Fire sensing data anti-interference transmission optimization method and system based on end-side cooperation

Abstract

The invention relates to the technical field of data anti-interference transmission, in particular to a fire sensing data anti-interference transmission optimization method and system based on end-side cooperation, and the method specifically comprises the steps: collecting fire sensing data; identifying the total data emergency degree of the fire sensing data in real time; extracting a data overall emergency degree of the fire sensing data corresponding to each position in the high-rise building, and determining a distribution strategy of the end-side equipment according to the data overall emergency degree; performing combined coding processing on the data overall emergency degree of the fire sensing data, and transmitting a coding sequence in batches through an end edge equipment data transmission network; according to the invention, the problems of data loss, interference and errors in the fire sensing data transmission process in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data anti-interference transmission technology, and is a fire sensing data anti-interference transmission optimization method and system based on end-edge collaboration. Background Art

[0002] In order to effectively prevent and respond to fires, buildings are usually equipped with a variety of fire sensing devices, such as sensor networks and cameras, to collect air temperature data, harmful gas concentration data, flame trend data, and crowd density data. These data are crucial for early warning and real-time monitoring of fires.

[0003] However, inside complex high-rise buildings, the transmission of fire sensing data is often disturbed due to electromagnetic interference, equipment failure or network instability, resulting in data loss or distortion. In addition, there are few data verification and repair mechanisms during data transmission. When data transmission is erroneous or lost, it cannot be corrected and supplemented in time, which makes the data transmitted to the fire management platform likely to contain errors, directly affecting the accuracy and timeliness of fire warnings, and also reducing the accuracy of subsequent analysis and decision-making. Summary of the invention

[0004] The technical problem to be solved by the present invention is to address the problems of data loss, interference and errors that are prone to occur during the transmission of fire perception data in the prior art, and propose an anti-interference transmission optimization method and system for fire perception data based on end-edge collaboration.

[0005] In order to achieve the above object, the technical solution of the fire sensing data anti-interference transmission optimization method based on edge-end collaboration of the present invention includes the following steps:

[0006] S1: Collect fire perception data at various locations inside high-rise buildings through sensor networks and cameras;

[0007] S2: Build an edge device data transmission network, and embed a fire perception data recognition and classification model in the edge device data transmission network. Use the fire perception data recognition and classification model to identify the overall urgency of the fire perception data at various locations inside the high-rise building in real time.

[0008] S3: extracting the overall urgency of the fire sensing data corresponding to each location inside the high-rise building, and determining the distribution strategy of the end-edge devices according to the overall urgency of the data;

[0009] S4: performing combined coding processing on the overall urgency of the fire sensing data, transmitting the coding sequence in batches through the edge device data transmission network, and executing a key data verification strategy on the input data on each edge device;

[0010] S5: Convert the verified coding sequence into a fire threat level, and synchronize the fire threat level to the fire management platform of the high-rise building.

[0011] Specifically, in S1, the fire sensing data at various locations inside the high-rise building include: air temperature data, harmful gas concentration data, flame trend data, and crowd density data.

[0012] Specifically, S2 includes the following specific steps:

[0013] S21: constructing an edge device data transmission network, and embedding a fire sensing data recognition and classification model in the end edge device on each data transmission line in the edge device data transmission network, wherein the fire sensing data recognition and classification model includes: a temperature data recognition layer, a gas concentration recognition layer, a flame trend recognition layer, and a crowd density recognition layer;

[0014] S22: Inputting the air temperature data at various locations inside the high-rise building into the temperature data identification layer, and identifying the temperature data emergency coefficient in real time, wherein the calculation strategy of the temperature data emergency coefficient is specifically as follows:

[0015]

[0016] Where i is a subscript, indicating the number of the fire perception period, and I indicates the total number of fire perception period numbers that have been continued up to the current data collection time point;

[0017] t is the duration of a fire perception period;

[0018] α wd,i represents the emergency coefficient of temperature data in the i-th fire sensing period;

[0019] wd i represents the air temperature data of the i-th fire sensing period;

[0020] wd i ′ represents all the air temperature data in the fire sensing period I and wd i The closest air temperature data;

[0021] S23: Input the harmful gas concentration data at various locations inside the high-rise building into the gas concentration identification layer, and identify the emergency coefficient of the harmful gas data in real time, wherein the calculation strategy of the emergency coefficient of the harmful gas data is specifically as follows:

[0022]

[0023] Among them, α qt,i represents the emergency coefficient of harmful gas data in the i-th fire sensing period;

[0024] qt i Represents the harmful gas concentration data of the i-th fire sensing period;

[0025] qt i ′ represents the concentration data of all harmful gases in a fire sensing period and qt i The closest harmful gas concentration data.

