Multi-service fusion-oriented intelligent building monitoring management method and system

Abstract

The invention is suitable for the field of intelligent building construction, and provides an intelligent building monitoring management method and system for multi-service fusion, and the method comprises the steps: collecting multi-dimensional data in real time, and constructing a preparatory resource pool; generating a space state atlas by combining the building digital twin model; performing multi-objective optimization deduction based on the atlas to generate an elastic collaborative resource scheduling scheme; during execution, the self-reflection adjustment is triggered through real-time comparison; and finally arranging the effective mode into a standardized treatment process. The system comprises a multi-dimensional data acquisition module, a digital twinborn fusion analysis module, an elastic cooperative scheduling module, a self-reflection adjustment module and an efficiency analysis module. According to the invention, dynamic and elastic management under multi-service fusion is realized, and the building management efficiency and toughness are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of intelligent building construction, and particularly relates to an intelligent building monitoring management method and system for multi-service integration. BACKGROUND

[0002] As the core direction of building intelligence, intelligent buildings are evolving towards integrated management of multi-service integration. With the development of technologies such as the Internet of Things, digital twins, and artificial intelligence, building management has expanded from single device monitoring (security, fire safety) to multi-service integration scenarios such as environmental regulation, personnel scheduling, and device collaboration. It needs to address the dynamic needs of different business scenarios such as office, business, and conference, realize real-time interaction between physical space and digital space, and improve management efficiency and user experience, which has become the core goal of the industry.

[0003] Existing intelligent building monitoring management solutions are mostly based on single business dimension. They collect environmental parameters and device operation data through sensors, and use preset static thresholds for simple alarm or scheduling. Some solutions introduce digital twin technology, but it is mainly used for building model visualization and does not deeply integrate multi-dimensional data for dynamic analysis. Resource scheduling relies on fixed strategies and lacks overall planning and flexible collaboration mechanisms for backup resources. SUMMARY

[0004] The purpose of the present application is to provide an intelligent building monitoring management method for multi-service integration, which aims to solve the technical problems existing in the prior art identified in the background.

[0005] The present application is implemented as follows: an intelligent building monitoring management method for multi-service integration, the method comprising:

[0006] Real-time collection of multi-dimensional data in the building physical space, and monitoring of devices in a dormant or low-load state and backup physical space, forming a backup resource pool;

[0007] Based on multi-dimensional data, combined with a pre-constructed building digital twin model, the current environmental carrying threshold and device operation margin of each functional partition are analyzed and fused, and a space state atlas is dynamically generated;

[0008] Based on the space state atlas, multi-objective optimization deduction is performed to generate an elastic collaborative resource scheduling scheme;

[0009] During the execution of the elastic collaborative resource scheduling scheme, the actual running state parameters are continuously monitored and compared with the preset values in the elastic collaborative resource scheduling scheme in real time. When it is detected that the actual running state parameters exceed the corresponding predicted value preset proportion threshold in the elastic collaborative resource scheduling scheme, a self-regulating mechanism is triggered;

[0010] After completing the self-regulation cycle, the multi-dimensional data, spatial state atlas, elastic collaborative resource scheduling scheme, execution instruction and final result of the whole cycle of the event are collected, the execution performance index of the resource scheduling strategy is analyzed, and the effective collaborative mode and parameter optimization result are arranged as a standardized spatial governance process.

[0011] As a further scheme of the application, the multi-dimensional data includes: current event type, personnel distribution density, personnel movement trajectory, environmental parameters of each functional partition, equipment operation state and equipment load margin.

[0012] As a further scheme of the application, the dynamically generated spatial state atlas specifically includes:

[0013] According to the building partition function and historical operation data, a dynamic environmental parameter carrying threshold upper limit and a key equipment operation margin lower limit are set for each functional partition;

[0014] Based on the physical space topology connection relationship and personnel movement trajectory data, a potential conduction path model of space pressure is established, the physical space topology connection relationship includes channel connectivity and functional area proximity, and the space pressure includes personnel density overrun and environmental parameter threshold approach;

[0015] Based on the equipment operation margin and the environmental parameter, the equipment resources and physical spaces whose current running load is lower than the set margin lower limit are identified and marked as available resource buffer;

[0016] The threshold margin mapping result, the pressure conduction path model and the resource buffer identification result are combined with the building space structure information of the building digital twin model to be rendered into a visualized spatial state atlas in real time.

[0017] As a further scheme of the application, the spatial state atlas is represented as:

[0018] ;

[0019] Among them:

[0020] The node set , ;

[0021] Each node represents a functional partition, is the personnel density, is the environmental parameter vector, is the equipment operation state vector, is the carrying threshold vector, is the resource buffer value;

[0022] The edge set ;

[0023] each edge representing the connection relationship between nodes;

[0024] tensor field where each element represents the pressure value at the coordinate ;

[0025] ;

[0026] the personnel density of node i, the spatial coordinate vector, the position vector of node i, the distance attenuation index, the exit distance influence coefficient;

[0027] function mapping ;

[0028] representing the three-dimensional geometric model of the building, a visualization texture based on pressure values and resource states.

