Intelligent fire-fighting collaborative early warning method and system

Abstract

The invention provides an intelligent fire-fighting collaborative early warning method and system, and the method comprises the steps: obtaining environment parameters at a current collection moment, the environment parameters comprising environment temperature, environment brightness and haze concentration, and obtaining a target fire-fighting early warning parameter type according to the environment parameters and a preset fire-fighting early warning parameter prediction model; according to the method, a single target fire-fighting early warning parameter is determined from various heterogeneous data and multi-source data according to environmental parameters, a corresponding target fire-fighting early warning parameter set is acquired according to the type of the target fire-fighting early warning parameter, and whether early warning information is output or not is determined according to the target fire-fighting early warning parameter set. According to the technical scheme, combination of traditional single data early warning and multi-source data fusion early warning is achieved, correspondingly, the problem that traditional single data early warning is low in accuracy is solved, the problems that multi-source data fusion early warning is complex in calculation and poor in timeliness are solved, and therefore timeliness and early warning accuracy can be taken into consideration.

Description

Technical Field

[0001] This application relates to the field of smart fire protection technology, and in particular to a smart fire collaborative early warning method and system. Background Technology

[0002] Fire safety is an important safeguard for people's lives and property. Among them, fire early warning is an effective measure to reduce losses. In cities, where people are densely populated and buildings are relatively large, it is even more necessary to do a good job in fire early warning.

[0003] Traditional fire alarm systems rely on single sensors, such as temperature or smoke sensors, for fire detection. However, this single detection method often proves insufficient in complex environments. For example, in hot weather, temperature sensors are easily interfered with, leading to frequent false alarms and missed alarms.

[0004] Therefore, in existing technologies, with the advancement of big data technology, in order to improve the accuracy of early warnings, various front-end devices such as sensors, monitoring equipment, alarms, and cameras are used to obtain massive amounts of multi-source heterogeneous and multimodal data. The accuracy of early warnings is improved by multi-source data fusion, for example, by calculating the confidence level between multi-source data and obtaining the consistency between multi-source data, thereby improving the accuracy of early warnings.

[0005] However, due to the large size of the city and the massive amount of data obtained, the fusion of multi-source data requires a large amount of data processing and calculation, which takes a certain amount of time and affects the timeliness of police alerts, leading to delays in police alerts. Summary of the Invention

[0006] This application provides a smart fire protection collaborative early warning method and system to solve the technical problems mentioned in the background art.

[0007] In a first aspect, this application provides a smart fire protection collaborative early warning method, including: acquiring environmental parameters at the current acquisition time, wherein the environmental parameters include: ambient temperature, ambient brightness, and haze concentration; Based on environmental parameters and a preset fire warning parameter prediction model, a target fire warning parameter type is obtained. The target fire warning parameter type is one of temperature information, smoke detection information, and image information. The temperature information is the temperature of the fire monitoring area obtained by a temperature sensor, the smoke detection information is the smoke concentration of the fire monitoring area obtained by a smoke sensor, and the image information is an image of the fire monitoring area obtained by a video shooting device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type that matches the environmental parameters from the temperature information, the smoke detection information, and the image information. Based on the target fire warning parameter type, obtain the corresponding target fire warning parameter set; Based on the target fire early warning parameter set, determine whether to output early warning information.

[0008] Optionally, before obtaining the target fire warning parameter type based on environmental parameters and a preset fire warning parameter prediction model, the method further includes: Acquire multiple sets of historical environmental parameters and historical fire early warning information, as well as historical temperature information, historical smoke detection information, and historical image information; Based on the prediction model of each group of historical environmental parameters and initial fire warning parameters, the prediction results are obtained; Based on the historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information, determine the type of historical target fire early warning parameters; The initial fire warning parameter prediction model is trained based on the historical target fire warning parameter type and the prediction result to obtain the preset fire warning parameter prediction model.

