early warning according to the signal of the open fire combustion level: this area already constitutes a fire.
The terminal 100 identifies the early warning level of the early warning parameter, and executes corresponding text early warning and/or acousto-optic early warning according to the early warning level.
Referring to fig. 4, an embodiment of the invention provides a fire warning apparatus 200, where the fire warning apparatus 200 includes a first building module 201, a second building module 202, a data processing module 203, a determining module 204, and a warning module 205.
The first construction module 201 is configured to construct an early warning parameter of an early warning node and an environment parameter map data structure in a target area where the early warning node is located; the second construction module 202 is used for training and constructing a target graph neural network model according to the graph data structure; the data processing module 203 is configured to acquire an actual environment parameter of the target area, and perform data preprocessing on the actual environment parameter; the determining module 204 is configured to determine an early warning parameter of the early warning node according to the preprocessed actual environment parameter and the target graph neural network model; the early warning module 205 is configured to perform fire early warning according to the early warning parameters.
Further, the first building module 201 is further configured to plan a plurality of feature nodes according to the environment parameters; and constructing the graph data structure according to the mutual influence of the early warning node and each node in the plurality of characteristic nodes.
Further, the first building module 201 is further configured to establish a connection between parameters having direct dependencies in the environment parameters; and establishing connection between the environmental parameters which have direct dependence relationship with the early warning parameters and the early warning parameters, thereby forming the graph data structure. Wherein the environmental parameters include carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity, air pressure intensity and illumination intensity.
Further, the second building module 202 is further configured to obtain, according to the early warning parameter of the early warning node, a training parameter matched with the early warning parameter; and training a preset network model by combining the graph data structure according to the early warning parameters and the training parameters so as to obtain the target graph neural network model.
Further, the data processing module 203 is further configured to obtain an actual environmental parameter in the target area through a sensor disposed in the target area; and carrying out non-dimensionalization processing on the actual environment parameters.
Further, the determining module 204 is further configured to input the actual environment parameters into the target graph neural network model as an input set of the target graph neural network model; and calculating the early warning parameters of the early warning nodes by the target graph neural network model.
Further, the early warning module 205 is further configured to identify an early warning level at which the early warning parameter is located; and executing corresponding text early warning and/or acousto-optic early warning according to the early warning grade of the early warning parameter.
In this embodiment, a graph data structure is constructed according to the early warning parameters of the early warning nodes and the environmental parameters in the target area, and the graph data structure may include environmental parameters with a plurality of dimensional data, so that the plurality of dimensional data may be collected to comprehensively and accurately represent the environmental information in the target area, and the environmental parameters and the early warning parameters of the plurality of dimensional data are connected according to the mutual relationship to construct the graph data structure. A target graph neural network model is trained and constructed based on the graph data structure, so that accurate fire early warning can be made for a target area in a targeted mode, and the reliability of the fire early warning is improved.
For the specific definition of the fire warning device 200, reference may be made to the above definition of the fire warning method, which is not described herein again. The above-mentioned modules of the fire early warning apparatus 200 may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Referring to fig. 5, fig. 5 is a schematic diagram of a hardware structure of a terminal 100 according to an embodiment of the present invention, and as shown in fig. 5, the terminal 100 includes:
one or more processors 1001 and a memory 1002, with one processor 1001 being an example in fig. 5. The processor 1001 and the memory 1002 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The memory 1002, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the fire early warning method in the embodiment of the present invention (for example, the first building module 201, the second building module 202, the data processing module 203, the determining module 204, and the early warning module 205 shown in fig. 4). The processor 1001 executes various functional applications of the server and data processing by running a nonvolatile software program, instructions, and modules stored in the memory 1002, that is, implements the fire early warning method of the above-described method embodiment.
The memory 1002 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the smoking behavior detection device, and the like. Further, the memory 1002 may include high-speed random access memory 1002, and may also include non-volatile memory 1002, such as at least one piece of disk memory 1002, flash memory devices, or other non-volatile solid-state memory 1002. In some embodiments, the memory 1002 may optionally include memory 1002 located remotely from the processor 1001, and these remote memories 1002 may be connected to the smoking behaviour detection apparatus by a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 1002 and when executed by the one or more processors 1001, perform the method in any of the above-described method embodiments, for example, the method steps S10 to S50 in fig. 2, and the method steps S11 to S12 in fig. 3, as described above, to implement the functions of the module 201 and 205 in fig. 4.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
The terminal 100 of the embodiments of the present invention exists in various forms including, but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals 100 include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals 100 include PDA, MID, and UMPC devices, etc., such as ipads.
