Fire-fighting facility maintenance method and system based on knowledge graph

Abstract

The invention discloses a fire-fighting facility maintenance method and system based on a knowledge graph, and relates to the technical field of fire fighting, and the method comprises the following steps: S1, constructing a fire-fighting facility maintenance knowledge graph, S2, calling an atomization maintenance step set corresponding to a facility, and S3, dynamically superposing maintenance guidance to an equipment entity based on an augmented reality technology, s4, collecting real-time maintenance action data and comparing the real-time maintenance action data with standard actions in the knowledge graph, S5, performing verification in compulsory execution and completing verification in steps, and S6, responding to an equipment abnormal state, and automatically triggering and pushing associated emergency plan operation guidance. According to the method, operation deviation is reduced through AR dynamic guidance, compliance is ensured through real-time action monitoring and double verification, an emergency plan is simplified in the mode that abnormal second-level triggering is smaller than or equal to 20 seconds, closed-loop management is achieved through bidirectional cooperation of the five modules, AR interaction efficiency is improved by 40%, leapfrogging operation is eradicated through a leak detection prevention controller, data driving execution-optimization intelligent closed loop is achieved, emergency response cross-terminal synchronization is achieved, and operation time is compressed.

Description

Technical Field

[0001] The present invention relates to the field of fire protection technology, and specifically to a fire protection facility maintenance method and system based on a knowledge graph. Background Art

[0002] Existing fire protection facility maintenance technology has systemic flaws. Its fundamental problems can be summarized into four core contradictions: the contradiction between information fragmentation and maintenance accuracy. Key data such as fire protection equipment structural drawings, maintenance manuals, historical work orders, etc. are scattered in paper documents, spreadsheets and manual experience. Maintenance personnel need to spend more than 60% of their time cross-searching multi-source information. In addition, the differences in maintenance standards for different brands of equipment (such as imported sprinkler systems and domestic controllers) are often ignored. Fire statistics in one city show that 38% of disassembly is caused by not checking the hidden buckle structure of a specific model of fire damper. Operations damaged key components. This knowledge gap reduced maintenance to a blind man groping in the dark, creating structural risks and a contradiction between subjective operation and process controllability. Core maintenance actions lacked quantitative monitoring: Parameters were out of control: Fire pipe flanges required 80-100 N·m of torque to tighten, but the actual operation relied entirely on feel, with a deviation rate exceeding 40%; timing was missing: the emergency battery replacement specification limited it to 15 minutes, but the lack of a timing mechanism resulted in an average overtime of 8 minutes; error correction was delayed: when the sensor wiring polarity was incorrect, existing technology could not identify it in real time. Tracing the source of a fire in a commercial complex revealed that this error The problem existed during maintenance three months ago but was not detected. There is a contradiction between the text plan and the timeliness of emergency response. Traditional emergency plans have fatal delays: the response chain is broken: from sensor alarm to manual review of the text plan, consultation with the command center and then to operation execution, the whole process takes more than 8 minutes, far exceeding the golden disposal period; information overload risk: the text plan contains more than 20 operation items, and the execution error rate in emergency situations is as high as 65% (such as accidentally touching the gas fire extinguishing device in an unlit area); resource scheduling is rigid: the command center cannot obtain the location and skill qualifications of on-site maintenance personnel in real time, and once There was a case where a certified personnel was 200 meters away from the fault point but dispatched a novice 1 kilometer away. This shows the contradiction between manual verification and quality reliability, and the acceptance mechanism has double failures: technical failure: the fire pump seal ring compression degree must be ≥90% to meet the standard, but relying solely on visual inspection leads to 25% of seal failures being missed; traceability failure: there is no digital track record of the maintenance process. After a tunnel fire, the valve pressure test value was missing and it took 23 days to define the responsibility. What is more serious is that the pass rate of the same facility fluctuated by more than 30% under the maintenance of different teams, exposing the subjective arbitrariness of the implementation of the standard. Summary of the Invention

[0003] The purpose of the invention provided by the present invention is to provide a fire protection facility maintenance method and system based on knowledge graph to solve the problems in the above-mentioned background technology.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: a fire protection facility maintenance method based on knowledge graph, comprising the following steps:

[0005] S1. Build a knowledge graph for fire protection facility maintenance, linking equipment structure, maintenance action standards, and emergency plans.

