Fire-fighting integrated system and method based on cloud platform

Abstract

The invention discloses a fire-fighting integrated system and method based on a cloud platform, and the method comprises the steps: obtaining a video image of a target region, obtaining user data, and calling sensor data; constructing a three-dimensional simulation graph for the target area according to the video image, analyzing a fire hazard danger coefficient of the target area in combination with the sensor data, and marking the fire hazard danger coefficient in the three-dimensional simulation graph; constructing a fire severity thermodynamic diagram in the three-dimensional simulation diagram according to the fire hazard coefficient, and dividing the target area into different areas according to a severity thermodynamic value in the fire severity thermodynamic diagram; and dividing the users into first users and second users according to the self-drop risk value, determining the number and proportion of the first users and the second users in different areas, and performing evacuation guidance on different users in combination with the three-dimensional simulation graph. The method has the characteristics of improving the rescue efficiency and optimizing the system intelligence.

Description

Technical Field

[0001] The present invention relates to the technical field of fire protection integration, and specifically to a fire protection integration system and method based on a cloud platform. Background Art

[0002] At present, significant progress has been made in the development of fire protection integration technology. Especially driven by emerging technologies such as the Internet of Things, artificial intelligence, and big data analysis, intelligent fire protection systems can achieve more efficient fire prevention, monitoring, and emergency response. These systems integrate various sensors, monitoring devices, and communication technologies to provide real-time data collection, intelligent analysis, and automated control, thereby improving the intelligent level of fire safety management. However, when a fire occurs, it is usually dependent on surveillance videos to judge the number of affected people on each floor and the severity of the fire, so as to carry out rescue work accordingly. The circuit system in the target area is extremely vulnerable to damage during a fire, which will cause the floor monitoring devices to malfunction. When the monitoring devices fail and the number of fire rescue users is limited and unable to rescue the affected users on each floor simultaneously, it is very difficult for fire users to accurately judge the severity of the fire and the number of affected people on each floor, resulting in difficulty in effectively judging the rescue emergency situation on each floor, and thus may lead to delays in the rescue of affected users in critical situations. In addition, due to the thick smoke and high temperature at the fire scene, the line of sight and mobility of trapped users will be severely affected, and the panicked mood will further reduce their judgment and decision-making abilities, resulting in them choosing the wrong route or missing the best escape opportunity during escape. Therefore, it is necessary to design a fire protection integration system and method based on a cloud platform to improve rescue efficiency and optimize system intelligence. Summary of the Invention

[0003] The purpose of the present invention is to provide a fire protection integration system and method based on a cloud platform to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solution: A fire protection integration method based on a cloud platform, the running steps of the method include:

[0005] Step S1: Obtain the video image of the target area through a camera device, obtain user data according to the video image, and retrieve sensor data;

[0006] Step S2: Construct a three-dimensional simulation diagram of the target area according to the video image, analyze the fire risk coefficient of the target area in combination with the sensor data, and mark it in the three-dimensional simulation diagram;

[0007] Step S3: Construct a fire severity heat map in the 3D simulation map according to the fire risk coefficient, and divide different regions of the target area according to the severity heat values in the fire severity heat map;

[0008] Step S4: Compare the self - risk reduction values in the user data with the threshold, divide the users with self - risk reduction values greater than the threshold into the first type of users respectively, and those with values less than or equal to the threshold into the second type of users. Determine the quantity and proportion of the first type of users and the second type of users in different regions, and combine with the 3D simulation map to provide evacuation guidance for different users. The self - risk reduction value is used to evaluate the ability of users to reduce risks through their own actions in case of a fire.

[0009] Further, step S1 further includes the following steps:

[0010] Step S11: Obtain the self - risk reduction parameters of users when they enter the target area. The self - risk analysis parameters include respiratory system vulnerability, age and gender, and exercise ability value;

[0011] By obtaining the thermal imaging of the user's face, evaluate the respiratory system vulnerability of the user according to the facial vascular microcirculation in the thermal imaging, identify the age and gender of the user according to the user's face, and quantify the exercise ability value of the user according to the gait extracted from the video image;

[0012] Step S12: Construct a self - risk reduction assessment model according to the self - risk reduction value, input the self - risk reduction parameters into the self - risk reduction assessment model to output the self - risk reduction value of the user, and record the self - risk reduction value in the user data;

[0013] Step S13: Obtain the IMEI number or IMSI number of the user's mobile phone through base station signal detection and record it in the user data, and monitor the position of the user in the target area according to the facial data in real - time;

[0014] Step S14: Assign detection weights to the IMEI numbers or IMSI numbers of all users in the target area according to the self - risk reduction value. The lower the self - risk reduction value of the user, the greater the assigned weight value. The detection weight refers to the priority of positioning according to the IMEI number or IMSI number to avoid the situation that some video images cannot be received due to a fire.

