Intelligent property management system

Abstract

The invention, which relates to the field of property management, discloses an intelligent property management system comprising a property scheduling management module, a monitoring management module, a routing inspection path algorithm module and a routing inspection execution module. The property dispatching management module is used for storing positions of all cameras, sensors and property facilities, states of the property facilities and maintenance records of the property facilities, and realizing linkage through the routing inspection path algorithm module; the monitoring management module is used for deploying a camera and executing deflection and zooming of the camera, so that the monitoring range of the camera covers a target area needing to be inspected; the monitoring management module comprises a temperature and humidity sensor, a smoke sensor and an illumination sensor which are used for collecting property environment information in real time; the routing inspection path algorithm module comprises environment modeling, priority allocation, path dynamic optimization, view angle adjustment and adaptive learning; through the technologies of environment modeling, priority distribution, path dynamic optimization and the like of the inspection path algorithm module, the dynamic adjustment of the visual angle of the camera and the inspection path is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of property management, and more specifically, to a smart property management system. Background Art

[0002] Smart property management relies on monitoring to ensure equipment safety and maintenance efficiency. Equipment inspection is a key component of this process. However, inspections must cover diverse and complex spaces within a building to ensure the normal operation of key equipment such as computer rooms, elevators, and power supplies.

[0003] In the existing technology, property management personnel are usually relied on to manually monitor the surveillance screens to achieve the purpose of property monitoring and management. However, it is difficult to combine it with patrol path algorithm optimization, resulting in some areas not meeting the patrol coverage requirements, thus forming monitoring blind spots and affecting safety. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a smart property management system, which solves the problems raised in the above-mentioned background technology through an inspection path algorithm module.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: a smart property management system, comprising a property scheduling management module, a monitoring management module, an inspection path algorithm module, and an inspection execution module;

[0006] The property dispatch management module is used to store the locations of all cameras, sensors, property facilities, the status of property facilities and their maintenance records, and realize linkage through the inspection path algorithm module;

[0007] The monitoring and management module is used to deploy cameras and perform camera deflection and zoom to ensure that the camera's monitoring range covers the target area for inspection. The monitoring and management module includes temperature and humidity sensors, smoke sensors, and light sensors for real-time collection of property environmental information.

[0008] The inspection path algorithm module includes environmental modeling, priority allocation, dynamic path optimization, view angle adjustment, and adaptive learning. The inspection path algorithm module constructs the three-dimensional structure of the property management area through environmental modeling and calculates the camera's field of view, which is used to determine the initial monitoring coverage.

[0009] The inspection path algorithm module calculates the inspection interval by assigning priorities and combining the inspection time adjustment strategy, and adjusts the inspection order according to the task priority assignment;

[0010] The inspection path algorithm module adjusts the camera's inspection angle in real time through dynamic path optimization, prioritizes the shortest path to ensure that inspection tasks run along the required path, and combines a hotspot area backtracking mechanism to increase inspection frequency in fault-prone areas.

[0011] The viewing angle adjustment in the inspection path algorithm module optimizes the monitoring coverage based on the error correction mechanism of the camera's horizontal rotation angle and pitch angle, and uses error compensation adjustment to stabilize the monitoring viewing angle;

[0012] The inspection path algorithm module optimizes the viewing angle and inspection interval by analyzing historical inspection data, so that the inspection path is optimized over time;

[0013] The inspection execution module is used to receive instructions from the inspection path algorithm module and control the camera to perform adjustment tasks. The camera is integrated with a pan-tilt control module, which is used to adjust the camera's deflection angle, rotation speed, and focal length.

[0014] In a preferred embodiment, environmental modeling includes constructing a three-dimensional model of the property management area and calculating the required monitoring range of the camera. At the same time, software debugging is used to detect errors to prevent the camera from being installed at the wrong angle or the space from blocking the view.

[0015] The three-dimensional modeling of the property management area is expressed as:

[0016] P={(x i ,y i ,z i )|i=1,2,…,N}

[0017] Where P represents the three-dimensional coordinate point set of the property management area; (x i ,y i ,z i ) is the coordinate of the i-th spatial sampling point in the property; N is the number of all modeling points;

[0018] Calculate the camera's field of view angle;

[0019]

[0020] FOV i is the field of view of camera i; R i is the peak value of the camera's monitoring radius; θ i is the horizontal opening angle of the camera; Indicates that during the tth software debugging, the installation error of camera i was detected; E max is the maximum value of the allowable error;

[0021] Establish error-proofing mechanisms for software debugging and detection errors;

[0022]

[0023] in The actual installation angle detected by the camera; is the theoretical installation angle of the camera; α is the error accumulation coefficient, which is used to determine the error correction rate;

[0024] like Then adjust the camera angle through the PTZ control module:

[0025]

[0026] in Indicates the rotation angle of camera i after adjustment.