[0006] S2. Scan the fire protection facility identification code through the terminal device to retrieve the atomic maintenance step set corresponding to the facility.

[0007] S3. Dynamically superimpose maintenance instructions on the equipment entity based on augmented reality technology.

[0008] S4. Collect maintenance action data in real time and compare it with standard actions in the knowledge graph.

[0009] S5. Enforce verification during execution and step completion verification, including sensor data compliance check and image recognition verification.

[0010] S6. In response to abnormal equipment status, automatically trigger and push the associated emergency plan operation instructions.

[0011] Furthermore, the generation of the atomic maintenance action unit set includes:

[0012] Deconstruct maintenance processes into independently verifiable action units.

[0013] A three-dimensional relationship model of equipment component action standards is established in the knowledge graph, where:

[0014] Action unit associated torque, angle, and duration parameter thresholds.

[0015] Verification standards for component status-associated image features.

[0016] The augmented reality technology dynamic overlay guidelines include:

[0017] Overlay a 3D device disassembly animation on the terminal display interface.

[0018] Position and display the operation direction arrow and torque value on the equipment entity.

[0019] Play real-person operation videos and align them with the device's spatial position.

[0020] Furthermore, the real-time maintenance action data adopts:

[0021] The terminal camera captures the operator's operating posture.

[0022] IoT sensors monitor tool parameters, including torque wrench values, pressure gauge readings, and operation duration.

[0023] The action recognition engine matches the standard action library based on spatiotemporal convolutional neural network.

[0024] Furthermore, the verification during execution includes:

[0025] When the action parameters deviate from the threshold set in the knowledge graph, a real-time sound and light alarm is triggered.

[0026] The current step is locked until the parameters meet the standards, otherwise it is prohibited to enter the next process.

[0027] Furthermore, the steps to complete the verification include:

[0028] It is mandatory to upload photos of the operation results from multiple angles.

[0029] Recognize component status features in images based on convolutional neural networks.

[0030] Compare the standard completion status features in the knowledge graph and output the compliance score.

[0031] Furthermore, the push of emergency plan includes:

[0032] When the firefighting facility sensor detects a sudden drop in pressure or abnormal temperature, the emergency knowledge subgraph is activated.

[0033] Highlight the locations of key operation buttons on the terminal interface.

[0034] Automatically play a simplified operation video with a single operation duration of no more than 20 seconds.

[0035] A fire protection facility maintenance system based on a knowledge graph, the system comprising:

[0036] The main control module is used to execute predetermined plans and issue emergency response instructions in emergency situations.

[0037] Knowledge graph engine, storage device structure model, atomic action library and emergency plan library.

[0038] The AR interaction module enables the spatial overlay of maintenance instructions on the equipment entity.

[0039] Motion monitoring module, integrating sensor data acquisition and image recognition dual verification units.

[0040] Emergency response module, which associates the real-time status of facilities with the knowledge subgraph of emergency plans.

[0041] There is a bidirectional signal connection between the main control module and the knowledge graph engine, a bidirectional signal connection between the main control module and the AR interaction module, a bidirectional signal connection between the main control module and the action monitoring module, and a bidirectional signal connection between the main control module and the emergency response module.

[0042] Furthermore, the action monitoring module includes:

[0043] Torque sensor module: real-time monitoring of tightening operation torque value.

[0044] Gesture recognition module: captures the operation trajectory through the mobile phone camera.

[0045] Anti-missing detection controller module: disables the next step selection when the current step verification is not completed.

[0046] The emergency response module includes:

[0047] Priority trigger module: activates the corresponding emergency plan according to the sensor abnormality level.

[0048] Simplified guide builder module: compresses complex operation processes into card-style guides with three steps or less.

[0049] Cross-terminal synchronization module: synchronously pushes emergency operation instructions to the mobile terminals of on-site personnel and the large screen of the command center.

[0050] An electronic device comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of a fire protection facility maintenance method based on a knowledge graph as described in any one of the above.

[0051] A readable storage medium stores a program or instruction, which, when executed by a processor, implements the steps of a fire protection facility maintenance method based on a knowledge graph as described in any one of the above.