[0029] As a further scheme of the present application, the multi-objective optimization deduction is performed to generate an elastic collaborative resource scheduling scheme, specifically including:

[0030] A plurality of optimization objectives are set, including minimizing personnel gathering risk, minimizing overall energy consumption, maximizing equipment service life, ensuring key area environmental comfort, and minimizing emergency response time;

[0031] Physical space structure constraints, key equipment capacity upper limit constraints, safety specification constraints, and time window constraints are loaded;

[0032] The deviation severity is calculated based on the deviation degree of the actual value of each index in the space state atlas from the threshold value;

[0033] According to the current event type and the severity of the space state atlas, the weight coefficients of each optimization objective in the overall objective function are adjusted in real time;

[0034] Under the condition of meeting all constraints, the resource scheduling strategy combination that makes the weighted target function reach the overall optimization is found, and an elastic collaborative resource scheduling scheme containing specific device control instructions, resource allocation path, execution time window, and expected effect is output.

[0035] As a further scheme of the present application, the weight coefficients of each optimization objective in the overall objective function are adjusted in real time, specifically:

[0036] ;

[0037] wherein, represents the updated weight coefficient of the first optimization objective at the next time point, represents the weight coefficient of the first optimization objective at the current time point, represents the weight coefficient of the first optimization objective at the next time point, represents the weight coefficient of the first optimization objective at the current time point, represents the weight coefficient of the first optimization objective at the next time point, represents the weight coefficient of the first optimization objective at the current time point, represents the adjustment amount of the weight;

[0038] ;

[0039] wherein, is the real-time deviation of the first optimization objective, , , is a proportional coefficient, is an integral coefficient, is a differential coefficient, represents the cumulative sum of the deviation from the initial time point to the current time point, represents the rate of change of the deviation.

[0040] As a further scheme of the present application, the continuously monitoring the actual operation state parameters and real-time comparison with the preset value in the elastic collaborative resource scheduling scheme specifically includes:

[0041] While executing the elastic collaborative resource scheduling scheme, continuously collecting index actual values, the index actual values including target area personnel density changes, environmental parameter actual values, actual load changes of the controlled equipment, resource allocation progress;

[0042] Real-time comparison calculation of actual deviation rate is performed between the collected index actual values and the corresponding index preset values in the elastic collaborative resource scheduling scheme;

[0043] The deviation alarm threshold for different indexes is set, and when the actual deviation rate of any index continuously exceeds the corresponding deviation alarm threshold for a preset time length, it is determined that the preset value is exceeded, and whether the exceeding proportion reaches the proportion threshold is calculated.

[0044] As a further scheme of the present application, the trigger self-regulatory mechanism specifically includes:

[0045] For the deviation exceeding the proportion threshold, the matched standby resource pool is automatically queried according to the data type and the exceeding proportion of the existing deviation, and an activation instruction is sent to the corresponding standby resource;

[0046] Re-calculate the secondary adjustment strategy based on the current actual state and the activated prepared resource pool resources, on the basis of the implemented elastic collaborative resource scheduling scheme, adjust the executing elastic collaborative resource scheduling scheme;

[0047] Pack the deviation of triggering adjustment, the taken adjustment measures and the effect data after adjustment as the execution deviation data and feed back to the real-time collected multi-dimensional data.

[0048] Another purpose of the present application is to provide a multi-service convergence oriented intelligent building monitoring management system, the system comprises:

[0049] The multi-dimensional data acquisition module is used for real-time acquisition of multi-dimensional data in the building physical space, and monitoring of devices in a dormant, low load state and standby physical space, to form a prepared resource pool.

[0050] The digital twin model fusion analysis module is used for fusion analysis of the current environmental carrying threshold and device operation margin of each functional partition based on multi-dimensional data and in combination with a pre-constructed building digital twin model, to dynamically generate a space state atlas.

[0051] The elastic collaborative resource scheduling module is used for multi-objective optimization deduction based on the space state atlas, to generate an elastic collaborative resource scheduling scheme.

[0052] The self-reflexive adjustment module is used for continuous monitoring of actual running state parameters and real-time comparison with preset values in the elastic collaborative resource scheduling scheme during execution of the elastic collaborative resource scheduling scheme, to trigger a self-reflexive adjustment mechanism when it is detected that the actual running state parameters exceed a preset proportion threshold of the corresponding predicted value in the elastic collaborative resource scheduling scheme.

