CN111815177A

CN111815177A - Fire safety assessment method, server, system and storage medium

Info

Publication number: CN111815177A
Application number: CN202010664951.4A
Authority: CN
Inventors: 郑金荣; 胡靓瑾
Original assignee: Hangzhou Haikang Fire Technology Co ltd
Current assignee: Hangzhou Haikang Fire Technology Co ltd
Priority date: 2020-07-10
Filing date: 2020-07-10
Publication date: 2020-10-23

Abstract

The application provides a fire safety assessment method, a server, a system and a storage medium. The method comprises the following steps: acquiring sample data, wherein the sample data is generated according to fire protection data of a target area, and the fire protection data comprises at least one of the following data: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; recording data collected by a collection terminal; the fire fighting data is used for inputting a fire fighting safety evaluation model to obtain the fire fighting safety level of the target area; and training the fire fighting safety evaluation model according to the sample data. According to the fire protection safety assessment model updating method and device, the fire protection safety assessment model is trained through sample data generated by fire protection data, automatic updating of the fire protection safety assessment model is achieved, the updating process of the fire protection safety assessment model is simplified, and updating efficiency is improved.

Description

Fire safety assessment method, server, system and storage medium

Technical Field

The application relates to the technical field of computers, in particular to a fire safety assessment method, a server, a system and a storage medium.

Background

Along with social development, factors influencing fire safety are more and more, and fire risks are more and more prominent. The fire safety assessment is carried out on the region through the fire safety assessment model based on deep learning, the region with low fire safety level is subjected to key treatment, and the fire safety is favorably improved.

Generally, a fire safety assessment model is constructed firstly, then the constructed fire safety assessment model is trained by utilizing a sample set, and the trained fire safety assessment model is uploaded to a server. After receiving the area data of the target area, the server carries out fire safety assessment on the target area by using a fire safety assessment model to obtain the fire safety level of the target area. When the fire safety assessment model in the server needs to be updated, operation and maintenance personnel collect area data of the sample areas to construct a new sample set, train the fire safety assessment model on the terminal equipment by using the new sample set, and then upload the trained fire safety assessment model to the server so as to update the fire safety assessment model.

At present, in a fire safety assessment mode, operation and maintenance personnel need to manually collect area data of a sample area and construct a new sample set to train a fire safety assessment model, and the updating process is complex and low in efficiency.

Disclosure of Invention

The embodiment of the application provides a fire safety assessment method, a server, a system and a storage medium, and aims to solve the problem that the existing fire safety assessment model is low in updating efficiency.

In a first aspect, an embodiment of the present application provides a fire safety assessment method, including:

acquiring sample data, wherein the sample data is generated according to fire protection data of a target area, and the fire protection data is used for inputting a fire protection safety evaluation model to obtain a fire protection safety level of the target area;

training the fire safety assessment model according to the sample data;

the fire fighting data comprises at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

In one possible embodiment, the detection data comprises at least one of the following data: water consumption data, electricity consumption data, combustible gas use data and smoke detection data;

the monitoring data comprises at least one of the following data: the fire-fighting control system comprises a fire control room duty data, an evacuation channel occupation data, a safety exit occupation data and a fire-fighting channel occupation data;

the recording data includes at least one of the following data: fire safety management data, maintenance data, law enforcement historical data and surrounding rescue force data.

In one possible implementation, obtaining sample data includes:

receiving a preset number of newly added sample data, wherein the preset number of newly added sample data is obtained from a sample library by a scheduling server according to a preset period until the preset number of newly added sample data is obtained; or, the scheduling server monitors the number of newly added sample data in the sample library, and when the number of newly added sample data reaches the preset number, the newly added sample data of the preset number is acquired from the sample library.

In one possible embodiment, the method further comprises:

sending the trained fire safety assessment model; and the trained fire safety assessment model is used for updating a local fire safety assessment model by the safety assessment server.

In one possible embodiment, the method further comprises:

determining the confidence level of the trained fire safety assessment model and sending the confidence level; and when the confidence coefficient of the trained fire safety assessment model is greater than that of the local fire safety assessment model of the safety assessment server, the trained fire safety assessment model is used for the safety assessment server to update the local fire safety assessment model.

In a second aspect, an embodiment of the present application provides a fire safety assessment method, including:

acquiring a trained fire safety assessment model, wherein the trained fire safety assessment model is obtained by training according to sample data, and the sample data is generated according to fire data of a target area;

acquiring fire fighting data of a target area, and inputting the fire fighting data into a local fire fighting safety evaluation model to obtain the fire fighting safety level of the target area;

the fire fighting data comprises at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

In a possible implementation manner, the sample data is newly added sample data obtained by the scheduling server from the sample library according to a preset period until a preset number of newly added sample data is obtained; or, the scheduling server monitors the number of newly added sample data in the sample library, and when the number of the newly added sample data reaches the preset number, the newly added sample data of the preset number is acquired from the sample library.

In one possible embodiment, obtaining a trained fire safety assessment model includes:

acquiring a trained fire safety assessment model obtained by a training server according to sample data;

receiving the confidence of the trained fire safety assessment model;

and when the confidence coefficient of the trained fire safety assessment model is greater than that of a local fire safety assessment model, updating the local fire safety assessment model into the trained fire safety assessment model.

In a third aspect, an embodiment of the present application provides a server, including: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executes computer-executable instructions stored by the memory, causing the at least one processor to perform the fire safety assessment method as described above in the first aspect and various possible implementations of the first aspect.

In a fourth aspect, an embodiment of the present application provides a server, including: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executes the computer-executable instructions stored by the memory, causing the at least one processor to perform the fire safety assessment method as described above in the second aspect and various possible embodiments of the second aspect.

In a fifth aspect, an embodiment of the present application provides a fire safety assessment system, where the system includes: a training server and a security assessment server;

the training server is used for executing the fire safety assessment method according to the first aspect and various possible embodiments of the first aspect;

the security assessment server is configured to execute the fire safety assessment method according to the second aspect and various possible embodiments of the second aspect.

In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the method for evaluating fire safety is implemented as described in the first aspect and various possible implementations of the first aspect.

In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer executing instruction is stored in the computer-readable storage medium, and when a processor executes the computer executing instruction, the fire safety assessment method according to the second aspect and various possible embodiments of the second aspect is implemented.

According to the fire safety assessment method, the server, the system and the storage medium provided by the embodiment of the application, sample data is firstly acquired, wherein the sample data is generated according to fire data of a target area, and the fire data comprises at least one of the following: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; recording data collected by a collection terminal; the fire fighting data is used for inputting a fire fighting safety evaluation model to obtain the fire fighting safety level of the target area; and then training the fire fighting safety evaluation model according to the sample data. According to the embodiment of the application, the detection data collected by the Internet of things equipment, the monitoring data collected by the camera, the fire fighting data such as the recording data collected by the collection terminal and the like are used for evaluating the fire fighting safety level of a target area on the one hand, and the sample data is also used for generating on the other hand, so that the sample data is obtained automatically and efficiently, the fire fighting safety evaluation model is trained by utilizing the sample data, the automatic updating of the fire fighting safety evaluation model is realized, the updating process of the fire fighting safety evaluation model is simplified, and the updating efficiency is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.