[0015] Further, step S2 further includes the following steps:

[0016] Step S21: Mark the key facilities in the target area in the 3D simulation map. The key facilities refer to those related to personnel safety, fire - fighting facilities, and evacuation channels in the fire emergency evacuation system;

[0017] Step S22: When a fire occurs, divide the target area into grid cells in the 3D simulation map, and analyze the fire risk coefficient of each grid cell at different timestamps based on the video image and sensor data;

[0018] Step S23: Obtain whether there are the fire fighting facilities and the water source area in the grid cells where the fire risk coefficient is lower than the fire risk coefficient threshold, obtain the IMEI number or IMSI number of the first user closest to the fire fighting facilities, and send an instruction to request the fire fighting facilities to extinguish the fire to it.

[0019] Further, step S22 further includes the following steps:

[0020] Step S221: Detect the flame area and the diffusion trajectory of the smoke according to the video image, and obtain visual smoke data, where the visual smoke data includes: the flame growth rate, the smoke coverage, and the smoke movement speed estimated based on the optical flow method;

[0021] Step S222: Calculate the composite hazard value of the sensor nodes according to the temperature sensor data, smoke concentration, CO concentration, and oxygen content in the sensor data;

[0022] Step S223: Analyze the fire risk coefficient of each grid cell according to the visual smoke data and the composite hazard value.

[0023] Further, step S3 further includes the following steps:

[0024] Step S31: Analyze the severity heat value of each grid cell in the fire severity heat map according to the fire risk coefficient;

[0025] Step S32: Divide the area of the severity heat value of each grid cell. When the area where the severity heat value is less than the first threshold is divided into the safe area, when the area where the severity heat value is greater than the first threshold and less than the second threshold is divided into the danger incubation period, and when the area where the severity heat value is greater than the second threshold is divided into the danger area.

[0026] Further, step S4 further includes the following steps:

[0027] Step SA1: Obtain the maximum number of people that each evacuation passage in the key facilities can accommodate, combine the actual number of people currently accommodated in the real-time passage of the evacuation passage to construct a comprehensive safety scoring formula, and calculate the comprehensive safety score of each evacuation passage according to the comprehensive safety scoring formula. The maximum number of people that can be accommodated is the maximum number when there is no overcrowding during emergency evacuation, which may lead to a decrease in the evacuation efficiency;

[0028] Step SA2: Normalize the weights of each evacuation route according to the comprehensive safety score and the corresponding remaining capacity of each evacuation route.

[0029] Step SA3: Extract user data from the 3D simulation map, and separately count the number of people in the dangerous area and the number of people in the dangerous latent area.

[0030] Step SA4: According to the corresponding number of people in the dangerous area and the dangerous latent area and the ratio, and combining the weights of each evacuation route, prioritize the allocation of the people in the dangerous area;

[0031] Subsequently allocate the people in the dangerous latent area, where in the allocation process, the second type of people is given priority, but the ratio of the first type of people to the second type of people is greater than the threshold.

[0032] Step SA5: Send the corresponding evacuation routes to the mobile phones of the users in the dangerous area and the dangerous latent area respectively through the base station signal.

[0033] Furthermore, the system includes a data acquisition module and a 3D simulation map construction module:

[0034] The data acquisition module is used to obtain the video image of the target area through the imaging device, obtain user data according to the video image, and retrieve sensor data;

[0035] The 3D simulation map construction module is used to construct a 3D simulation map of the target area according to the video image, analyze the fire danger coefficient of the target area in combination with the sensor data, and mark it in the 3D simulation map.

[0036] Furthermore, the system further includes a region division module and an evacuation decision module:

[0037] The region division module is used to construct a fire severity heat map in the 3D simulation map according to the fire danger coefficient, and divide different regions of the target area according to the severity heat value in the fire severity heat map;

[0038] The evacuation decision module is used to compare the self-risk reduction value in the user data with the threshold, divide the users with the self-risk reduction value greater than the threshold into the first type of users respectively, and vice versa as the second type of users, determine the quantity and ratio of the first type of users and the second type of users in different regions, and combine the 3D simulation map to provide evacuation guidance for different users. The self-risk reduction value is used to evaluate the ability of users to reduce risks through their own actions in case of fire.

[0039] In a third aspect of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the method described in the first aspect of the present application.

[0040] In a fourth aspect of the present application, there is provided a computer-readable storage medium for storing a computer program. When the computer program runs on a computer, the computer is caused to execute the method described in the first aspect of the present application.

[0041] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The video images obtained by the imaging device of the present invention can not only capture user data in real time, but also quickly construct a three-dimensional simulation map when a fire occurs, providing intuitive and accurate spatial information for fire emergency response. Combining with sensor data, the present invention can deeply analyze the fire risk coefficient of the target area and visually display it in the three-dimensional simulation map, enabling managers to quickly grasp the fire situation. Further, a fire severity heat map is constructed based on the fire risk coefficient, and the target area is divided into a safe area, a latent danger area, and a danger area accordingly, providing a scientific basis for personnel evacuation. By evaluating the self-reducing risk value of users, the self-rescue capabilities of different users in case of fire can be distinguished, so as to formulate a more personalized evacuation guidance plan to ensure the efficiency and safety of the evacuation process. In addition, the comprehensive safety score and remaining capacity of the evacuation passage are also considered, and through normalized weight allocation, the priority evacuation of personnel in the danger area and the latent danger area is realized. During the evacuation process, the present invention can update the user status in real time, monitor the stranded users, and send alarms to rescue personnel in a timely manner, providing strong support for rescue operations, thereby improving the rescue efficiency and optimizing the system intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0043] Figure 1 It is a schematic flowchart diagram of a fire-fighting integration method based on a cloud platform provided in Embodiment 1 of the present invention.

[0044] Figure 2 It is a schematic diagram of the module composition of a fire-fighting integration system based on a cloud platform provided in Embodiment 2 of the present invention.

[0045] Figure 3 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0047] This embodiment can be applied to scenarios where firefighters have not arrived yet when a fire occurs. This method can be executed by a fire protection integration system based on a cloud platform provided in this embodiment. Figure 1 It is a schematic flowchart of a fire protection integration method based on a cloud platform provided in the first embodiment of the present invention. This method specifically includes the following steps:

[0048] Step S1: Obtain video images of the target area through a camera device, and obtain user data and retrieve sensor data according to the video images;

[0049] Step S2: Construct a three-dimensional simulation map of the target area according to the video images, analyze the fire risk coefficient of the target area in combination with the sensor data, and mark it in the three-dimensional simulation map;

[0050] Step S3: Construct a fire severity heat map in the three-dimensional simulation map according to the fire risk coefficient, and divide different areas of the target area according to the severity heat values in the fire severity heat map;

[0051] Step S4: Compare the self-reducing risk value in the user data with the threshold. Users with a self-reducing risk value greater than the threshold are respectively classified as first users, and vice versa as second users. Determine the quantity and proportion of the first users and the second users in different areas, and conduct evacuation guidance for different users in combination with the three-dimensional simulation map. The self-reducing risk value is used to evaluate the ability of users to reduce risks through their own actions in the event of a fire.

[0052] Specifically, by fusing the user body data and position coordinates collected in real time by the camera device, combining the dynamic marking of the fire risk coefficient and the regional classification of the fire severity heat map in the three-dimensional simulation map, and accurately dividing the evacuation priorities of the first users (high self-rescue ability) and the second users (low self-rescue ability) based on the self-reducing risk value, an intelligent evacuation system of "data-driven, hierarchical management, and precise guidance" in the fire scenario is realized. Through the deep integration and real-time analysis of multi-dimensional data (user ability, fire situation dynamics, spatial structure), it is possible to dynamically optimize the evacuation path allocation, give priority to ensuring the escape safety of users with low self-rescue ability, and at the same time use the three-dimensional simulation map to visually guide the rapid evacuation of people in high-risk areas, significantly improving the evacuation efficiency and success rate, reducing secondary risks caused by crowding, misjudgment or information lag, and comprehensively enhancing the scientific and humanized level of fire emergency response.

[0053] In some preferred embodiments, step S1 further includes the following steps:

[0054] Step S11: Obtain the user's self-reduction risk parameters when the user enters the target area. The self-reduction analysis parameters include respiratory system vulnerability, age and gender, and exercise ability value;

[0055] By obtaining the thermal image of the user's face, evaluate the respiratory system vulnerability R of the user according to the microcirculation of facial blood vessels in the thermal image, identify the age A and gender of the user according to the user's face, and extract the user's gait from the video image to quantify the exercise ability value M; g and gender, and extract the user's gait from the video image to quantify the exercise ability value M;

[0056] Step S12: Construct a self-reduction risk assessment model Q according to the self-reduction risk value:

[0057]

[0058] In the formula, α1 and α2 represent weight coefficients, k1 represents the attenuation coefficient, G = 1.2 represents female students, G = 1.0 represents male students, A0 represents the standard age, M base represents the reference exercise ability value, H struc represents, and η represents a constant;

[0059] Input the self-reduction risk parameters into the self-reduction risk assessment model to output the user's self-reduction risk value, and record the self-reduction risk value in the user data;

[0060] Step S13: Obtain the IMEI number or IMSI number of the user's mobile phone through base station signal detection and record it in the user data, and monitor the position of the user in the target area in real time according to the facial data;

[0061] Step S14: Assign detection weights to the IMEI numbers or IMSI numbers of all users in the target area according to the self-reduction risk value. The lower the self-reduction risk value of the user, the greater the assigned weight value. When the self-reduction risk value is lower than the threshold, perform real-time detection on the user to judge the security of the user. The detection weight refers to the priority of positioning according to the IMEI number or IMSI number to avoid the situation that some video images cannot be received due to a fire.

[0062] Specifically, by automatically obtaining the user's age, gender, and physical health indicators through facial data, the rapid identification of the user's physiological characteristics is realized, providing a data basis for evaluating the individual's escape ability; by matching the body data with the self-reducing risk database to generate a self-reducing risk value, the dynamic quantification of the user's self-rescue ability in a fire is realized, providing a scientific basis for preferentially evacuating low-ability people (the second user); by binding the user's mobile phone IMEI / IMSI number through the base station signal and combining the facial data for real-time positioning, the continuous tracking and dynamic update of the user's location are realized, ensuring that the evacuation instructions can be accurately pushed to specific personnel within the target area, avoiding omission or misjudgment.

[0063] In some preferred embodiments, the step S2 further includes the following steps:

[0064] Step S21: Mark the key facilities within the target area in the three-dimensional simulation diagram. The key facilities refer to those that are important for personnel safety, fire-fighting facilities, and evacuation channels in the fire emergency evacuation system;

[0065] Step S22: When a fire occurs, divide the target area into 1m×1m grid cells in the three-dimensional simulation diagram. Each grid cell includes: spatial coordinates (x, y), time stamp t. Analyze the fire risk coefficient of each grid cell at different time stamps based on the video image and sensor data;

[0066] Step S23: Check whether there are the fire-fighting facilities and the water source area within the grid cells whose fire risk coefficient is lower than the fire risk coefficient threshold. Obtain the IMEI number or IMSI number of the first user closest to the fire-fighting facilities, and send a request for the fire-fighting facilities to extinguish the fire instruction to it.

[0067] Specifically, by constructing a three-dimensional simulation diagram based on the video image and accurately marking key facilities such as evacuation channels, fire-fighting facilities, and water source areas, combined with the 1m×1m grid-based dynamic division of the target area during a fire and the fusion analysis of multi-source data (video, sensors), the refined real-time monitoring and spatial visualization of the fire risk coefficient are realized. The system can quickly locate high-risk spreading areas, dynamically update the evacuation path planning, and at the same time optimize the allocation efficiency of emergency resources (such as fire hydrants, water sources), significantly improving the fire response speed and the scientific nature of evacuation decisions, and maximizing the protection of personnel safety and reducing disaster losses.

[0068] In some preferred embodiments, the step S22 further includes the following steps:

[0069] Step S221: Detect the flame area and the diffusion trajectory of the smoke according to the video image, and obtain visual smoke data. The visual smoke data includes: the flame growth rate G f 、the smoke coverage Cs and estimating the moving speed of the smoke based on the optical flow method In the formula, p t represents the smoke position at time t, p t-1 represents the smoke position at time t-1, and Δt represents the change in time;

[0070] Step S222: Calculate the composite hazard value of the sensor node according to the temperature sensor data, smoke concentration, CO concentration and oxygen content in the sensor data: In the formula, α, β, γ, δ represent weight coefficients, and T i represents the i-th temperature sensor data, and S i represents the i-th smoke concentration data, CO i represents the i-th CO sensor data, and O 2i represents the i-th oxygen sensor data;

[0071] Step S223: Analyze the fire hazard coefficient of each grid cell according to the visual smoke data and the composite hazard value: In the formula, H(x, y, t) represents the fire hazard coefficient at the t-th moment at the coordinates (x, y), ω1 and ω2 represent weight coefficients, and H crit represents the critical hazard threshold, and ∈ represents a small amount to prevent division by zero error.

[0072] Specifically, by integrating video image analysis technology to real-time monitor the flame growth rate, smoke coverage, and smoke moving speed, combining the composite hazard value calculation model of multi-sensor data (temperature, smoke concentration, CO concentration, oxygen content), and constructing the fire hazard coefficient of the grid cell based on dynamic weight allocation and non-linear function (such as hyperbolic tangent function), the multi-dimensional accurate assessment and spatial dynamic modeling of fire risk are realized. Through the deep integration of visual and sensor data, the trend of fire spread can be captured in real time, the danger level of local areas can be quantified, providing a scientific basis for the dynamic optimization of evacuation routes and the precise allocation of emergency resources, significantly enhancing the situation awareness ability and emergency response efficiency in fire scenarios, and effectively reducing the risk of casualties and secondary disasters.

[0073] In some preferred embodiments, the step S3 further includes the following steps:

[0074] Step S31: Construct a fire severity heat map for the three-dimensional simulation diagram according to the magnitude of the fire hazard coefficient. Among them, obtain the maximum value H of the fire hazard coefficient that is the closest to the perimeter of each grid cell max and the distance d between the two, and calculate the severity heat value of each grid cell In the formula, H represents the fire hazard coefficient of the current grid cell;

[0075] Step S32: Divide the severity heat values of each grid cell into regions. When the region where the severity heat value is less than the first threshold is divided into the safe area, when the region where the severity heat value is greater than the first threshold and less than the second threshold is divided into the dangerous latency period, and when the region where the severity heat value is greater than the second threshold is divided into the dangerous area.

[0076] Specifically, by combining the dynamic relationship between the fire danger coefficient and the maximum surrounding danger value, a fire severity heat map is constructed, and based on the heat value threshold, a scientific division of the target area into a safe area, a dangerous latency area, and a dangerous area is realized, achieving precise identification of the spatial classification of fire risks and dynamic visualization. By quantifying the fire spread trend and local danger gradient, it can reflect the fire spread direction and potential high-risk areas in real time, providing data support for the dynamic adjustment of evacuation routes and the targeted allocation of rescue resources, significantly improving the regional control efficiency and emergency decision-making reliability in fire scenarios, effectively preventing people from entering dangerous areas and reducing the overall disaster losses.

[0077] In some preferred embodiments, step S4 further includes the following steps:

[0078] Step SA1: Obtain the maximum number of people N that each evacuation passage in the key facilities can accommodate, max and construct a comprehensive safety score formula by combining the current actual number of people in the real-time passage of the evacuation passage, and calculate the comprehensive safety score of each evacuation passage according to the comprehensive safety score formula: In the formula, S j represents the comprehensive safety score of the j-th evacuation passage, N j represents the number of people currently on the j-th evacuation passage, λ represents the path length sensitivity coefficient, L j represents the length of the j-th evacuation passage, W j represents the effective width of the j-th evacuation passage, and the maximum number of people that can be accommodated is the maximum number when there is no overcrowding during emergency evacuation, which may lead to a decrease in evacuation efficiency;

[0079] Step SA2: Normalize the weights of each evacuation passage according to the comprehensive safety score and the corresponding remaining capacity of each evacuation passage: In the formula, k represents the number of evacuation passages;

[0080] Step SA3: Extract user data from the 3D simulation diagram, and respectively count the number of people P1 in the dangerous area and the number of people P2 in the dangerous latency area;

[0081] Step SA4: According to the number of corresponding personnel in the danger area and the latent danger area and the ratio, and combining the weights of each evacuation passage, prioritize the allocation of the personnel in the danger area: In the formula, represents the weight coefficient;

[0082] Subsequently allocate the personnel in the latent danger area: A 2,j = τ·P2·ω j , where τ represents the weight coefficient. Among them, during the allocation process, the second personnel are given priority, but the ratio of the first personnel to the second personnel is greater than the threshold. Among them, during the evacuation process of the user, the self-risk reduction value of the second user is relatively low, and they need to be prioritized first. However, in an emergency, their self-escape ability is relatively weak, and they can receive timely help from the first personnel when problems occur during the escape process of the second user;

[0083] Step SA5: Send the corresponding evacuation passages to the mobile phones of the users in the danger area and the latent danger area respectively through the base station signal.

[0084] Specifically, by calculating the comprehensive safety score based on the real-time occupancy, path length, and effective width of the evacuation passage, and combining the normalized weight allocation to dynamically optimize the passage priority, a scientific quantitative evaluation and dynamic scheduling of the evacuation resources are realized. By distinguishing the personnel in the danger area and the latent danger area, and introducing the weight coefficient of the user's self-risk reduction value, the evacuation safety of low-self-risk users (the second personnel) is preferentially guaranteed. At the same time, through threshold control, it is ensured that high-risk users (the first personnel) provide assistance when necessary, forming a mutual assistance mechanism. In addition, by using the base station signal to push the evacuation instructions to the user's mobile phone in real time, accurate guidance of the evacuation path and information synchronization are realized. The personnel diversion efficiency in an emergency is improved, the evacuation needs of high-risk and low-risk groups are balanced, and at the same time, through dynamic data-driven decision-making, the congestion risk and the probability of secondary disasters are minimized, ensuring the safety and efficiency of the overall evacuation process.

[0085] In some optional embodiments, step S4 further includes the following steps:

[0086] Step SB1: Update in real time whether the user enters the safe area, and judge whether there are any stranded users in the danger area and the latent area. When it is determined that there are no stranded users, no user protection guidance is formulated;

[0087] Step SB2: When it is determined that there are stranded users in the latent area, locate the specific position of the user by obtaining the corresponding IMEI number or IMSI number in the user data, highlight the key facilities around the stranded user in the 3D simulation diagram, automatically send an alarm to the rescue personnel, and display the 3D simulation diagram and the detailed data of the stranded user, waiting for the instructions of the rescue personnel.

[0088] Specifically, by real-time monitoring of user location data and dynamically updating the status of the safe area, accurately positioning the users staying in the latent area in combination with the IMEI / IMSI number, and highlighting the key facilities (such as fire corridors, water source areas, etc.) around them in the 3D simulation map, the rapid identification of the stranded personnel and the directional linkage of rescue resources are realized. Through automated alarm push and real-time synchronization of rescue personnel and 3D scene data, this technical solution significantly shortens the emergency response time, ensures that the stranded users (especially those with low self-risk reduction ability) can be quickly located and obtain rescue support, and at the same time avoids secondary risks caused by information delay, comprehensively improving the personnel safety guarantee and rescue operation efficiency in the fire scene.

[0089] Based on the same inventive concept as the above method embodiment, the embodiment of the present invention also provides a fire integration system based on a cloud platform. Figure 2 It is a schematic diagram of the module composition of a fire integration system based on a cloud platform provided by the embodiment of the present invention. As Figure 2 shown, the system includes a data acquisition module, a 3D simulation map construction module, a region division module, and an evacuation decision module:

[0090] The data acquisition module is used to obtain the video image of the target area through a camera device, obtain user data according to the video image, and retrieve sensor data;

[0091] The 3D simulation map construction module is used to construct a 3D simulation map of the target area according to the video image, analyze the fire danger coefficient of the target area in combination with the sensor data, and mark it in the 3D simulation map;

[0092] The region division module is used to construct a fire severity heat map in the 3D simulation map according to the fire danger coefficient, and divide different regions of the target area according to the severity heat value in the fire severity heat map;

[0093] The evacuation decision module is used to compare the self-risk reduction value in the user data with a threshold, classify the users with the self-risk reduction value greater than the threshold as first users respectively, and the others as second users, determine the quantity and proportion of the first users and the second users in different regions, and conduct evacuation guidance for different users in combination with the 3D simulation map. The self-risk reduction value is used to evaluate the ability of users to reduce risks through their own actions in the event of a fire.

[0094] It should be noted that although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0095] Based on the same inventive concept as the above method embodiment, an electronic device is further provided in an embodiment of the present application, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the control method in the above embodiment.

[0096] In one embodiment, the electronic device may be a server. In this embodiment, the structure of the electronic device may be as Figure 3 shown, including a memory 2001, a communication module 2003, and one or more processors 2002.

[0097] The memory 2001 is used to store the computer program executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and programs required to run the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0098] The memory 2001 may be a volatile memory, such as a random-access memory (RAM); the memory 2001 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); or the memory 2001 is any other medium that can be used to carry or store the desired computer program in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2001 may be a combination of the above memories.

[0099] The processor 2002 may include one or more central processing units (CPUs) or be a digital processing unit, etc. The processor 2002 is used to implement the above audio data processing method when calling the computer program stored in the memory 2001.

[0100] The communication module 2003 is used to communicate with terminal devices and other servers.

[0101] In the embodiments of the present application, the specific connection medium between the above-mentioned memory 2001, communication module 2003 and processor 2002 is not limited. In the embodiments of the present application Figure 3 it is described that the memory 2001 and the processor 2002 are connected through a bus 2004, and the bus 2004 is described by an arrow in Figure 3 The connection manners between other components are only for illustrative purposes and are not to be construed as limiting. The bus 2004 may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of description, Figure 3 only one arrow is used for description in

[0102] Based on the same inventive concept as the above method embodiments, an embodiment of the present invention further provides a computer-readable storage medium, which is used to store a computer program. When the computer program runs on a computer, the electronic device is enabled to implement the control method in the above embodiments. The computer-readable storage medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0103] Based on the same inventive concept as the above method embodiments, an embodiment of the present invention further provides a computer program product, which includes a computer program. When the program product runs on an electronic device, the computer program is used to cause the electronic device to execute the steps in the control method according to various exemplary embodiments of the present application described above in this specification. The program product may adopt any combination of one or more readable media. These computer program instructions may be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or Figure 1 one block or multiple blocks.

[0104] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

Claims

1. A fire integration method based on a cloud platform, characterized in that: Obtain video images of a target area through a camera device, obtain user data and retrieve sensor data according to the video images; Construct a three-dimensional simulation map of the target area according to the video images, analyze the fire risk coefficient of the target area in combination with the sensor data and mark it on the three-dimensional simulation map; Construct a fire severity heat map in the three-dimensional simulation map according to the fire risk coefficient, and divide different areas of the target area according to the severity heat values in the fire severity heat map; Compare the self-reducing risk value in the user data with a threshold value, divide the users with a self-reducing risk value greater than the threshold value into first users respectively, and vice versa as second users, determine the quantity and proportion of the first users and the second users in different areas, and conduct evacuation guidance for different users in combination with the three-dimensional simulation map. The self-reducing risk value is used to evaluate the ability of users to reduce risks through their own actions in case of a fire.

2. The fire protection integration method based on a cloud platform according to claim 1, characterized in that: The obtaining video images of a target area through a camera device, obtaining user data and retrieving sensor data according to the video images includes: Obtain the thermal imaging of the user's face, evaluate the respiratory system vulnerability of the user according to the facial blood microcirculation in the thermal imaging, identify the age and gender of the user according to the user's face, and extract the user's gait from the video image to quantify the user's motor ability value; Construct a self-reducing risk assessment model according to the self-reducing risk value, input the self-reducing risk parameters into the self-reducing risk assessment model to output the self-reducing risk value of the user, and record the self-reducing risk value in the user data; Obtain the IMEI number or IMSI number of the user's mobile phone through base station signal detection and record it in the user data, and monitor the position of the user in the target area in real time according to the facial data; Assign detection weights to the IMEI numbers or IMSI numbers of all users in the target area according to the self-reducing risk value. The lower the self-reducing risk value, the greater the weight value assigned. The detection weight refers to the priority of positioning according to the IMEI number or IMSI number to avoid the situation that some video images cannot be received due to a fire.