[0009] Optionally, determining the type of historical target fire early warning parameters based on the historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information includes: The historical temperature information, historical smoke detection information, and historical image information are used to obtain corresponding historical prediction and early warning information. Based on the historical temperature information, historical smoke detection information, historical image information, corresponding historical predicted early warning information, and the historical actual early warning information, the type of historical target fire early warning parameter is determined.

[0010] Optionally, obtaining the corresponding target fire warning parameter set based on the target fire warning parameter type includes: Based on the target fire warning parameter type, obtain the target fire warning parameter set between the historical time and the current collection time.

[0011] Optionally, the environmental parameters may further include: the location corresponding to the environmental parameters; The step of obtaining the corresponding target fire warning parameter set according to the target fire warning parameter type includes: Based on the location corresponding to the environmental parameters, determine the target fire early warning parameter set at the location corresponding to the environmental parameters.

[0012] Optionally, determining whether to output warning information based on the target fire warning parameter set includes: Based on the target fire early warning parameter set and time series model, the actual early warning level is output; When the actual warning level is greater than the preset warning level, the warning information is output.

[0013] Secondly, this application provides a smart fire-fighting collaborative early warning system, comprising: The acquisition module is used to acquire environmental parameters at the current acquisition time. Environmental parameters include: ambient temperature, ambient brightness, and haze concentration. The model processing module is used to obtain the target fire warning parameter type based on environmental parameters and a preset fire warning parameter prediction model. The target fire warning parameter type is one of temperature information, smoke detection information, and image information. Temperature information is the temperature of the fire monitoring area obtained by a temperature sensor, smoke detection information is the smoke concentration of the fire monitoring area obtained by a smoke sensor, and image information is an image of the fire monitoring area obtained by a video shooting device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type that matches the environmental parameters from the temperature information, smoke detection information, and image information. The acquisition module is also used to acquire the corresponding target fire warning parameter set based on the target fire warning parameter type; The prediction module is used to determine whether to output a warning message based on the target fire warning parameter set.

[0014] Optionally, before the model processing module predicts the model based on environmental parameters and preset fire warning parameters to obtain the target fire warning parameter type, the training module is used for: Acquire multiple sets of historical environmental parameters and historical fire early warning information, as well as historical temperature information, historical smoke detection information, and historical image information; The prediction results are obtained based on the prediction model for each set of historical environmental parameters and initial fire warning parameters; Based on historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information, determine the type of historical target fire early warning parameters; Based on the historical target fire warning parameter types and prediction results, the initial fire warning parameter prediction model is trained to obtain the preset fire warning parameter prediction model.

[0015] Optionally, when determining the type of historical target fire warning parameters based on historical temperature information, historical smoke detection information, historical image information, and historical fire warning information, the training module is specifically used for: Historical temperature information, historical smoke detection information, and historical image information are used to obtain corresponding historical forecast and early warning information. Based on historical temperature information, historical smoke detection information, historical image information, and corresponding historical predicted early warning information and historical actual early warning information, the types of historical target fire early warning parameters are determined.

[0016] Optionally, when the acquisition module obtains the corresponding target fire warning parameter set based on the target fire warning parameter type, it is specifically used for: Based on the target fire warning parameter type, obtain the target fire warning parameter set between the historical time and the current collection time.

[0017] Optionally, environmental parameters may also include: the location corresponding to the environmental parameters; When the acquisition module retrieves the corresponding target fire warning parameter set based on the target fire warning parameter type, it is specifically used for: Based on the location corresponding to the environmental parameters, determine the target fire early warning parameter set at the location corresponding to the environmental parameters.

[0018] Optionally, when the prediction module determines whether to output a warning message based on the target fire warning parameter set, it is specifically used for: Based on the target fire warning parameter set and time series model, the actual warning level is output; When the actual warning level is greater than the preset warning level, the warning information is output. Thirdly, this application provides a terminal device, including: a processor and a memory; The memory stores instructions that the computer executes; The processor executes computer execution instructions stored in memory, causing the processor to perform the method as described in any of the first aspects.

[0019] Fourthly, embodiments of this application provide a readable storage medium including a program or instructions that, when run on a computer, execute the method described in any of the first aspects above.

[0020] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0021] The intelligent fire-fighting collaborative early warning method and system provided in this application acquires environmental parameters at the current acquisition time, including ambient temperature, ambient brightness, and haze concentration. Based on the environmental parameters and a preset fire-fighting early warning parameter prediction model, a target fire-fighting early warning parameter type is obtained. This allows a single target fire-fighting early warning parameter to be determined from various heterogeneous and multi-source data based on the environmental parameters. The target fire-fighting early warning parameter type is one of temperature information, smoke detection information, or image information. The temperature information is the temperature of the fire monitoring area obtained by a temperature sensor, the smoke detection information is the smoke concentration of the fire monitoring area obtained by a smoke sensor, and the image information is an image of the fire monitoring area obtained by a video shooting device. The preset fire-fighting early warning parameter prediction model is used to determine the target fire-fighting early warning parameter type that matches the environmental parameters from the temperature information, smoke detection information, and image information. Based on the target fire-fighting early warning parameter type, a corresponding target fire-fighting early warning parameter set is obtained, and based on the target fire-fighting early warning parameter set, it is determined whether to output early warning information. This embodiment combines traditional single-data early warning with multi-source data fusion early warning. Accordingly, the solution in this embodiment solves the problem of low accuracy in traditional single-data early warning and the problem of complex calculation and poor timeliness in multi-source data fusion early warning, thus achieving a balance between timeliness and early warning accuracy. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart of a smart fire-fighting collaborative early warning method provided in an embodiment of this application; Figure 2 A flowchart illustrating the training process of a preset fire early warning parameter prediction model provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a smart fire-fighting collaborative early warning system provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application are described clearly and completely below. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are also within the scope of protection of this application.

[0025] For urban fire early warning systems, existing technologies increasingly employ multi-data fusion methods. These methods utilize various detection devices, such as sensors, monitoring equipment, alarms, and cameras, to acquire massive amounts of multi-source, heterogeneous, and multimodal data. The fusion of this multi-source, heterogeneous, and multimodal data is then used to issue early warnings. While this multi-data fusion method can significantly improve the accuracy of early warnings, it requires complex data processing and computation on massive amounts of multi-source, heterogeneous, and multimodal data. This process is time-consuming and impacts the timeliness of early warnings, potentially leading to delays.

[0026] Therefore, to address the technical problems existing in the prior art, this application proposes a smart fire-fighting collaborative early warning method and system. This method combines traditional single-sensor early warning methods with existing multi-data fusion methods. Since environmental parameters affect the degree of influence of various data points in multi-source heterogeneous and multi-modal data on early warning, for example, temperature sensors are easily interfered with when the temperature is high, and smoke sensors are easily interfered with when there is a lot of smog in the air. Therefore, by selecting a single fire-fighting parameter that is more accurate for early warning from multi-source heterogeneous and multi-modal data based on environmental parameters, and using this single fire-fighting parameter for early warning, the amount of data processing and calculation is reduced, the early warning process is simplified, and delays in early warning are avoided. This allows the method of this application to balance efficiency and early warning accuracy.

[0027] Figure 1 This is a flowchart illustrating a smart fire-fighting collaborative early warning method provided in an embodiment of this application. The executing entity of the method shown in this embodiment can be a terminal device equipped with a smart fire-fighting collaborative early warning system, such as a server. Figure 1 As shown, the method in this embodiment includes: S101. Obtain the environmental parameters at the current collection time. The environmental parameters include: ambient temperature, ambient brightness, and haze concentration.

[0028] In this step, when a fire occurs, the temperature in the area where the fire is located will rise. However, when the ambient temperature is high, it will affect the temperature sensor in the area where the fire is located. For example, when the ambient temperature is high, the temperature sensor in the area where the fire is located will detect a higher temperature. In this case, it will be mistakenly thought that a fire has occurred, thus generating an incorrect warning message. Therefore, when the ambient temperature is high, it is not suitable to determine whether a fire has occurred based on temperature information.

[0029] Regarding ambient brightness, when a fire occurs, the pixel values ​​corresponding to the fire area in the image are higher. When the ambient brightness is high, such as during the day, even if there is no fire, the brightness of the captured image is also high. Therefore, even if a fire occurs, the brightness area in the image is less visually distinguishable from other areas. When the ambient brightness is low, once a fire occurs, the brightness area in the image is more clearly distinguishable from other areas from the viewing angle. Therefore, ambient brightness has a significant impact on determining whether a fire has occurred through image information.

[0030] When a fire occurs, a large amount of smoke is produced. Smoke can be detected by smoke sensors to confirm the fire. However, when the concentration of smog in the air is high, smoke sensors may also detect smoke, mistaking the smog for smoke from a fire and thus generating false fire warnings. Therefore, when the concentration of smog is high, it is generally not suitable to use smoke detection information to confirm whether a fire has occurred.

[0031] Therefore, it is necessary to monitor ambient temperature, ambient brightness, and haze concentration to obtain the corresponding environmental parameters.

[0032] It should be noted that this embodiment only shows the acquisition of ambient temperature, ambient brightness, and haze concentration. In practice, other environmental parameters that may affect alarm warnings can also be obtained, such as humidity. This application does not limit this.

[0033] S102. Based on environmental parameters and a preset fire warning parameter prediction model, obtain the target fire warning parameter type. The target fire warning parameter type is one of temperature information, smoke detection information, or image information. Temperature information is the temperature of the fire monitoring area obtained through a temperature sensor, smoke detection information is the smoke concentration of the fire monitoring area obtained through a smoke sensor, and image information is an image of the fire monitoring area obtained through a video shooting device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type that matches the environmental parameters from the temperature information, smoke detection information, and image information.

[0034] In this step, the city contains multiple fire monitoring areas, such as schools, shopping malls, and residential buildings. For each fire monitoring area, temperature sensors, smoke sensors, and video recording equipment are installed at corresponding locations to collect temperature, smoke, and image information. After collecting the temperature, smoke, and image information, it is stored in a database for future data retrieval.

[0035] After obtaining the environmental parameters corresponding to the current acquisition time, the environmental parameters are input into the preset fire warning parameter prediction model so that the preset fire warning parameter prediction model can determine the target fire warning parameter type from temperature information, smoke detection information and image information based on the environmental parameters.

[0036] The preset fire early warning parameter prediction model is obtained through pre-training, and its training process is described in the following embodiment.

[0037] S103. Obtain the corresponding target fire warning parameter set according to the target fire warning parameter type.

[0038] In this step, after identifying the target fire warning parameter type, the corresponding target fire warning parameter set is retrieved from the database. For example, if the target fire warning parameter type is temperature information, the temperature information set collected from the fire monitoring area is retrieved from the database.

[0039] Optionally, one specific implementation of S103 is: based on the target fire warning parameter type, obtain the target fire warning parameter set between the historical time and the current collection time.

[0040] Specifically, in this embodiment, environmental parameters can be collected every 5 minutes. After determining the target fire warning parameter type based on the environmental parameters, all target fire warning parameters between the historical time and the current time are obtained and sorted in chronological order to form a target fire warning parameter set.

[0041] The time between the historical moment and the current acquisition moment must include at least the previous acquisition moment. This way, the target fire warning parameters corresponding to all target fire warning parameter types under the environmental parameters corresponding to the current acquisition moment can be obtained, thereby improving the accuracy of the warning.

[0042] Optionally, environmental parameters also include: the location corresponding to the environmental parameters; correspondingly, based on the target fire warning parameter type, the corresponding target fire warning parameter set is obtained, including: Based on the location corresponding to the environmental parameters, determine the target fire early warning parameter set at the location corresponding to the environmental parameters.

[0043] Specifically, cities have large areas, and different environmental monitoring areas within the same city have different environmental parameters, such as weather conditions. For example, some environmental monitoring areas in the same city may experience cloudy or rainy weather, while others may experience sunny weather. Therefore, cities are divided into multiple environmental monitoring areas, for example, based on administrative divisions or grids. In this way, when determining the target fire warning parameter type for a fire monitoring area within each environmental monitoring area, the environmental parameters of that area can be used to determine the target fire warning parameter type, resulting in more accurate warnings.

[0044] Therefore, the environmental parameters also include the location corresponding to the environmental parameters, that is, the environmental monitoring area where the environmental parameters are collected, in order to distinguish different environmental monitoring areas, and after determining the target fire warning parameter type, the target fire warning parameter set within the corresponding environmental monitoring area is determined according to the location corresponding to the environmental parameters.

[0045] For users, when they need to obtain a fire warning for any fire monitoring area in the city, they can input the location of the environmental monitoring area where the fire monitoring area is located, and thus obtain the corresponding environmental parameters.

[0046] S104. Based on the target fire warning parameter set, determine whether to output warning information.

[0047] In this step, the target fire warning parameter set contains multiple target fire warning parameters. Based on the trend of the target fire warning parameters changing over time, it is determined whether to output warning information.

[0048] Alternatively, one specific implementation of S104 includes: S1041. Output the actual warning level based on the target fire warning parameter set and time series model.

[0049] Specifically, the time series model can be a Long Short-Term Memory (LSTM) artificial neural network model, which extracts features such as the dynamic changing trends of target fire warning parameters in the target fire warning parameter set and outputs the actual warning level. The actual warning level can include, for example, high, medium, and low levels, with the probability of a fire decreasing sequentially.

[0050] The training methods for time series models can refer to existing technologies, and will not be elaborated here.

[0051] S1042. When the actual warning level is greater than the preset warning level, determine to output the warning information.

[0052] Specifically, different target fire warning parameter types correspond to different preset warning levels. The preset warning level for any target fire warning parameter type can be obtained by statistically summarizing a large number of target fire warning parameters and actual fire situations.

[0053] Therefore, after obtaining the actual early warning information, it is compared with the preset early warning level corresponding to the target fire early warning parameter type. When the actual early warning level is greater than the preset early warning level, it indicates that the probability of a fire is relatively high, and the early warning information is output, that is, the corresponding actual early warning level is output.

[0054] In this embodiment, environmental parameters at the current acquisition time are obtained, including ambient temperature, ambient brightness, and haze concentration. Based on these environmental parameters and a preset fire warning parameter prediction model, a target fire warning parameter type is obtained. This allows a single target fire warning parameter to be determined from various heterogeneous and multi-source data based on the environmental parameters. The target fire warning parameter type is one of temperature information, smoke detection information, or image information. Temperature information refers to the temperature of the fire monitoring area obtained by a temperature sensor; smoke detection information refers to the smoke concentration of the fire monitoring area obtained by a smoke sensor; and image information refers to an image of the fire monitoring area obtained by a video recording device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type matching the environmental parameters from these three sources. Based on the target fire warning parameter type, a corresponding target fire warning parameter set is obtained. Finally, based on the target fire warning parameter set, it is determined whether to output a warning message. This combines traditional single-data warning and multi-source data fusion warning. Accordingly, this embodiment solves the problem of low accuracy in traditional single-data warnings and the problems of complex calculation and poor timeliness in multi-source data fusion warnings, thus achieving a balance between timeliness and warning accuracy.

[0055] Figure 2 This is a flowchart illustrating the training process of a preset fire warning parameter prediction model provided in one embodiment of this application. The execution entity of the training method shown in this embodiment can be a terminal device equipped with a smart fire collaborative early warning system, or other terminal devices. When the execution entity is another terminal device, after the preset fire warning parameter prediction model is trained, it needs to be embedded into the terminal device equipped with the smart fire collaborative early warning system to achieve smart fire collaborative early warning.

[0056] like Figure 2 As shown, the method includes: S201. Acquire multiple sets of historical environmental parameters and historical fire early warning information, as well as historical temperature information, historical smoke detection information, and historical image information.

[0057] In this step, a massive amount of historical environmental parameters and historical fire early warning information from different cities and environmental monitoring areas are acquired, as well as historical temperature information, historical smoke detection information, and historical image information. This increases the diversity of training data, thereby improving the robustness and stability of the pre-set fire early warning parameter prediction model.

[0058] S202. Based on the prediction model of each set of historical environmental parameters and initial fire warning parameters, obtain the prediction results.

[0059] In this step, the initial fire warning parameter prediction model can be a generative adversarial network (GAN) model. By processing historical environmental parameters through the GAN model, a more realistic prediction result can be obtained.

[0060] S203. Based on historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information, determine the type of historical target fire early warning parameters.

[0061] In this step, historical fire warning information includes both actual fires and fires that did not actually occur. Based on these data, historical real warning information is obtained. Then, historical predicted warning information is calculated based on historical temperature information, historical smoke detection information, and historical image information. Finally, the historical warning information that is closest to the historical real warning information among the three historical predicted warning information is obtained.

[0062] Therefore, alternatively, one possible implementation of S203 is as follows: S2031. Based on historical temperature information, historical smoke detection information, and historical image information, obtain the corresponding historical forecast and early warning information respectively.

[0063] Specifically, traditional single data early warning methods are used to calculate historical predictive early warning information based on historical temperature information, historical smoke detection information, and historical image information. The historical predictive early warning information can be classified as high, medium, and low, with the probability of fire occurrence decreasing sequentially from high to low.

[0064] S2032. Based on historical temperature information, historical smoke detection information, historical image information, and corresponding historical predicted early warning information and historical actual early warning information, determine the type of historical target fire early warning parameters.

[0065] Specifically, for example, when historical real early warning information shows that a fire has actually occurred, the historical early warning information corresponding to historical temperature information, historical smoke detection information, and historical image information are high-level, low-level, and low-level, respectively. This indicates that the historical early warning information determined using historical temperature information is closest to the real label. In this case, historical temperature information is the determined historical target fire early warning parameter type.

[0066] When historical real-time warning information shows that no fire has actually occurred, and the historical warning information corresponding to historical temperature information, historical smoke detection information, and historical image information are medium, low, and high respectively, it means that the historical warning information determined using historical smoke detection information is closest to the real label. In this case, historical smoke detection information is the determined historical target fire warning parameter type.

[0067] S204. Based on the historical target fire warning parameter types and prediction results, train the initial fire warning parameter prediction model to obtain the preset fire warning parameter prediction model.

[0068] In this step, for the view example in step S203, in the first example, the prediction results of the historical environmental parameters corresponding to historical temperature information, historical smoke detection information, and historical image information are compared with the historical temperature information by the output of the primary fire warning parameter prediction model, and the model is trained using the loss function.

[0069] In the second example, the prediction results of the historical environmental parameters corresponding to historical temperature information, historical smoke detection information, and historical image information are compared with the historical smoke detection information to train the initial fire warning parameter prediction model.

[0070] Based on the above method, a prediction model for preset fire early warning parameters is obtained.

[0071] It should be noted that, for specific cities or specific environmental monitoring areas, during the use of the preset fire warning parameter prediction model, the accuracy of the preset fire warning parameter prediction model is improved based on the environmental parameters, temperature information, smoke detection information, image information, and the accuracy of the warning at the time of use, so that the preset fire warning parameter prediction model is more matched with the corresponding city or environmental monitoring area.

[0072] This embodiment acquires multiple sets of historical environmental parameters, historical fire early warning information, historical temperature information, historical smoke detection information, and historical image information. Based on each set of historical environmental parameters and an initial fire early warning parameter prediction model, prediction results are obtained. The types of historical target fire early warning parameters are determined based on historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information. The initial fire early warning parameter prediction model is trained based on the historical target fire early warning parameter types and prediction results to obtain a preset fire early warning parameter prediction model. This training of the preset fire early warning parameter prediction model enables it to more accurately output the target fire early warning parameter type based on environmental parameters, thereby improving the accuracy of early warnings.