Fig. 1 is a schematic structural diagram of a fire safety assessment system according to an embodiment of the present application;

fig. 2 is a schematic diagram of an architecture of a fire safety assessment system according to another embodiment of the present application;

fig. 3 is a schematic flow chart of a fire safety assessment method according to an embodiment of the present application;

fig. 4 is a schematic flow chart of a fire safety assessment method according to another embodiment of the present application;

fig. 5 is a schematic flow chart of a fire safety assessment method according to another embodiment of the present application;

fig. 6 is a schematic flow chart illustrating a fire safety assessment method according to yet another embodiment of the present application;

fig. 7 is a schematic flow chart of a fire safety assessment method according to a next embodiment of the present application;

fig. 8 is a schematic flow chart of a fire safety assessment method according to still another embodiment of the present application;

FIG. 9 is a schematic diagram of a business process of the defense security assessment system in FIG. 2;

fig. 10 is a schematic structural diagram of a fire safety assessment device according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of a fire safety assessment device according to another embodiment of the present application;

fig. 12 is a schematic structural diagram of a fire safety assessment device according to another embodiment of the present application;

fig. 13 is a schematic structural diagram of a fire safety assessment device according to yet another embodiment of the present application;

fig. 14 is a schematic hardware structure diagram of a training server according to an embodiment of the present application;

fig. 15 is a schematic hardware structure diagram of a security assessment server according to another embodiment of the present application;

fig. 16 is a schematic hardware structure diagram of a dispatch server according to another embodiment of the present application;

fig. 17 is a schematic hardware structure diagram of a data access server according to still another embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

According to the method and the device, the fire fighting data of the target area are acquired, on one hand, the fire fighting data are input into the fire fighting safety assessment model to assess the fire fighting safety level of the target area, on the other hand, the fire fighting data are generated into sample data to be added into the sample library, and therefore the fire fighting safety assessment model is updated through the sample library. The fire protection data used for evaluating the fire protection safety level of the target area is used for generating sample data, the sample data in the sample library can be automatically and efficiently supplemented, the fire protection safety evaluation model is automatically updated based on the sample library, the updating process of the fire protection safety evaluation model can be simplified, and the updating efficiency is improved.

Fig. 1 is a schematic structural diagram of a fire safety assessment system according to an embodiment of the present application. As shown in fig. 1, the fire safety assessment system provided by the present embodiment includes a collection device 11, a training server 12, a safety assessment server 13, and a terminal device 14. The acquisition device 11 may include, but is not limited to, one or more of an internet of things device, a camera, and an acquisition terminal. The internet of things devices may include, but are not limited to, one or more of water meters, electricity meters, gas meters, smoke detectors. The acquisition terminal may include, but is not limited to, one or more of a tablet computer and a desktop computer. Terminal device 14 may include, but is not limited to, one or more of a cell phone, a tablet, a laptop, and a desktop.

The acquisition device 11 acquires fire data of a target area and transmits the fire data to the security evaluation server 13. For example, the target area is an area of a building, in which internet of things devices such as a water meter, an electric meter, a gas meter, and a smoke detector are installed, and a camera is disposed at a location such as a control room, an evacuation passageway, and a security exit of the building. The Internet of things equipment and the camera can upload the acquired fire fighting data to the data access server through the network. On one hand, the safety evaluation server 13 inputs the fire protection data of the target area into a fire protection safety evaluation model, and the obtained fire protection safety level of the target area is evaluated by using the fire protection safety evaluation model; on the other hand, corresponding sample data is generated from the fire-fighting data of the target area and is added into the sample library. The sample library may be implemented by a separate electronic device, or may be integrated in the security assessment server 13, or implemented in the training server 12, which is not limited herein. In one application scenario, the security assessment server 13 sends the fire safety level of the target area to the terminal device 14. The terminal device 14 displays the fire safety rating of the target area for viewing by the user. In an application scenario, if the fire safety level is lower than a preset level threshold, a fire hazard exists. After obtaining the fire safety level of the target area, the safety evaluation server 13 sends a warning message to the terminal device 14 when the fire safety level is lower than a preset level threshold, so as to prompt the user to perform corresponding processing on the target area, so as to reduce the fire hazard of the target area. For example, treatments that may be taken include, but are not limited to, adding a smoke detector, fire extinguisher, etc. to the target area, removing occupancy from a fire aisle, adding a person on duty in a fire room, etc.

The training server 12 obtains sample data in the sample library, and trains the fire safety assessment model to be trained according to the sample data to obtain the trained fire safety assessment model. The fire safety assessment model to be trained may be stored locally by the training server 12, or may be a fire safety assessment model obtained by the training server 12 from the safety assessment server 13 and local to the safety assessment server 13. The training server 12 sends the trained fire safety assessment model to the safety assessment server 13. The security evaluation server 13 updates the locally stored fire safety evaluation model to the trained fire safety evaluation model.

Fig. 2 is a schematic structural diagram of a fire safety assessment system according to another embodiment of the present application. As shown in fig. 2, the fire safety assessment system provided by the present embodiment includes a collection device 21, a data access server 22, a scheduling server 23, a training server 24, a safety assessment server 25, and a terminal device 26.

The acquisition device 21 acquires the fire data of the target area and transmits the fire data to the data access server 22. The data access server 22 sends the fire-fighting data of the target area to the security evaluation server 25 on one hand, and generates corresponding sample data of the fire-fighting data of the target area on the other hand, and adds the sample data into the sample library. The sample library may be implemented by a separate electronic device, or may be integrated in the data access server 22 or the scheduling server 23, which is not limited herein.

After receiving the fire data of the target area, the security evaluation server 25 inputs the fire data of the target area into the fire safety evaluation model, and evaluates the obtained fire safety level of the target area by using the fire safety evaluation model. The security evaluation server 25 transmits the fire safety level of the target area to the terminal device 26. Terminal device 26 displays the fire safety rating of the target area for viewing by the user.

The scheduling server 23 acquires sample data from the sample library and sends the sample data to the training server 24. The training server 24 trains the fire safety assessment model according to the sample data to obtain a trained fire safety assessment model, and sends the trained fire safety assessment model to the scheduling server 23. The dispatch server 23 sends the trained fire safety assessment model to the safety assessment server 25. The security evaluation server 25 updates the locally stored fire safety evaluation model to the trained fire safety evaluation model.

It should be noted that the data access server 22, the scheduling server 23, the training server 24, and the security assessment server 25 in fig. 2 may be respectively deployed in different servers, or two or more of them may be integrated into the same server, which is not limited herein. For example, the dispatch server 23 and the security assessment server 25 may be integrated into the same server implementation; as another example, the data access server 22, the scheduling server 23, and the security assessment server 25 may be integrated into the same server implementation. In addition, the system architectures of fig. 1 and fig. 2 are only used for example, and the fire safety assessment method provided by the embodiment of the application may also be applied to other system architectures, which are not limited herein.

Fig. 3 is a schematic flow chart of a fire safety assessment method according to an embodiment of the present application. The method may be performed by a training server. As shown in fig. 3, the method includes:

s301, obtaining sample data, generating the sample data according to the fire protection data of the target area, and inputting the fire protection data into a fire protection safety assessment model to obtain the fire protection safety level of the target area. Wherein the fire protection data comprises at least one of: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; and recording data acquired by the acquisition terminal.

In this embodiment, the fire safety assessment model may be a fire safety assessment model based on deep learning or machine learning. The fire safety assessment model is used for assessing the fire safety level of the target area according to the fire data of the target area. The specific algorithm of the fire safety assessment model is not limited herein, and for example, a Support Vector Machine (SVM) classification algorithm, a random forest algorithm, a neural network algorithm, and the like may be used.

The training server may obtain the sample data from the sample library, or may obtain the sample data from the sample library by another server, and then forward the sample data to the training server, which is not limited herein. For example, in the fire safety assessment system shown in fig. 2, the scheduling server obtains sample data from the sample library and sends the sample data to the training server. The sample library includes sample data generated from the fire data of the target area. The sample data in the sample library can be generated by a security evaluation server, a data access server and the like according to the fire protection data of the target area, and is stored in the sample library. For example, in the fire safety assessment system shown in fig. 1, sample data may be generated by a safety assessment server and stored into a sample repository; in the fire safety assessment system shown in fig. 2, sample data may be generated by the data access server and stored in the sample repository.