[0052] The present invention provides a fire protection facility maintenance method and system based on knowledge graph, which has the following beneficial effects:

[0053] (1) In the present invention, precise maintenance guidance is provided by constructing a knowledge graph covering multiple brands and models of equipment, associating structures, action standards and emergency plans, eliminating information blind spots, and providing comprehensive and reliable knowledge support for maintenance. The atomic maintenance step set is combined with parameter thresholds and image verification standards to greatly reduce human operational errors. Intelligent process control and augmented reality dynamic guidance intuitively display the operation process, reduce understanding deviations, shorten the training cycle, real-time action monitoring and comparison to instantly identify problems such as torque overlimit and posture errors, and force locking steps until compliance is achieved to ensure operational standardization. Double verification ensures quality. Verification during execution: when parameters exceed the threshold, sound and light alarms are triggered and the process is locked to prevent error accumulation. Verification after step completion: multi-angle image recognition and comparison of component status, output of compliance score, quantification of maintenance quality, efficient emergency response, automatic activation of emergency plan sub-graph when equipment is abnormal, push of simplified operation videos of ≤20 seconds and highlighting of key buttons, shortening emergency response time by more than 70%, sustainable optimization capabilities, knowledge graph supports dynamic update of equipment information and new standards to adapt to the iterative needs of fire protection facilities.

[0054] (2) In the present invention, a modular collaborative architecture is used, and the five core modules are connected through bidirectional signals to achieve real-time data intercommunication and task collaboration. The main control module intelligently dispatches resources to ensure the orderly and efficient maintenance process, and the whole process is closed-loop managed. The motion monitoring module integrates torque sensors, posture recognition, and anti-missing detection controllers to achieve an "operation-monitoring-verification" closed loop. The emergency response module includes a priority trigger, a simplified guidance generator, and a cross-terminal synchronization module to ensure that instructions reach the scene and the command center in seconds. The human-computer interaction is upgraded, and the AR interaction module accurately superimposes virtual guidance on the physical equipment, reducing the difficulty of operation and improving execution efficiency by 40%.

[0055] (3) In the present invention, the intelligent closed-loop operation and maintenance ecology, the real-time data collection in the method drives the system action monitoring module to perform instant analysis, and the results are fed back to the knowledge graph engine optimization standard to form an "execution-learning-optimization" closed loop. The system module provides hardware support for the mandatory execution verification in the method to ensure the implementation of the method logic and double the emergency coordination capability. The method detects equipment anomalies and triggers the system emergency response module, which pushes simplified instructions synchronously across terminals to achieve "monitoring-response-command" integrated disposal, compressing the emergency operation time to within 30 seconds, and improving both maintenance efficiency and safety. The method provides an atomic step set, and the system presents it intuitively through the AR module, reducing the maintenance personnel's time to find information by 80%. The double verification mechanism is linked with the anti-missing detection controller to eliminate skipping operations, and the maintenance compliance rate reaches more than 99%. It is scalable and intelligently managed. The system knowledge graph engine dynamically manages new data accumulated by the method, supports continuous iteration of maintenance standards, and automatically records data and generates reports throughout the entire process, promoting fire protection maintenance from "experience-driven" to "data-driven". BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a general system diagram of a fire protection facility maintenance method and system based on a knowledge graph of the present invention;

[0057] Figure 2 A schematic diagram of a fire protection facility maintenance method and a system action monitoring module based on a knowledge graph according to the present invention;

[0058] Figure 3 This is a schematic diagram of a fire protection facility maintenance method and system emergency response module based on a knowledge graph of the present invention;

[0059] Figure 4 This is a flow chart of a fire protection facility maintenance method and system based on knowledge graph of the present invention.

[0060] In the figure: 1. Main control module; 2. Knowledge graph engine; 3. AR interaction module; 4. Action monitoring module; 5. Emergency response module. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0062] Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but are not to be construed as limiting the present invention.

[0063] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0064] See also Figure 1-4, the present invention provides a technical solution: a fire protection facility maintenance method based on knowledge graph, characterized in that it includes the following steps: S1, constructing a fire protection facility maintenance knowledge graph, associating equipment structure, maintenance action standards and emergency plans, when constructing the fire protection facility maintenance knowledge graph, widely collecting detailed information of various fire protection equipment, covering structural drawings, maintenance manuals and historical maintenance data of equipment of different brands and models, etc., to ensure the comprehensiveness and accuracy of the knowledge graph, provide a solid and reliable knowledge foundation for subsequent maintenance, and reduce maintenance errors caused by incomplete information, S2, scanning the fire protection facility identification code through the terminal device, and retrieving the atomic maintenance step set corresponding to the facility. The generation of the atomic maintenance action unit set includes: decomposing the maintenance process The structure is an independently verifiable action unit, and a three-dimensional relationship model of the equipment component action standards is established in the knowledge graph, among which: the action unit is associated with torque, angle, and duration parameter thresholds, and the component status is associated with the image feature verification standard. After the terminal device scans the fire protection facility identification code, it can quickly and accurately retrieve the corresponding atomic maintenance step set. Thanks to the powerful association and retrieval capabilities of the knowledge graph, this process greatly shortens the time for maintenance personnel to find information, allowing them to quickly engage in maintenance work and improve work efficiency. S3, based on augmented reality technology, dynamically superimpose maintenance instructions on equipment entities. Augmented reality technology dynamically superimposes instructions including: superimposing three-dimensional equipment disassembly animation on the terminal display interface, locating and displaying operation direction arrows and torque values ​​on the equipment entity. , play real-person operation videos and align them with the spatial position of the equipment. The application of augmented reality technology not only makes maintenance instructions more intuitive and vivid, but also reduces operational errors caused by misunderstandings. For example, the three-dimensional equipment disassembly animation allows maintenance personnel to clearly see the internal structure of the equipment and the disassembly sequence. The precise positioning display of the operation direction arrows and torque values ​​ensures the accuracy and standardization of the operation. The synchronous playback and spatial alignment of real-person operation videos further enhance the operation guidance effect. S4. Real-time collection of maintenance action data and comparison with standard actions in the knowledge graph. Real-time maintenance action data uses: terminal cameras to capture personnel operating postures, IoT sensors to monitor tool parameters, including torque wrench values, pressure gauge readings, and operation time. Action recognition The recognition engine is based on the spatiotemporal convolutional neural network to match the standard action library, realizing the real-time collection and comparison of maintenance action data. With the help of terminal cameras, IoT sensors and action recognition engines, it can timely discover irregularities in operations, such as inconsistent torque wrench values, excessive operation time, etc., and immediately remind maintenance personnel to correct them, effectively improving the compliance of maintenance actions. S5, mandatory verification during execution and step completion verification, including sensor data compliance check and image recognition verification. Verification during execution includes: when the action parameters deviate from the threshold set in the knowledge graph, a real-time sound and light alarm is triggered, and the current step is locked until the parameters meet the standards, otherwise it is prohibited to enter the next process. Step completion verification includes: mandatory requirements to upload photos of operation results from multiple angles,Based on the convolutional neural network, the component status features in the image are identified, compared with the standard completion status features in the knowledge graph, and the compliance score is output. The verification in execution and the step completion verification mechanism are enforced, which doubly guarantees the rigor of the maintenance process. The sensor data compliance check and image recognition verification ensure that each step meets the established standards and avoids maintenance loopholes caused by negligence. When the action parameters deviate from the threshold, the real-time sound and light alarm and step locking function force the maintenance personnel to correct the error and ensure the maintenance quality. The step completion verification requires uploading photos of the operation results from multiple angles and performing image recognition comparison to further verify the maintenance effect. The output compliance score also provides a quantitative basis for the subsequent maintenance quality assessment. S6, responds to abnormal equipment status, automatically triggers and pushes The associated emergency plan operation instructions are sent. The push of emergency plans includes: when the fire-fighting facility sensor detects a sudden drop in pressure or abnormal temperature, the emergency knowledge sub-graph is activated, the key operation button position is highlighted on the terminal interface, and a simplified operation video with a single operation time of no more than 20 seconds is automatically played. When responding to abnormal equipment status, the associated emergency plan operation instructions can be quickly and automatically triggered and pushed, which greatly shortens the emergency response time. When the fire-fighting facility sensor detects an abnormality, the activation of the emergency knowledge sub-graph and the playback of the simplified operation video allow on-site personnel to master key emergency operations in the shortest time, reduce accident risks, and improve maintenance accuracy. By deconstructing the maintenance process into atomic maintenance action units and associating parameter thresholds with image feature verification standards, Combined with the powerful association ability of knowledge graphs, it provides maintenance personnel with precise operation guidance, reduces errors caused by human factors, improves the maintenance quality of fire protection facilities, enhances maintenance efficiency, uses terminal equipment to quickly retrieve maintenance step sets, uses augmented reality technology to intuitively display operation instructions, collects and compares data in real time to promptly discover problems, and quickly pushes emergency plans in the event of anomalies. A series of measures improve maintenance work efficiency in all aspects, shortens maintenance cycles, and strengthens safety and reliability. During the maintenance process, action data is monitored in real time and compared with standards. Mandatory verification and step locking mechanisms ensure operational specifications. The emergency response mechanism can respond to equipment anomalies in a timely manner, ensure that fire protection facilities are always in good condition, reduce fire risks, ensure the safety of personnel and buildings, and optimize user experience. The application of augmented reality technology makes operating instructions more intuitive and easier for maintenance personnel to understand and execute, reducing learning costs and operating difficulties, improving the user experience, and realizing intelligent management. The entire system uses advanced technologies such as knowledge graphs, augmented reality, the Internet of Things, and artificial intelligence to achieve intelligent management of fire protection facility maintenance. It can automatically record maintenance data and generate maintenance reports to facilitate subsequent analysis and decision-making, promoting the maintenance and management of fire protection facilities to move towards modernization and intelligence. It has good scalability. The knowledge graph can be continuously updated and improved to incorporate new equipment information, maintenance standards, and emergency plans to adapt to the replacement of fire protection facilities and changes in maintenance requirements. The various modules of the system can also expand and upgrade their functions according to actual needs, and has broad application prospects.

[0065] A fire protection facility maintenance system based on knowledge graph, the system includes: a main control module 1, which is used to execute predetermined plans and issue emergency response instructions under emergency conditions, a knowledge graph engine 2, which stores device structure models, atomic action libraries and emergency plan libraries, an AR interaction module 3, which realizes the spatial superposition of maintenance instructions on equipment entities, an action monitoring module 4, which integrates sensor data acquisition and image recognition dual verification units, an emergency response module 5, which associates the real-time status of facilities with the knowledge subgraph of the emergency plan, a two-way signal connection between the main control module 1 and the knowledge graph engine 2, a two-way signal connection between the main control module 1 and the AR interaction module 3, a two-way signal connection between the main control module 1 and the action monitoring module 4, and a main control module 1. A bidirectional signal connection is established between module 1 and emergency response module 5. The motion monitoring module 4 includes: a torque sensor module for real-time monitoring of tightening torque values; a posture recognition module for capturing operation trajectories using a mobile phone camera; an anti-missing detection controller module for disabling the next step selection when verification of the current step is not complete; and emergency response module 5 includes: a priority trigger module for activating the corresponding emergency plan based on the sensor anomaly level; a simplified guidance generator module for compressing complex operation processes into card-style instructions with three or fewer steps; and a cross-terminal synchronization module for simultaneously pushing emergency operation instructions to on-site personnel's mobile terminals and the command center's large screen. These modules work together to form a complete and efficient maintenance system. The main control module 1 serves as the core, rationally allocating resources across modules to ensure the orderly execution of the maintenance process. The knowledge graph engine 2 provides knowledge support for the entire system. The AR interaction module 3 enhances the visualization and convenience of operations. The motion monitoring module 4 enables precise monitoring and verification, and the emergency response module 5 ensures the system's rapid response capabilities in emergency situations. The bidirectional signal connection between the modules ensures the real-time flow and interaction of information, enabling the efficient and stable operation of the entire system.

[0066] An electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of a fire protection facility maintenance method based on a knowledge graph as described above are implemented.

[0067] A readable storage medium stores a program or instruction, which, when executed by a processor, implements the steps of a fire protection facility maintenance method based on a knowledge graph as described above.

[0068] The above are only preferred embodiments of the present invention. It should be pointed out that those skilled in the art can make several modifications and improvements without departing from the inventive concept of the present invention, and these all fall within the scope of protection of the present invention.