[0053] The performance analysis module is used for collection of multi-dimensional data, space state atlas, elastic collaborative resource scheduling scheme, execution instruction and final result of the whole cycle of the event after completion of the self-reflexive adjustment cycle, analysis of execution performance indicators of the resource scheduling strategy, and arrangement of verified effective collaborative modes and parameter optimization results into a standardized space governance process.

[0054] The present application has the following advantages:

[0055] The present application adopts the idea of multi-dimensional data fusion, digital twin dynamic analysis, elastic collaborative scheduling, self-reflexive adjustment and standardized process, fundamentally solves the problem of insufficient adaptability of the prior art in a multi-service convergence scenario, breaks through the limitation of single service data by real-time acquisition of multi-dimensional data and construction of a prepared resource pool, and provides an elastic basis for resource scheduling.

[0056] Combining the building digital twin model to generate a spatial state map achieves accurate mapping of physical and digital spaces, dynamically presenting environmental load, pressure transmission, and resource buffering status, solving the lag of static threshold assessment.

[0057] Multi-objective optimization and deduction dynamically adjusts objective weights based on the scenario, ensuring global optimization of resource scheduling in terms of safety, efficiency, and user experience, avoiding the one-sidedness of a single-goal orientation. The reflexive adjustment mechanism enhances the system's resilience to emergencies through real-time deviation monitoring and activation of reserve resources, compensating for the rigidity of fixed strategies.

[0058] Ultimately, a standardized space governance process was established, enabling the accumulation and reuse of experience and driving the continuous evolution of management capabilities. Through a closed-loop design of perception-analysis-decision-execution-optimization, the overall solution enables dynamic, efficient, and adaptive management of smart buildings in multi-service convergence scenarios, significantly improving resource utilization efficiency and system responsiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A flowchart of a multi-service integrated smart building monitoring and management method provided by an embodiment of the present invention;

[0060] Figure 2 A flowchart of dynamically generating a spatial state map according to an embodiment of the present invention;

[0061] Figure 3 A flowchart of generating a flexible collaborative resource scheduling solution provided by an embodiment of the present invention;

[0062] Figure 4 A flowchart of an embodiment of the present invention that continuously monitors actual operating status parameters and compares them in real time with preset values ​​in the elastic collaborative resource scheduling solution;

[0063] Figure 5 A flow chart of a reflexive regulation mechanism provided by an embodiment of the present invention;

[0064] Figure 6 This is a structural block diagram of a multi-service integrated intelligent building monitoring and management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present 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 only used to explain the present invention and are not intended to limit the present invention.

[0066] Figure 1 A flowchart of a multi-service integrated smart building monitoring and management method provided by an embodiment of the present invention is shown in FIG.Figure 1 The method comprises:

[0067] S100, collecting multi-dimensional data in the building physical space in real time, and monitoring devices in a dormant or low-load state and standby physical spaces to form a standby resource pool, wherein the multi-dimensional data comprises a current event type, a personnel distribution density, a personnel movement trajectory, environmental parameters of each functional partition, a device operation state, and a device load margin.

[0068] The standby resource pool can improve the system's ability to respond to sudden conditions, quickly activate standby resources to relieve pressure when there is a sudden increase in personnel or excessive load on devices, help improve resource utilization, manage idle resources, and avoid waste, and support a self-regulating mechanism that provides supplemental resources for secondary adjustment when there is a deviation in the execution of a scheduling plan, ensuring dynamic adaptation of resources in multi-business scenarios.

[0069] S200, based on the multi-dimensional data, combining a pre-constructed building digital twin model, and analyzing the current environmental carrying threshold and device operation margin of each functional partition to dynamically generate a space state atlas;

[0070] This step converts complex building operation states into a space state atlas that is perceptible and predictable through deep integration of multi-dimensional data and a building digital twin model. Based on the actual use of each functional partition of the building (such as office areas, commercial areas, and leisure areas) and historical operation data, dynamic upper limits of environmental parameter carrying thresholds and lower limits of key device operation margins are set for each area. These thresholds are not fixed values but are automatically adjusted according to time periods and event types to ensure that the evaluation of building states is more in line with actual scenario requirements.

[0071] On this basis, combined with the topological connection relationship of the physical space (such as whether the channels are connected and whether the functional areas are adjacent) and the personnel movement trajectory data, a potential conduction path model of space pressure is constructed. This model can simulate how pressure such as personnel density exceeding the limit and environmental parameters approaching the threshold spreads from one area to other areas.

[0072] By analyzing the device operation margin and environmental parameters, the system can identify devices (devices in a low-load state) and physical spaces (temporarily idle spaces) with a load below the set margin in real time, and label them as available resource buffers. The existence of these buffers provides flexibility for subsequent resource scheduling, ensuring that standby resources can be quickly called upon in the event of sudden demand.

[0073] The mapping result of the threshold margin, the pressure conduction path model, the resource buffer identification result, and the three-dimensional space structure information of the building digital twin model are combined, and a visual space state atlas is generated through real-time rendering technology. This atlas not only visually displays the current state of each region, but also presents the pressure values of each point in the space through tensor field calculation, allowing managers to not only see the current operating state, but also predict potential risk diffusion trends.

[0074] This step breaks through the limitations of single parameter monitoring and static threshold judgment in traditional building monitoring, achieving dynamic, three-dimensional, and forward-looking perception of building state. The setting of dynamic threshold makes the evaluation of environmental carrying capacity and equipment operation more in line with actual scene changes, avoiding the problem of over-protection or under-protection under static threshold; the construction of pressure conduction path model enables the system to go beyond simple presentation of the current state, providing early insight into the diffusion path of risks and the possibility of proactive intervention rather than passive response; real-time identification of resource buffer lays the foundation for subsequent flexible resource scheduling, ensuring that idle resources can be quickly activated and utilized; and the visual atlas combined with digital twin not only converts complex multi-dimensional data into intuitive spatial images, but also allows managers to quickly understand the overall operation state of the building without professional knowledge, greatly improving decision-making efficiency and accuracy.

[0075] As shown in Figure 2 , the dynamically generated space state atlas specifically includes:

[0076] S210, setting dynamic environmental parameter carrying threshold upper limit and key equipment operation margin lower limit for each functional partition according to building partition function and historical operation data;

[0077] S220, establishing a potential conduction path model of space pressure based on physical space topology connection relationship and personnel movement trajectory data, the physical space topology connection relationship including channel connectivity and functional area proximity, and the space pressure including personnel density over-limit and environmental parameter approaching threshold;

[0078] S230, identifying equipment resources and physical spaces with current running load below the set margin lower limit based on equipment operation margin and environmental parameters, and marking them as available resource buffer;

[0079] S240, combining threshold margin mapping result, pressure conduction path model, resource buffer identification result, and building space structure information of building digital twin model, and real-time rendering into a visual space state atlas.

[0080] In this step, the space state atlas is represented as:

[0081] ;

[0082] wherein:

[0083] a set of nodes , ;

[0084] each node represents a functional zone, is a people density, is an environmental parameter vector, is a device operational status vector, is a carrying threshold vector, is a resource buffer value;

[0085] a set of edges ;

[0086] each edge represents a connection between nodes;

[0087] a tensor field wherein each element represents a pressure value at coordinate :

[0088] ;

[0089] is a people density of node i, is a spatial coordinate vector, is a position vector of node i, is a distance decay exponent, is an exit distance influence coefficient;

[0090] a functional map ;

[0091] represents a building three-dimensional geometric model, is a visualization texture based on pressure values and resource states.

[0092] S300, based on the spatial state atlas, multi-objective optimization deduction is carried out to generate an elastic collaborative resource scheduling scheme;

[0093] This step first sets multi-dimensional optimization targets according to the actual operation needs of the building. These targets include not only the dimensions of ensuring personnel safety and experience, but also the dimensions of efficient use of resources: minimizing overall energy consumption, maximizing device service life, and covering the timeliness of emergency response: minimizing emergency response time, forming a comprehensive target system covering safety, efficiency, and experience.

[0094] While setting the goals, a series of constraints are loaded to ensure the feasibility of the scheduling scheme. These constraints include physical space structure constraints, key equipment capacity upper limit constraints, safety specification constraints, and time window constraints. These constraints serve as the boundaries of decision-making, ensuring that the generated scheme is executable in the actual scenario.

[0095] And in order to make the optimization more in line with the actual state of the current building, the deviation severity is calculated based on the deviation of the actual value of each indicator in the space state atlas from the threshold value. For example, if the temperature has approached the upper limit of the bearing threshold, its deviation severity will be marked as high, while the equipment load in another area is far below the lower limit of the margin, and the deviation is low. This quantitative deviation will be the basis for subsequent adjustment of the target weight.

[0096] According to the current event type and the severity of the space state atlas, the weight coefficient of each optimization target in the overall objective function is dynamically adjusted in real time. This adjustment is not a fixed rule, but a kind of adaptive adjustment mechanism: through real-time deviation, deviation accumulation and deviation change rate, the weight is dynamically corrected, so that the objective function is more in line with the current most urgent demand. For example, when detecting a sharp rise in the density of people in a certain area, the weight of minimizing the risk of people gathering will be greatly increased, while the weight of minimizing the overall energy consumption will be correspondingly reduced; if it is in a state of daily smooth operation, the weights of maximizing equipment service life and minimizing overall energy consumption will dominate.