The fire fighting data can be acquired by the acquisition equipment. The acquisition device may include, but is not limited to, at least one of an internet of things device, a camera, and an acquisition terminal.

The detection data of the target area can be acquired through the Internet of things equipment. Optionally, the probe data comprises at least one of: water consumption data, electricity consumption data, combustible gas use data and smoke detection data. For example, the internet of things devices may include, but are not limited to, one or more of water meters, electricity meters, gas meters, smoke detectors. The water meter is used for collecting water consumption data in the target area, the electricity meter is used for collecting power consumption data in the target area, the gas meter is used for collecting combustible gas use data of the target area, and the smoke detector is used for collecting smoke detection data of the target area.

Monitoring data of the target area can be acquired by the camera. Optionally, the monitoring data comprises at least one of the following data: the fire-fighting control system comprises a control room duty data, an evacuation channel occupation data, a safety exit occupation data and a fire-fighting channel occupation data.

The recorded data of the target area can be acquired through the acquisition terminal. Optionally, the recording data comprises at least one of the following data: fire safety management data, maintenance data, law enforcement historical data and surrounding rescue force data. For example, the acquisition terminal is a desktop computer, and fire managers manually acquire fire-fighting related recorded data and input the recorded data into the acquisition terminal. The fire safety management data can include recorded data of inspection, fire safety training and fire duty management of the unit enterprises in the target area on fire equipment; the maintenance data can comprise recorded data of the inspection of the fire fighting equipment in the target area by a maintenance company of a third party; the law enforcement historical data can comprise recorded data of fire control inspection of a target area by a fire control law enforcement department; the surrounding rescue effort data may include fire hydrants surrounding the target area, the number and distance of rescue teams, and the like.

And S302, training the fire safety assessment model according to the sample data.

In this embodiment, the training server trains the fire safety assessment model to be trained according to the sample data, so as to obtain the trained fire safety assessment model. And the trained fire safety assessment model is used for updating the local fire safety assessment model by the safety assessment server. The fire safety assessment model to be trained may be stored locally by the training server, or may be obtained by the training server from the safety assessment server, and is not limited herein.

In the embodiment of the application, sample data is firstly acquired, wherein the sample data is generated according to fire protection data of a target area, and the fire protection data comprises at least one of the following: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; recording data collected by a collection terminal; and the fire fighting data is used for inputting the fire fighting safety assessment model to obtain the fire fighting safety grade of the target area, and then the fire fighting safety assessment model is trained according to the sample data. According to the embodiment of the application, the detection data collected by the Internet of things equipment, the monitoring data collected by the camera, the fire fighting data such as the recording data collected by the collection terminal and the like are used for evaluating the fire fighting safety level of a target area on the one hand, and the sample data is also used for generating on the other hand, so that the sample data is obtained automatically and efficiently, the fire fighting safety evaluation model is trained by utilizing the sample data, the automatic updating of the fire fighting safety evaluation model is realized, the updating process of the fire fighting safety evaluation model is simplified, and the updating efficiency is improved.

As an embodiment of the present application, on the basis of the embodiment shown in fig. 3, S301 may include:

receiving a preset number of newly added sample data, wherein the preset number of newly added sample data is used for acquiring the newly added sample data from the sample library by the scheduling server according to a preset period until the preset number of newly added sample data is acquired; or, the scheduling server monitors the number of the newly added sample data in the sample library, and when the number of the newly added sample data reaches a preset number, the newly added sample data of the preset number is obtained from the sample library.

In this embodiment, the fire safety assessment system may be as shown in fig. 2. The training server may receive a preset number of newly added sample data sent by the scheduling server, add the newly added sample data to the training sample set, or receive a training sample set containing a preset number of newly added sample data sent by the scheduling server, which is not limited herein.

For example, the scheduling server may obtain a preset number of newly added sample data from the sample library. The newly added sample data is stored in the sample library at a time later than the designated time, and the designated time is the last time when the preset number of newly added sample data is obtained. And the scheduling server adds the newly added sample data with the preset number to the training sample set and sends the training sample set to the training server.

The preset number may be preset, or configured by a user through a terminal device, and is not limited herein. Specific values of the preset number are not limited herein, and may be, for example, 100, 500, 1000, and the like. And the dispatching server acquires a preset number of newly added sample data from the sample library, and the newly added sample data is used for being added into the training sample set so as to update the training sample set. The method for the scheduling server to obtain the preset number of newly added sample data from the sample library may include, but is not limited to, any one of the following two implementation manners:

in one implementation mode, the scheduling server obtains newly added sample data from the sample library according to a preset period until a preset number of newly added sample data are obtained. The preset period may be preset or configured by a user through a terminal device, and is not limited herein. Specific values of the preset period are not limited herein, and may be, for example, obtained once every 2 hours, obtained once every day, obtained once every week, and the like.

In another implementation manner, the scheduling server monitors the number of newly added sample data in the sample library, and when the number of newly added sample data reaches a preset number, the newly added sample data of the preset number is acquired from the sample library.

In the embodiment, the scheduling server acquires the preset number of newly-added sample data from the sample library, the preset number of newly-added sample data is added to the training sample set, the preset number of newly-added sample data can be added to the training sample set at each time so as to update the training sample set, and after the training sample set is updated at each time, the training sample set can be used for performing one-time training on the fire safety assessment model, so that the automatic dynamic update of the fire safety assessment model is realized.

Based on the embodiment shown in fig. 3, fig. 4 is a schematic flow chart of a fire safety assessment method according to another embodiment of the present application. As shown in fig. 4, the method includes:

s401, obtaining sample data, generating the sample data according to the fire protection data of the target area, and inputting the fire protection data into a fire protection safety assessment model to obtain the fire protection safety level of the target area. Wherein the fire protection data comprises at least one of: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; and recording data acquired by the acquisition terminal.

S402, training the fire fighting safety evaluation model according to the sample data.

S403, sending the trained fire safety assessment model; and the trained fire safety assessment model is used for updating the local fire safety assessment model by the safety assessment server.

In this embodiment, the training server trains the fire safety assessment model according to the sample data, and after obtaining the fire safety assessment model, the trained fire safety assessment model may be directly sent to the safety assessment server, or the trained fire safety assessment model may be forwarded to the safety assessment server by another server, which is not limited herein. For example, in the fire safety assessment system shown in fig. 1, a training server sends a trained fire safety assessment model to a safety assessment server; in the fire safety assessment system shown in fig. 2, a training server sends a trained fire safety assessment model to a scheduling server, and the scheduling server forwards the trained fire safety assessment model to a safety assessment server.

And after receiving the trained fire safety assessment model, the safety assessment server updates the local fire safety assessment model into the trained fire safety assessment model, so that the fire safety assessment model is updated.

Optionally, on the basis of the embodiment shown in fig. 4, the method may further include:

In this embodiment, the confidence represents the evaluation accuracy of the fire safety evaluation model, and the higher the confidence is, the higher the evaluation accuracy is. For example, if 800 evaluation results of 1000 sample data obtained by the fire safety evaluation model are correct and 200 evaluation results are incorrect, the confidence level of the fire safety evaluation model is 80%.

The training server may determine a confidence level of the trained fire safety assessment model. For example, the confidence may be determined by the training server according to the percentage of the total sample data in the number of sample data correctly evaluated by the trained fire safety evaluation model. The confidence is used to determine whether to use the trained fire safety assessment model for model updating.

For example, in the fire safety assessment system shown in fig. 1, the training server may send the trained fire safety assessment model and its confidence to the safety assessment server. The security assessment server determines whether to perform model updating according to the confidence. Specifically, the security assessment server may compare the confidence of the trained fire safety assessment model with the confidence of the local fire safety assessment model. If the confidence of the trained fire safety assessment model is greater than that of the local fire safety assessment model, updating the local fire safety assessment model into the trained fire safety assessment model; and if the confidence coefficient of the trained fire safety assessment model is less than or equal to that of the local fire safety assessment model, the local fire safety assessment model is not updated, and the trained fire safety assessment model is deleted.

