CN113554364A - Disaster emergency management method, device, equipment and computer storage medium - Google Patents
Disaster emergency management method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN113554364A CN113554364A CN202111111491.3A CN202111111491A CN113554364A CN 113554364 A CN113554364 A CN 113554364A CN 202111111491 A CN202111111491 A CN 202111111491A CN 113554364 A CN113554364 A CN 113554364A
- Authority
- CN
- China
- Prior art keywords
- disaster
- coefficient
- preset
- emergency management
- fire
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 106
- 238000001514 detection method Methods 0.000 claims abstract description 73
- 238000012544 monitoring process Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 26
- 239000000779 smoke Substances 0.000 claims description 33
- 238000013527 convolutional neural network Methods 0.000 claims description 23
- 230000006399 behavior Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000013145 classification model Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of emergency management, and discloses a disaster emergency management method, a disaster emergency management device, disaster emergency management equipment and a computer storage medium, wherein the method comprises the following steps: acquiring original disaster data through preset monitoring sensing equipment; determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information; and controlling preset Internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation. According to the disaster emergency management system and the disaster emergency management method, the disaster occurrence type is automatically determined directly according to the original disaster data collected by the preset monitoring sensing equipment, the corresponding disaster emergency management operation is executed according to the internet of things equipment controlled by the disaster occurrence type, the supervision personnel are not needed to continuously monitor the disaster data, the internet of things equipment is not needed to be manually opened by the supervision personnel, the disaster emergency management cost is greatly reduced, and the disaster emergency management efficiency is also improved.
Description
Technical Field
The invention relates to the technical field of emergency management, in particular to a disaster emergency management method, device, equipment and computer storage medium.
Background
At present, the industrial technology and the computer technology in China are rapidly developed, and relatively centralized industrial layout and a representative chemical industry park are formed. With the development of industrial enterprises and the increasing scale of the industrial enterprises, huge potential risks may exist in the production process.
In the prior art, most of disaster emergency treatment schemes of industrial parks are in a mode of combining monitoring equipment detection and artificial dispersion. Although different industrial parks have been equipped with corresponding protective apparatus according to the demand of difference, often mutual independence between supervisory equipment and the calamity treatment equipment, supervisory personnel often need open calamity treatment equipment manually after monitoring the disaster through supervisory equipment, but, often because supervisory personnel's negligence, can't discover the disaster the very first time, also can't just in time open calamity treatment equipment when the disaster just takes place. Because the disaster detection is not timely and the disaster control is delayed, once a dangerous situation occurs, great personnel and property loss can be caused.
Disclosure of Invention
The invention mainly aims to provide a disaster emergency management method, a disaster emergency management device, disaster emergency management equipment and a computer storage medium, and aims to solve the technical problem that the existing disaster emergency management scheme is low in efficiency.
In order to achieve the above object, the present invention provides a disaster emergency management method, including the steps of:
acquiring original disaster data through preset monitoring sensing equipment;
determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information;
and controlling preset Internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation.
Optionally, the preset monitoring sensing device includes a camera, the original disaster data includes a first environment image collected by the camera, the disaster occurrence information is determined according to the original disaster data and a preset disaster detection model, and the step of determining the disaster occurrence type according to the disaster occurrence information includes:
inputting the first environment image into a preset fire detection model for classification to obtain a smoke concentration coefficient, a flame color coefficient, a flame shape coefficient and a flame motion track coefficient;
and determining the disaster occurrence type and the disaster level according to the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient, the flame motion track coefficient and the corresponding preset fire coefficient range.
Optionally, before the step of collecting the original disaster data by the preset monitoring and sensing device, the method further includes:
acquiring a pre-collected sample fire picture set and marking disaster occurrence information corresponding to each picture in the sample fire picture set; the disaster occurrence information marking comprises smoke concentration coefficient marking, flame color coefficient marking, flame shape coefficient marking and flame movement track coefficient marking;
and training a preset Convolutional Neural Network (CNN) model to be trained based on an iterative training mode through the sample fire picture set and the disaster occurrence information label to obtain the preset fire detection model.
Optionally, the step of determining the disaster occurrence type and the disaster level according to the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient, the flame movement trajectory coefficient, and the corresponding preset fire coefficient range includes:
if the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient and the flame movement track coefficient are all located in the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire disaster occurs, and the disaster level is a first emergency level;
if at least one of the flame shape coefficient and the flame motion track coefficient is within a corresponding preset fire coefficient range, one of the smoke concentration coefficient and the flame color coefficient is within the corresponding preset fire coefficient range, and the other one of the smoke concentration coefficient and the flame color coefficient is outside the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire possibly occurs, and the disaster level is a second emergency level;
and if the flame shape coefficient and the flame motion track coefficient are both outside the corresponding preset fire coefficient range, and at least one of the smoke concentration coefficient and the flame color coefficient is within the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire possibly occurs, and the disaster level is a third emergency level.