[0097] Under the premise of meeting all the constraints, the algorithm will find the combination of resource scheduling strategies that makes the weighted target function optimal. This process not only considers the regulation of single resource, but also realizes the coordination across resources. The final output of the flexible and collaborative resource scheduling scheme is not an abstract strategy, but an instruction set containing specific execution details, such as specific parameters of device regulation, path of resource allocation, explicit execution time window and expected effect, ensuring that the scheme can be directly interpreted and implemented by the execution layer.

[0098] This step, through the dynamic weight adjustment of multiple targets, enables the system to flexibly switch the decision focus according to the priority of the actual scene, achieving a dynamic balance between safety, efficiency and experience; the loading of comprehensive constraints ensures the feasibility of the scheme, avoiding the situation of theoretical optimization but actual unexecutability; the flexible and collaborative scheduling mode breaks the island state of devices and space resources, realizes the linkage of cross-system resources, and greatly improves the resource utilization efficiency; at the same time, the specific execution details and expected effect in the scheme provide a clear benchmark for subsequent execution and monitoring, ensuring the precision and controllability of scheduling actions. This closed-loop design of goal-constraint-dynamic optimization-precise execution makes the resource scheduling both flexible in dealing with complex scenarios and precise in execution.

[0099] For example, Figure 3As shown, the multi-objective optimization deduction is performed to generate an elastic collaborative resource scheduling scheme, specifically including:

[0100] S310, a plurality of optimization objectives are set, including minimizing personnel gathering risk, minimizing overall energy consumption, maximizing equipment service life, ensuring key area environmental comfort, and minimizing emergency response time;

[0101] S320, loading physical space structure constraints, key equipment capacity upper limit constraints, safety specification constraints, and time window constraints;

[0102] S330, the deviation severity is calculated based on the deviation of the actual value of each index in the space state atlas from the threshold value;

[0103] S340, the weight coefficient of each optimization objective in the overall objective function is adjusted in real time according to the current event type and the severity of the space state atlas;

[0104] S350, under the condition of meeting all constraints, the resource scheduling strategy combination that makes the weighted target function optimal is found, and an elastic collaborative resource scheduling scheme containing specific device control instructions, resource allocation path, execution time window and expected effect is output.

[0105] In this step, the weight coefficient of each optimization objective in the overall objective function is adjusted in real time, specifically:

[0106] ;

[0107] Wherein, represents the updated weight coefficient of the i-th optimization objective at the next time, represents the weight coefficient of the i-th optimization objective at the current time, represents the adjustment amount of the weight; ;

[0108] ;

[0109] Wherein, is the real-time deviation of the i-th optimization objective, , is a proportional coefficient, is an integral coefficient, is a differential coefficient, represents the cumulative sum of the deviation from the initial time to the current time, represents the rate of change of the deviation.

[0110] ​​​​S400, during the execution of the elastic collaborative resource scheduling scheme, the actual running state parameters are continuously monitored and compared with the preset values in the elastic collaborative resource scheduling scheme in real time, and when it is detected that the actual running state parameters exceed the corresponding predicted value preset proportion threshold in the elastic collaborative resource scheduling scheme, a self-regulating mechanism is triggered;

[0111] After the elastic collaborative resource scheduling scheme starts to execute, a continuous dynamic monitoring mode is entered, and various types of index actual values related to the scheme execution effect are collected in real time. These indexes include personnel dimension: real-time change trend of target area personnel density, whether it is continuously rising or gradually falling, environmental dimension: actual values of temperature, humidity, air quality and other parameters, and equipment and resource dimension: actual load change of the controlled air conditioner, actual carrying efficiency of the elevator, and activation progress of the standby space.

[0112] Then, the collected index actual values are compared with the corresponding preset values in the elastic collaborative resource scheduling scheme in real time, and the actual deviation rate is calculated. When the actual deviation rate of a certain index continuously exceeds the corresponding alarm threshold and reaches a preset time length, the system determines that the index has exceeded the predicted value in the elastic collaborative resource scheduling scheme, and further calculates whether the exceeding proportion reaches the preset proportion threshold. If it does, the self-regulating mechanism is formally triggered.

[0113] The start of the self-regulating mechanism means that the system enters the active intervention stage: first, according to the deviation data type and the exceeding proportion, the system automatically queries the standby resource pool and quickly locates the matching standby resources: if the personnel density is excessive, the standby channel, temporary rest area or idle floor space can be activated; if the device load is insufficient, the standby air conditioner, elevator and other devices in the dormant state are started, and precise activation instructions are sent to these standby resources to ensure that the resources can be put into use in the shortest time.