[0073] Figure 3This is a schematic diagram of the structure of a smart fire-fighting collaborative early warning system provided in one embodiment of this application. Figure 3 As shown in the figure, the intelligent fire-fighting collaborative early warning system in this embodiment includes: an acquisition module 301, a model processing module 302, and a prediction module 303. Optionally, such as... Figure 3 As shown, the intelligent fire protection collaborative early warning system also includes: training module 304.

[0074] The acquisition module 301 is used to acquire environmental parameters at the current acquisition time. The environmental parameters include: ambient temperature, ambient brightness, and haze concentration. The model processing module 302 is used to obtain the target fire warning parameter type based on environmental parameters and a preset fire warning parameter prediction model. The target fire warning parameter type is one of temperature information, smoke detection information, and image information. The temperature information is the temperature of the fire monitoring area obtained by the temperature sensor, the smoke detection information is the smoke concentration of the fire monitoring area obtained by the smoke sensor, and the image information is the image of the fire monitoring area obtained by the video shooting device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type that matches the environmental parameters from the temperature information, smoke detection information, and image information. The acquisition module 301 is also used to acquire the corresponding target fire warning parameter set according to the target fire warning parameter type; The prediction module 302 is used to determine whether to output early warning information based on the target fire early warning parameter set.

[0075] Optionally, before the model processing module 302 predicts the model based on environmental parameters and preset fire warning parameters to obtain the target fire warning parameter type, the training module 304 is used for: Acquire multiple sets of historical environmental parameters and historical fire early warning information, as well as historical temperature information, historical smoke detection information, and historical image information; The prediction results are obtained based on the prediction model for each set of historical environmental parameters and initial fire warning parameters; Based on historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information, determine the type of historical target fire early warning parameters; Based on the historical target fire warning parameter types and prediction results, the initial fire warning parameter prediction model is trained to obtain the preset fire warning parameter prediction model.

[0076] Optionally, when determining the type of historical target fire warning parameters based on historical temperature information, historical smoke detection information, historical image information, and historical fire warning information, the training module 304 is specifically used for: Historical temperature information, historical smoke detection information, and historical image information are used to obtain corresponding historical forecast and early warning information. Based on historical temperature information, historical smoke detection information, historical image information, and corresponding historical predicted early warning information and historical actual early warning information, the types of historical target fire early warning parameters are determined.

[0077] Optionally, when the acquisition module 301 acquires the corresponding target fire warning parameter set based on the target fire warning parameter type, it is specifically used for: Based on the target fire warning parameter type, obtain the target fire warning parameter set between the historical time and the current collection time.

[0078] Optionally, environmental parameters may also include: the location corresponding to the environmental parameters; When module 301 obtains the corresponding target fire warning parameter set based on the target fire warning parameter type, it is specifically used for: Based on the location corresponding to the environmental parameters, determine the target fire early warning parameter set at the location corresponding to the environmental parameters.

[0079] Optionally, when the prediction module determines whether to output a warning message based on the target fire warning parameter set, it is specifically used for: Based on the target fire warning parameter set and time series model, the actual warning level is output; When the actual warning level is greater than the preset warning level, the warning information is output.

[0080] The intelligent fire-fighting collaborative early warning system provided in this application embodiment can be referred to the above method embodiment for its specific implementation process. Its implementation principle and technical effect are similar, and will not be repeated here.

[0081] Figure 4 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 4 As shown, the terminal device includes a processor 410 and a memory 420.

[0082] The memory 420 stores computer-executed instructions.

[0083] The processor 410 executes the computer execution instructions stored in the memory 420, causing the processor 410 to perform the method described in any of the above embodiments.