Optionally, the step of controlling a preset internet of things device corresponding to the disaster occurrence type to execute a corresponding disaster emergency management operation includes:
if the disaster occurrence type is that a fire disaster occurs and the disaster level is a first emergency level, acquiring the position information of the preset monitoring sensing equipment;
generating a target escape route based on the position information;
the target escape route is broadcasted through voice through a broadcasting device located on the target escape route, and/or the target escape route is displayed through an indicator lamp and/or a display screen located on the target escape route.
Optionally, the preset monitoring sensing device includes a camera, the original disaster data includes a second environment image collected by the camera, the disaster occurrence information is determined according to the original disaster data and a preset disaster detection model, and the step of determining the disaster occurrence type according to the disaster occurrence information includes:
inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the field personnel;
comparing the behavior characteristics of the field personnel with preset trampling accident characteristics to determine similarity;
and if the similarity is greater than or equal to a preset similarity threshold value, determining that the disaster occurrence type is that a trample accident has occurred.
Optionally, before the step of inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the field personnel, the method further includes:
performing personnel density analysis on the second environment image to determine personnel density corresponding to the second environment image;
if the personnel density is greater than a preset density threshold value, executing the following steps: and inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the field personnel.
In order to achieve the above object, the present invention also provides a disaster emergency management device including:
the acquisition module is used for acquiring original disaster data through preset monitoring sensing equipment;
the determining module is used for determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information;
and the execution module is used for controlling the preset internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation.
In addition, to achieve the above object, the present invention also provides a disaster emergency management apparatus, including: the disaster emergency management system comprises a memory, a processor and a disaster emergency management program stored on the memory and capable of running on the processor, wherein the disaster emergency management program realizes the steps of the disaster emergency management method when being executed by the processor.
In order to achieve the above object, the present invention also provides a computer storage medium having a disaster emergency management program stored thereon, the disaster emergency management program implementing the steps of the disaster emergency management method as described above when executed by a processor.
Furthermore, to achieve the above object, the present invention also provides a computer program product comprising a disaster emergency management program, which when executed by a processor, implements the steps of the disaster emergency management method as described above.
The method comprises the steps of collecting original disaster data through preset monitoring sensing equipment; determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information; and controlling preset Internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation. According to the disaster emergency management system and the disaster emergency management method, the disaster occurrence type is automatically determined directly according to the original disaster data collected by the preset monitoring sensing equipment, the corresponding disaster emergency management operation is executed according to the internet of things equipment controlled by the disaster occurrence type, the supervision personnel are not needed to continuously monitor the disaster data, the internet of things equipment is not needed to be manually opened by the supervision personnel, the disaster emergency management cost is greatly reduced, and the disaster emergency management efficiency is also improved.
Drawings
Fig. 1 is a schematic structural diagram of a disaster emergency management device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a first embodiment of a disaster emergency management method according to the present invention;
fig. 3 is a schematic block diagram of a disaster emergency management device according to 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.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a disaster emergency management device in a hardware operating environment according to an embodiment of the present invention.
The disaster emergency management equipment in the embodiment of the invention can be a PC or server equipment, and a virtual machine runs on the disaster emergency management equipment.
As shown in fig. 1, the disaster emergency management apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the disaster emergency management device configuration shown in fig. 1 does not constitute a limitation of the device and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a disaster emergency management program.
In the disaster emergency management device shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call a disaster emergency management program stored in the memory 1005 and perform operations in the disaster emergency management method described below.
Based on the hardware structure, the embodiment of the disaster emergency management method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a disaster emergency management method according to a first embodiment of the present invention, where the method includes:
step S10, collecting original disaster data through a preset monitoring sensing device;
the disaster emergency management method is applied to a disaster emergency management system, and the disaster emergency management system can be a server, a terminal, a robot or a PC device.
In the prior art, most of disaster emergency treatment schemes of industrial parks are in a mode of combining monitoring equipment detection and artificial dispersion. Although different industrial parks have been equipped with corresponding protective apparatus according to the demand of difference, often mutual independence between supervisory equipment and the calamity treatment equipment, supervisory personnel often need open calamity treatment equipment manually after monitoring the disaster through supervisory equipment, but, often because supervisory personnel's negligence, can't discover the disaster the very first time, also can't just in time open calamity treatment equipment when the disaster just takes place. Because the disaster detection is not timely and the disaster control is delayed, once a dangerous situation occurs, great personnel and property loss can be caused.
In this context, the present embodiment provides a disaster emergency management scheme.
In this embodiment, different monitoring and sensing devices are often provided for different types of disaster monitoring, for example, a water level sensor and a camera are generally configured for flood monitoring; for fire monitoring, a temperature sensor, a smoke sensor and a camera are generally configured; a pressure sensor and a camera are generally provided for detecting a stepping accident. According to the disaster management requirement of the industrial park, the monitoring sensing equipment is preset on each monitoring point position of the industrial park so as to collect original disaster data in the monitoring range.