(3) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(4) And other electronic devices with data interaction functions.
Embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer-executable instructions for an electronic device to perform the method in any of the above method embodiments, for example, the method steps S10 to S50 in fig. 2, and the method steps S11 to S12 in fig. 3 described above are performed to implement the functions of the module 201 and 205 in fig. 4.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the method of any of the above-described method embodiments, for example, performing the above-described method steps S10-S50 in fig. 2, S11-S12 in fig. 3, and implementing the functions of module 201 and 205 in fig. 4.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A fire early warning method, comprising:
establishing connection of parameters with direct dependence relation in environmental parameters in a target area where the early warning node is located, wherein the environmental parameters comprise carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity, air pressure intensity and illumination intensity;
establishing connection between the environmental parameters which have direct dependence relationship with the early warning parameters of the early warning nodes and the early warning parameters, thereby forming a graph data structure;
acquiring training parameters matched with the early warning parameters according to the early warning parameters;
training a preset network model according to the early warning parameters and the training parameters and by combining the graph data structure, thereby obtaining a target graph neural network model;
acquiring actual environment parameters of the target area, and performing data preprocessing on the actual environment parameters;
determining early warning parameters of the early warning nodes according to the preprocessed actual environment parameters and the preprocessed target graph neural network model;
and carrying out fire early warning according to the early warning parameters.
2. A fire early warning method according to claim 1, wherein the step of collecting actual environmental parameters of the target area and preprocessing the actual environmental parameters comprises;
acquiring actual environmental parameters in the target area through a sensor arranged in the target area;
and carrying out non-dimensionalization processing on the actual environment parameters.
3. A fire early warning method as set forth in claim 1, wherein the step of determining early warning parameters of the early warning node according to the preprocessed actual environment parameters and the target graph neural network model comprises:
inputting the actual environment parameters into the target graph neural network model as an input set of the target graph neural network model;
and calculating the early warning parameters of the early warning nodes by the target graph neural network model.
4. A fire early warning method according to claim 1, wherein the step of performing fire early warning according to the early warning parameter includes:
identifying the early warning grade of the early warning parameter;
and executing corresponding text early warning and/or acousto-optic early warning according to the early warning grade of the early warning parameter.
5. A fire warning device, comprising:
the system comprises a first construction module, a second construction module and a third construction module, wherein the first construction module is used for establishing connection of parameters with direct dependency relationship in environmental parameters in a target area where an early warning node is located, the environmental parameters comprise carbon monoxide concentration, carbon dioxide concentration change rate, smoke concentration, temperature, oxygen concentration, humidity, air pressure intensity and illumination intensity, and the environmental parameters with direct dependency relationship with early warning parameters of the early warning node are connected with the early warning parameters to form a graph data structure;
the second construction module is used for acquiring training parameters matched with the early warning parameters according to the early warning parameters, and training a preset network model by combining the graph data structure according to the early warning parameters and the training parameters so as to obtain a target graph neural network model;
the data processing module is used for acquiring the actual environment parameters of the target area and carrying out data preprocessing on the actual environment parameters;
the determining module is used for determining early warning parameters of the early warning nodes according to the preprocessed actual environment parameters and the target graph neural network model;
and the early warning module is used for carrying out fire early warning according to the early warning parameters.
6. A terminal, characterized in that the terminal comprises: a memory, a processor and a program stored in the memory and executable on the processor, the program, when executed by the processor, implementing the steps of the fire early warning method as claimed in any one of claims 1 to 4.