[0114] Secondly, based on the current actual running state and the activated standby resources, the secondary adjustment strategy calculation is carried out on the basis of the original elastic collaborative resource scheduling scheme. This adjustment is not a wholesale negation of the original scheme, but a targeted optimization. For example, if the air conditioning adjustment in the original scheme fails to effectively reduce the temperature in a certain area, the secondary adjustment may increase the fresh air volume in that area, turn on the air conditioner in the adjacent area to assist in heat dissipation, and simultaneously guide personnel to flow to the buffer space with suitable temperature, realizing cross-resource collaborative remediation.

[0115] Finally, the data such as the reason for triggering the adjustment (such as which index deviates, how much the proportion exceeds), the specific adjustment measures taken and the actual effect after the adjustment are packaged and fed back to the multi-dimensional data collection module as execution deviation data, becoming the input of the next round of data collection and analysis, forming an execution-monitoring-adjustment-feedback closed loop.

[0116] Real-time monitoring and deviation comparison ensures that the system can discover the deviation between the scheme and the actual situation in the first time, avoiding the accumulation of small deviations into big problems; differentiated deviation alarm thresholds make monitoring more in line with the characteristics of different scenarios, neither too sensitive to lead to frequent adjustments, nor too slow to miss risks; the self-regulating mechanism realizes the upgrade from passive response to active remedy by activating the prepared resource and secondary strategy adjustment, greatly improving the response speed and processing capacity of the system to sudden conditions; and real-time feedback of deviation data makes each adjustment an experience for optimizing the system, promoting the continuous evolution of resource scheduling strategies, and ultimately realizing the efficient, safe, and comfortable operation of intelligent buildings in dynamic changes.

[0117] As shown in Figure 4 , the continuous monitoring of the actual operation state parameters and the real-time comparison with the preset values in the elastic collaborative resource scheduling scheme specifically includes:

[0118] S410, while executing the elastic collaborative resource scheduling scheme, continuously collecting index actual values, including target area personnel density changes, environmental parameter actual values, actual load changes of the controlled equipment, and resource allocation progress;

[0119] S420, comparing the collected index actual values with the corresponding index preset values in the elastic collaborative resource scheduling scheme to calculate the actual deviation rate;

[0120] S430, set the deviation alarm threshold for different indicators, when the actual deviation rate of any indicator continuously exceeds the corresponding deviation alarm threshold for a preset duration, it is determined that the preset value is exceeded, and whether the exceeding proportion reaches the proportion threshold is calculated.

[0121] As shown in Figure 5 , the trigger self-regulating mechanism specifically includes:

[0122] S441, for deviations exceeding the proportion threshold, automatically query the matching prepared resource pool according to the type of data with deviation and the exceeding proportion, and send an activation instruction to the corresponding prepared resource;

[0123] S442, based on the current actual state and the activated prepared resource pool, recompute the secondary adjustment strategy based on the implemented elastic collaborative resource scheduling scheme, and adjust the ongoing elastic collaborative resource scheduling scheme;

[0124] S443, package the triggered deviation, the taken adjustment measures, and the effect data after adjustment as execution deviation data and feed back to the real-time collected multi-dimensional data in real time.

[0125] S500, after completing the self-reflexive adjustment cycle, collect the multi-dimensional data, spatial state atlas, elastic collaborative resource scheduling scheme, execution instruction and final result of the whole cycle of the event, analyze the execution performance index of the resource scheduling strategy, and arrange the verified effective collaborative mode and parameter optimization result into a standardized spatial governance process.

[0126] After the completion of the self-reflexive adjustment cycle, the whole cycle data collection mechanism will be started to comprehensively capture various information related to the event: both the real-time collected multi-dimensional raw data, the decision output in the process, and the final execution result. These data are not simply stacked, but are structured and integrated according to the time axis and logical relationship to form a complete event file, providing panoramic raw materials for subsequent analysis.

[0127] Based on the collected whole cycle data, the execution performance index of the resource scheduling strategy will be focused on for in-depth analysis. These indexes not only include intuitive result indexes (whether the event resolution time is within the expected range, whether the final state returns to the normal threshold), but also cover process indexes: response delay time of resource scheduling instruction, activation efficiency of prepared resource pool, amplitude of deviation reduction after self-reflexive adjustment, and resource utilization indexes: activation rate of standby equipment, actual carrying efficiency of buffer space, input-output ratio of energy consumption and effect. Through cross analysis of these indexes, the advantages and disadvantages of the current scheduling strategy are accurately located.

[0128] Then the verified effective collaborative mode and parameter optimization result will be refined from the analysis result, and will be arranged into a standardized spatial governance process. The standardization here is not a rigid fixed process, but a modular scheme that retains the core logic and flexibility: on the one hand, the verified resource scheduling combination, parameter threshold and execution step are solidified into reusable templates; on the other hand, variable interfaces are reserved for templates to adapt to different scenarios, ensuring that the standardized process can be quickly implemented and flexibly adapted to new scenarios. These will be coded as modular instructions, which can be directly called and parameter adjusted according to the actual scale next time the same event occurs.