Step S20, determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information;
in this embodiment, the disaster emergency management system inputs the original disaster data into a preset disaster detection model for classification, so as to obtain disaster occurrence information. The preset disaster detection model is a pre-trained model used for predicting disaster occurrence information; the disaster occurrence information refers to characteristic parameters of a disaster of a certain specific type determined according to original disaster data. It is understood that the disaster occurrence information may include a plurality of information items, for example, if the disaster detection model is preset as a fire detection model, the disaster occurrence information may include a smoke concentration coefficient, a flame color coefficient, a flame shape coefficient, and a flame movement trajectory coefficient; if the preset disaster detection model is a flood detection model, the disaster occurrence information may include a water level height coefficient, a water velocity coefficient, and a water level increase velocity coefficient.
The preset disaster detection model may be an image classification model, such as a CNN (Convolutional Neural Networks) model, which may include one or more output values corresponding to disaster occurrence information. And if the original disaster data is a picture, directly inputting the sample disaster picture into a model by the disaster emergency management system, and directly outputting a plurality of output values by the model to obtain corresponding disaster occurrence information.
After determining the disaster occurrence information, determining a disaster occurrence type according to the disaster occurrence information, where the disaster occurrence type refers to whether a disaster corresponding to a disaster type corresponding to a preset disaster detection model occurs, and the disaster occurrence type generally includes three types, namely an occurred disaster type, a possible occurred disaster type, and an unexecuted disaster type, corresponding to the disaster type corresponding to the preset disaster detection model.
Further, if the original disaster data is a picture, before step S20, the method may further include: carrying out characteristic disaster object identification on the original disaster data to obtain a target characteristic disaster object corresponding to the original disaster data; a target disaster detection model corresponding to the target characteristic disaster object is set as the preset disaster detection model in step S20. It can be understood that different disaster detection models are often set for different types of disaster detection, and different characteristic disaster objects often exist in different types of disaster scene pictures, and the characteristic disaster objects have corresponding disaster detection models. For example, a fire exists in the picture of the fire scene, a water exists in the picture of the flood scene, and a person exceeding a preset density threshold exists in the picture of the stepping accident scene, wherein the fire, the water and the person exceeding the preset density threshold are characteristic disaster objects, and the corresponding disaster detection models are respectively a fire detection model, a flood detection model and a stepping accident detection model. Since different disaster detection may require collecting site pictures, and if the site pictures are sequentially input into different disaster detection models, the computing power of the system may be continuously occupied in a large amount, for this reason, in this embodiment, a characteristic disaster object is detected first, and a target disaster detection model corresponding to current disaster data is determined, and certainly, a characteristic disaster object exists and does not necessarily represent a corresponding disaster, and therefore, it is also necessary to further analyze and determine whether a disaster really occurs according to the target disaster detection model in a targeted manner, so that the problem of too high computing power occupancy rate generated by traversing all disaster detection models can be avoided.
Of course, if the characteristic disaster object cannot be identified in the original disaster data, the original disaster data may be sequentially input to different disaster detection models to obtain different disaster occurrence information, and the disaster occurrence type corresponding to the disaster may be determined.
And step S30, controlling the preset Internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation.
In this embodiment, after the disaster occurrence type is determined, the preset internet of things device corresponding to the disaster occurrence type may be controlled to perform a corresponding disaster emergency management operation. Different disaster occurrence types can correspond to different internet of things devices and different disaster emergency management operations.
In the embodiment, original disaster data are collected through preset monitoring sensing equipment; determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information; and controlling preset Internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation. According to the disaster emergency management system and the disaster emergency management method, the disaster occurrence type is automatically determined directly according to the original disaster data collected by the preset monitoring sensing equipment, the corresponding disaster emergency management operation is executed according to the internet of things equipment controlled by the disaster occurrence type, the supervision personnel are not needed to continuously monitor the disaster data, the internet of things equipment is not needed to be manually opened by the supervision personnel, the disaster emergency management cost is greatly reduced, and the disaster emergency management efficiency is also improved.
Further, based on the above embodiment, a second embodiment of the disaster emergency management method of the present invention is provided.
Optionally, the preset monitoring sensing device includes a camera, the original disaster data includes a first environment image collected by the camera, and the step S20 includes:
step S21, inputting the first environment image into a preset fire detection model for classification to obtain a smoke concentration coefficient, a flame color coefficient, a flame shape coefficient and a flame motion track coefficient;
and step S22, determining the disaster occurrence type and disaster level according to the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient, the flame movement track coefficient and the corresponding preset fire coefficient range.
In this embodiment, the preset disaster detection model is a preset fire detection model, the preset monitoring sensing device includes a camera, and the corresponding original disaster data is an environment image (a first environment image, for distinguishing) collected by the camera. The preset fire detection model is a pre-trained model used for predicting the disaster occurrence information of the fire; the disaster level refers to the degree of urgency of the disaster. The disaster occurrence information of the fire refers to the characteristic parameters of the fire determined according to the original disaster data. It is understood that the disaster occurrence information of the fire may include a plurality of information items such as a smoke density coefficient, a flame color coefficient, a flame shape coefficient, and a flame movement trajectory coefficient.
The preset fire detection model is a CNN image classification model, which may include a plurality of output values, which are disaster occurrence information. The disaster emergency management system directly inputs the first environment image into the model, and the model directly outputs a plurality of output values to obtain corresponding disaster occurrence information.