7. A readable storage medium, storing a computer program which, when executed by a processor, implements the steps of the fire early warning method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910912978.8A CN110675587B (en) | 2019-09-25 | 2019-09-25 | Fire early warning method, device, terminal and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910912978.8A CN110675587B (en) | 2019-09-25 | 2019-09-25 | Fire early warning method, device, terminal and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110675587A CN110675587A (en) | 2020-01-10 |
| CN110675587B true CN110675587B (en) | 2022-03-29 |
Family
ID=69078978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910912978.8A Active CN110675587B (en) | 2019-09-25 | 2019-09-25 | Fire early warning method, device, terminal and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110675587B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111243214A (en) * | 2020-01-19 | 2020-06-05 | 佛山科学技术学院 | Industrial machine room fire monitoring system and method based on machine learning |
| CN112353191A (en) * | 2020-11-09 | 2021-02-12 | 常州恒邦展示器材有限公司 | Multifunctional artistic display rack convenient for exhibition |
| WO2023207295A1 (en) * | 2022-04-29 | 2023-11-02 | 华为技术有限公司 | Data processing method, data processing unit, system and related device |
| CN116758691A (en) * | 2023-05-05 | 2023-09-15 | 深圳市广安消防装饰工程有限公司 | Fire-fighting early warning method and device based on multi-mode data |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537033B (en) * | 2014-12-23 | 2017-08-11 | 清华大学 | Interval type indices prediction method based on Bayesian network and extreme learning machine |
| CN104766433A (en) * | 2015-04-23 | 2015-07-08 | 河南理工大学 | Electrical fire warning system based on data fusion |
| US10522031B2 (en) * | 2015-09-01 | 2019-12-31 | Honeywell International Inc. | System and method providing early prediction and forecasting of false alarms by applying statistical inference models |
| CN107633638B (en) * | 2017-07-24 | 2019-09-03 | 南京邮电大学 | A kind of Intelligent Fire Detection method based on WSN |
| CN109766840B (en) * | 2019-01-10 | 2024-02-20 | 腾讯科技（深圳）有限公司 | Facial expression recognition method, device, terminal and storage medium |
| CN109978005A (en) * | 2019-02-25 | 2019-07-05 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of fire alarm method, device, storage medium and terminal device |
-
2019
- 2019-09-25 CN CN201910912978.8A patent/CN110675587B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110675587A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110675587B (en) | Fire early warning method, device, terminal and readable storage medium | |
| EP2924579A1 (en) | Event correlation | |
| CN109583758B (en) | Early warning rule correction method and device of monitoring system and computer equipment | |
| CN109241897B (en) | Monitoring image processing method and device, gateway equipment and storage medium | |
| Di Fonzo et al. | A new method for identifying rapid decline dynamics in wild vertebrate populations | |
| CN113095132B (en) | Neural network based gas field identification method, system, terminal and storage medium | |
| CN111307194B (en) | Beidou-based environmental equipment detection method, device, equipment and storage medium | |
| CN108053627A (en) | A kind of fire alarm method, device and equipment | |
| CN111738463A (en) | Operation and maintenance method, device, system, electronic equipment and storage medium | |
| CN111540020B (en) | Method and device for determining target behavior, storage medium and electronic device | |
| CN115985056A (en) | Combustible gas real-time monitoring and early warning method and system, storage medium and electronic equipment | |
| CN113947014A (en) | BIM-based tunnel fire emergency rescue method, terminal and storage medium | |
| CN109743339B (en) | Network security monitoring method and device for power plant station and computer equipment | |
| CN110619211A (en) | Malicious software identification method, system and related device based on dynamic characteristics | |
| CN113591751A (en) | Transformer substation abnormal condition warning method and device, computer equipment and storage medium | |
| CN111476086B (en) | Method, device, computer device and readable storage medium for identifying smoke and fire | |
| CN115827379A (en) | Abnormal process detection method, device, equipment and medium | |
| CN111105582B (en) | Forest fire prevention monitoring method and system, computer equipment and readable storage medium | |
| CN112561276A (en) | Operation risk demonstration method and device, storage medium and electronic device | |
| CN112184493A (en) | Data processing method, system and storage medium based on big data and assembly type building platform | |
| CN113660107B (en) | Fault locating method, system, computer equipment and storage medium | |
| CN115619222B (en) | Early warning information processing method and device for multiple disasters and terminal equipment | |
| CN113572768B (en) | Analysis method for abnormal change of number of botnet family propagation sources | |
| CN110750418B (en) | Information processing method, electronic equipment and information processing system | |
| US20230267822A1 (en) | Reporting apparatus, non-transitory computer readable medium, and method for reporting |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |