Intelligent fire-fighting inspection system based on multi-module cooperation

Abstract

The invention is suitable for the technical field of fire safety and intelligent scheduling control, and provides an intelligent fire-fighting inspection system based on multi-module collaboration, which comprises a data acquisition and layout comparison module, a data processing module, a data processing module and a data processing module, and the analysis module is used for acquiring the current inspection data, the initial inspection frequency index and the corresponding initial layout data of the target inspection area, and analyzing the current inspection data and the initial layout data. According to the invention, by introducing a positive and negative influence identification mechanism and combining multiple types of fire-fighting performance evaluation parameters, bidirectional quantitative evaluation of fire-fighting performance change in layout change is realized. Compared with the prior art in which only deterioration items are identified for frequency adjustment, the method further identifies the optimization influence possibly brought by layout adjustment, constructs the comprehensive correction factor based on the weighted combination, and dynamically corrects the inspection frequency index, thereby avoiding the resource waste caused by high frequency.

Description

Technical Field

[0001] This invention belongs to the field of fire safety and intelligent dispatch control technology, and in particular relates to an intelligent fire inspection system based on multi-module collaboration. Background Technology

[0002] Currently, with the increasing construction density of large public spaces such as commercial complexes and supermarkets, higher demands are being placed on dynamic fire safety inspections. To promptly identify potential safety hazards, existing technologies widely utilize intelligent inspection systems based on inspection frequency indices. These systems typically generate corresponding inspection priorities or frequency indices based on parameters such as area attributes, equipment density, and historical alarm records, thereby guiding actual inspection scheduling strategies and achieving the orderly allocation and dynamic management of fire protection resources.

[0003] However, existing technologies generally focus on identifying and responding to layout changes that may degrade fire safety performance, such as new facilities obstructing fire exits, narrowing evacuation routes, or affecting equipment accessibility. They then increase inspection frequency or shorten inspection cycles after such situations are detected. While this type of adjustment mechanism, based on a one-way increase in risk, has some practical value, it overlooks the potential optimizing effects of some layout changes on fire safety performance. For example, some newly added partitions, while obstructing some passageways, may actually improve lighting or airflow in the area, thus enhancing visibility and perception accuracy.

[0004] Therefore, the existing model has two significant defects: first, it fails to achieve two-way identification and analysis of the "positive and negative changes" in fire protection performance, resulting in a one-sided assessment basis for the adjustment of inspection frequency; second, it lacks a mechanism for handling the mutual cancellation relationship between the influence of multiple factors, making it difficult to fully reflect the real fire protection status. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent fire inspection system based on multi-module collaboration, which aims to solve the problems mentioned in the background art.

[0006] This invention is implemented as follows: an intelligent fire inspection system based on multi-module collaboration, the system comprising:

[0007] The data acquisition and layout comparison module is used to acquire the current inspection data, initial inspection frequency index and corresponding initial layout data of the target inspection area, analyze the current inspection data and initial layout data, and filter out the specified layout changes that have the effect of deteriorating fire performance.

[0008] The positive and negative impact identification module is used to determine whether a specified layout change has an impact on fire performance optimization based on the current inspection data. If it does, it is marked as the target layout change.

[0009] The impact magnitude assessment and weight allocation module is used to identify several fire performance degradation impact types and several optimization impact types in each target layout change item, calculate the impact change magnitude of each impact type, and assign corresponding weights to each impact type according to the preset weight allocation table, and generate the comprehensive correction factor of the target layout change item by linear combination.

[0010] The frequency index correction module is used to combine the comprehensive correction factors of all target layout changes to generate the inspection frequency adjustment coefficient, correct the initial inspection frequency index, obtain the corrected inspection frequency index, and use it to dynamically adjust the inspection frequency or scheduling strategy of the target inspection area.

[0011] As a further limitation of the technical solution of this embodiment of the invention, the data acquisition and layout comparison module is used to extract information on changes in the location of fire protection facilities based on the current inspection data and the initial layout data, and to determine whether any of the following types of fire performance degradation exist, so as to identify the specified layout changes that have a fire performance degradation effect. The fire performance degradation effect types include:

[0012] Firefighting facilities are obstructed, evacuation routes are narrowed, accessibility of firefighting facilities is reduced, and surveillance visibility is decreased.

[0013] As a further limitation of the technical solution of this embodiment of the invention, the positive and negative influence identification module specifically includes:

[0014] The optimization impact identification unit is used to parse the current inspection data and analyze whether there is an optimization impact type that has an optimization impact on fire protection performance after any specified layout change occurs. The optimization impact types include enhanced lighting, smooth airflow, expanded camera coverage, and smooth evacuation routes.

[0015] The target change determination unit is used to identify a specified layout change as a target layout change when it is determined that the specified layout change has an impact on fire performance optimization, and to extract the fire performance deterioration impact type and optimization impact type corresponding to the target layout change.

[0016] As a further limitation of the technical solution of the present invention, the influence magnitude assessment and weight allocation module is preset with a weight allocation table, which is used to assign corresponding weighted weight values ​​to each deterioration influence type and each optimization influence type when any layout change causes one or more fire performance deterioration influence types and one or more optimization influence types to occur simultaneously. The weighted weight value corresponding to the deterioration influence type is given a positive sign, and the weighted weight value corresponding to the optimization influence type is given a negative sign.

[0017] The weighted weight values ​​are set based on the independent influence intensity of each type of influence in historical data. The weighted weight values ​​corresponding to the deteriorating influence type are given a positive sign, and the weighted weight values ​​corresponding to the optimizing influence type are given a negative sign, so that different influence types can form an offsetting relationship in the weighted combination calculation, thereby comprehensively generating the correction factor of the target layout change item.

[0018] As a further limitation of the technical solution of this embodiment of the invention, the influence magnitude assessment and weight allocation module specifically includes:

[0019] The impact type identification and magnitude calculation unit is used to identify several fire performance deterioration impact types and several optimization impact types corresponding to each target layout change item, and extract fire performance evaluation parameters related to each impact type based on the current inspection data and initial layout data, calculate the parameter change values ​​before and after the layout change, so as to determine the impact change magnitude of each impact type.

[0020] The weighting and allocation unit is used to call the preset weighting allocation table and assign corresponding weighted weight values ​​to each identified fire performance degradation impact type and optimization impact type.

[0021] The correction factor generation unit is used to multiply the magnitude of the impact change of each impact type with its corresponding weighted weight value in a linear combination manner, and then sum up all the product results to generate the comprehensive correction factor corresponding to the target layout change item.

[0022] As a further limitation of the technical solution of this embodiment of the invention, the fire performance evaluation parameters include, but are not limited to:

[0023] Fire protection facility obstruction rate, effective width of evacuation routes, accessibility score of fire protection facilities, light intensity, airflow, field of view integrity of surveillance cameras, or other structural parameters that can quantify the fire protection performance status.

[0024] As a further limitation of the technical solution of this embodiment of the invention, the frequency index correction module specifically includes:

[0025] The adjustment coefficient generation unit is used to calculate the average value of the comprehensive correction factor of all target layout changes, and combine it with the preset intensity control factor to generate the corresponding inspection frequency adjustment coefficient.

[0026] The frequency index correction unit is used to call a preset correction function and correct the initial inspection frequency index based on the inspection frequency adjustment coefficient to obtain the corrected inspection frequency index.

[0027] The frequency index application unit is used to apply the corrected inspection frequency index to the dynamic adjustment of the inspection frequency of the target inspection area, so as to control the actual inspection execution frequency or cycle setting.

[0028] As a further limitation of the technical solution of this embodiment of the invention, the preset correction function is:

[0029] ;

[0030] in, This refers to the revised inspection frequency index. This refers to the initial inspection frequency index. This refers to the total number of target layout changes. It refers to the first The comprehensive correction factor corresponding to each target layout change item. This refers to the average of the comprehensive correction factors for all target layout changes. This refers to the preset intensity control factor, and it satisfies... , This refers to the inspection frequency adjustment coefficient;

[0031] In the preset correction function:

[0032] ;

[0033] in, It refers to the first The number of all impact types involved in each target layout change item It refers to the first Among the target layout changes, the first one is... The magnitude of change in impact corresponding to each type of impact. It refers to the first Among the target layout changes, the first one is... The weighted weights corresponding to each type of influence.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] This invention introduces a mechanism for identifying both positive and negative impacts, combined with multiple types of fire performance evaluation parameters, to achieve a two-way quantitative assessment of fire performance changes during layout modifications. Compared to existing technologies that only identify deteriorating factors and adjust frequencies accordingly, this invention further identifies the potential optimization effects of layout adjustments and constructs a comprehensive correction factor based on weighted combinations to dynamically adjust the inspection frequency index, thereby avoiding resource waste caused by excessively high frequencies. This mechanism not only improves the objectivity and accuracy of inspection decisions but also significantly enhances the system's responsiveness to actual spatial structural evolution, making it particularly suitable for large commercial venues with frequent layout changes. Attached Figure Description

[0036] Figure 1 Application architecture diagram of the system provided in the embodiments of the present invention;

[0037] Figure 2 This is a structural block diagram of the positive and negative influence identification module in the system provided in the embodiments of the present invention;

[0038] Figure 3 This is a structural block diagram of the influence magnitude assessment and weight allocation module in the system provided in the embodiments of the present invention;

[0039] Figure 4 This is a structural block diagram of the frequency exponential correction module in the system provided in an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0041] Figure 1 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0042] In another preferred embodiment of the present invention, an intelligent fire inspection system based on multi-module collaboration includes:

[0043] The data acquisition and layout comparison module 100 is used to acquire the current inspection data, initial inspection frequency index and corresponding initial layout data of the target inspection area, analyze the current inspection data and initial layout data, and filter out the specified layout changes that have the effect of deteriorating fire performance.

[0044] The data acquisition and layout comparison module 100 is used to extract information on changes in the location of fire protection facilities based on the current inspection data and the initial layout data, and to determine whether any of the following types of fire performance degradation exist, so as to identify the specified layout changes that have a fire performance degradation impact. The fire performance degradation impact types include:

[0045] Firefighting facilities are obstructed, evacuation routes are narrowed, accessibility of firefighting facilities is reduced, and surveillance visibility is decreased.

[0046] In this embodiment of the invention, the target inspection area can be the interior space of buildings with a certain degree of structural complexity and personnel mobility, such as large commercial complexes, shopping malls, supermarkets, convention centers, and office buildings. These areas generally have the characteristics of clear zoning, dense facilities, complex passage networks, and diverse functional distribution. Moreover, with daily activities such as business adjustments and exhibition updates, their internal layout frequently undergoes non-structural changes. Therefore, the need for monitoring the status of fire protection facilities and adjusting the frequency of inspections is particularly urgent.

[0047] Current inspection data may include, but is not limited to, environmental monitoring image data, laser point cloud data, spatial modeling information, fire protection facility sensor status data, infrared or visible light monitoring images, inspection robot feedback information, and manual operation feedback records. This data can be collected through various means, such as automated inspection equipment (e.g., fire inspection robots), fixed cameras, sensor networks, or management personnel inspection terminals, and uploaded to the central control system for unified processing.

[0048] The initial inspection frequency index is used to set a basic inspection frequency threshold or recommended frequency for the target inspection area. Its purpose is to provide a starting point reference for inspection plan scheduling. It is usually derived from system evaluation upon successful fire safety acceptance or preset based on regulations or industry standards. The initial inspection frequency index has mature applications in existing technologies, for example, setting a basic frequency based on the number of equipment, area level, and historical failure rate. However, the core problem with existing models is that when assessing the fire safety impact of layout changes, they only weight and sum factors that worsen the impact, without considering the fire safety performance optimization effects that some layout changes may bring. This fails to achieve a counterbalancing analysis of positive and negative effects, leading to the system overestimating the inspection frequency, resulting in resource waste and decreased execution efficiency.

[0049] Initial layout data generally comes from spatial layout information, structural drawings, 3D modeling results, or datasets output by BIM systems generated during the fire safety acceptance phase. It typically includes spatial zoning structure, original layout locations of various fire-fighting equipment, distribution of fixed obstacles, standard width and direction of evacuation routes, camera installation angles and coverage areas, etc.

[0050] In the specific implementation process, the data acquisition and layout comparison module 100 uses layout alignment and difference analysis to identify specified layout changes. This module first performs spatial reconstruction processing on the current inspection data and the initial layout data to establish a structural mapping model under a unified coordinate system. It often achieves the alignment and fusion of dynamic and static layouts through 3D point cloud fitting, sparse feature matching, geometric projection of image semantic segmentation results, or parameter comparison based on the BIM model.

[0051] After alignment, the module further performs gridded partitioning analysis, using methods such as grid difference mapping, voxel occupancy grid analysis, or offset calculation based on Euclidean distance field to identify whether there are suspicious behaviors such as positional movement, increased obstruction, visual obstruction, or passage encroachment of fire protection facilities and their surrounding structures in the current state compared to the initial state.

[0052] Taking the obstruction of fire-fighting facilities as an example, after comparing the current data with the initial model, if the system finds that newly added obstructions (such as temporary shelves, display cases, decorative panels, etc.) around the fire-fighting facilities form a semi-enclosed or closed coverage in terms of structure, and their boundaries overlap with the facility itself in the image projection, resulting in a significant decrease in the image texture clarity or brightness intensity of the area where the facility is located, then the system can determine that the area constitutes an obstruction. For narrowing evacuation routes, the system automatically determines whether a bottleneck is caused by newly added objects by calculating the equivalent width of the route section and combining it with national standard thresholds. It also assesses the impact on evacuation behavior through simulated pedestrian flow analysis.

[0053] When determining a decline in facility accessibility, the system further assesses whether the physical access paths for firefighters to critical facilities (such as fire extinguishers and fire hydrants) are significantly blocked, and whether there are situations requiring detours or inefficient access. The judgment criteria are based on the inspection path generation algorithm and the facility contact behavior model. For detecting reduced surveillance visibility, the system compares initial and current view images to identify whether the addition of walls, billboards, or construction barriers has caused dead zones, blurred recognition, or target obstruction in the camera's view. If critical areas (such as evacuation routes and fire control equipment) are obstructed for an extended period, it constitutes a deterioration in visibility.

[0054] Through the above series of structured identification and rule-driven analysis, the module finally screens out the specified layout changes that have a deterioration effect on fire performance, and uses them as the basic input data for subsequent positive and negative impact identification and correction factor evaluation, ensuring that the entire dynamic inspection and adjustment mechanism has a logical closed loop and is feasible to implement.

[0055] Although this embodiment only uses the above four impact types as the primary identification categories due to their strong practicality, clear identification logic, and unified evaluation standards, the system still has scalability. In practical applications, other potential fire performance degradation impact types can be introduced, such as: misleading fire protection facility markings (e.g., incorrect arrow direction); weakened fire source isolation zone function (e.g., mobile equipment blocking fire doors); structural collapse risk caused by inverted stacked structures; obstructed or misconnected fire linkage interfaces; and increased risk of smoke retention due to poor ventilation in local areas.

[0056] Furthermore, the intelligent fire inspection system based on multi-module collaboration also includes:

[0057] The positive and negative impact identification module 200 is used to determine whether a specified layout change has an impact on fire performance optimization based on the current inspection data. If it does, it is marked as a target layout change.

[0058] Specifically, Figure 2 The diagram shows a structural block diagram of the positive and negative influence identification module 200 in the system provided by an embodiment of the present invention.

[0059] In a preferred embodiment provided by the present invention, the positive and negative influence identification module 200 specifically includes:

[0060] The optimization impact identification unit 201 is used to parse the current inspection data and analyze whether there is an optimization impact type that has an optimization impact on fire protection performance after any specified layout change occurs. The optimization impact types include enhanced lighting, smooth airflow, expanded camera coverage, and smooth evacuation routes.

[0061] The target change determination unit 202 is used to determine a specified layout change as a target layout change when it is determined that a specified layout change has an impact on fire performance optimization, and to extract the fire performance deterioration impact type and optimization impact type corresponding to the target layout change.

[0062] In this embodiment of the invention, the specific implementation of the optimized impact identification unit 201 can perform feature extraction and quantification based on multi-source information in the current inspection data. Specifically, this unit preferably integrates an image processing subunit, an environmental parameter analysis subunit, and a structural space modeling subunit, and can extract indicative features related to fire performance optimization from visible images, sensor sampling data, point cloud models, or time-series feedback returned by inspection equipment.

[0063] Taking enhanced illumination as an example, the system can compare the changes in brightness histogram, color temperature distribution, and shadow area of ​​key areas (such as the front of fire-fighting facilities) in the current inspection image and the initial state image. If it is found that the brightness of the illuminated surface of the facility is increased, the shading structure is reduced, and the average ambient illuminance is increased beyond the set threshold, then it can be determined that an enhanced illumination phenomenon has occurred in that area. For smooth airflow, air velocity sensors or temperature and humidity field analysis data can be used to calculate the increase in local airflow velocity or air exchange efficiency after the new layout is formed. The system can make judgments through simplified CFD models or historical ventilation simulation data.

[0064] Regarding expanding camera coverage, the system reconstructs the camera field-of-view model by calculating the reflection angle, spatial transparency, and occlusion reduction effects of the new layout on the camera's field of view, and determines whether key areas have transitioned from being invisible to being visible. For ensuring smooth evacuation routes, a path connectivity analysis algorithm reconstructs the shortest evacuation path map after the layout changes. If a decrease in the number of path nodes, a gentler turning angle, or an increase in the average passage width per unit area is observed, these are considered optimization effects that improve evacuation route smoothness.

[0065] Although this embodiment primarily employs four optimization impact types—enhanced lighting, improved airflow, expanded camera coverage, and smoother evacuation routes—based on their clear identification logic, controllable data sources, and strong parameter quantification capabilities, the system itself possesses scalability. In other applications, other optimization impact types can be introduced, such as reduced noise interference, improved signage visibility, clearly identifiable fireproof partitions, and optimized orientation of fire extinguishing equipment labels. The system can expand its judgment capabilities through continuous training and rule updates.

[0066] The analysis methods and identification processes used by the optimized impact identification unit 201 are all technical means that can be implemented under existing technical conditions, and have high engineering feasibility and integration stability.

[0067] The target change determination unit 202 is used to mark a specified layout change as a target layout change when it is detected that the change also has an impact on fire performance optimization, and to extract all its corresponding deterioration and optimization impact types. It should be noted that a layout change often triggers multiple positive and negative impacts simultaneously in practical applications.

[0068] For example, adding a glass partition wall to an area may cause two negative impacts: narrowing evacuation routes and reducing accessibility to fire-fighting facilities. However, due to decreased spatial enclosure and increased light penetration, it also creates an positive impact: enhanced lighting. Similarly, adding an elevated display stand to a shopping mall area may obstruct fire-fighting facilities and reduce surveillance visibility, but the improved flow of traffic after a redesigned corridor layout creates a positive impact: smoother evacuation routes. In these structural changes, multiple positive and negative impact types coexist. Therefore, the system needs to extract all existing types simultaneously for subsequent impact magnitude assessment and weighted combination analysis.

[0069] Identifying the target layout changes reflects that, under the current inspection status, these changes not only pose potential risks but also have certain positive impacts. Their actual impact on fire performance is complex and cannot be simply categorized as a single deteriorating trend. Therefore, including them in the target layout changes provides a more objective and balanced assessment basis for the subsequent generation of comprehensive correction factors, thereby improving the rationality and targeting of inspection frequency adjustments.

[0070] Furthermore, the intelligent fire inspection system based on multi-module collaboration also includes:

[0071] The impact magnitude assessment and weight allocation module 300 is used to identify several fire performance degradation impact types and several optimization impact types in each target layout change item, calculate the impact change magnitude of each impact type, and assign corresponding weights to each impact type according to the preset weight allocation table, and generate the comprehensive correction factor of the target layout change item by linear combination.

[0072] The impact magnitude assessment and weight allocation module has a preset weight allocation table, which is used to assign corresponding weighted weight values ​​to each deterioration impact type and each optimization impact type when any layout change causes one or more fire performance deterioration impact types and one or more optimization impact types to occur simultaneously. The weighted weight value corresponding to the deterioration impact type is given a positive sign, and the weighted weight value corresponding to the optimization impact type is given a negative sign.

[0073] The weighted weight values ​​are set based on the independent influence intensity of each type of influence in historical data. The weighted weight values ​​corresponding to the deteriorating influence type are given a positive sign, and the weighted weight values ​​corresponding to the optimizing influence type are given a negative sign, so that different influence types can form an offsetting relationship in the weighted combination calculation, thereby comprehensively generating the correction factor of the target layout change item.

[0074] Specifically, Figure 3 The diagram shows the structural block diagram of the influence magnitude assessment and weight allocation module 300 in the system provided by the embodiment of the present invention.

[0075] In a preferred embodiment of the present invention, the influence magnitude assessment and weight allocation module 300 specifically includes:

[0076] The impact type identification and magnitude calculation unit 301 is used to identify several fire performance deterioration impact types and several optimization impact types corresponding to each target layout change item, and extract fire performance evaluation parameters related to each impact type based on the current inspection data and initial layout data, calculate the parameter change values ​​before and after the layout change, so as to determine the impact change magnitude of each impact type.

[0077] The weight call and allocation unit 302 is used to call the preset weight allocation table and assign corresponding weight values ​​to each identified fire performance deterioration impact type and optimization impact type.

[0078] The correction factor generation unit 303 is used to multiply the magnitude of the impact change of each impact type with its corresponding weighted weight value in a linear combination manner, and then sum up all the product results to generate the comprehensive correction factor corresponding to the target layout change item.

[0079] Fire performance evaluation parameters include, but are not limited to:

[0080] Fire protection facility obstruction rate, effective width of evacuation routes, accessibility score of fire protection facilities, light intensity, airflow, field of view integrity of surveillance cameras, or other structural parameters that can quantify the fire protection performance status.

[0081] In this embodiment of the invention, the impact type identification and magnitude calculation unit 301 is specifically used to perform structured identification of the fire performance deterioration impact type and optimization impact type involved in each target layout change item, and extract fire performance evaluation parameters associated with each type of impact based on the initial layout data and the current inspection data, thereby calculating the parameter change magnitude corresponding to the type before and after the layout change, as the basis for the impact change magnitude.

[0082] In practice, this unit completes the parameter extraction task based on the fusion analysis of image sequences, laser point clouds, infrared scans, environmental sensor data, and pre-built BIM models. The methods for obtaining various fire performance evaluation parameters are as follows:

[0083] Fire protection facility obstruction rate: The visible area of ​​the target facility surface is quantified by combining image semantic segmentation with depth map reconstruction, and the obstruction percentage is obtained by comparing it with the complete visible area of ​​the facility in the initial layout model.

[0084] Effective width of evacuation routes: Identify the boundary lines of the routes in a two-dimensional plan view or point cloud model, calculate the effective passage width at the narrowest point of the route, and exclude the interference of irrelevant objects;

[0085] Fire safety facility accessibility rating: The difficulty of the shortest path for people from the accessible starting point to the facility location is simulated using path planning algorithms (such as A*, Dijkstra), and the rating is based on a comprehensive index of factors such as the number of obstacles, the number of detours, and the path redundancy.

[0086] Illumination intensity: Collect the brightness value or unit luminous flux of the area where the fire protection facilities are located, based on image histogram analysis or illuminance meter data;

[0087] Airflow smoothness: Based on the comparison of the initial and current wind speed field distribution changes using thermal / wind speed sensors, etc.

[0088] Completeness of field of view of surveillance cameras: By using edge detection and target occlusion analysis of images captured by cameras, dead zones are identified, and the proportion of the visible area in the image is calculated.

[0089] The above-mentioned data collection methods are all mature and widely used existing technologies such as visual recognition, SLAM navigation, IoT sensing, and environmental modeling. They can be integrated into existing intelligent inspection platforms without the need to develop underlying algorithms.

[0090] The weight invocation and allocation unit 302 is primarily responsible for invoking the system's preset weight allocation table based on the identified multiple influence types, and assigning weighted weight values ​​to each influence type. This preset weight allocation table originates from the training phase or historical experience accumulation phase before system deployment and can be established in the following manner:

[0091] In the statistical analysis of historical fire hazard data, the probability of risk escalation corresponding to different types of changes is analyzed.

[0092] The descriptions of the severity levels of various hazards in comprehensive regulatory provisions (such as the "Code for Fire Protection Design of Buildings" and the "Guidelines for Fire Inspection of Shopping Malls");

[0093] An influencing factor system is formed by combining expert scores or simulation data (such as traffic delays caused by narrowing passages in real-world simulations).

[0094] This table is commonly used in dynamic safety assessment systems, facility maintenance priority ranking systems, and intelligent fire inspection dispatch systems, and has been successfully applied in practical deployments.

[0095] The system stipulates that the weight of the type of fire performance degradation is positive, and the weight of the type of optimization is negative. This is mainly to form a numerical "offset" mechanism in the final linear combination. That is, when a change brings both positive and negative effects, the positive (negative) weight can reduce the overall weight of the degradation effect (positive) in numerical terms, thereby reflecting the balance of the actual fire performance.

[0096] The function of the correction factor generation unit 303 is to linearly combine the identified magnitude of change in influence with the corresponding weight values. The reason for using linear combination is that: this method is transparent, highly interpretable, and facilitates traceable auditing; it can quickly overlay multiple types of effect results, making it suitable for multi-factor combination analysis; and in engineering applications, it facilitates integration with subsequent parameter modules such as adjustment coefficients and exponential models.

[0097] Of course, in addition to the linear combination method, other methods such as weighted average, normalized comparison index, and fuzzy logic evaluation can also be considered to construct the correction factor. However, the linear combination method has higher operability and integration efficiency under the current fire inspection data structure and response mechanism.

[0098] Furthermore, the intelligent fire inspection system based on multi-module collaboration also includes:

[0099] The frequency index correction module 400 is used to combine the comprehensive correction factors of all target layout changes to generate the inspection frequency adjustment coefficient, correct the initial inspection frequency index, obtain the corrected inspection frequency index, and use it to dynamically adjust the inspection frequency or scheduling strategy of the target inspection area.

[0100] Specifically, Figure 4 A structural block diagram of the frequency exponent correction module 400 in the system provided in an embodiment of the present invention is shown.

[0101] In a preferred embodiment of the present invention, the frequency exponent correction module 400 specifically includes:

[0102] The adjustment coefficient generation unit 401 is used to calculate the average value of the comprehensive correction factor of all target layout changes, and combine it with the preset intensity control factor to generate the corresponding inspection frequency adjustment coefficient.

[0103] The frequency index correction unit 402 is used to call a preset correction function and correct the initial inspection frequency index based on the inspection frequency adjustment coefficient to obtain the corrected inspection frequency index.

[0104] The frequency index application unit 403 is used to apply the corrected inspection frequency index to the dynamic adjustment of the inspection frequency of the target inspection area in order to control its actual inspection execution frequency or cycle setting.

[0105] The preset correction function is:

[0106] ;

[0107] in, This refers to the revised inspection frequency index. This refers to the initial inspection frequency index. This refers to the total number of target layout changes. It refers to the first The comprehensive correction factor corresponding to each target layout change item. This refers to the average of the comprehensive correction factors for all target layout changes. This refers to the preset intensity control factor, and it satisfies... , This refers to the inspection frequency adjustment coefficient;

[0108] In the preset correction function:

[0109] ;

[0110] in, It refers to the first The number of all impact types involved in each target layout change item It refers to the first Among the target layout changes, the first one is... The magnitude of change in impact corresponding to each type of impact. It refers to the first Among the target layout changes, the first one is... The weighted weights corresponding to each type of influence.