[0027] In a preferred embodiment, the priority allocation in the inspection path algorithm module is used to dynamically adjust the inspection sequence based on the historical failure rate of the inspection area, dynamic environmental changes, and the aging level of the equipment, so that the required areas are monitored first;

[0028]

[0029]

[0030] where R i is the inspection risk score of area i; α1, α2, α3 are weight parameters; is the historical failure rate of region i; is the dynamic environmental change of region i; is the aging level of the equipment in area i; is the software debugging error score; γ is the software debugging correction coefficient; is the actual inspection time interval of area i in the actual inspection task; is the ideal inspection time interval calculated based on the inspection demand of area i; β is the inspection time error adjustment coefficient.

[0031] In a preferred embodiment, the path dynamic optimization calculation in the inspection path algorithm module is performed, and its goal is to find the path from the current monitoring state C i To target monitoring state C j The ideal adjustment path;

[0032]

[0033] in The calculated value from camera C in the t+1th round i To camera C j The ideal inspection path adjustment cost; d(C i ,C j ) is camera C i Rotate to camera C j The minimum angle adjustment required for the position; β is the risk weight parameter; R jFor camera C j Inspection risk score of the corresponding area; C i Indicates the current monitoring status; C j Indicates the target monitoring status; is the path calculation error value detected by software debugging; δ is the path error correction coefficient;

[0034] During the dynamic optimization of the path, the system analyzes the historical inspection path through software debugging and calculates the deviation between the actual inspection path and the theoretical inspection path;

[0035]

[0036] in is the error value of the inspection path in the t+1th round; The inspection path distance actually adjusted for the camera; is the ideal inspection path calculated by the system; λ is the path error adjustment coefficient.

[0037] In a preferred embodiment, the viewing angle adjustment in the inspection path algorithm module is used to enable the camera to adjust the horizontal rotation angle and pitch angle according to changes in the environment during the inspection task;

[0038]

[0039] in is the horizontal rotation angle of camera i in the actual inspection task; The theoretical horizontal rotation angle of camera i calibrated during the installation and debugging phase; is the pitch angle of camera i in the actual inspection task; The theoretical pitch angle calibrated for camera i during the installation and debugging phase; FOV i is the field of view of camera i; R i is the monitoring radius of camera i; ψ, ξ are the rotation error adjustment coefficients.

[0040] In a preferred embodiment, the adaptive learning in the inspection path algorithm module optimizes the camera state based on historical inspection data, so that the inspection task is continuously optimized over time; the optimization is based on historical data fitting and error compensation to calculate the optimized monitoring angle and inspection interval;

[0041]

[0042] in is the field of view angle of camera i after optimization in round t+1; The field of view angle calculated by camera i during the tth round of inspection; R j is the inspection risk score of area j; di(C i,C j ) is the adjustment path distance from camera i to camera j; is the error correction value of the tth software test; ν is the error correction factor; is the learning rate.

[0043] In a preferred embodiment, the system further includes an inspection task execution supervision module, which establishes an inspection task execution deviation evaluation model based on three factors; calculates an execution deviation value based on the inspection task execution deviation evaluation model; if the execution deviation value is greater than an execution deviation threshold, it is determined to be an execution deviation and triggers an abnormality alarm;

[0044] The three factors include path deviation, coverage area, and task execution. The path deviation factor is used to calculate the difference between the camera's actual inspection path and the ideal path, assessing whether the inspection task is executed according to the planned trajectory.

[0045] The coverage area factor is used to compare the actual monitoring range with the theoretical coverage area to detect whether there are any missed areas that have not been inspected for a long time;

[0046] Task execution factors are used to monitor camera rotation accuracy, zoom adjustment error, and inspection time deviation, and to evaluate the consistency of inspection task execution.

[0047] In a preferred embodiment, the path deviation error is calculated based on the path deviation factor, and the proposed path deviation error is E path ; Calculate the coverage area error based on the coverage area factor, and propose the coverage area error as E cover ; Calculate the task execution error based on the task execution factors, and propose the task execution error as E task ;

[0048]

[0049] Where Q is the number of cameras in the system; The actual inspection path point of camera i and theoretical inspection path points Bezier curve matching error between max is the maximum path deviation value allowed by the system; The actual installation angle detected by the camera; is the theoretical installation angle of the camera; θ max The maximum angle of camera rotation; is the actual inspection time interval of area i in the actual inspection task; is the ideal inspection time interval calculated based on the inspection requirements for area i; T max G is the peak value of the allowed inspection time deviation; pathis the path deviation weighting factor, which is used to dynamically adjust the impact of the path error on the final execution deviation;

[0050] Where A is the total number of inspection areas; A actual,j is the actual coverage area of the jth monitoring area; A ideal,j A is the theoretical calculated coverage area of the jth monitoring area; actual,j ∩A ideal,j Indicates the intersection area of the actual monitoring area and the theoretical monitoring area; G is the cumulative risk score of the jth monitoring area that has not been inspected in the past; cover is the coverage error weighting factor;

[0051] in is the actual and theoretical zoom ratio of camera i; Z max The peak zoom ratio of the camera; Weight factor for task execution.

[0052] In a preferred embodiment, an inspection task execution deviation evaluation model is established based on three factors, and the execution deviation value is calculated based on the inspection task execution deviation evaluation model. The execution deviation value is E total ;

[0053]

[0054] in Indicates the nonlinear adjustment value of the path deviation error; Indicates the nonlinear adjustment value of the coverage area error; represents the nonlinear adjustment value of the task execution error; λ1, λ2, λ3 are error attenuation factors; W path ,W cover ,W task E path 、E cover 、E task The importance weight of ; δ is the normalization factor.

[0055] Technical effects and advantages of the present invention:

[0056] 1. Through the environmental modeling, priority allocation, and dynamic path optimization technologies of the inspection path algorithm module, dynamic adjustment of camera viewing angles and inspection paths is achieved. Traditional inspection systems rely on manual path planning, which may lead to blind spots in monitoring coverage. However, this invention uses a path optimization algorithm based on three-dimensional environmental modeling to calculate the optimal inspection route, ensuring that the field of view of the surveillance camera maximizes coverage of key areas. At the same time, the short path priority mechanism and hot spot area backtracking mechanism can intelligently adjust monitoring tasks, increase the inspection frequency in fault-prone areas, and ensure the safety of property management and the reliability of equipment operation and maintenance.

[0057] 2. By introducing a software debugging and error-proofing mechanism, the system can detect camera installation errors and make real-time corrections. For example, during the 3D modeling phase, the deviation between the camera's theoretical installation angle and the actual measured angle is calculated, and dynamic adjustments are made based on the cumulative error coefficient to ensure that the monitoring range remains consistent with the calculated path.

[0058] 3. The inspection task execution supervision module can calculate the execution deviation value in real time and monitor the execution accuracy of the inspection task; based on the evaluation of path deviation factors, coverage area factors and task execution factors, the system can identify problems such as errors between the actual inspection path and the ideal path, insufficient monitoring coverage, and camera rotation accuracy deviation; once the system detects that the inspection task deviation value exceeds the preset threshold, it will trigger an alarm and adjust the inspection parameters, thereby improving the reliability and adaptability of the entire property management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] Refer to the instruction manual Figure 1 , a smart property management system according to an embodiment of the present invention includes a property scheduling management module, a monitoring management module, an inspection path algorithm module, and an inspection execution module;

[0062] The property dispatch management module is used to store the locations of all cameras, sensors, property facilities, the status of property facilities and their maintenance records, and realize linkage through the inspection path algorithm module;

[0063] The monitoring and management module is used to deploy cameras and perform camera deflection and zoom to ensure that the camera's monitoring range covers the target area for inspection. The monitoring and management module includes temperature and humidity sensors, smoke sensors, and light sensors for real-time collection of property environmental information.

[0064] The inspection path algorithm module includes environmental modeling, priority allocation, dynamic path optimization, view angle adjustment, and adaptive learning. The inspection path algorithm module constructs the three-dimensional structure of the property management area through environmental modeling and calculates the camera's field of view, which is used to determine the initial monitoring coverage.

[0065] The inspection path algorithm module calculates the inspection interval by assigning priorities and combining it with the inspection time adjustment strategy. It also adjusts the inspection sequence based on the task priority, so that cameras in high-risk areas are given priority in inspection tasks.

[0066] The inspection path algorithm module adjusts the camera's inspection angle in real time through dynamic path optimization, prioritizes the shortest path to ensure that inspection tasks run along the required path, and combines a hotspot area backtracking mechanism to increase inspection frequency in fault-prone areas.

[0067] The viewing angle adjustment in the inspection path algorithm module optimizes the monitoring coverage range based on the error correction mechanism of the camera's horizontal rotation angle and pitch angle. It also uses error compensation adjustment to stabilize the monitoring viewing angle, reduce monitoring blind spots, and improve inspection accuracy.

[0068] The inspection path algorithm module optimizes the viewing angle and inspection interval by analyzing historical inspection data, so that the inspection path is optimized over time;

[0069] The inspection execution module is used to receive instructions from the inspection path algorithm module and control the camera to perform adjustment tasks. The camera is integrated with a pan-tilt control module, which is used to adjust the camera's deflection angle, rotation speed, and focal length.

[0070] Environmental modeling involves constructing a three-dimensional model of the property management area and calculating the required monitoring range of the camera. Software debugging is also used to detect errors and prevent camera installation angle errors and spatial obstructions that affect the field of view.

[0071] The three-dimensional modeling of the property management area is expressed as:

[0072] P={(x i ,y i ,z i )|i=1,2,…,N}

[0073] Where P represents the three-dimensional coordinate point set of the property management area. P is used to build a spatial model to ensure that the inspection path calculation can accurately match the building structure and monitoring requirements; (x i ,y i ,z i ) is the coordinate of the i-th spatial sampling point within the property; N is the number of all modeling points, which is used to determine the modeling accuracy;

[0074] Calculate the camera's field of view angle;

[0075]

[0076] FOV i is the field of view of camera i; R i is the peak value of the camera's monitoring radius; θi is the horizontal opening angle of the camera; Indicates that during the tth software debugging, the installation error of camera i was detected; E max is the maximum value of the allowable error, E max Used to calibrate the monitoring area;

[0077] Establish error-proofing mechanisms for software debugging and detection errors; Indicates that during the t+1th software debugging, an installation error of camera i was detected;

[0078]

[0079] in The actual installation angle detected by the camera; is the theoretical installation angle of the camera; α is the error accumulation coefficient, which is used to determine the error correction rate;

[0080] like Then adjust the camera angle through the PTZ control module:

[0081]

[0082] in Indicates the rotation angle of camera i after adjustment. Used to compensate for installation errors or optimize the monitoring angle; if the error is too large, the system will trigger an alarm and require manual re-inspection.

[0083] The priority allocation in the inspection path algorithm module is used to dynamically adjust the inspection sequence based on the historical failure rate of the inspection area, dynamic environmental changes, and the aging level of the equipment, so that the required areas are monitored first;

[0084]

[0085] where R i is the inspection risk score of area i, R i The higher the value, the higher the inspection priority of the area. α1, α2, and α3 are weight parameters, which are used to adjust The degree of impact on priorities; is the historical failure rate of region i; is the dynamic environmental change of area i, which includes factors such as crowd density and equipment load, which affect monitoring requirements; is the aging level of the equipment in area i. The higher the aging level, the greater the probability of failure, and the inspection frequency should be increased; is the software debugging error score, which represents the calculation error of the current inspection priority calculated at the tth inspection. If the error is too large, the priority allocation is corrected. γ is the software debugging correction coefficient, which is used to determine the impact of the error on the inspection priority. Indicates the correction value of the inspection priority error after calculation in round t+1; is the actual inspection time interval of area i in the actual inspection task; is the ideal inspection time interval calculated based on the inspection requirements for area i; β is the inspection time error adjustment coefficient, which is used to control the impact of the inspection time error on the inspection priority;

[0086] In order to prevent errors in inspection priority calculation, the system monitors and dynamically corrects inspection priority errors through software debugging;

[0087] Error detection: Before calculating the inspection path, the software simulates multiple inspection cycles and records the error of each area. and If the deviation is too large, Then adjust the inspection priority; where ε is the allowable error threshold;

[0088] Error correction: When This indicates that the inspection priority for this area is incorrectly set too high and the inspection frequency should be reduced:

[0089]

[0090] in is the new inspection time interval; θ is the time adjustment factor, which is used to prevent sudden changes from causing inspection instability; when This indicates that the inspection priority of this area is incorrectly set too low and the inspection frequency should be increased:

[0091]

[0092] Reduce the inspection time interval so that the area is inspected more frequently; where S max Indicates the maximum allowable value of the inspection priority error. If this value is exceeded, the system will reduce the inspection frequency of the area to prevent excessive inspection and waste of resources. min Indicates the minimum allowable value of inspection priority error. If it is lower than this value, the system increases the inspection frequency of the area to ensure that key areas are adequately monitored.