In the fire safety assessment system shown in fig. 2, the training server sends the trained fire safety assessment model and its confidence level to the scheduling server. And determining whether to update the fire safety assessment model local to the safety assessment server or not by the scheduling server according to the confidence. The scheduling server stores the confidence of the fire safety assessment model local to the safety assessment server. And the scheduling server compares the confidence of the trained fire safety assessment model with the confidence of the local fire safety assessment model of the safety assessment server. If the confidence of the trained fire safety assessment model is greater than the confidence of the local fire safety assessment model of the safety assessment server, the trained fire safety assessment model is sent to the safety assessment server to update the fire safety assessment model; and if the confidence coefficient of the trained fire safety assessment model is less than or equal to the confidence coefficient of the local fire safety assessment model of the safety assessment server, the trained fire safety assessment model is not sent to the safety assessment server, and the fire safety assessment model is not updated.

In this embodiment, by determining the confidence level of the trained fire safety assessment model, the fire safety assessment model is updated only when the confidence level of the trained fire safety assessment model is greater than the confidence level of the local fire safety assessment model of the safety assessment server, so that the accuracy of the updated fire safety assessment model can be improved.

Fig. 5 is a schematic flow chart of a fire safety assessment method according to another embodiment of the present application. The method may be performed by a security assessment server. As shown in fig. 5, the method includes:

s501, obtaining the trained fire safety assessment model, wherein the trained fire safety assessment model is obtained by training according to sample data, and the sample data is generated according to the fire data of the target area. Wherein the fire protection data comprises at least one of: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; and recording data acquired by the acquisition terminal.

In this embodiment, the training server obtains the trained fire safety assessment model according to the sample data training. The safety evaluation server can receive the trained fire safety evaluation model directly sent by the training server or forwarded by other servers. For example, in the fire safety assessment system shown in fig. 1, the safety assessment server receives a trained fire safety assessment model sent by the training server; in the fire safety assessment system shown in fig. 2, a training server sends a trained fire safety assessment model to a scheduling server, and a safety assessment server receives the trained fire safety assessment model sent by the scheduling server. The trained fire safety assessment model can be used for updating a local fire safety assessment model by a safety assessment server.

Optionally, the probe data comprises at least one of: water consumption data, electricity consumption data, combustible gas use data and smoke detection data;

the monitoring data includes at least one of the following data: the fire-fighting control system comprises a fire control room duty data, an evacuation channel occupation data, a safety exit occupation data and a fire-fighting channel occupation data;

S502, fire fighting data of the target area are obtained, and the fire fighting data are input into a local fire fighting safety evaluation model to obtain the fire fighting safety level of the target area.

In this embodiment, the security evaluation server may receive the fire protection data of the target area sent by the acquisition device, and may also receive the fire protection data of the target area sent by another server, which is not limited herein. For example, in the fire safety assessment system shown in fig. 1, the safety assessment server receives fire data of a target area sent by the acquisition device; in the fire safety assessment system shown in fig. 2, the acquisition device transmits acquired fire data of a target area to the data access server, and the safety assessment model receives the fire data of the target area transmitted by the data access server. And the safety evaluation server inputs the fire fighting data into a local fire fighting safety evaluation model to obtain the fire fighting safety level of the target area.

In the embodiment of the application, a trained fire safety assessment model is obtained, the trained fire safety assessment model is obtained according to sample data training, the sample data is generated according to fire data of a target area, and the fire data comprises at least one of the following: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; recording data collected by a collection terminal; and acquiring fire fighting data of the target area, and inputting the fire fighting data into a local fire fighting safety evaluation model to obtain the fire fighting safety level of the target area. In the embodiment of the application, the fire-fighting data such as the detection data collected by the internet of things equipment, the monitoring data collected by the camera and the recording data collected by the collection terminal are used for evaluating the fire safety level of the target area on the one hand, and the sample data is also used for generating on the other hand, so that the sample data is obtained automatically and efficiently, the fire safety evaluation model is updated by using the sample data, the automatic update of the fire safety evaluation model is realized, the update process of the fire safety evaluation model is simplified, and the update efficiency is improved.

Optionally, the sample data is obtained from the sample base by the scheduling server according to a preset period until a preset number of newly added sample data is obtained; or, the scheduling server monitors the number of newly added sample data in the sample library, and when the number of the newly added sample data reaches a preset number, the preset number of the newly added sample data is obtained from the sample library.

In one implementation, after the security assessment server obtains the trained fire safety assessment model, the local fire safety assessment model is updated to the trained fire safety assessment model.

In another implementation, the security assessment server may further receive a confidence level of the trained fire safety assessment model; and when the confidence coefficient of the trained fire safety assessment model is greater than that of the local fire safety assessment model, updating the local fire safety assessment model into the trained fire safety assessment model.

In this implementation, the training server may determine a confidence level of the trained fire safety assessment model. The security assessment server may receive the confidence level sent by the training server, or the training server sends the confidence level to the dispatch server, which sends the confidence level to the security assessment server. And the safety evaluation server compares the confidence of the trained fire safety evaluation model with the confidence of the local fire safety evaluation model, updates the local fire safety evaluation model into the trained fire safety evaluation model when the confidence of the trained fire safety evaluation model is greater than that of the local fire safety evaluation model, does not update the local fire safety evaluation model when the confidence of the trained fire safety evaluation model is less than or equal to that of the local fire safety evaluation model, and deletes the trained fire safety evaluation model.

Fig. 6 is a schematic flow chart of a fire safety assessment method according to yet another embodiment of the present application. The method is performed by the dispatch server described above in fig. 2. As shown in fig. 6, the method includes:

s601, obtaining sample data, generating the sample data according to the fire protection data of the target area, and inputting the fire protection data into a fire protection safety assessment model to obtain the fire protection safety level of the target area.

In this embodiment, the scheduling server may obtain sample data from the sample library. The sample library includes sample data generated from the fire data of the target area. And the fire fighting data of the target area is used for inputting the fire fighting safety evaluation model to obtain the fire fighting safety level of the target area. The sample data in the sample library can be generated by the data access server according to the fire protection data of the target area and stored in the sample library. In addition, the scheduling server may also directly obtain the sample data from the data access server, and the manner in which the scheduling server obtains the sample data is not limited here.

The fire protection data includes at least one of: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; and recording data acquired by the acquisition terminal. Optionally, the probe data comprises at least one of: water consumption data, electricity consumption data, combustible gas use data and smoke detection data; the monitoring data includes at least one of the following data: the fire-fighting control system comprises a fire control room duty data, an evacuation channel occupation data, a safety exit occupation data and a fire-fighting channel occupation data; the recording data includes at least one of the following data: fire safety management data, maintenance data, law enforcement historical data and surrounding rescue force data.

And S602, sending sample data to the training server, wherein the sample data is used for the training server to train the fire safety assessment model.

In this embodiment, the scheduling server may extract all or part of the sample data from the sample library to form a training sample set, and send the training sample set to the training server. The training server trains the fire safety assessment model based on the training sample set, so that the fire safety assessment model is updated. The training frequency of the fire safety assessment model is not limited, for example, when the number of newly added sample data in the sample library reaches a preset number, the scheduling server can send a training sample set to the training server for one-time training of the fire safety assessment model by the training server; alternatively, the scheduling server may send the training sample set to the training server at regular time intervals, so that the training server performs one training on the fire safety assessment model.