3. The fire protection integration method based on a cloud platform according to claim 2, wherein: The constructing a three-dimensional simulation map of the target area according to the video images, analyzing the fire risk coefficient of the target area in combination with the sensor data and marking it on the three-dimensional simulation map includes: Mark key facilities in the target area in the three-dimensional simulation map. The key facilities refer to facilities for personnel safety, fire fighting facilities and evacuation channels in the fire emergency evacuation system; When a fire occurs, divide the target area into grid cells in the three-dimensional simulation map, and analyze the fire risk coefficient of each grid cell at different time stamps according to the video images and sensor data; Obtain whether there are the fire fighting facilities and the water source area in the grid cells with a fire risk coefficient lower than the fire risk coefficient threshold, obtain the IMEI number or IMSI number of the first user closest to the fire fighting facilities, and send a request for the fire fighting facilities to extinguish the fire instruction to it.

4. The fire protection integration method based on a cloud platform according to claim 3, characterized in that: When a fire occurs, the target area is divided into grid cells in the 3D simulation map, and the fire risk coefficient of each grid cell at different timestamps is analyzed according to the video image and sensor data, including: Detect the flame area and the diffusion trajectory of the smoke according to the video image to obtain visual smoke data; Calculate the composite risk value of the sensor nodes according to the sensor data in the sensor data; Dynamically couple according to the visual smoke data and the composite risk value to obtain the fire risk coefficient of each grid cell.

5. The fire protection integration method based on a cloud platform according to claim 4, characterized in that: Construct a fire severity heat map in the 3D simulation map according to the fire risk coefficient, and divide the target area into different areas according to the severity heat value in the fire severity heat map, including: Analyze the severity heat value of each grid cell in the fire severity heat map according to the fire risk coefficient; Perform area division on the severity heat value of each grid cell. When the severity heat value is less than the first threshold, the area is divided into the safe area. When the severity heat value is greater than the first threshold and less than the second threshold, the area is divided into the dangerous latency period. When the severity heat value is greater than the second threshold, the area is divided into the dangerous area.

6. The fire integration method based on a cloud platform according to claim 5, characterized in that: Compare the self-risk reduction value in the user data with the threshold, divide the users with the self-risk reduction value greater than the threshold into the first users respectively, and vice versa for the second users. Determine the number and proportion of the first users and the second users in different areas, and combine the 3D simulation map to provide evacuation guidance for different users, including: Obtain the maximum number of people that each evacuation passage in the key facilities can accommodate, combine the actual number of people currently accommodated in the real-time passage of the evacuation passage to construct a comprehensive safety score formula, and calculate the comprehensive safety score of each evacuation passage according to the comprehensive safety score formula. The maximum number of people that can be accommodated is the maximum number when there is no overcrowding during emergency evacuation, which may lead to a decrease in the evacuation efficiency; Normalize the weights of each evacuation passage according to the comprehensive safety score and the corresponding remaining capacity of each evacuation passage; Extract user data from the 3D simulation map, and respectively count the number of people in the dangerous area and the number of people in the dangerous latency area; According to the corresponding number of people and the proportion in the dangerous area and the dangerous latency area, and combine the weights of each evacuation passage to give priority to the allocation of the people in the dangerous area; Perform subsequent allocation on the people in the dangerous latency area. During the allocation process, give priority to the second type of people, but the ratio of the first type of people to the second type of people is greater than the threshold; Send the corresponding evacuation passage to the mobile phones of the users in the dangerous area and the dangerous latency area through the base station signal.

7. A fire protection integration system based on a cloud platform, characterized in that: The system includes a data acquisition module and a 3D simulation map construction module: The data acquisition module is used to obtain the video image of the target area through a camera device, obtain user data according to the video image, and retrieve sensor data; The three-dimensional simulation map construction module is used to construct a three-dimensional simulation map of the target area based on the video image, analyze the fire risk coefficient of the target area in combination with the sensor data, and mark it on the three-dimensional simulation map.

8. The fire protection integration system based on a cloud platform according to claim 7, characterized in that: The system further includes a region division module and an evacuation decision-making module: The region division module is used to construct a fire severity heat map in the three-dimensional simulation map according to the fire risk coefficient, and divide different regions of the target area according to the severity heat values in the fire severity heat map; The evacuation decision-making module is used to compare the self-risk reduction value in the user data with a threshold, divide the users with the self-risk reduction value greater than the threshold into first users respectively, and vice versa as second users, determine the quantity and proportion of the first users and the second users in different regions, and conduct evacuation guidance for different users in combination with the three-dimensional simulation map. The self-risk reduction value is used to evaluate the ability of users to reduce risks through their own actions in case of a fire.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the electronic device implements the method described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program. When the computer program runs on a computer, the computer executes the method described in any one of claims 1 to 6.

Images