[0093] Dynamic optimization: After each round of inspection, the system recalculates R i and Continuously adjust the inspection task scheduling to optimize the inspection path.

[0094] The goal of the dynamic optimization calculation of the inspection path algorithm module is to find the path from the current monitoring state C i To target monitoring state C j The optimal ideal adjustment path is to minimize the path cost while taking into account the regional risk score and software debugging error correction;

[0095]

[0096] in The calculated value from camera C in the t+1th round i To camera C j The optimal ideal inspection path adjustment cost; d(C i ,C j ) is camera C i Rotate to camera C j The minimum angle adjustment required for the position; β is the risk weight parameter, which is used to determine the impact of regional risk on path planning; R j For camera C j The inspection risk score of the corresponding area, the higher the risk, the higher the priority of the path; C i Indicates the current monitoring status; C j Indicates the target monitoring status; The path calculation error value detected by software debugging indicates the deviation between the actual inspection path and the theoretical calculation path. If the error is too large, the inspection path is corrected. δ is the path error correction coefficient, which is used to control the impact of the error on the path calculation.

[0097] During the dynamic optimization of the path, the system analyzes the historical inspection path through software debugging and calculates the deviation between the actual inspection path and the theoretical inspection path;

[0098]

[0099] in is the error value of the inspection path in the t+1th round; The inspection path distance actually adjusted for the camera; is the ideal optimal inspection path calculated by the system; λ is the path error adjustment coefficient, which is used to determine the error correction rate; when the software debugging detects that the actual path has a large error with the theoretical path (i.e. Where ε is the allowable error threshold), the system will automatically adjust the inspection path;

[0100] The path correction methods for the above scheme include:

[0101] If the path error is too large, it is expressed as: Reduce the path adjustment range to make camera adjustment more accurate and avoid monitoring blind spots caused by path deviation;

[0102]

[0103] If the path error is small, it can be expressed as: Increase the path adjustment range to enable the camera to complete inspection tasks faster and improve monitoring efficiency;

[0104]

[0105] in is the inspection path after adjustment; η is the path adjustment factor, which is used to prevent path instability caused by mutation; K max is the maximum allowable threshold of path error. If this value is exceeded, the system needs to recalculate the inspection path to prevent major deviations; K min The minimum allowable threshold for path error. If the value is lower than this, the system needs to make appropriate path adjustments to avoid insufficient adjustments affecting inspection efficiency.

[0106] The viewing angle adjustment in the inspection path algorithm module is used to enable the camera to adjust the horizontal rotation angle and pitch angle according to changes in the environment during the inspection task;

[0107]

[0108] in is the horizontal rotation angle of camera i in the actual inspection task; The theoretical horizontal rotation angle of camera i calibrated during the installation and debugging phase; is the pitch angle of camera i in the actual inspection task; The theoretical pitch angle calibrated for camera i during the installation and debugging phase; FOV i is the field of view of camera i; R i is the monitoring radius of camera i; ψ, ξ are the rotation error adjustment coefficients, which are used to correct the horizontal rotation angle and pitch angle respectively;

[0109] The software debugging error prevention mechanism in viewing angle adjustment includes:

[0110] Error detection: Before the inspection task is executed, the system collects the current horizontal angle and pitch angle of the camera and calculates the deviation between the actual adjustment angle and the theoretical value:

[0111]

[0112] If the error exceeds the set threshold E max , enter the error correction process;

[0113] Error correction includes horizontal rotation angle correction and pitch angle correction;

[0114] Horizontal rotation angle correction:

[0115]

[0116] Pitch angle correction:

[0117]

[0118] in are the corrected rotation angles respectively; is the error correction factor, Used to control the adjustment rate of error correction to prevent excessive adjustment from causing frequent camera shaking; E max is the maximum value of the allowable error; represents the horizontal rotation angle error of camera i during the tth round of inspection; It represents the pitch angle error of camera i during the tth inspection round.

[0119] Adaptive learning in the inspection path algorithm module optimizes camera status based on historical inspection data, allowing inspection tasks to be continuously optimized over time. Optimization is based on historical data fitting and error compensation to calculate the optimized monitoring angle and inspection interval.

[0120]

[0121] in is the field of view angle of camera i after optimization in round t+1; The field of view angle calculated by camera i during the tth round of inspection; R j is the inspection risk score of area j; di(C i ,C j ) is the adjustment path distance from camera i to camera j; is the error correction value of the tth software test, which is used to correct the calculation error in the optimization process; ν is the error correction factor, which is used to ensure that the error correction meets the long-term optimization requirements; is the learning rate, which is used to control the step size of the field of view angle adjustment during the inspection path optimization process to ensure that the adjustment range is not too large or too small to achieve stable optimization; N is the total number of cameras or monitoring nodes in the inspection area;

[0122] Software debugging error prevention mechanisms include:

[0123] Error analysis: The system records the camera adjustment path, zoom parameters, and monitoring coverage during each inspection, and calculates the error between the actual adjustment value and the theoretical optimal value;

[0124] Error correction: If software debugging detects an error in the inspection path Then adjust the optimization strategy:

[0125]

[0126] Among them, M max Indicates the maximum error threshold allowed during inspection path optimization. If the error exceeds this value, the system needs to adjust the inspection parameters to prevent the accumulation of monitoring deviations; reduce the adjustment range of the field of view to avoid loss of monitoring area due to over-optimization;

[0127] Adaptive optimization: Combined with historical inspection data, the system uses deep learning methods (such as LSTM and reinforcement learning) to continuously train and optimize inspection paths, giving the system long-term learning capabilities and improving monitoring accuracy.

[0128] The system also includes an inspection task execution supervision module, which establishes an inspection task execution deviation assessment model based on three factors; calculates the execution deviation value based on the inspection task execution deviation assessment model; if the execution deviation value is greater than the execution deviation threshold, it is determined to be an execution deviation and triggers an abnormality alarm;

[0129] The three factors include path deviation, coverage area, and task execution. The path deviation factor is used to calculate the difference between the camera's actual inspection path and the ideal path, assessing whether the inspection task is executed according to the planned trajectory.

[0130] The coverage area factor is used to compare the actual monitoring range with the theoretical coverage area to detect whether there are any missed areas that have not been inspected for a long time;

[0131] Task execution factors are used to monitor camera rotation accuracy, zoom adjustment error, and inspection time deviation, and to evaluate the consistency of inspection task execution.

[0132] The path deviation error is calculated based on the path deviation factor, and the proposed path deviation error is E path ; Calculate the coverage area error based on the coverage area factor, and propose the coverage area error as E cover ; Calculate the task execution error based on the task execution factors, and propose the task execution error as E task ;

[0133]

[0134] Where Q is the number of cameras in the system; The actual inspection path point of camera i and theoretical inspection path points Bezier curve matching error between max is the maximum path deviation value allowed by the system; The actual installation angle detected by the camera; is the theoretical installation angle of the camera; θmax The maximum angle of camera rotation; is the actual and theoretical inspection time interval of camera i; T max G is the peak value of the allowed inspection time deviation; path The path deviation weighting factor is used to dynamically adjust the impact of the path error on the final execution deviation, and is adjusted according to the complexity of the environment.

[0135] Where A is the total number of inspection areas; A actual,j is the actual coverage area of the jth monitoring area; A ideal,j The theoretically calculated optimal coverage area for the jth monitoring area; A actual,j ∩A ideal,j It represents the intersection area of the actual monitoring area and the theoretical monitoring area, that is, the part that is successfully covered; G is the cumulative risk score of the jth monitoring area that has not been inspected in the past, and the weight of the area that has not been inspected for a long time increases; cover is the coverage error weighting factor, which dynamically adjusts the impact of coverage error according to the risk level of the area and the complexity of the environment;

[0136] in is the actual and theoretical zoom ratio of camera i; Z max The peak zoom ratio of the camera; This is the task execution weight factor. If a camera has multiple errors in historical inspections, its weight will automatically increase to make its impact stronger.

[0137] Based on the three factors, the inspection task execution deviation evaluation model is established, and the execution deviation value is calculated based on the inspection task execution deviation evaluation model. The proposed execution deviation value is E total ;

[0138]

[0139] Among them, α, β, and γ are nonlinear adjustment factors, which make different deviations change dynamically during calculation to prevent a single factor from excessively affecting the overall result; The nonlinear adjustment value representing the path deviation error is used to calculate the degree of match between the camera's actual inspection path and the ideal path; The nonlinear adjustment value representing the coverage area error measures the overlap between the actual monitoring range and the theoretical coverage range; represents the nonlinear adjustment value of the task execution error, which comprehensively calculates the deviation of the camera rotation angle, zoom ratio and inspection time; λ1, λ2, λ3 are error attenuation factors, which are used to smooth the impact of different errors on the final calculated value; W path ,W cover ,W task E path、E cover 、E task The importance weight of can be adjusted dynamically over time; δ is a normalization factor, which is used to ensure that the calculation results are within a stable range and make the model more adaptable.