[0026] Specifically, S2 also includes the following specific steps:

[0027] S24: After the fire occurs, the monitoring video stream data of various positions inside the high-rise building is captured by a camera, key frames in the video are extracted by a motion detection algorithm, and filtering and noise reduction processing is performed on the key frame images;

[0028] S25: Preset the upper and lower thresholds of the flame color through a color segmentation algorithm to obtain a binary image, and mark the flame area on the binary image;

[0029] S26: importing the flame trend data in the flame area into the flame trend identification layer, and identifying the emergency coefficient of the flame trend data in real time, wherein the calculation strategy of the emergency coefficient of the flame trend data is specifically as follows:

[0030]

[0031] Among them, β hy,i represents the emergency coefficient of the flame trend data in the i-th fire perception period;

[0032] represents the pixel mean of all pixel blocks in the flame area during the i-th fire perception period; Represents all flame trend data in a fire sensing period The nearest pixel mean;

[0033] S27: Learn and create background models at various locations inside high-rise buildings, separate the crowd area from the background image through background subtraction algorithm, and extract the crowd area in the key frame image;

[0034] S28: Importing the crowd density data in the crowd area into the crowd density recognition layer, and identifying the emergency coefficient of the crowd density data in real time, wherein the calculation strategy of the emergency coefficient of the crowd density data is specifically as follows:

[0035]

[0036] Among them, β rl,i represents the emergency coefficient of the crowd density data in the i-th fire perception period;

[0037] NU i represents the total number of pixel blocks in the crowd area during the i-th fire perception period; nu i ′ represents the total flow density data of all people in I fire sensing period and nu i The total number of closest pixel blocks;

[0038] S29: According to S21-S28, the overall urgency JZ of the fire sensing data corresponding to each position inside the high-rise building is identified in real time. The calculation strategy of the overall urgency JZ is:

[0039] JZ=exp(α wd,i α qt,i )+exp(β hy,i β rl,i ).

[0040] Specifically, in S3, the distribution strategy of the edge device specifically includes:

[0041] S31: extracting the overall urgency of data at all locations inside the high-rise building to form an urgency set G. In the urgency set G, the median of the overall urgency of data is selected as a reference configuration line, wherein the reference number of end-edge devices on the reference configuration line is M;

[0042] S32: deploying the end-edge devices on other data transmission lines on the end-edge device data transmission network according to the reference configuration line, specifically:

[0043]

[0044] Among them, sb x Indicates the number of end-side devices that need to be configured on the data transmission line at the xth position after deployment;

[0045] x is a subscript, indicating the xth position inside a high-rise building, X is the total number of positions inside a high-rise building, JZ x ,L x Respectively represent the overall urgency of the data at the xth position and the length of the data transmission line; JZ 0.5X ,L 0.5X They respectively represent the overall urgency of data at the end of the reference configuration line and the data transmission line length of the reference configuration line.

[0046] Specifically, in S4, the combined coding process is specifically as follows:

[0047] Starting from 1, a unique serial number is assigned to each message; and a unique identifier is defined for each emergency coefficient, including: the identifier of the temperature data emergency coefficient is TEMPERATURE, the identifier of the harmful gas data emergency coefficient is GAS, the identifier of the flame trend data emergency coefficient is FLAME, and the identifier of the crowd density data emergency coefficient is DENSITY;

[0048] Extract the real-time data content of four emergency coefficients and generate a checksum through a summation algorithm;

[0049] The sequence number, identifier, data content and checksum are combined and encoded into a complete message.

[0050] Specifically, in S4, the key data verification strategy specifically includes:

[0051] S41: listen to the incoming message on the end-edge device and perform the initial integrity check on the incoming message. When the sequence number or checksum of the message is missing during transmission, send a message retransmission request to the previous end-edge device on the transmission line; otherwise, execute S42;

[0052] S42: Preset an expected sequence number set, extract the sequence number of the incoming message, and put the sequence number of the incoming message into the data buffer to form an accepted sequence number set, compare the expected sequence number set with the accepted sequence number set, perform a first key data verification process, and obtain a missing sequence number set;

[0053] If the missing sequence number set is not empty, it indicates that key data is lost on the data transmission line of this section, and S44 is executed;

[0054] If the missing sequence number set is empty, execute S43;

[0055] S43: extracting the checksum and data content from the received message, performing a second key data verification process, and recalculating the checksum using a summation algorithm;

[0056] If the recalculated checksum is consistent with the checksum of the incoming message, it means that no key data is lost on this data transmission line, and the incoming message will continue to be transmitted to the next end-edge device;

[0057] If the recalculated checksum is inconsistent with the checksum of the incoming message, it means that key data is lost on the data transmission line of this section, and S44 is executed.

[0058] Specifically, in S4, the key data verification strategy also includes:

[0059] S44: Return and retrieve the actual message sending position inside the high-rise building at the end of the transmission line, and synchronously query six message sending positions that are closest to the actual message sending position in a straight line from all positions;

[0060] S45: extracting the latest message from the six message sending locations on the data transmission network of the edge device to form a complete message set;

[0061] S46: extracting the emergency coefficient corresponding to the missing sequence number in the missing sequence number set, and performing a completion process on the emergency coefficient corresponding to the missing sequence number through the completion message set, wherein the completion process specifically includes:

[0062]

[0063] Among them, Q′ represents the emergency coefficient corresponding to the missing sequence number after completion processing;

[0064] h is a subscript, indicating the message sending position number among the 6 message sending positions;

[0065] d h is the straight-line distance between the hth message sending location and the actual message sending location;

[0066] Q h Indicates the urgency coefficient corresponding to the missing sequence number in the latest message at the location where the hth message is sent on the data transmission network of the edge device;

[0067] S47: Acquire a complete message that has completed the completion processing, and transmit the complete message to the next end-edge device.

[0068] In addition, the fire sensing data anti-interference transmission optimization system based on edge-end collaboration of the present invention includes the following modules:

[0069] Fire perception data acquisition module, urgency calculation module, distribution strategy determination module, key data verification module and fire threat level conversion module;

[0070] The fire sensing data collection module collects fire sensing data at various locations inside the high-rise building through a sensor network and a camera;

[0071] The urgency calculation module is used to construct an edge device data transmission network, and embed a fire perception data recognition and classification model in the edge device data transmission network, and use the fire perception data recognition and classification model to identify the overall urgency of the fire perception data corresponding to each location inside the high-rise building in real time;

[0072] The distribution strategy determination module is used to extract the overall urgency of the fire sensing data corresponding to each location inside the high-rise building, and determine the distribution strategy of the edge device according to the overall urgency of the data;

[0073] The key data checking module performs combined coding processing on the overall urgency of the fire sensing data, transmits the coding sequence in batches through the edge device data transmission network, and executes the key data checking strategy on the input data of each edge device;

[0074] The fire threat level conversion module is used to convert the verified code sequence into a fire threat level, and synchronize the fire threat level to the fire management platform of the high-rise building.

[0075] A computer-readable storage medium stores instructions. When a computer reads the instructions, the computer executes the anti-interference transmission optimization method for fire perception data based on end-edge collaboration.

[0076] An electronic device includes 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 above-mentioned fire perception data anti-interference transmission optimization method based on end-edge collaboration is implemented.

[0077] Compared with the prior art, the technical effects of the present invention are as follows:

[0078] 1. The present invention embeds multiple fire perception data identification and classification models in the edge device data transmission network to identify and classify various types of fire perception data in real time, thereby ensuring the accuracy and timeliness of data transmission. The present invention effectively reduces interference and loss during data transmission through combined coding processing and key data verification strategies, thereby improving data integrity and reliability.

[0079] 2. By extracting the overall urgency of data from various locations inside a high-rise building, the system can dynamically adjust the distribution strategy of the edge devices; the intelligent distribution strategy of the present invention based on actual conditions not only optimizes the utilization of resources, but also improves the monitoring coverage and response speed, and reduces the monitoring blind spots.