Further, before step S10, the method further includes:
step S01, acquiring a pre-collected sample fire picture set and marking disaster occurrence information corresponding to each picture in the sample fire picture set; the disaster occurrence information marking comprises smoke concentration coefficient marking, flame color coefficient marking, flame shape coefficient marking and flame movement track coefficient marking;
and step S02, training a preset Convolutional Neural Network (CNN) model to be trained based on an iterative training mode through the sample fire picture set and the disaster occurrence information label to obtain the preset fire detection model.
In this embodiment, the pictures of fire scenes with different smoke concentration coefficients, flame color coefficients, flame shape coefficients and flame motion trajectory coefficients can be manually captured and collected, disaster occurrence information is labeled for each picture of the fire scenes, and then the pictures are uploaded to the disaster emergency management system, and the disaster emergency management system performs fire detection model training according to the sample fire picture set and the disaster occurrence information labels corresponding to each picture.
The specific training process of the fire detection model is that an initial CNN model to be trained is preset in the disaster emergency management system, the initial CNN model can be a CNN model with multiple classification targets, namely multiple output values, and the initial CNN model can be a structure of the existing CNN model capable of realizing the multiple classification targets. The disaster emergency management system takes a sample fire picture set as input of the initial CNN model, the initial CNN model performs feature extraction on the sample fire picture to obtain disaster occurrence information predicted by the initial CNN model, then the disaster emergency management system marks and calculates a loss value of a loss function according to the predicted disaster occurrence information and the disaster occurrence information, judges whether the CNN model converges according to the loss value, if the CNN model does not converge, inputs the sample fire picture set into the CNN model again after adjusting model parameters of the initial CNN model, and performs iterative training for multiple times until the CNN model converges to obtain a trained preset fire detection model.
Further, considering that there may be fewer artificially shot sample fire pictures, that is, the number of samples is small, if model training is directly performed according to the sample fire pictures with small number, the accuracy of a preset fire detection model obtained through training is low, and determination of subsequent disaster occurrence information is affected, for the defect, countercheck sample pictures can be generated according to the fire scene pictures after the artificially shot fire scene pictures are obtained, disaster occurrence information is labeled for each fire scene picture and the countercheck sample picture, then the fire scene pictures and the countercheck sample pictures are jointly used as a sample fire picture set, and then fire detection model training is performed. So, through regard as sample conflagration picture with the scene of fire picture and its to resisting sample picture jointly, can increase the quantity of sample conflagration picture, and then promote the accuracy of predetermineeing the training of fire detection model.
Further, the step S22 includes:
step S221, if the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient and the flame movement track coefficient are all located in corresponding preset fire coefficient ranges, determining that the disaster occurrence type is that a fire disaster occurs, and the disaster level is a first emergency level;
step S222, if one of the flame shape coefficient and the flame motion track coefficient is located in a corresponding preset fire coefficient range, the other of the flame shape coefficient and the flame motion track coefficient is located outside the corresponding preset fire coefficient range, and the smoke concentration coefficient and the flame color coefficient are both located in the corresponding preset fire coefficient range, or if the flame shape coefficient and the flame motion track coefficient are both located in the corresponding preset fire coefficient range, one of the smoke concentration coefficient and the flame color coefficient is located in the corresponding preset fire coefficient range, and the other of the smoke concentration coefficient and the flame color coefficient is located outside the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire is likely to occur, and the disaster level is a second emergency level;
step S223, if the flame shape coefficient and the flame movement track coefficient are both outside the corresponding preset fire coefficient range, and at least one of the smoke concentration coefficient and the flame color coefficient is within the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire may have occurred, and the disaster level is a third emergency level.
In this embodiment, in a fire detection scenario, corresponding preset fire coefficient ranges are set for different disaster occurrence information in advance, where the preset fire coefficient ranges are set according to smoke concentration, flame color, flame shape, and flame movement locus during a fire occurrence field test, and generally, the more the number of coefficients falling into the preset fire coefficient ranges, the greater the probability that a fire has occurred. Therefore, if the disaster information falls into the corresponding preset fire coefficient range, it can be determined that a fire has occurred, and the corresponding disaster level is the first emergency level.
Because the smoke concentration coefficient is easily influenced by weather and field ventilation degree, the flame color coefficient is easily influenced by clothing colors of garden personnel or colors of other objects, and relatively speaking, the flame shape coefficient and the flame motion track coefficient are not easily influenced by external interference, so that the reliability of the flame shape coefficient and the flame motion track coefficient is higher than that of the smoke concentration coefficient and the flame color coefficient when determining whether a fire disaster happens according to the disaster occurrence information, therefore, if any three of the four coefficients fall into the corresponding preset fire coefficient range and any one of the four coefficients is positioned outside the preset fire coefficient range, the disaster occurrence type is determined as that the fire disaster possibly happens, and the disaster level is a second emergency level; or if the flame shape coefficient and the flame motion track coefficient are both in the corresponding preset fire coefficient range, and the smoke concentration coefficient and the flame color coefficient are both outside the corresponding preset fire coefficient range, it can also be determined that the disaster occurrence type is that a fire possibly occurs, and the disaster level is a second emergency level.