In an embodiment of the application, sample data is acquired, wherein the sample data is generated according to fire protection data of a target area, and the fire protection data includes at least one of the following: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; recording data collected by a collection terminal; the fire protection data are used for inputting the fire protection safety assessment model to obtain the fire protection safety level of the target area, the sample data are sent to the training server, and the training server trains the fire protection safety assessment model through the sample data. In the embodiment of the application, the fire-fighting data such as the detection data collected by the internet of things equipment, the monitoring data collected by the camera and the recording data collected by the collection terminal are used for evaluating the fire safety level of the target area on the one hand, and the sample data is also used for generating on the other hand, so that the sample data is obtained automatically and efficiently, the fire safety evaluation model is updated by using the sample data, the automatic update of the fire safety evaluation model is realized, the update process of the fire safety evaluation model is simplified, and the update efficiency is improved.

Based on the embodiment shown in fig. 6, fig. 7 is a schematic flow chart of a fire safety assessment method provided in the next embodiment of the present application. As shown in fig. 7, the method includes:

s701, acquiring a preset number of newly added sample data from the sample library, wherein the newly added sample data is the sample data stored in the sample library and the time is later than the specified time, the specified time is the last time of acquiring the preset number of newly added sample data, the sample data is generated according to fire protection data of a target area, and the fire protection data is used for inputting a fire protection safety evaluation model so as to obtain the fire protection safety level of the target area.

S702, adding the preset number of newly added sample data into the training sample set.

In this embodiment, the preset number may be preset, or configured by a user through a terminal device, which is not limited herein. Specific values of the preset number are not limited herein, and may be, for example, 100, 500, 1000, and the like. And the dispatching server acquires a preset number of newly added sample data from the sample library, and the newly added sample data is used for being added into the training sample set so as to update the training sample set. And the scheduling server adds the newly added sample data with the preset number to the training sample set each time.

Taking the preset number of samples as 1000 as an example, assuming that the time for the scheduling server to obtain 1000 newly added sample data from the sample library last time is 5 month 16 # 08:00 (i.e. the specified time), when the number of newly added sample data added into the sample library after 5 month 16 # 08:00 reaches 1000, the scheduling server adds 1000 newly added sample data after 5 month 16 # 08:00 into the training data set.

When newly added sample data is added to the training sample set, the scheduling server can retain all the original sample data in the training sample set; or delete some original sample data in the training sample set, for example, delete a preset number of oldest added original sample data in the training sample set. Taking 5000 original sample data in the training sample set and the preset number of the sample data as an example, the scheduling server may add 1000 newly added sample data to the training sample set, and retain the original 5000 sample data, so that the total number of the sample data in the training sample set after updating is 6000; the scheduling server may also add 1000 newly-added sample data to the training sample set, delete the oldest 1000 sample data from the original 5000 sample data, and keep the total number of sample data in the updated training sample set at 5000.

The scheduling server may obtain the preset number of newly added sample data at one time, or obtain the preset number of newly added sample data in multiple times, which is not limited herein. For example, the manner in which the scheduling server obtains the preset number of newly added sample data may include, but is not limited to, any one of the following two implementation manners:

in one implementation mode, the scheduling server obtains newly added sample data from the sample library according to a preset period until a preset number of newly added sample data are obtained.

The preset period may be preset or configured by a user through a terminal device, and is not limited herein. Specific values of the preset period are not limited herein, and may be, for example, obtained once every 2 hours, obtained once every day, obtained once every week, and the like.

Taking the preset number of 1000 and the preset period of once per day as an example, the scheduling server acquires newly added sample data stored in the sample database on the same day from the sample database every day, temporarily stores the newly added sample data, and adds the 1000 newly added sample data into the training sample set when acquiring 1000 newly added sample data all the time after multiple days. And then the scheduling server repeats the acquiring process, and when 1000 newly-added sample data are acquired, the 1000 newly-added sample data are added into the training sample data set, and the training sample set is updated once.

The scheduling server may monitor the number of newly added sample data in the sample library, and the specific monitoring mode is not limited herein. For example, the scheduling server may query the number of newly added sample data in the sample library at regular intervals, or set a parameter for recording the number of newly added sample data in the sample library. And adding 1 to the parameter every time one newly added sample data is added in the sample library. And when the parameters reach the preset number, triggering a prompt message. And when monitoring that the number of the newly added sample data reaches a preset number, the scheduling server acquires the newly added sample data with the preset number from the sample library at one time.

And S703, sending a training sample set to the training server, wherein the training sample set is used for the training server to train the fire safety assessment model.

In this embodiment, the training server trains the fire safety assessment model according to the training sample set, so as to improve the assessment accuracy of the fire safety assessment model and update the fire safety assessment model. The training sample set comprises a plurality of sample data, wherein each sample data comprises fire protection data used as training input and a fire protection safety level of an area corresponding to the fire protection data obtained by manually marking the fire protection data. The training server trains the current fire safety assessment model according to the training sample set, and the trained fire safety assessment model can be obtained.

In the embodiment, the newly added sample data with the preset number is added to the training sample set by acquiring the newly added sample data with the preset number from the sample library, the newly added sample data with the preset number can be added to the training sample set at each time so as to update the training sample set, and after the training sample set is updated at each time, the training sample set can be used for training the fire safety assessment model once, so that the automatic dynamic update of the fire safety assessment model is realized.

As an embodiment of the present application, on the basis of the embodiment shown in fig. 6, in this embodiment, configuration parameters may be set by a user to control an update process of the fire safety assessment model. The method may further comprise:

and receiving and storing configuration parameters sent by the terminal equipment, wherein the configuration parameters comprise a preset number and/or a preset period.

In this embodiment, the terminal device may receive the configuration parameter input by the user, and send the configuration parameter to the scheduling server. And the scheduling server receives and stores the configuration parameters, and controls the process of acquiring sample data from the database according to the configuration parameters, so as to control the updating process of the fire safety assessment model. Wherein the configuration parameters may include at least one of: the preset number and the preset period. The preset period may include a sample sampling period; or the preset period may include a sample sampling period and a sample acquisition frequency. The sample sampling period characterization server obtains sample data from the sample library according to the period, for example, if the sample sampling period is one day, the server obtains the sample data from the sample library every day. The sample collection frequency represents the number of times that the server obtains sample data from the sample base in a single sample collection period, for example, if the sample collection period is one day and the sample collection frequency is 3 times, the server obtains three times of sample data from the sample base every day. According to the embodiment, the user can flexibly control the updating process of the fire safety assessment model through the configuration parameters, and the applicability of the updating process to different scenes is improved.

As an embodiment of the present application, on the basis of the embodiment shown in fig. 7, in this embodiment, by deleting sample data before the time, the total number of sample data in the training sample set is kept not to exceed the preset threshold, so as to prevent the training efficiency from being affected by an oversize training sample set. After S703, the method further includes:

and when the total number of the sample data in the training sample set exceeds a preset threshold, deleting the sample data of the appointed number before the training sample set, wherein the appointed number is the difference value between the total number and the preset threshold.

In this embodiment, the preset threshold may be set according to actual requirements, and is not limited herein, for example, the preset threshold may be 10000, 50000, and the like. The preset threshold is used as an upper limit value of the number of the sample data in the training sample set, so that the problems that the number of the samples in the training sample set is larger and larger with the addition of the sample data, the training time is too long, and the training efficiency is low are solved. Taking the preset threshold value of 10000 as an example, assuming that the scheduling server monitors that the total number of sample data in the training sample set is 12000, the server sorts all sample data from morning to evening according to the time of adding the sample data into the training sample set, and deletes 2000 sample data in the front ranking (namely 12000-10000-2000), so that the total number of the sample data in the training sample set is maintained to be not more than 10000.

By setting the preset threshold and deleting the sample data before, the embodiment can prevent the problem of low training efficiency caused by overlarge sample data in the training sample set, and update the sample data in the training sample set.