[0080] 3. The system of the present invention introduces a multi-level data verification and repair mechanism in the data transmission process. By executing the key data verification strategy on the edge device and performing data completion processing when the data is lost or erroneous, the accuracy of the transmitted data is ensured. The mechanism adopted by the present invention effectively copes with various uncertainties in the data transmission process and improves the robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0082] in:

[0083] Figure 1 It is a flow chart of the anti-interference transmission optimization method of fire sensing data based on end-edge collaboration of the present invention;

[0084] Figure 2 It is a structural schematic diagram of the fire sensing data anti-interference transmission optimization system based on end-edge collaboration of the present invention. DETAILED DESCRIPTION

[0085] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0086] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0087] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0088] Embodiment 1:

[0089] like Figure 1 As shown, the anti-interference transmission optimization method of fire sensing data based on device-edge collaboration in an embodiment of the present invention includes the following specific steps:

[0090] S1: Collect fire perception data at various locations inside high-rise buildings through sensor networks and cameras;

[0091] In S1, the fire sensing data at various locations inside a high-rise building include: air temperature data, harmful gas concentration data, flame trend data, and crowd density data.

[0092] S2: Build an edge device data transmission network, and embed multiple fire perception data recognition and classification models in the edge device data transmission network. Use the fire perception data recognition and classification models to identify the overall urgency of the fire perception data at various locations inside the high-rise building in real time.

[0093] S2 includes the following specific steps:

[0094] S21: constructing an edge device data transmission network, and embedding multiple fire sensing data recognition and classification models in the end edge device on each data transmission line in the edge device data transmission network, wherein the fire sensing data recognition and classification models include: a temperature data recognition layer, a gas concentration recognition layer, a flame trend recognition layer, and a crowd density recognition layer;

[0095] S22: Inputting the air temperature data at various locations inside the high-rise building into the temperature data identification layer, and identifying the temperature data emergency coefficient in real time, wherein the calculation strategy of the temperature data emergency coefficient is specifically as follows:

[0096]

[0097] Where i is a subscript, indicating the number of the fire perception period, and I indicates the total number of fire perception period numbers that have been continued up to the current data collection time point;

[0098] t is the duration of a fire perception period;

[0099] α wd,i represents the emergency coefficient of temperature data in the i-th fire sensing period;

[0100] wd i represents the air temperature data of the i-th fire sensing period;

[0101] wd i ′ represents all the air temperature data in the fire sensing period I and wd i The closest air temperature data;

[0102] S23: Input the harmful gas concentration data at various locations inside the high-rise building into the gas concentration identification layer, and identify the emergency coefficient of the harmful gas data in real time, wherein the calculation strategy of the emergency coefficient of the harmful gas data is specifically as follows:

[0103]

[0104] Among them, α qt,i represents the emergency coefficient of harmful gas data in the i-th fire sensing period;

[0105] qt iRepresents the harmful gas concentration data of the i-th fire sensing period;

[0106] qt i ′ represents the concentration data of all harmful gases in a fire sensing period and qt i The closest harmful gas concentration data.

[0107] S2 also includes the following specific steps:

[0108] S24: After the fire occurs, the monitoring video stream data of various positions inside the high-rise building is captured by a camera, key frames in the video are extracted by a motion detection algorithm, and filtering and noise reduction processing is performed on the key frame images;

[0109] S25: Preset the upper and lower thresholds of the flame color through a color segmentation algorithm to obtain a binary image, and mark the flame area on the binary image;

[0110] S26: importing the flame trend data in the flame area into the flame trend identification layer, and identifying the emergency coefficient of the flame trend data in real time, wherein the calculation strategy of the emergency coefficient of the flame trend data is specifically as follows:

[0111]

[0112] Among them, β hy,i represents the emergency coefficient of the flame trend data in the i-th fire perception period;

[0113] represents the pixel mean of all pixel blocks in the flame area during the i-th fire perception period; Represents all flame trend data in a fire sensing period The nearest pixel mean;

[0114] S27: Learn and create background models at various locations inside high-rise buildings, separate the crowd area from the background image through background subtraction algorithm, and extract the crowd area in the key frame image;

[0115] S28: Importing the crowd density data in the crowd area into the crowd density recognition layer, and identifying the emergency coefficient of the crowd density data in real time, wherein the calculation strategy of the emergency coefficient of the crowd density data is specifically as follows:

[0116]

[0117] Among them, β rl,i represents the emergency coefficient of the crowd density data in the i-th fire perception period;

[0118] NU irepresents the total number of pixel blocks in the crowd area during the i-th fire perception period; nu i ′ represents the total flow density data of all people in I fire sensing period and nu i The total number of closest pixel blocks;

[0119] S29: According to S21-S28, the overall urgency JZ of the fire sensing data corresponding to each position inside the high-rise building is identified in real time. The calculation strategy of the overall urgency JZ is:

[0120] JZ=exp(α wd,i α qt,i )+exp(β hy,i β rl,i ).