[0140] 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, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart property management system, comprising a property scheduling management module, a monitoring management module, an inspection path algorithm module, and an inspection execution module, characterized in that: The property dispatch management module is used to store the locations of all cameras, sensors, property facilities, the status of property facilities and their maintenance records, and realize linkage through the inspection path algorithm module; The monitoring and management module is used to deploy cameras and perform camera deflection and zoom to ensure that the camera's monitoring range covers the target area for inspection. The monitoring and management module includes temperature and humidity sensors, smoke sensors, and light sensors for real-time collection of property environmental information. The inspection path algorithm module includes environment modeling, priority allocation, dynamic path optimization, perspective adjustment, and adaptive learning; The inspection path algorithm module constructs the three-dimensional structure of the property management area through environmental modeling and calculates the camera's field of view, which is used to determine the initial monitoring coverage; The inspection path algorithm module calculates the inspection interval by assigning priorities and combining the inspection time adjustment strategy, and adjusts the inspection order according to the task priority assignment; The inspection path algorithm module adjusts the camera's inspection angle in real time through dynamic path optimization, prioritizes the shortest path to ensure that inspection tasks run along the required path, and combines a hotspot area backtracking mechanism to increase inspection frequency in fault-prone areas. The viewing angle adjustment in the inspection path algorithm module optimizes the monitoring coverage based on the error correction mechanism of the camera's horizontal rotation angle and pitch angle, and uses error compensation adjustment to stabilize the monitoring viewing angle; The inspection path algorithm module optimizes the viewing angle and inspection interval by analyzing historical inspection data, so that the inspection path is optimized over time; The inspection execution module is used to receive instructions from the inspection path algorithm module and control the camera to perform adjustment tasks. The camera is integrated with a pan-tilt control module, which is used to adjust the camera's deflection angle, rotation speed, and focal length.

2. A smart property management system according to claim 1, characterized in that: Environmental modeling involves constructing a three-dimensional model of the property management area and calculating the required monitoring range of the camera. Software debugging is also used to detect errors and prevent camera installation angle errors and spatial obstructions that affect the field of view. The three-dimensional modeling of the property management area is expressed as: P={(x i ,y i ,z i )∣i=1,2,…,N} Where P represents the three-dimensional coordinate point set of the property management area; (x i ,y i ,z i ) are the coordinates of the i-th spatial sampling point within the property; N is the number of all modeling points; Calculate the camera's field of view angle; FOV i is the field of view of camera i; R i is the peak value of the camera's monitoring radius; θ i is the horizontal opening angle of the camera; Indicates that during the tth software debugging, the installation error of camera i was detected; E max is the maximum value of the allowable error; Establish error-proofing mechanisms for software debugging and detection errors; in The actual installation angle detected by the camera; is the theoretical installation angle of the camera; α is the error accumulation coefficient, which is used to determine the error correction rate; like Then adjust the camera angle through the PTZ control module: in Indicates the rotation angle of camera i after adjustment.

3. The smart property management system according to claim 2, characterized in that: The priority allocation in the inspection path algorithm module is used to dynamically adjust the inspection sequence based on the historical failure rate of the inspection area, dynamic environmental changes, and the aging level of the equipment, so that the required areas are monitored first; where R i is the inspection risk score of area i; α1, α2, α3 are weight parameters; is the historical failure rate of region i; is the dynamic environmental change of region i; is the aging level of the equipment in area i; Score software debugging errors; γ is the software debugging correction coefficient; is the actual inspection time interval of area i in the actual inspection task; The ideal inspection time interval calculated for area i based on the inspection requirements; β is the inspection time error adjustment coefficient.