[0111] In this embodiment of the invention, the main purpose of introducing a comprehensive correction factor is to introduce a unified measurement of positive and negative factors during the dynamic adjustment of the inspection frequency index, so as to achieve a more objective and interpretable frequency correction judgment. Traditional models often only consider the impact of layout changes on fire performance degradation, thus often overestimating the risk level and leading to an excessively high inspection frequency, thereby increasing unnecessary manpower and resource investment. This invention, while identifying the types of fire performance degradation impacts, also considers possible simultaneous optimization effects and forms a comprehensive correction factor through linear combination calculation, ensuring that the correction result reflects the balance between risk and improvement.

[0112] When multiple target layout changes coexist, the system averages the comprehensive correction factors of each change as the basis for frequency adjustment. This approach helps eliminate disturbances from individual extreme values, maintaining a stable overall adjustment trend. Furthermore, the system introduces an intensity control factor, allowing users to flexibly control the adjustment range based on scenario risk tolerance. The final correction mechanism uses "1 minus the adjustment coefficient" as the frequency adjustment coefficient, multiplied by the initial frequency index. If the adjustment coefficient is large, it reflects a significant improvement in fire performance due to the current overall layout changes, and the frequency will be reasonably reduced; if the adjustment coefficient approaches zero, the frequency will remain essentially unchanged.

[0113] The frequency index application unit 403 is used to apply the corrected inspection frequency index to the dynamic adjustment of the inspection frequency in the target inspection area. This unit, through integration with the system scheduling strategy module, automatically corrects the execution frequency or time period of subsequent inspection tasks in that area. When the corrected inspection frequency index decreases compared to the initial value, the system automatically extends the inspection cycle or reduces the inspection frequency to alleviate the pressure of ineffective tasks; conversely, it automatically increases the inspection density to address potential increases in risk. This application process can be embedded into existing intelligent inspection platforms and dynamically invoked through a task generation engine or scheduling module, exhibiting good system compatibility and deployment feasibility.

[0114] This case study achieves a structural optimization of the traditional inspection frequency assessment method, which is centered on "deterioration," by comprehensively considering both positive and negative changes in fire performance. Its significant advantages are twofold: firstly, it can accurately capture the increased fire performance risk caused by changes in regional structure, triggering timely frequency adjustments; secondly, it can identify the positive improvement effects brought about by layout adjustments, avoiding unnecessary frequency redundancy and thus saving inspection resources. This mechanism is particularly suitable for scenarios with frequent layout adjustments and high management pressure, such as large shopping malls, commercial complexes, and warehousing and logistics parks, possessing significant practical value and broad prospects for promotion.

[0115] Taking a specific application scenario as an example, assuming the target area is a commercial floor, the system detects two changes in the target layout. The first change detects a 1.5-meter reduction in evacuation route width (weight +0.8), a 30% increase in surveillance obstruction (weight +0.5), and a 15% increase in light intensity (weight -0.4). A linear weighted calculation yields a comprehensive correction factor of 1.29. The second change detects a 20% increase in facility obstruction (weight +0.6), an improvement in airflow of 0.5 m / s (weight -0.5), and an improvement in path unobstructedness (weight -0.3). A linear weighted calculation yields a comprehensive correction factor of -0.25. The average of these two changes is 0.52. Assuming an intensity control factor of 0.5, a final adjustment coefficient of 0.26, and an initial frequency index of 1.0, the corrected factor is 0.74. This means the originally planned daily inspection frequency will be adjusted to once every 1.35 days. This example illustrates that the present invention, by integrating positive and negative factors, can achieve a more rational, economical, and dynamically adjustable inspection frequency control strategy. This mechanism has a complete engineering implementation path and is suitable for deployment in frequently changing and dynamically responsive inspection scenarios such as large commercial complexes, underground spaces, and high-density public buildings, demonstrating promising prospects for widespread application.

[0116] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0117] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0118] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0120] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent fire inspection system based on multi-module collaboration, characterized in that, The system includes: The data acquisition and layout comparison module is used to acquire the current inspection data, initial inspection frequency index and corresponding initial layout data of the target inspection area, analyze the current inspection data and initial layout data, and filter out the specified layout changes that have the effect of deteriorating fire performance. The positive and negative impact identification module is used to determine whether a specified layout change has an impact on fire performance optimization based on the current inspection data. If it does, it is marked as the target layout change. The impact magnitude assessment and weight allocation module is used to identify several fire performance degradation impact types and several optimization impact types in each target layout change item, calculate the impact change magnitude of each impact type, and assign corresponding weights to each impact type according to the preset weight allocation table, and generate the comprehensive correction factor of the target layout change item by linear combination. The frequency index correction module is used to combine the comprehensive correction factors of all target layout changes to generate the inspection frequency adjustment coefficient, correct the initial inspection frequency index, obtain the corrected inspection frequency index, and use it to dynamically adjust the inspection frequency or scheduling strategy of the target inspection area.