[0121] S3: extracting the overall urgency of the fire sensing data corresponding to each location inside the high-rise building, and determining the distribution strategy of the end-edge devices according to the overall urgency of the data;

[0122] In S3, the distribution strategy of the edge device specifically includes:

[0123] S31: extracting the overall urgency of data at all locations inside the high-rise building to form an urgency set G. In the urgency set G, the median of the overall urgency of data is selected as a reference configuration line, wherein the reference number of end-edge devices on the reference configuration line is M;

[0124] S32: deploying the end-side devices on other data transmission lines on the end-side device data transmission network according to the reference configuration line, specifically:

[0125]

[0126] Among them, sb x Indicates the number of end-side devices that need to be configured on the data transmission line at the xth position after deployment;

[0127] x is a subscript, indicating the xth position inside a high-rise building, X is the total number of positions inside a high-rise building, JZ x ,L x Respectively represent the overall urgency of the data at the xth position and the length of the data transmission line; JZ 0.5X ,L 0.5X They respectively represent the overall urgency of data at the end of the reference configuration line and the data transmission line length of the reference configuration line.

[0128] S4: performing combined coding processing on the overall urgency of the fire sensing data, transmitting the coding sequence in batches through the edge device data transmission network, and executing a key data verification strategy on the input data on each edge device;

[0129] In S4, the combined coding process is specifically as follows:

[0130] Starting from 1, a unique serial number is assigned to each message; and a unique identifier is defined for each emergency coefficient, including: the identifier of the temperature data emergency coefficient is TEMPERATURE, the identifier of the harmful gas data emergency coefficient is GAS, the identifier of the flame trend data emergency coefficient is FLAME, and the identifier of the crowd density data emergency coefficient is DENSITY;

[0131] Extract the real-time data content of four emergency coefficients and generate a checksum through a summation algorithm;

[0132] The sequence number, identifier, data content and checksum are combined and encoded into a complete message.

[0133] In S4, the key data verification strategy specifically includes:

[0134] S41: listen to the incoming message on the end-edge device and perform the initial integrity check on the incoming message. When the sequence number or checksum of the message is missing during transmission, send a message retransmission request to the previous end-edge device on the transmission line; otherwise, execute S42;

[0135] S42: Preset an expected sequence number set, extract the sequence number of the incoming message, and put the sequence number of the incoming message into the data buffer to form an accepted sequence number set, compare the expected sequence number set with the accepted sequence number set, perform a first key data verification process, and obtain a missing sequence number set;

[0136] If the missing sequence number set is not empty, it indicates that key data is lost on the data transmission line of this section, and S44 is executed;

[0137] If the missing sequence number set is empty, execute S43;

[0138] S43: extracting the checksum and data content from the received message, performing a second key data verification process, and recalculating the checksum using a summation algorithm;

[0139] If the recalculated checksum is consistent with the checksum of the incoming message, it means that no key data is lost on this data transmission line, and the incoming message will continue to be transmitted to the next end-edge device;

[0140] If the recalculated checksum is inconsistent with the checksum of the incoming message, it means that key data is lost on the data transmission line of this section, and S44 is executed.

[0141] In S4, the key data verification strategy also includes:

[0142] S44: Return and retrieve the actual message sending position inside the high-rise building at the end of the transmission line, and synchronously query six message sending positions that are closest to the actual message sending position in a straight line from all positions;

[0143] S45: extracting the latest message from the six message sending locations on the data transmission network of the edge device to form a complete message set;

[0144] S46: extracting the emergency coefficient corresponding to the missing sequence number in the missing sequence number set, and performing a completion process on the emergency coefficient corresponding to the missing sequence number through the completion message set, wherein the completion process specifically includes:

[0145]

[0146] Among them, Q′ represents the emergency coefficient corresponding to the missing sequence number after completion processing;

[0147] h is a subscript, indicating the message sending position number among the 6 message sending positions;

[0148] d h is the straight-line distance between the hth message sending location and the actual message sending location;

[0149] Q h Indicates the urgency coefficient corresponding to the missing sequence number in the latest message at the location where the hth message is sent on the data transmission network of the edge device;

[0150] S47: Acquire a complete message that has completed the completion processing, and transmit the complete message to the next end-edge device.