And if the flame shape coefficient and the flame motion track coefficient are both outside the corresponding preset fire coefficient range, and at least one of the smoke concentration coefficient and the flame color coefficient is within the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire possibly occurs, and the disaster level is a third emergency level.
Wherein the first urgency level is higher in urgency than the second urgency level, which is higher in urgency than the third urgency level.
It can be understood that if all the four coefficients are located outside the corresponding preset fire coefficient range, it can be determined that the disaster occurrence type is that a fire does not occur.
Further, the step S30 includes:
step S31, if the disaster occurrence type is that a fire disaster occurs and the disaster level is a first emergency level, acquiring the position information of the preset monitoring sensing equipment;
step S32, generating a target escape route based on the position information;
and step S33, the target escape route is broadcasted through voice through a broadcasting device positioned on the target escape route, and/or the target escape route is displayed through an indicator lamp and/or a display screen positioned on the target escape route.
In this embodiment, if the disaster occurrence type is that a fire has occurred, and the disaster level is the first emergency level, it is necessary to obtain location information corresponding to the preset monitoring sensing device, where the location information is a place where the fire has occurred, and after the place where the fire has occurred is determined, a target escape route can be planned for people located at or near the place where the fire has occurred or nearby by combining a map of an industrial park and a building internal passage map, so that the people can get away from the place where the fire has occurred as soon as possible according to the target escape route. After the target escape route is determined, the target escape route can be broadcasted through a voice of a broadcasting device located on the target escape route or in a certain range of the target escape route, and/or the target escape route can be displayed through an indicator lamp and/or a display screen located on the target escape route or in a certain range of the target escape route, so that people can be helped to get away from a fire place as soon as possible according to the target escape route.
Alternatively, the step S32 includes: determining a candidate escape route based on the position information, sending a monitoring instruction to an intelligent escape door and window on the candidate escape route, if a feedback signal of the intelligent escape door and window is not received within a preset time, it is indicated that the intelligent escape door and window may have a fault, and if an escape person escapes according to the escape route where the faulty intelligent escape door and window is located, personal safety of the escape person may be threatened, so that the escape route where the faulty intelligent escape door and window may exist is required to be removed from the candidate escape route. Then, the route with the shortest distance is selected as the target escape route from the remaining candidate escape routes.
Optionally, if the disaster occurrence type is that a fire disaster occurs, and the disaster level is a first emergency level, the position information corresponding to the preset monitoring sensing equipment can be informed to the fire department in a preset alarm manner, so that the fire department can put out a fire and rescue the fire as soon as possible.
Optionally, if the disaster occurrence type is that the conflagration is probably happened, the disaster level is the second emergency level, because the conflagration exists the possibility of not taking place this moment, consequently, can send conflagration second grade to the management terminal and report an emergency and ask for help or increased vigilance, so that the management terminal sends the pronunciation to report an emergency and ask for help or increased vigilance and/or light to report an emergency and ask for help or increased vigilance, and send conflagration second grade to the management terminal and report an emergency and ask for help or increased vigilance and stop the suggestion, check near the position that suggestion managers located to predetermineeing monitoring and sensing equipment, only when detecting that the management terminal is located the position certain range that predetermineeing monitoring and sensing equipment located, this conflagration second grade is reported an emergency and raised the police and just can stop, so, can ensure that managers carry out the disaster to the scene and confirm, avoid the condition that the disaster that leads to because of carelessness is put down a job.
Further, if the management terminal is detected to be located in a certain range of the position where the preset monitoring sensing equipment is located, sending a fire scene verification control to the management terminal, wherein the scene verification control comprises a fire occurrence confirmation control and a fire non-occurrence confirmation control; and if the fire disaster does not occur, updating the type of the occurrence of the fire disaster into the type of the non-occurrence of the fire disaster.
Optionally, if the disaster occurrence type is that a fire may have occurred and the disaster level is a third emergency level, sending original disaster data to the management terminal, so that the management terminal can determine whether the fire has occurred according to the original disaster data, and if the management terminal determines that the fire has occurred according to the original disaster data, the disaster emergency management system updates the disaster occurrence type to that the fire has occurred, updates the disaster level to the first emergency level, and executes a corresponding disaster emergency management operation; and if the management terminal confirms that the fire does not occur according to the original disaster data, updating the disaster occurrence type to that the fire does not occur.
Further, based on the above embodiment, a third embodiment of the disaster emergency management method of the present invention is provided.
The preset monitoring sensing equipment comprises a camera, the original disaster data comprises a second environment image acquired by the camera, and the step S20 comprises the following steps:
step A1, inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of field personnel;
step A2, comparing the behavior characteristics of the field personnel with preset trampling accident characteristics to determine similarity;
and A3, if the similarity is larger than or equal to a preset similarity threshold, determining that the disaster occurrence type is that a tread accident has occurred.