As an embodiment of the present application, on the basis of the embodiment shown in fig. 6 or fig. 7, the method may further include:

receiving a trained fire safety assessment model sent by a training server;

and sending the trained fire safety assessment model to a safety assessment server, wherein the trained fire safety assessment model is used for updating the local fire safety assessment model by the safety assessment server.

In this embodiment, after the training server trains the fire safety assessment model according to the sample data, the trained fire safety assessment model can be obtained. And the training server sends the trained fire safety assessment model to the scheduling server. And after receiving the trained fire safety assessment model, the scheduling server sends the trained fire safety assessment model to the safety assessment server. And the safety evaluation server updates the locally stored fire safety evaluation model into the trained fire safety evaluation model.

Optionally, the method may further include:

receiving the confidence degree of the trained fire safety assessment model sent by the training server;

and when the confidence coefficient of the trained fire safety assessment model is greater than that of the local fire safety assessment model of the safety assessment server, the scheduling server sends the trained fire safety assessment model to the safety assessment server.

In this embodiment, the training server may send the trained fire safety assessment model and its confidence to the scheduling server. The scheduling server stores the confidence of the fire safety assessment model local to the safety assessment server. And the scheduling server compares the confidence of the trained fire safety assessment model with the confidence of the local fire safety assessment model of the safety assessment server. If the confidence of the trained fire safety assessment model is greater than the confidence of the local fire safety assessment model of the safety assessment server, the trained fire safety assessment model is sent to the safety assessment server to update the fire safety assessment model; and if the confidence coefficient of the trained fire safety assessment model is less than or equal to the confidence coefficient of the local fire safety assessment model of the safety assessment server, the trained fire safety assessment model is not sent to the safety assessment server, and the fire safety assessment model is not updated.

In this embodiment, by comparing the confidence level of the trained fire safety assessment model with the confidence level of the local fire safety assessment model of the safety assessment server, the fire safety assessment model is updated only when the confidence level of the trained fire safety assessment model is greater than the confidence level of the local fire safety assessment model of the safety assessment server, so that the accuracy of the updated fire safety assessment model can be improved.

Fig. 8 is a schematic flow chart of a fire safety assessment method according to still another embodiment of the present application. The method may be performed by the data access server in fig. 2. As shown in fig. 8, the method includes:

s801, acquiring fire fighting data of a target area; and the fire fighting data is used for inputting the fire fighting safety evaluation model so as to obtain the fire fighting safety level of the target area. Wherein the fire protection data comprises at least one of: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; and recording data acquired by the acquisition terminal.

S802, generating sample data according to the fire protection data of the target area, storing the sample data in a sample library, and using the sample data for training a server to train a fire protection safety evaluation model.

In this embodiment, the fire fighting data of the target area may be acquired by the acquisition device and sent to the data access server, or may be manually acquired by the user, input to the terminal device, and sent to the data access server through the terminal device, which is not limited herein. The acquisition device may comprise at least one of: the system comprises the Internet of things equipment, a camera and a collection terminal. The acquisition device may be deployed within the target area. The fire protection data have two purposes, on one hand, the fire protection data are input into the fire protection safety assessment model by the safety assessment server to obtain the fire protection safety level of the target area, on the other hand, the data access server generates sample data of the fire protection data, and the sample data is used for the training server to train the fire protection safety assessment model.

In the embodiment of the application, fire fighting data of a target area are acquired; the fire protection data includes at least one of: detecting data acquired through the Internet of things equipment; monitoring data collected by a camera; recording data collected by a collection terminal; the fire protection data are used for inputting the fire protection safety assessment model to obtain the fire protection safety level of the target area, sample data are obtained, the sample data are generated according to the fire protection data of the target area and are stored in a sample library, and the sample data are used for training the server to train the fire protection safety assessment model. In the embodiment of the application, the fire-fighting data such as the detection data collected by the internet of things equipment, the monitoring data collected by the camera and the recording data collected by the collection terminal are used for evaluating the fire-fighting safety level of the target area on the one hand, and the sample data is generated on the other hand, so that the sample data is obtained automatically and efficiently, the fire-fighting safety evaluation model is updated by using the sample data, the automatic update of the fire-fighting safety evaluation model is realized, the fire-fighting safety evaluation process is simplified, and the update efficiency is improved.

Optionally, the probe data comprises at least one of: water consumption data, electricity consumption data, combustible gas use data and smoke detection data; the monitoring data includes at least one of the following data: the fire-fighting control system comprises a fire control room duty data, an evacuation channel occupation data, a safety exit occupation data and a fire-fighting channel occupation data; the recording data includes at least one of the following data: fire safety management data, maintenance data, law enforcement historical data and surrounding rescue force data.

Optionally, S802 may include:

sending the fire-fighting data to the first terminal equipment;

receiving an artificial calibration result sent by a first terminal device, wherein the artificial calibration result comprises a fire safety level of a target area;

and generating sample data according to the fire-fighting data and the manual calibration result.

In this embodiment, corresponding sample data can be obtained by manually calibrating the fire-fighting data. The data access server may send the fire protection data to the first terminal device. The first terminal equipment is equipment for calibrating personnel. The first terminal equipment displays fire protection data to a calibration worker, and the calibration worker calibrates the fire protection data according to manual experience to obtain the fire protection safety level of the area corresponding to the fire protection data, namely a manual calibration result. And the first terminal equipment receives the manual calibration result input by the calibration personnel and sends the manual calibration result to the data access server. And the data access server generates the fire-fighting data and the corresponding manual calibration result into sample data. The first terminal device may be a mobile phone, a tablet, a notebook computer, a desktop computer, and the like, which is not limited herein.

Optionally, the method may further include:

and sending fire fighting data to the safety evaluation server, wherein the fire fighting data is used for the safety evaluation server to input a fire fighting safety evaluation model so as to obtain the fire fighting safety level of the target area, and sending the fire fighting safety level of the target area to the second terminal equipment.

In this embodiment, the data access server sends the fire data to the security assessment server. And the safety evaluation server inputs the fire fighting data into the fire fighting safety evaluation model to obtain the fire fighting safety level of the target area output by the fire fighting safety evaluation model. And the safety evaluation server sends the fire safety level of the target area to the second terminal equipment. The second terminal device can display the fire safety level of the target area to the user, so that the user can check the fire safety level of the target area and perform corresponding processing. For example, a user judges whether the fire protection deployment of the target area needs to be enhanced according to the fire protection safety level of the target area, if so, the fire protection deployment of the target area is enhanced by increasing fire protection equipment such as a smoke detector, a fire extinguisher and the like of the target area, removing occupied objects of a fire protection channel, increasing operators on duty in a fire room, increasing polling frequency and the like, so that the fire protection safety is improved. Optionally, after the security evaluation server evaluates the fire safety level of the target area by using the fire safety evaluation model, when the fire safety level is lower than a preset level threshold, a warning message is sent to the second terminal device to prompt the user to perform corresponding processing on the target area, so that the fire hazard of the target area is reduced.

The fire-fighting safety evaluation method provided by the embodiment of the application is described below by taking the fire-fighting safety evaluation system in fig. 2 as an example. Fig. 9 is a schematic business flow diagram of the defense security assessment system in fig. 2. Referring to fig. 9, the business process can be divided into four parts: the method comprises a data acquisition process, a training plan configuration process, a model training process and a fire safety assessment process. The four sections will be described below.

1. Data acquisition process

The data acquisition adopts the following three modes:

A. the data are collected through the Internet of things equipment and are uploaded to the data access server through the Internet of things. The fire fighting data collected by the Internet of things equipment comprises but is not limited to index data such as water consumption, electricity consumption, combustible gas, smoke detection and the like.

B. The data is collected by a camera and is uploaded to a data access server through the Internet. The camera intelligently analyzes, but is not limited to, the duty data of the control room, the occupancy data of the evacuation channel, the occupancy data of the security exit, the occupancy data of the fire fighting channel and the like in a video mode.