[0129] Figure 6 A structural block diagram of a smart building monitoring and management system for multi-service integration is shown in FIG. 1. Figure 6 The system includes:

[0130] A multi-dimensional data acquisition module 100 is configured to acquire multi-dimensional data in a physical space of a building in real time, and monitor devices in a dormant or low-load state and standby physical spaces to form a prepared resource pool.

[0131] The digital twin model fusion analysis module 200 is configured to fuse and analyze the current environmental bearing threshold and equipment operation margin of each functional subarea based on multidimensional data and in combination with a pre-constructed building digital twin model, and dynamically generate a space state atlas;

[0132] The elastic collaborative resource scheduling module 300 is configured to perform multi-objective optimization deduction based on the space state atlas, and generate an elastic collaborative resource scheduling scheme;

[0133] The self-regulating module 400 is configured to continuously monitor actual operation state parameters and compare them with preset values in the elastic collaborative resource scheduling scheme in real time during execution of the elastic collaborative resource scheduling scheme, and trigger a self-regulating mechanism when it is detected that the actual operation state parameters exceed a preset proportion threshold of the corresponding predicted values in the elastic collaborative resource scheduling scheme.

[0134] The performance analysis module 500 is configured to collect multidimensional data, a space state atlas, an elastic collaborative resource scheduling scheme, execution instructions and final results of a whole cycle of the current event after completion of a self-regulating cycle, analyze an execution performance index of a resource scheduling strategy, and arrange a verified collaborative mode and parameter optimization result into a standardized space governance process.

[0135] The technical features of the above-described embodiments can be combined in any manner, and to make the description concise, all possible combinations of the technical features in the above-described embodiments are not described, however, as long as the combinations of the technical features do not contradict each other, they should be considered as the scope of the present disclosure.

[0136] The above-described embodiments only express several implementation manners of the present disclosure, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the present patent. It should be noted that, for ordinary skilled persons in the art, without departing from the concept of the present disclosure, several modifications and improvements can be made, which are all within the protection scope of the present disclosure. Therefore, the protection scope of the present patent should be subject to the appended claims.

[0137] The above-described embodiments are only preferred embodiments of the present disclosure, and are not used to limit the present disclosure, and any modification, equivalent replacement and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A smart building monitoring and management method for multi-service integration, characterized in that: The method comprises: Real-time collection of multi-dimensional data within the building's physical space, and monitoring of dormant, low-load equipment and spare physical spaces to form a reserve resource pool; Based on multi-dimensional data and combined with a pre-built building digital twin model, the current environmental load threshold and equipment operating margin of each functional zone are integrated and analyzed to dynamically generate a spatial status map; Based on the spatial state map, multi-objective optimization deduction is carried out to generate a flexible collaborative resource scheduling solution; During the execution of the elastic collaborative resource scheduling scheme, the actual operating status parameters are continuously monitored and compared in real time with the preset values ​​in the elastic collaborative resource scheduling scheme. When it is detected that the actual operating status parameters exceed the preset ratio threshold of the corresponding predicted values ​​in the elastic collaborative resource scheduling scheme, a reflexive adjustment mechanism is triggered; After completing the reflexive adjustment cycle, we collect multi-dimensional data, spatial status maps, flexible collaborative resource scheduling plans, execution instructions and final results of the entire event cycle, analyze the execution efficiency indicators of the resource scheduling strategy, and organize the verified effective collaborative models and parameter optimization results into a standardized spatial governance process.

2. The method according to claim 1, characterized in that The multi-dimensional data includes: current event type, personnel distribution density, personnel movement trajectory, environmental parameters of each functional area, equipment operating status and equipment load margin.

3. The method according to claim 2, characterized in that The dynamically generated spatial state map specifically includes: According to the building zoning functions and historical operation data, set the upper limit of the dynamic environmental parameter load threshold and the lower limit of the key equipment operation margin for each functional zone; Based on the topological connectivity of physical space and personnel movement trajectory data, a potential transmission path model of spatial pressure is established. The topological connectivity of physical space includes channel connectivity and functional area proximity. The spatial pressure includes excessive personnel density and environmental parameters approaching thresholds. Based on equipment operating margins and environmental parameters, identify equipment resources and physical spaces whose current operating loads are below the set margin lower limit and mark them as available resource buffers; The threshold margin mapping results, pressure conduction path model, and resource buffer zone identification results are combined with the architectural spatial structure information of the building digital twin model and rendered in real time into a visual spatial status map.