[0151] S5: Convert the verified coding sequence into a fire threat level, and synchronize the fire threat level to the fire management platform of the high-rise building.

[0152] Embodiment 2:

[0153] like Figure 2 As shown, the fire sensing data anti-interference transmission optimization system based on device-edge collaboration according to an embodiment of the present invention includes the following modules:

[0154] Fire perception data acquisition module, urgency calculation module, distribution strategy determination module, key data verification module and fire threat level conversion module;

[0155] The fire sensing data collection module collects fire sensing data at various locations inside the high-rise building through a sensor network and a camera;

[0156] The urgency calculation module is used to construct an edge device data transmission network, and embed a fire perception data recognition and classification model in the edge device data transmission network, and use the fire perception data recognition and classification model to identify the overall urgency of the fire perception data corresponding to each location inside the high-rise building in real time;

[0157] The distribution strategy determination module is used to extract the overall urgency of the fire sensing data corresponding to each location inside the high-rise building, and determine the distribution strategy of the edge device according to the overall urgency of the data;

[0158] The key data checking module performs combined coding processing on the overall urgency of the fire sensing data, transmits the coding sequence in batches through the edge device data transmission network, and executes the key data checking strategy on the input data of each edge device;

[0159] The fire threat level conversion module is used to convert the verified code sequence into a fire threat level, and synchronize the fire threat level to the fire management platform of the high-rise building.

[0160] Embodiment three:

[0161] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0162] The processor executes the above-mentioned fire perception data anti-interference transmission optimization method based on end-edge collaboration by calling the computer program stored in the memory.

[0163] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the anti-interference transmission optimization method for fire sensing data based on edge collaboration provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0164] Embodiment 4:

[0165] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0166] When the computer program runs on a computer device, the computer device executes the above-mentioned fire perception data anti-interference transmission optimization method based on end-edge collaboration.

[0167] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0168] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0169] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0170] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0171] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0172] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0173] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0174] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0176] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0177] In summary, the technical effects of the present invention are as follows:

[0178] 1. The present invention embeds multiple fire perception data identification and classification models in the edge device data transmission network to identify and classify various types of fire perception data in real time, thereby ensuring the accuracy and timeliness of data transmission. The present invention effectively reduces interference and loss during data transmission through combined coding processing and key data verification strategies, thereby improving data integrity and reliability.

[0179] 2. By extracting the overall urgency of data from various locations inside a high-rise building, the system can dynamically adjust the distribution strategy of the edge devices; the intelligent distribution strategy of the present invention based on actual conditions not only optimizes the utilization of resources, but also improves the monitoring coverage and response speed, and reduces the monitoring blind spots.

[0180] 3. The system of the present invention introduces a multi-level data verification and repair mechanism in the data transmission process. By executing the key data verification strategy on the edge device and performing data completion processing when the data is lost or erroneous, the accuracy of the transmitted data is ensured. The mechanism adopted by the present invention effectively copes with various uncertainties in the data transmission process and improves the robustness of the system.

[0181] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A fire sensing data anti-interference transmission optimization method based on edge-to-end collaboration is characterized in that: The method comprises the following specific steps: S1: Collect fire perception data at various locations inside high-rise buildings through sensor networks and cameras; S2: Build an edge device data transmission network, and embed a fire perception data recognition and classification model in the edge device data transmission network. Use the fire perception data recognition and classification model to identify the overall urgency of the fire perception data at various locations inside the high-rise building in real time. S3: extracting the overall urgency of the fire sensing data corresponding to each location inside the high-rise building, and determining the distribution strategy of the end-edge devices according to the overall urgency of the data; S4: performing combined coding processing on the overall urgency of the fire sensing data, transmitting the coding sequence in batches through the edge device data transmission network, and executing a key data verification strategy on the input data on each edge device; S5: Convert the verified coding sequence into a fire threat level, and synchronize the fire threat level to the fire management platform of the high-rise building.

2. The method for optimizing fire sensing data anti-interference transmission based on edge-end collaboration according to claim 1 is characterized in that: In S1, the fire sensing data at various locations inside a high-rise building include: air temperature data, harmful gas concentration data, flame trend data, and crowd density data.