4. The smart property management system according to claim 3, characterized in that: The goal of the dynamic optimization calculation of the inspection path algorithm module is to find the path from the current monitoring state C i To target monitoring state C j The ideal adjustment path; in The calculated value from camera C in the t+1th round i To camera C j The ideal inspection path adjustment cost; d(C i ,C j ) is camera C i Rotate to camera C j The minimum angle adjustment required for the position; β is the risk weight parameter; R j For camera C j Inspection risk score of the corresponding area; C i Indicates the current monitoring status; C j Indicates the target monitoring status; Calculate error values for paths detected by software debugging; δ is the path error correction coefficient; During the dynamic optimization of the path, the system analyzes the historical inspection path through software debugging and calculates the deviation between the actual inspection path and the theoretical inspection path; in is the error value of the inspection path in the t+1th round; The inspection path distance actually adjusted for the camera; Ideal inspection path calculated for the system; λ is the path error adjustment coefficient.

5. The smart property management system according to claim 4, characterized in that: The viewing angle adjustment in the inspection path algorithm module is used to enable the camera to adjust the horizontal rotation angle and pitch angle according to changes in the environment during the inspection task; in is the horizontal rotation angle of camera i in the actual inspection task; The theoretical horizontal rotation angle of camera i calibrated during the installation and debugging phase; is the pitch angle of camera i in the actual inspection task; The theoretical pitch angle calibrated for camera i during the installation and debugging phase; FOV i is the field of view of camera i; R i is the monitoring radius of camera i; ψ, ξ are the rotation error adjustment coefficients.

6. The smart property management system according to claim 5, characterized in that: Adaptive learning in the inspection path algorithm module optimizes camera status based on historical inspection data, allowing inspection tasks to be continuously optimized over time. Optimization is based on historical data fitting and error compensation to calculate the optimized monitoring angle and inspection interval. in is the field of view angle of camera i after optimization in round t+1; The field of view angle calculated by camera i during the tth round of inspection; R j is the inspection risk score of area j; di(C i ,C j ) is the adjustment path distance from camera i to camera j; is the error correction value of the tth software test; ν is the error correction factor; h is the learning rate.

7. The smart property management system according to claim 6, characterized in that: The system also includes an inspection task execution supervision module, which establishes an inspection task execution deviation assessment model based on three factors; calculates the execution deviation value based on the inspection task execution deviation assessment model; if the execution deviation value is greater than the execution deviation threshold, it is determined to be an execution deviation and triggers an abnormality alarm; The three factors include path deviation factor, coverage area factor, and task execution factor; The path deviation factor is used to calculate the difference between the actual inspection path of the camera and the ideal path, and to evaluate whether the inspection task is executed according to the planned trajectory; The coverage area factor is used to compare the actual monitoring range with the theoretical coverage area to detect whether there are any missed areas that have not been inspected for a long time; Task execution factors are used to monitor camera rotation accuracy, zoom adjustment error, and inspection time deviation, and to evaluate the consistency of inspection task execution.

8. The smart property management system according to claim 7, characterized in that: The path deviation error is calculated based on the path deviation factor, and the proposed path deviation error is E path ; Calculate the coverage area error based on the coverage area factor, and propose the coverage area error as E cover ; Calculate the task execution error based on the task execution factors, and propose the task execution error as E task ; Where Q is the number of cameras in the system; The actual inspection path point of camera i and theoretical inspection path points Bezier curve matching error between max is the maximum path deviation value allowed by the system; The actual installation angle detected by the camera; is the theoretical installation angle of the camera; θ max The maximum angle of camera rotation; is the actual inspection time interval of area i in the actual inspection task; is the ideal inspection time interval calculated based on the inspection requirements for area i; T max G is the peak value of the allowed inspection time deviation; path is the path deviation weighting factor, which is used to dynamically adjust the impact of the path error on the final execution deviation; Where A is the total number of inspection areas; A actual,j is the actual coverage area of the jth monitoring area; A ideal,j A is the theoretical calculated coverage area of the jth monitoring area; actual,j ∩A ideal,j Indicates the intersection area of the actual monitoring area and the theoretical monitoring area; G is the cumulative risk score of the jth monitoring area that has not been inspected in the past; cover is the coverage error weighting factor; in is the actual and theoretical zoom ratio of camera i; Z max The peak zoom ratio of the camera; Weight factor for task execution.

9. The smart property management system according to claim 8, characterized in that: Based on the three factors, the inspection task execution deviation evaluation model is established, and the execution deviation value is calculated based on the inspection task execution deviation evaluation model. The proposed execution deviation value is E total ; in Indicates the nonlinear adjustment value of the path deviation error; Indicates the nonlinear adjustment value of the coverage area error; represents the nonlinear adjustment value of the task execution error; λ1, λ2, λ3 are error attenuation factors; W path ,W cover ,W task E path 、E cover 、E task The importance weight of ; δ is the normalization factor.

Images