Claims

1. A fire protection facility maintenance method based on knowledge graph, characterized in that: The steps include: S1. Build a knowledge graph for fire protection facility maintenance, linking equipment structure, maintenance action standards, and emergency plans; S2. Scan the fire protection facility identification code through the terminal device to retrieve the atomic maintenance step set corresponding to the facility; S3. Dynamically superimpose maintenance instructions on equipment entities based on augmented reality technology; S4, collect real-time maintenance action data and compare it with standard actions in the knowledge graph; S5, verification during enforcement and step completion verification, including sensor data compliance checks and image recognition verification; S6. In response to abnormal equipment status, automatically trigger and push the associated emergency plan operation instructions.

2. A fire protection facility maintenance method based on knowledge graph according to claim 1, characterized in that: The generation of the atomic maintenance action unit set includes: Deconstruct the maintenance process into independently verifiable action units; A three-dimensional relationship model of equipment component action standards is established in the knowledge graph, where: Action unit associated torque, angle, and duration parameter thresholds; Verification standards for component status-related image features; The augmented reality technology dynamic overlay guidelines include: Overlay a 3D device disassembly animation on the terminal display interface; Position and display the operation direction arrow and torque value on the equipment entity; Play real-person operation videos and align them with the device's spatial position.

3. A fire protection facility maintenance method based on knowledge graph according to claim 1, characterized in that: The real-time maintenance action data collection: The terminal camera captures the operator's operating posture; IoT sensors monitor tool parameters, including torque wrench values, pressure gauge readings, and operation duration; The action recognition engine matches the standard action library based on spatiotemporal convolutional neural network.

4. A fire protection facility maintenance method based on knowledge graph according to claim 1, characterized in that: The verification during execution includes: When the action parameters deviate from the threshold set in the knowledge graph, a real-time sound and light alarm is triggered; The current step is locked until the parameters meet the standards, otherwise it is prohibited to enter the next process.

5. The fire protection facility maintenance method based on knowledge graph according to claim 1 is characterized in that: The steps to complete the verification include: It is mandatory to upload photos of the operation results from multiple angles; Identify component status features in images based on convolutional neural networks; Compare the standard completion status features in the knowledge graph and output the compliance score.

6. A fire protection facility maintenance method based on knowledge graph according to claim 1, characterized in that: The push emergency plan includes: When the firefighting facility sensor detects a sudden drop in pressure or abnormal temperature, the emergency knowledge subgraph is activated; Highlight the locations of key operation buttons on the terminal interface; Automatically play a simplified operation video with a single operation duration of no more than 20 seconds.

7. A fire protection facility maintenance system based on knowledge graph, characterized in that: The system comprises: A main control module (1) is used to execute predetermined plans and issue emergency response instructions in emergency situations; Knowledge graph engine (2), storage device structure model, atomic action library and emergency plan library; AR interaction module (3) realizes spatial superposition of maintenance instructions on the equipment entity; Motion monitoring module (4), integrating sensor data acquisition and image recognition dual verification units; Emergency response module (5), which associates the real-time status of facilities with the knowledge subgraph of emergency plans; A bidirectional signal connection is established between the main control module (1) and the knowledge graph engine (2), a bidirectional signal connection is established between the main control module (1) and the AR interaction module (3), a bidirectional signal connection is established between the main control module (1) and the action monitoring module (4), and a bidirectional signal connection is established between the main control module (1) and the emergency response module (5).

8. The fire protection facility maintenance system based on knowledge graph according to claim 1 is characterized in that: The action monitoring module (4) comprises: Torque sensor module: real-time monitoring of tightening operation torque value; Gesture recognition module: captures the operation trajectory through the mobile phone camera; Anti-missing inspection controller module: disables the next step selection when the current step verification is not completed; The emergency response module (5) comprises: Priority trigger module: activates the corresponding emergency plan according to the abnormal level of the sensor; Simplified guide builder module: compresses complex operation processes into card-style guides with three steps or less; Cross-terminal synchronization module: synchronously pushes emergency operation instructions to the mobile terminals of on-site personnel and the large screen of the command center.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of a fire protection facility maintenance method based on a knowledge graph as described in any one of claims 1 to 6 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of a fire protection facility maintenance method based on a knowledge graph as described in any one of claims 1 to 6 are implemented.

Images