C. The data are manually collected through a collecting terminal and are uploaded to a data access server through the Internet. The collected data includes, but is not limited to, fire safety management data, maintenance data, law enforcement history data, surrounding rescue force data, and the like.

The data access server sorts the fire protection data acquired in the three modes, and the sorted data generates sample data and stores the sample data into a sample library, wherein on one hand, each fire protection data is taken as a characteristic variable, and a fire protection safety evaluation grade obtained by manually calibrating the fire protection data is taken as an expected output result (namely, a manual calibration result); and on the other hand, the fire protection data is sent to a safety evaluation server for fire protection safety evaluation.

The sample library may use a relational database for data storage, such as a Postgresql database, a mysql database, an oracle database, and the like, or may use a non-relational database for data storage, such as a NoSQL database, a key-value database, and the like, which is not limited herein.

2. Training plan configuration process

The configuration personnel configure the training plan through the terminal device, and the configuration parameters include the sample training number (namely the preset number), the sample acquisition period and the sample acquisition frequency. And after the training plan configuration is completed, the terminal equipment stores the configuration plan to the scheduling server.

Number of sample training: when the number of newly added samples obtained from the sample library reaches the sample training number, the scheduling server sends a training instruction to the training server.

Sample collection period: the scheduling server obtains new sample data from the sample library according to the period, such as every day, every week or other self-defined time.

Sample collection frequency: the number of times that the scheduling server acquires data from the sample library in a sample acquisition period is referred to.

3. Model training procedure

The scheduling server acquires newly added sample data from the sample library according to the training plan, judges whether the number of the acquired samples reaches the training number of the samples, waits for the next sample acquisition period if the number of the acquired samples does not reach the training number of the samples, and continues to acquire the newly added sample data from the sample library; and if so, sending the training sample set to a training server to train the fire safety assessment model. And after the training server trains a fire safety assessment model by using a machine learning algorithm or a deep learning algorithm, the trained fire safety assessment model is returned to the scheduling server. And the dispatching server judges whether the trained fire safety assessment model is optimized or not, and if so, the trained fire safety assessment model is issued to the safety assessment server. And the safety evaluation server updates a local fire safety evaluation model.

Along with the continuous accumulation of sample data, the fire safety assessment model is continuously improved, after the fire safety assessment model is optimized in each period, a new fire safety assessment model is issued to the safety assessment server through the scheduling server, and the effect of dynamically updating the fire safety assessment model is achieved.

The training server may use the CPU (Central Processing Unit) power and/or the GPU (Graphics Processing Unit) power of the training server to perform data computation during the training process.

4. Fire safety assessment process

After receiving the fire protection data acquired by the data access server, the security evaluation server sorts the fire protection data, for example, a target area comprises a plurality of enterprise units, and the fire protection data can be sorted into unit data corresponding to each enterprise unit; or the area where one enterprise unit is located can be used as one target area, and each target area corresponds to one fire-fighting data. And the safety evaluation server inputs the sorted fire fighting data into a local fire fighting safety evaluation model for calculation to obtain the fire fighting safety evaluation level of each enterprise unit, and then pushes the fire fighting safety evaluation level to the terminal equipment. The terminal device may render and display the fire safety assessment level, for example, display the fire safety assessment level of each enterprise unit in the target area in a thermodynamic diagram manner.

It should be noted that the execution sequence of the model training process and the fire safety evaluation process is not limited herein, and the two processes may be executed in parallel, or the fire safety evaluation process may be executed first and then the model training process, or the model training process may be executed first and then the fire safety evaluation process. The data access server, the call server, the training server, and the security evaluation server may be integrated into one server, or may be divided into a plurality of servers, which is not limited herein.

Fig. 10 is a schematic structural diagram of a fire safety assessment device according to an embodiment of the present application. The fire safety evaluation device can be applied to a training server. As shown in fig. 10, the fire safety evaluation device 100 includes: an acquisition module 1001 and a processing module 1002.

The obtaining module 1001 is configured to obtain sample data, where the sample data is generated according to the fire protection data of the target area, and the fire protection data is used to input the fire protection safety assessment model to obtain a fire protection safety level of the target area.

The processing module 1002 is configured to train the fire safety assessment model according to the sample data.

Fire protection data comprising at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

Optionally, the obtaining module 1001 is specifically configured to:

Optionally, the apparatus further comprises a sending module.

A sending module configured to: sending the trained fire safety assessment model; and the trained fire safety assessment model is used for updating the local fire safety assessment model by the safety assessment server.

Optionally, the processing module 1002 is further configured to: determining the confidence of the trained fire safety assessment model;

a sending module, further configured to: sending the confidence level; and when the confidence coefficient of the trained fire safety assessment model is greater than that of the local fire safety assessment model of the safety assessment server, the trained fire safety assessment model is used for the safety assessment server to update the local fire safety assessment model.

The fire safety assessment apparatus of this embodiment may be used to implement the technical solution of fig. 3 and the corresponding method embodiment, and its implementation principle and technical effect are similar, which are not described herein again.

Fig. 11 is a schematic structural diagram of a fire safety assessment device according to another embodiment of the present application. The fire safety evaluation device can be applied to a safety evaluation server. As shown in fig. 11, the fire safety evaluation device 110 includes: an acquisition module 1101 and a processing module 1102.

The obtaining module 1101 is configured to obtain a trained fire safety assessment model, where the trained fire safety assessment model is obtained by training according to sample data, and the sample data is generated according to fire data of a target area.

The obtaining module 1101 is further configured to obtain fire fighting data of the target area.

And the processing module 1102 is configured to input the fire protection data into a local fire protection safety assessment model to obtain a fire protection safety level of the target area.

Fire protection data comprising at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

Optionally, the obtaining module 1101 is specifically configured to:

and acquiring a trained fire safety assessment model obtained by the training server according to the sample data.

Optionally, the obtaining module 1101 is further configured to: and receiving the confidence of the trained fire safety assessment model.

The processing module 1102 is specifically configured to update the local fire safety assessment model to the trained fire safety assessment model when the confidence of the trained fire safety assessment model is greater than the confidence of the local fire safety assessment model.

The fire safety assessment apparatus of this embodiment may be used to implement the technical solution of fig. 5 and the corresponding method embodiment, and its implementation principle and technical effect are similar, which are not described herein again.

Fig. 12 is a schematic structural diagram of a fire safety assessment device according to another embodiment of the present application. The fire safety assessment device can be applied to a scheduling server. As shown in fig. 12, the fire safety evaluation device 120 includes: an obtaining module 1201 and a sending module 1202.

The obtaining module 1201 is configured to obtain sample data, where the sample data is generated according to the fire protection data of the target area, and the fire protection data is used to input the fire protection safety assessment model to obtain a fire protection safety level of the target area.

A sending module 1202, configured to send sample data to the training server, where the sample data is used for the training server to train the fire safety assessment model.

Fire protection data comprising at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

Optionally, the obtaining module 1201 is specifically configured to:

acquiring a preset number of newly added sample data from a sample library, wherein the newly added sample data is the sample data stored in the sample library at a time later than a specified time, and the specified time is the last time of acquiring the preset number of newly added sample data;

adding a preset number of newly added sample data into a training sample set;

the sending module 1202 is specifically configured to:

a training sample set is sent to a training server.

Optionally, the obtaining module 1201 is specifically configured to:

acquiring newly added sample data from the sample library according to a preset period until a preset number of newly added sample data are acquired;

or monitoring the number of newly added sample data in the sample library, and acquiring the newly added sample data with the preset number from the sample library when the number of the newly added sample data reaches the preset number.