3. The method for optimizing fire sensing data anti-interference transmission based on edge-end collaboration according to claim 2 is characterized in that: S2 includes the following specific steps: S21: constructing an edge device data transmission network, and embedding a fire perception data recognition and classification model in the end edge device on each data transmission line in the edge device data transmission network, wherein the fire perception data recognition and classification model includes: a temperature data recognition layer, a gas concentration recognition layer, a flame trend recognition layer, and a crowd density recognition layer; S22: Inputting the air temperature data at various locations inside the high-rise building into the temperature data identification layer, and identifying the temperature data emergency coefficient in real time, wherein the calculation strategy of the temperature data emergency coefficient is specifically as follows: Where i is a subscript, indicating the number of the fire perception period, and I indicates the total number of fire perception period numbers that have been continued up to the current data collection time point; t is the duration of a fire sensing period; α wd,i represents the emergency coefficient of temperature data in the i-th fire sensing period; wd i represents the air temperature data of the i-th fire sensing period; wd i ′ represents all the air temperature data in the fire sensing period I and wd i The closest air temperature data; S23: Input the harmful gas concentration data at various locations inside the high-rise building into the gas concentration identification layer, and identify the emergency coefficient of the harmful gas data in real time, wherein the calculation strategy of the emergency coefficient of the harmful gas data is specifically as follows: Among them, α qt,i represents the emergency coefficient of harmful gas data in the i-th fire sensing period; qt i Represents the harmful gas concentration data of the i-th fire sensing period; qt i ′ represents the concentration data of all harmful gases in a fire sensing period and qt i The closest harmful gas concentration data.

4. The method for optimizing fire sensing data anti-interference transmission based on edge-end collaboration according to claim 3 is characterized in that: S2 also includes the following specific steps: S24: After the fire occurs, the monitoring video stream data of various positions inside the high-rise building is captured by a camera, key frames in the video are extracted by a motion detection algorithm, and filtering and noise reduction processing is performed on the key frame images; S25: Preset the upper and lower thresholds of the flame color through a color segmentation algorithm to obtain a binary image, and mark the flame area on the binary image; S26: importing the flame trend data in the flame area into the flame trend identification layer, and identifying the emergency coefficient of the flame trend data in real time, wherein the calculation strategy of the emergency coefficient of the flame trend data is specifically as follows: Among them, β hy,i represents the emergency coefficient of the flame trend data in the i-th fire perception period; represents the pixel mean of all pixel blocks in the flame area during the i-th fire perception period; Represents all flame trend data in a fire sensing period The nearest pixel mean; S27: Learn and create background models at various locations inside high-rise buildings, separate the crowd area from the background image through background subtraction algorithm, and extract the crowd area in the key frame image; S28: Importing the crowd density data in the crowd area into the crowd density recognition layer, and identifying the emergency coefficient of the crowd density data in real time, wherein the calculation strategy of the emergency coefficient of the crowd density data is specifically as follows: Among them, β rl,i represents the emergency coefficient of the crowd density data in the i-th fire perception period; NU i represents the total number of pixel blocks in the crowd area during the i-th fire perception period; nu i ′ represents the total flow density data of all people in I fire sensing period and nu i The total number of closest pixel blocks; S29: According to S21-S28, the overall urgency JZ of the fire sensing data corresponding to each position inside the high-rise building is identified in real time. The calculation strategy of the overall urgency JZ is: JZ=exp(α wd,i a qt,i )+exp(β hy,i b rl,i )。 5. The method for optimizing fire sensing data anti-interference transmission based on edge-end collaboration according to claim 4 is characterized in that: In S3, the distribution strategy of the edge device specifically includes: S31: extracting the overall urgency of data at all locations inside the high-rise building to form an urgency set G. In the urgency set G, the median of the overall urgency of data is selected as a reference configuration line, wherein the reference number of end-edge devices on the reference configuration line is M; S32: deploying the end-side devices on other data transmission lines on the end-side device data transmission network according to the reference configuration line, specifically: Among them, sb x Indicates the number of end-side devices that need to be configured on the data transmission line at the xth position after deployment; x is a subscript, indicating the xth position inside a high-rise building, X is the total number of positions inside a high-rise building, JZ x ,L x Respectively represent the overall urgency of the data at the xth position and the length of the data transmission line; JZ 0.5X ,L 0.5X They respectively represent the overall urgency of data at the end of the reference configuration line and the data transmission line length of the reference configuration line.