In this embodiment, the preset disaster detection model is a preset stepping accident detection model, the preset monitoring sensing device includes a camera, and the corresponding original disaster data is an environment image (a second environment image, so as to distinguish) collected by the camera. The preset trampling accident detection model is a pre-trained model used for predicting the behavior characteristics of field personnel. The disaster occurrence information of the trampling accident refers to the behavior characteristics of the field personnel determined according to the original disaster data.
The preset trampling accident detection model is a CNN image classification model, and the output value of the model is disaster occurrence information, namely the behavior characteristics of field personnel. And the disaster emergency management system directly inputs the second environment image into the model, and the model directly outputs the behavior characteristics of the field personnel. The training mode of the preset pedaling accident detection model is similar to that of the fire detection model, and reference may be made to the second embodiment, which is not described again in this embodiment.
Then, comparing the similarity of the behavior characteristics of the personnel on site with the preset trampling accident characteristics, and if the similarity of the behavior characteristics of the personnel on site and the preset trampling accident characteristics is greater than or equal to a preset similarity threshold value, determining that the disaster occurrence type is that a trampling accident occurs; and if the similarity of the two is smaller than a preset similarity threshold value, determining that the disaster occurrence type is that no trample accident occurs.
Correspondingly, if the stepping accident is determined to occur, the corresponding internet of things equipment can be controlled to execute corresponding disaster emergency management operation, for example, an emergency hospital is called through a preset calling device, prompt information for requesting rescue is automatically played after the calling party is connected, the prompt information can include the place where the stepping accident occurs, the number of personnel and the like, wherein the place where the stepping accident occurs is determined according to the position of the camera, and the number of personnel can be determined by the number of personnel with the behavior characteristics of the field personnel according with the characteristics of the preset stepping accident; the broadcasting equipment in the preset range of the camera can be used, and/or the position of the emergency equipment is preset by the output of the indicating lamp and/or the display screen, so that nearby personnel can rescue the injured personnel as soon as possible.
Further, before the step a1, the method further includes:
step B1, performing personnel density analysis on the second environment image to determine personnel density corresponding to the second environment image;
step B2, if the personnel density is larger than a preset density threshold value, executing the following steps: and inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the field personnel.
Considering that the stepping accident generally occurs in a scene with a large person density, the stepping accident is difficult to occur in a scene with a small person density, and when the person density is small, the stepping accident detection is generally not necessary. Therefore, after the second environment image is acquired, the embodiment first performs personnel density analysis to determine the personnel density corresponding to the second environment image, and the specific process of the personnel density analysis is to determine the number of faces in a single image, and then calculate the number of faces in a unit area, that is, the personnel density, according to the effective shooting area of the camera.
If the person density is greater than the preset density threshold, the possibility of a stepping accident exists, and therefore step a1 needs to be executed; if the person density is less than or equal to the preset density threshold, the possibility of a stepping accident can be eliminated, and the step a1 is not required to be executed.
The present invention also provides a disaster emergency management apparatus, which includes, with reference to fig. 3:
the system comprises an acquisition module 10, a monitoring and sensing module and a control module, wherein the acquisition module is used for acquiring original disaster data through preset monitoring and sensing equipment;
a determining module 20, configured to determine disaster occurrence information according to the original disaster data and a preset disaster detection model, and determine a disaster occurrence type according to the disaster occurrence information;
and the execution module 30 is configured to control a preset internet of things device corresponding to the disaster occurrence type to execute a corresponding disaster emergency management operation.
The method executed by each program unit can refer to each embodiment of the disaster emergency management method of the present invention, and is not described herein again.
The present invention also provides a disaster emergency management apparatus, including: the disaster emergency management system comprises a memory, a processor and a disaster emergency management program which is stored on the memory and can be operated on the processor, and the method for realizing the disaster emergency management program when the disaster emergency management program is executed by the processor can refer to each embodiment of the disaster emergency management method of the invention, and is not described herein again.
The invention also provides a computer storage medium.
The computer storage medium of the present invention stores a disaster emergency management program that, when executed by a processor, implements the steps of the disaster emergency management method as described above.
The method implemented when the disaster emergency management program running on the processor is executed may refer to each embodiment of the disaster emergency management method of the present invention, and details thereof are not repeated herein.
The invention also provides a computer program product.
The inventive computer program product comprises a disaster emergency management program which, when executed by a processor, implements the steps of the disaster emergency management method as described above.
The method implemented when the disaster emergency management program running on the processor is executed may refer to each embodiment of the disaster emergency management method of the present invention, and details thereof are not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A disaster emergency management method is characterized by comprising the following steps:
acquiring original disaster data through preset monitoring sensing equipment;
determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information;
and controlling preset Internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation.
2. The method as claimed in claim 1, wherein the preset monitoring sensing device includes a camera, the original disaster data includes a first environment image collected by the camera, the determining of disaster occurrence information according to the original disaster data and a preset disaster detection model, and the determining of the disaster occurrence type according to the disaster occurrence information includes:
inputting the first environment image into a preset fire detection model for classification to obtain a smoke concentration coefficient, a flame color coefficient, a flame shape coefficient and a flame motion track coefficient;
and determining the disaster occurrence type and the disaster level according to the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient, the flame motion track coefficient and the corresponding preset fire coefficient range.