2. The intelligent fire inspection system based on multi-module collaboration according to claim 1, characterized in that, The data acquisition and layout comparison module is used to extract information on changes in the location of fire protection facilities based on the current inspection data and the initial layout data, and to determine whether any of the following types of fire performance degradation effects exist, so as to identify the specified layout changes that have fire performance degradation effects. The types of impacts on fire performance degradation include: obstruction of fire protection facilities, narrowing of evacuation routes, reduced accessibility of fire protection facilities, and reduced visibility of surveillance equipment.

3. The intelligent fire inspection system based on multi-module collaboration according to claim 2, characterized in that, The positive and negative influence identification module specifically includes: The optimization impact identification unit is used to parse the current inspection data and analyze whether there is an optimization impact type that has an optimization impact on fire protection performance after any specified layout change occurs. The optimization impact types include enhanced lighting, smooth airflow, expanded camera coverage, and smooth evacuation routes. The target change determination unit is used to identify a specified layout change as a target layout change when it is determined that the specified layout change has an impact on fire performance optimization, and to extract the fire performance deterioration impact type and optimization impact type corresponding to the target layout change.

4. The intelligent fire inspection system based on multi-module collaboration according to claim 3, characterized in that, The impact magnitude assessment and weight allocation module has a preset weight allocation table, which is used to assign corresponding weighted weight values ​​to each deterioration impact type and each optimization impact type when any layout change causes one or more fire performance deterioration impact types and one or more optimization impact types to occur simultaneously. The weighted weight value corresponding to the deterioration impact type is given a positive sign, and the weighted weight value corresponding to the optimization impact type is given a negative sign. The weighted weight values ​​are set based on the independent influence intensity of each type of influence in historical data. The weighted weight values ​​corresponding to the deteriorating influence type are given a positive sign, and the weighted weight values ​​corresponding to the optimizing influence type are given a negative sign, so that different influence types can form an offsetting relationship in the weighted combination calculation, thereby comprehensively generating the correction factor of the target layout change item.

5. The intelligent fire inspection system based on multi-module collaboration according to claim 4, characterized in that, The impact magnitude assessment and weight allocation module specifically includes: The impact type identification and magnitude calculation unit is used to identify several fire performance deterioration impact types and several optimization impact types corresponding to each target layout change item, and extract fire performance evaluation parameters related to each impact type based on the current inspection data and initial layout data, calculate the parameter change values ​​before and after the layout change, so as to determine the impact change magnitude of each impact type. The weighting and allocation unit is used to call the preset weighting allocation table and assign corresponding weighted weight values ​​to each identified fire performance degradation impact type and optimization impact type. The correction factor generation unit is used to multiply the magnitude of the impact change of each impact type with its corresponding weighted weight value in a linear combination manner, and then sum up all the product results to generate the comprehensive correction factor corresponding to the target layout change item.

6. The intelligent fire inspection system based on multi-module collaboration according to claim 5, characterized in that, The fire performance evaluation parameters include, but are not limited to: Fire protection facility obstruction rate, effective width of evacuation routes, accessibility score of fire protection facilities, light intensity, airflow, field of view integrity of surveillance cameras, or other structural parameters that can quantify the fire protection performance status.

7. The intelligent fire inspection system based on multi-module collaboration according to claim 6, characterized in that, The frequency index correction module specifically includes: The adjustment coefficient generation unit is used to calculate the average value of the comprehensive correction factor of all target layout changes, and combine it with the preset intensity control factor to generate the corresponding inspection frequency adjustment coefficient. The frequency index correction unit is used to call a preset correction function and correct the initial inspection frequency index based on the inspection frequency adjustment coefficient to obtain the corrected inspection frequency index. The frequency index application unit is used to apply the corrected inspection frequency index to the dynamic adjustment of the inspection frequency of the target inspection area, so as to control the actual inspection execution frequency or cycle setting.

8. The intelligent fire inspection system based on multi-module collaboration according to claim 7, characterized in that, The preset correction function is: ； in, This refers to the revised inspection frequency index. This refers to the initial inspection frequency index. This refers to the total number of target layout changes. It refers to the first The comprehensive correction factor corresponding to each target layout change item. This refers to the average of the comprehensive correction factors for all target layout changes. This refers to the preset intensity control factor, and it satisfies... , This refers to the inspection frequency adjustment coefficient; In the preset correction function: ； in, It refers to the first The number of all impact types involved in each target layout change item It refers to the first Among the target layout changes, the first one is... The magnitude of change in impact corresponding to each type of impact. It refers to the first Among the target layout changes, the first one is... The weighted weights corresponding to each type of influence.

Images