6. The method for optimizing fire sensing data anti-interference transmission based on edge-to-end collaboration according to claim 5 is characterized in that: In S4, the combined coding process is specifically as follows: Starting from 1, a unique serial number is assigned to each message; and a unique identifier is defined for each emergency coefficient, including: the identifier of the temperature data emergency coefficient is TEMPERATURE, the identifier of the harmful gas data emergency coefficient is GAS, the identifier of the flame trend data emergency coefficient is FLAME, and the identifier of the crowd density data emergency coefficient is DENSITY; Extract the real-time data content of four emergency coefficients and generate a checksum through a summation algorithm; The sequence number, identifier, data content and checksum are combined and encoded into a complete message.

7. The method for optimizing fire sensing data anti-interference transmission based on edge-to-end collaboration according to claim 6 is characterized in that: In S4, the key data verification strategy specifically includes: S41: listen to the incoming message on the end-edge device and perform the initial integrity check on the incoming message. When the sequence number or checksum of the message is missing during transmission, send a message retransmission request to the previous end-edge device on the transmission line; otherwise, execute S42; S42: Preset an expected sequence number set, extract the sequence number of the incoming message, and put the sequence number of the incoming message into the data buffer to form an accepted sequence number set, compare the expected sequence number set with the accepted sequence number set, perform a first key data verification process, and obtain a missing sequence number set; If the missing sequence number set is not empty, it indicates that key data is lost on the data transmission line of this section, and S44 is executed; If the missing sequence number set is empty, execute S43; S43: extracting the checksum and data content from the received message, performing a second key data verification process, and recalculating the checksum using a summation algorithm; If the recalculated checksum is consistent with the checksum of the incoming message, it means that no key data is lost on this data transmission line, and the incoming message will continue to be transmitted to the next end-edge device; If the recalculated checksum is inconsistent with the checksum of the incoming message, it means that key data is lost on the data transmission line of this section, and S44 is executed.

8. The method for optimizing fire sensing data anti-interference transmission based on edge-to-end collaboration according to claim 7 is characterized in that: In S4, the key data verification strategy also includes: S44: Return and retrieve the actual message sending position inside the high-rise building at the end of the transmission line, and synchronously query six message sending positions that are closest to the actual message sending position in a straight line from all positions; S45: extracting the latest message from the six message sending locations on the data transmission network of the edge device to form a complete message set; S46: extracting the emergency coefficient corresponding to the missing sequence number in the missing sequence number set, and performing a completion process on the emergency coefficient corresponding to the missing sequence number through the completion message set, wherein the completion process specifically includes: Among them, Q′ represents the emergency coefficient corresponding to the missing sequence number after completion processing; h is a subscript, indicating the message sending position number among the 6 message sending positions; d h is the straight-line distance between the location where the hth message is sent and the actual location where the message is sent; Q h Indicates the urgency coefficient corresponding to the missing sequence number in the latest message at the location where the hth message is sent on the data transmission network of the edge device; S47: Acquire a complete message that has completed the completion processing, and transmit the complete message to the next end-edge device.

9. A fire sensing data anti-interference transmission optimization system based on edge-end collaboration, used to implement the fire sensing data anti-interference transmission optimization method based on edge-end collaboration as claimed in any one of claims 1 to 8, characterized in that: The system includes the following modules: Fire perception data acquisition module, urgency calculation module, distribution strategy determination module, key data verification module and fire threat level conversion module; The fire sensing data collection module collects fire sensing data at various locations inside the high-rise building through a sensor network and a camera; The urgency calculation module is used to construct an edge device data transmission network, and embed a fire perception data recognition and classification model in the edge device data transmission network, and use the fire perception data recognition and classification model to identify the overall urgency of the fire perception data corresponding to each location inside the high-rise building in real time; The distribution strategy determination module is used to extract the overall urgency of the fire sensing data corresponding to each location inside the high-rise building, and determine the distribution strategy of the edge device according to the overall urgency of the data; The key data checking module performs combined coding processing on the overall urgency of the fire sensing data, transmits the coding sequence in batches through the edge device data transmission network, and executes the key data checking strategy on the input data of each edge device; The fire threat level conversion module is used to convert the verified code sequence into a fire threat level, and synchronize the fire threat level to the fire management platform of the high-rise building.

Images