3. The disaster emergency management method according to claim 2, wherein the step of collecting original disaster data through the preset monitoring sensing device is preceded by:
acquiring a pre-collected sample fire picture set and marking disaster occurrence information corresponding to each picture in the sample fire picture set; the disaster occurrence information marking comprises smoke concentration coefficient marking, flame color coefficient marking, flame shape coefficient marking and flame movement track coefficient marking;
and training a preset Convolutional Neural Network (CNN) model to be trained based on an iterative training mode through the sample fire picture set and the disaster occurrence information label to obtain the preset fire detection model.
4. The disaster emergency management method according to claim 2, wherein the step of determining the disaster occurrence type and disaster level according to the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient, the flame motion trajectory coefficient, and the corresponding preset fire coefficient range comprises:
if the smoke concentration coefficient, the flame color coefficient, the flame shape coefficient and the flame movement track coefficient are all located in the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire disaster occurs, and the disaster level is a first emergency level;
if one of the flame shape coefficient and the flame motion track coefficient is located in a corresponding preset fire coefficient range, the other one of the flame shape coefficient and the flame motion track coefficient is located outside the corresponding preset fire coefficient range, and the smoke concentration coefficient and the flame color coefficient are both located in the corresponding preset fire coefficient range, or if the flame shape coefficient and the flame motion track coefficient are both located in the corresponding preset fire coefficient range, and the smoke concentration coefficient and the flame color coefficient are both located outside the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire possibly occurs, and the disaster level is a second emergency level;
and if the flame shape coefficient and the flame motion track coefficient are both outside the corresponding preset fire coefficient range, and at least one of the smoke concentration coefficient and the flame color coefficient is within the corresponding preset fire coefficient range, determining that the disaster occurrence type is that a fire possibly occurs, and the disaster level is a third emergency level.
5. The disaster emergency management method according to claim 1, wherein the step of controlling the preset internet of things device corresponding to the disaster occurrence type to perform the corresponding disaster emergency management operation comprises:
if the disaster occurrence type is that a fire disaster occurs and the disaster level is a first emergency level, acquiring the position information of the preset monitoring sensing equipment;
generating a target escape route based on the position information;
the target escape route is broadcasted through voice through a broadcasting device located on the target escape route, and/or the target escape route is displayed through an indicator lamp and/or a display screen located on the target escape route.
6. The method as claimed in claim 1, wherein the preset monitoring sensing device includes a camera, the original disaster data includes a second environment image collected by the camera, the determining of disaster occurrence information according to the original disaster data and a preset disaster detection model, and the determining of the disaster occurrence type according to the disaster occurrence information includes:
inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the field personnel;
comparing the behavior characteristics of the field personnel with preset trampling accident characteristics to determine similarity;
and if the similarity is greater than or equal to a preset similarity threshold value, determining that the disaster occurrence type is that a trample accident has occurred.
7. The disaster emergency management method according to claim 6, wherein before the step of inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the on-site personnel, the method further comprises:
performing personnel density analysis on the second environment image to determine personnel density corresponding to the second environment image;
if the personnel density is greater than a preset density threshold value, executing the following steps: and inputting the second environment image into a preset stepping accident detection model for classification to obtain the behavior characteristics of the field personnel.
8. A disaster emergency management device, comprising:
the acquisition module is used for acquiring original disaster data through preset monitoring sensing equipment;
the determining module is used for determining disaster occurrence information according to the original disaster data and a preset disaster detection model, and determining a disaster occurrence type according to the disaster occurrence information;
and the execution module is used for controlling the preset internet of things equipment corresponding to the disaster occurrence type to execute corresponding disaster emergency management operation.
9. A disaster emergency management apparatus, comprising: a memory, a processor and a disaster emergency management program stored on the memory and executable on the processor, the disaster emergency management program when executed by the processor implementing the steps of the disaster emergency management method according to any one of claims 1 to 7.