4. The method according to claim 3, characterized in that The spatial state map Expressed as: ； in: Node Collection , ; Each node Represents a functional partition, is the population density, is the environmental parameter vector, Equipment operation status vector, is the carrying threshold vector, Buffer value for resources; Edge Set ; Each edge Indicates the connection relationship between nodes; Tensor Field , where each element Representing coordinates Pressure value at: ； is the personnel density of node i, is the space coordinate vector, is the position vector of node i, is the distance decay exponent, is the exit distance influence coefficient; Function Mapping ; Represents the three-dimensional geometric model of the building, A visualization texture based on pressure values ​​and resource status.

5. The method according to claim 3, characterized in that The multi-objective optimization deduction is performed to generate a flexible collaborative resource scheduling solution, specifically including: Set multiple optimization goals, including minimizing the risk of personnel gathering, minimizing overall energy consumption, maximizing equipment life, ensuring environmental comfort in key areas, and minimizing emergency response time; Load physical space structure constraints, key equipment capacity upper limit constraints, safety specification constraints, and time window constraints; The severity of the deviation is calculated based on the degree of deviation between the actual value of each indicator in the spatial state map and the threshold; According to the current event type and the severity of the spatial state map, the weight coefficients of the defined optimization objectives in the overall objective function are adjusted in real time; Under the conditions of satisfying all constraints, we find the resource scheduling strategy combination that makes each objective function after weight assignment reach the overall optimality, and output a flexible collaborative resource scheduling plan that includes specific equipment control instructions, resource allocation paths, execution time windows and expected effects.

6. The method according to claim 5, characterized in that The weight coefficients of the optimization objectives defined in the real-time adjustment in the overall objective function are specifically: ； in, Indicates the The optimization goal is at the next moment The updated weight coefficient of Indicates the The optimization goal at the current moment The weight coefficient of Indicates the amount of weight adjustment; ； in, For the The real-time deviation of the optimization target, , is the proportionality coefficient, is the integration coefficient, is the differential coefficient, Represents the cumulative sum of deviations from the initial moment to the current moment, Indicates the rate of change of the deviation.

7. The method according to claim 5, characterized in that The continuous monitoring of actual operating status parameters and the real-time comparison with the preset values ​​in the elastic collaborative resource scheduling solution specifically include: While executing the flexible collaborative resource scheduling solution, continuously collecting actual values ​​of indicators, including changes in population density in the target area, actual values ​​of environmental parameters, actual load changes of the regulated equipment, and resource allocation progress; Compare the actual values ​​of the collected indicators with the corresponding preset values ​​of the indicators in the elastic collaborative resource scheduling solution in real time to calculate the actual deviation rate; Deviation alarm thresholds are set for different indicators. When the actual deviation rate of any indicator exceeds the corresponding deviation alarm threshold for a preset period of time, it is determined to exceed the preset value, and the excess ratio is calculated to see whether it reaches the ratio threshold.

8. The method according to claim 7, characterized in that The trigger reflexive regulation mechanism is specifically: For deviations exceeding the ratio threshold, the system automatically queries the matching reserve resource pool based on the type of data and the excess ratio, and sends activation instructions to the corresponding reserve resources. Based on the current actual status and activated reserve resource pool resources, the secondary adjustment strategy is recalculated on the basis of the implemented elastic collaborative resource scheduling plan, and the elastic collaborative resource scheduling plan in execution is adjusted; The deviation that triggers the adjustment, the adjustment measures taken, and the effect data after the adjustment are packaged as execution deviation data and fed back in real time to the multi-dimensional data collected in real time.

9. A smart building monitoring and management system for multi-service integration, characterized by: The system comprises: The multi-dimensional data acquisition module is used to collect multi-dimensional data in the building's physical space in real time, and monitor the equipment in dormant or low-load states and spare physical spaces to form a reserve resource pool; The digital twin model fusion analysis module is used to integrate and analyze the current environmental load threshold and equipment operating margin of each functional zone based on multi-dimensional data and pre-built building digital twin models, and dynamically generate a spatial status map; The elastic collaborative resource scheduling module is used to perform multi-objective optimization deduction based on the spatial state map and generate elastic collaborative resource scheduling solutions; A reflexive adjustment module is used to continuously monitor actual operating status parameters during the execution of the elastic collaborative resource scheduling scheme and compare them in real time with preset values ​​in the elastic collaborative resource scheduling scheme. When it is detected that the actual operating status parameters exceed a preset ratio threshold of the corresponding predicted value in the elastic collaborative resource scheduling scheme, the reflexive adjustment mechanism is triggered; The performance analysis module is used to collect multi-dimensional data, spatial status maps, elastic collaborative resource scheduling plans, execution instructions and final results of the entire event cycle after completing the reflexive adjustment cycle, analyze the execution performance indicators of the resource scheduling strategy, and organize the verified effective collaborative models and parameter optimization results into a standardized spatial governance process.

Images