[0084] The terminal device provided in this application embodiment can be referred to the above method embodiment for its specific implementation process. The implementation principle and technical effect are similar, and will not be repeated here.

[0085] In the above Figure 4In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0086] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage.

[0087] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0088] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method shown in the above-described method embodiments.

[0089] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, 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 storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0090] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0091] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A smart fire-fighting collaborative early warning method, characterized in that, include: Obtain environmental parameters at the current data collection time, including: ambient temperature, ambient brightness, and haze concentration; Based on environmental parameters and a preset fire warning parameter prediction model, a target fire warning parameter type is obtained. The target fire warning parameter type is one of temperature information, smoke detection information, and image information. The temperature information is the temperature of the fire monitoring area obtained by a temperature sensor, the smoke detection information is the smoke concentration of the fire monitoring area obtained by a smoke sensor, and the image information is an image of the fire monitoring area obtained by a video shooting device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type that matches the environmental parameters from the temperature information, the smoke detection information, and the image information. Based on the target fire warning parameter type, obtain the corresponding target fire warning parameter set; Based on the target fire early warning parameter set, determine whether to output early warning information.

2. The method according to claim 1, characterized in that, Before obtaining the target fire warning parameter type based on environmental parameters and a preset fire warning parameter prediction model, the process also includes: Acquire multiple sets of historical environmental parameters and historical fire early warning information, as well as historical temperature information, historical smoke detection information, and historical image information; Based on the prediction model of each group of historical environmental parameters and initial fire warning parameters, the prediction results are obtained; Based on the historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information, determine the type of historical target fire early warning parameters; The initial fire warning parameter prediction model is trained based on the historical target fire warning parameter type and the prediction result to obtain the preset fire warning parameter prediction model.

3. The method according to claim 2, characterized in that, The step of determining the type of historical target fire early warning parameters based on the historical temperature information, historical smoke detection information, historical image information, and historical fire early warning information includes: The historical temperature information, historical smoke detection information, and historical image information are used to obtain corresponding historical prediction and early warning information. Based on the historical temperature information, historical smoke detection information, historical image information, corresponding historical predicted early warning information, and the historical actual early warning information, the type of historical target fire early warning parameter is determined.

4. The method according to any one of claims 1-3, characterized in that, The step of obtaining the corresponding target fire warning parameter set according to the target fire warning parameter type includes: Based on the target fire warning parameter type, obtain the target fire warning parameter set between the historical time and the current collection time.

5. The method according to any one of claims 1-3, characterized in that, The environmental parameters also include: the location corresponding to the environmental parameters; The step of obtaining the corresponding target fire warning parameter set according to the target fire warning parameter type includes: Based on the location corresponding to the environmental parameters, determine the target fire early warning parameter set at the location corresponding to the environmental parameters.

6. The method according to claim 1, characterized in that, The step of determining whether to output a warning message based on the target fire warning parameter set includes: Based on the target fire early warning parameter set and time series model, the actual early warning level is output; When the actual warning level is greater than the preset warning level, the warning information is output.

7. A smart fire-fighting collaborative early warning system, characterized in that, include: The acquisition module is used to acquire environmental parameters at the current acquisition time, including: ambient temperature, ambient brightness, and haze concentration. The model processing module is used to obtain the target fire warning parameter type based on environmental parameters and a preset fire warning parameter prediction model. The target fire warning parameter type is one of temperature information, smoke detection information, and image information. The temperature information is the temperature of the fire monitoring area obtained by a temperature sensor, the smoke detection information is the smoke concentration of the fire monitoring area obtained by a smoke sensor, and the image information is an image of the fire monitoring area obtained by a video shooting device. The preset fire warning parameter prediction model is used to determine the target fire warning parameter type that matches the environmental parameters from the temperature information, the smoke detection information, and the image information. The acquisition module is further configured to acquire the corresponding target fire warning parameter set according to the target fire warning parameter type; The prediction module is used to determine whether to output a warning message based on the target fire warning parameter set.

8. A terminal device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images