10. A computer storage medium having a disaster emergency management program stored thereon, the disaster emergency management program when executed by a processor implementing the steps of the disaster emergency management method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111491.3A CN113554364A (en) | 2021-09-23 | 2021-09-23 | Disaster emergency management method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111491.3A CN113554364A (en) | 2021-09-23 | 2021-09-23 | Disaster emergency management method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113554364A true CN113554364A (en) | 2021-10-26 |
Family
ID=78106543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111111491.3A Pending CN113554364A (en) | 2021-09-23 | 2021-09-23 | Disaster emergency management method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554364A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114827778A (en) * | 2022-07-01 | 2022-07-29 | 深圳市信润富联数字科技有限公司 | Method, system, equipment and computer readable storage medium for monitoring oil storage tank |
| CN115424404A (en) * | 2022-09-06 | 2022-12-02 | 湖南省永神科技有限公司 | Lighting system with fire alarm function |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590401A (en) * | 2015-12-15 | 2016-05-18 | 天维尔信息科技股份有限公司 | Early-warning linkage method and system based on video images |
| CN107147872A (en) * | 2017-05-10 | 2017-09-08 | 合肥慧图软件有限公司 | A kind of pyrotechnics warning system being combined based on video monitoring with image procossing |
| CN109377713A (en) * | 2018-09-26 | 2019-02-22 | 石化盈科信息技术有限责任公司 | A kind of fire alarm method and system |
| CN111860324A (en) * | 2020-07-20 | 2020-10-30 | 北京华正明天信息技术股份有限公司 | High-frequency component detection and color identification fire early warning method based on wavelet transformation |
| CN112001375A (en) * | 2020-10-29 | 2020-11-27 | 成都睿沿科技有限公司 | Flame detection method and device, electronic equipment and storage medium |
| CN112489351A (en) * | 2020-11-30 | 2021-03-12 | 北京华正明天信息技术股份有限公司 | School fire early warning method based on picture recognition |
| CN112651275A (en) * | 2020-09-01 | 2021-04-13 | 武汉科技大学 | Intelligent system for recognizing pedaling accident inducement behaviors in intensive personnel places |
-
2021
- 2021-09-23 CN CN202111111491.3A patent/CN113554364A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590401A (en) * | 2015-12-15 | 2016-05-18 | 天维尔信息科技股份有限公司 | Early-warning linkage method and system based on video images |
| CN107147872A (en) * | 2017-05-10 | 2017-09-08 | 合肥慧图软件有限公司 | A kind of pyrotechnics warning system being combined based on video monitoring with image procossing |
| CN109377713A (en) * | 2018-09-26 | 2019-02-22 | 石化盈科信息技术有限责任公司 | A kind of fire alarm method and system |
| CN111860324A (en) * | 2020-07-20 | 2020-10-30 | 北京华正明天信息技术股份有限公司 | High-frequency component detection and color identification fire early warning method based on wavelet transformation |
| CN112651275A (en) * | 2020-09-01 | 2021-04-13 | 武汉科技大学 | Intelligent system for recognizing pedaling accident inducement behaviors in intensive personnel places |
| CN112001375A (en) * | 2020-10-29 | 2020-11-27 | 成都睿沿科技有限公司 | Flame detection method and device, electronic equipment and storage medium |
| CN112489351A (en) * | 2020-11-30 | 2021-03-12 | 北京华正明天信息技术股份有限公司 | School fire early warning method based on picture recognition |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114827778A (en) * | 2022-07-01 | 2022-07-29 | 深圳市信润富联数字科技有限公司 | Method, system, equipment and computer readable storage medium for monitoring oil storage tank |
| CN114827778B (en) * | 2022-07-01 | 2022-09-16 | 深圳市信润富联数字科技有限公司 | Method, system, equipment and computer readable storage medium for monitoring oil storage tank |
| CN115424404A (en) * | 2022-09-06 | 2022-12-02 | 湖南省永神科技有限公司 | Lighting system with fire alarm function |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114237087A (en) | Early warning method and device for monitoring system and computer readable storage medium | |
| CN113554364A (en) | Disaster emergency management method, device, equipment and computer storage medium | |
| CN111754715B (en) | Fire-fighting emergency response method, device and system | |
| CN112044006A (en) | Monitoring fire-fighting system for building | |
| CN114973140A (en) | Dangerous area personnel intrusion monitoring method and system based on machine vision | |
| CN109544870B (en) | Alarm judgment method for intelligent monitoring system and intelligent monitoring system | |
| CN108776452B (en) | Special equipment field maintenance monitoring method and system | |
| CN110147762A (en) | A kind of embedded type fire control wrong report elimination system | |
| CN111178828A (en) | Method and system for building fire safety early warning | |
| CN118091054B (en) | Dangerous gas on-line monitoring system and method | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN113392706A (en) | Device and method for detecting smoking and using mobile phone behaviors | |
| CN117919641A (en) | Fire control management system based on artificial intelligence | |
| KR20220071880A (en) | Digital twin disaster management system customized for underground public areas | |
| CN116958900A (en) | Visual fire data monitoring system and monitoring method thereof | |
| KR20210148155A (en) | A system that integrates heterogeneous emergency detection and response capabilities | |
| CN115378968B (en) | Biological laboratory safety detection system based on edge calculation | |
| KR102081577B1 (en) | Intelligence Fire Detecting System Using CCTV | |
| KR20220148430A (en) | Iot platform and underground environment monitering system and it's method using ai | |
| CN116128169B (en) | Multisystem linkage control method and device for intelligent transportation | |
| KR102665312B1 (en) | Tunnel control enclosure and enclosure control method for safe evacuation | |
| KR20200051923A (en) | Method for controlling a security robot, apparatus for supporting the same | |
| CN117975642B (en) | Intelligent management system for fire-fighting facilities | |
| KR102586132B1 (en) | Closed circuit television system for detecting fallen people in industrial sites and operation method thereof | |
| KR102635901B1 (en) | Hazardous object recognition system and method at construction site using AI robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211026 |
|
| RJ01 | Rejection of invention patent application after publication |