Optionally, the apparatus further comprises:

and the receiving module is used for receiving and storing the configuration parameters sent by the terminal equipment, wherein the configuration parameters comprise a preset number and/or a preset period.

Optionally, the apparatus further comprises:

and the processing module is used for deleting the sample data of the appointed number before the training sample set time when the total number of the sample data in the training sample set exceeds a preset threshold, wherein the appointed number is the difference value between the total number and the preset threshold.

Optionally, the obtaining module 1201 is further configured to:

receiving a trained fire safety assessment model sent by a training server;

a sending module 1202, further configured to:

Optionally, the obtaining module 1201 is further configured to:

the sending module 1201 is specifically configured to:

and when the confidence coefficient of the trained fire safety assessment model is greater than that of the local fire safety assessment model of the safety assessment server, sending the trained fire safety assessment model to the safety assessment server.

The fire safety assessment apparatus of this embodiment may be used to implement the technical solution of fig. 6 and the corresponding method embodiment, and its implementation principle and technical effect are similar, which are not described herein again.

Fig. 13 is a schematic structural diagram of a fire safety assessment device according to yet another embodiment of the present application. The fire safety evaluation device can be applied to a data access server. As shown in fig. 13, the fire safety evaluation device 130 includes: an obtaining module 1301 and a processing module 1302.

An obtaining module 1301, configured to obtain fire data of a target area; and the fire fighting data is used for inputting the fire fighting safety evaluation model so as to obtain the fire fighting safety level of the target area.

And the processing module 1302 is configured to generate sample data according to the fire protection data of the target area, and store the sample data in a sample library, where the sample data is used for training the server to train the fire protection safety assessment model.

The obtaining module 1301 obtains the fire-fighting data in at least one of the following manners:

acquiring detection data acquired by the Internet of things equipment;

acquiring monitoring data acquired by a camera;

and acquiring the recorded data acquired by the acquisition terminal.

Optionally, the processing module 1302 is specifically configured to:

sending the fire-fighting data to the first terminal equipment;

Optionally, the apparatus further comprises:

and the sending module is used for sending the fire fighting data to the safety evaluation server, the fire fighting data is used for the safety evaluation server to input the fire fighting safety evaluation model so as to obtain the fire fighting safety level of the target area, and the fire fighting safety level of the target area is sent to the second terminal equipment.

The fire safety assessment apparatus of this embodiment may be used to implement the technical solution of fig. 8 and the corresponding method embodiment, and its implementation principle and technical effect are similar, which are not described herein again.

Fig. 14 is a schematic hardware structure diagram of a training server according to an embodiment of the present application. As shown in fig. 14, the training server 140 provided in the present embodiment includes: at least one processor 1401, and memory 1402. The training server 140 further comprises a communication component 1403. The processor 1401, the memory 1402, and the communication unit 1403 are connected by a bus 1404.

In a specific implementation process, the at least one processor 1401 executes computer-executable instructions stored in the memory 1402, so that the at least one processor 1401 performs the fire safety assessment method as described in fig. 3 and its corresponding embodiments.

For a specific implementation process of the processor 1401, reference may be made to the above method embodiments, which implement similar principles and technical effects, and this embodiment is not described herein again.

Fig. 15 is a schematic hardware structure diagram of a security assessment server according to yet another embodiment of the present application. As shown in fig. 15, the security evaluation server 150 according to the present embodiment includes: at least one processor 1501 and memory 1502. The security assessment server 150 also includes a communication component 1503. The processor 1501, the memory 1502, and the communication section 1503 are connected by a bus 1504.

In a specific implementation, the at least one processor 1501 executes the computer executable instructions stored in the memory 1502, so that the at least one processor 1501 executes the fire safety assessment method as described above in fig. 5 and its corresponding embodiments.

For a specific implementation process of the processor 1501, reference may be made to the above method embodiments, which implement similar principles and technical effects, and this embodiment is not described herein again.

Fig. 16 is a schematic hardware structure diagram of a dispatch server according to another embodiment of the present application. As shown in fig. 16, the scheduling server 160 provided in the present embodiment includes: at least one processor 1601, and a memory 1602. The dispatch server 160 also includes a communication component 1603. The processor 1601, the memory 1602, and the communication unit 1603 are connected via a bus 1604.

In a specific implementation, the at least one processor 1601 executes the computer executable instructions stored by the memory 1602, so that the at least one processor 1601 executes the method for fire safety assessment as described above in fig. 6 and its corresponding embodiments.

For a specific implementation process of the processor 1601, reference may be made to the above method embodiments, which achieve similar implementation principles and technical effects, and details of this embodiment are not described herein again.

Fig. 17 is a schematic hardware structure diagram of a data access server according to still another embodiment of the present application. As shown in fig. 17, the data access server 170 provided in the present embodiment includes: at least one processor 1701 and memory 1702. The data access server 170 further comprises a communication component 1703. The processor 1701, the memory 1702, and the communication unit 1703 are connected by a bus 1704.

In particular implementations, the at least one processor 1701 executes computer-executable instructions stored by the memory 1702 to cause the at least one processor 1701 to perform a fire safety assessment method as described above with respect to FIG. 8 and its corresponding embodiments.

For a specific implementation process of the processor 1701, reference may be made to the above method embodiments, which have similar implementation principles and technical effects, and no further description is given here.

In the embodiments shown in fig. 14-17, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in the incorporated application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The application also provides a fire safety evaluation system, includes:

a training server as in the embodiment shown in fig. 14 above, a security assessment server as in the embodiment shown in fig. 15 above.

The application also provides a fire safety evaluation system, which comprises at least one of the following items:

a training server as in the embodiment shown in fig. 14 above, a security assessment server as in the embodiment shown in fig. 15 above, a scheduling server as in the embodiment shown in fig. 16 above, and a data access server as in the embodiment shown in fig. 17 above.

The present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the fire safety assessment method as shown in fig. 3 and the corresponding embodiment thereof is implemented.

The present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the fire safety assessment method as shown in fig. 5 and the corresponding embodiment thereof is implemented.

The present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the fire safety assessment method as described in fig. 6 and its corresponding embodiment is implemented.

The present application further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the fire safety assessment method as described in fig. 8 and its corresponding embodiment is implemented. The readable storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 or all of the 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 application.

Claims

1. A fire safety assessment method, comprising:

training the fire safety assessment model according to the sample data;

the fire fighting data comprises at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

2. The method of claim 1,

the probe data includes at least one of: water consumption data, electricity consumption data, combustible gas use data and smoke detection data;

3. The method of claim 1 or 2, wherein obtaining sample data comprises:

4. The method according to claim 1 or 2, characterized in that the method further comprises:

5. The method of claim 4, further comprising:

6. A fire safety assessment method, comprising:

the fire fighting data comprises at least one of:

detecting data acquired through the Internet of things equipment;

monitoring data collected by a camera;

and recording data acquired by the acquisition terminal.

7. The method of claim 6, wherein the probe data comprises at least one of: water consumption data, electricity consumption data, combustible gas use data and smoke detection data;

8. The method according to claim 6 or 7, wherein the sample data is newly added sample data obtained by the scheduling server from the sample library according to a preset period until a preset number of newly added sample data is obtained; or, the scheduling server monitors the number of newly added sample data in the sample library, and when the number of the newly added sample data reaches the preset number, the newly added sample data of the preset number is acquired from the sample library.

9. The method of claim 6 or 7, wherein obtaining a trained fire safety assessment model comprises:

receiving the confidence of the trained fire safety assessment model;

10. A server, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the fire safety assessment method of any of claims 1-9.

11. A fire safety assessment system, the system comprising: a training server and a security assessment server;

the training server is used for executing the fire safety assessment method of any one of claims 1-5;

the security assessment server is used for executing the fire protection security assessment method of any one of claims 6-9.

12. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, implement the fire safety assessment method of any one of claims 1-9.