Intelligent property management system and method based on Internet of Things application

Abstract

The invention relates to the field of Internet of Things application, and discloses an intelligent property management system and method based on Internet of Things application, and the system comprises an equipment state sensing module, an implicit work order generation engine, a work order-resource dynamic matching module, and an emergency logic reconstruction module. Through an innovative state-work order mapping mechanism, real-time perception and dynamic analysis of the equipment state are realized, the work order can be automatically generated at the initial stage of potential abnormity of the equipment, and the problem of traditional fault lag is avoided. Resource configuration is optimized through intelligent scheduling, the shortest response path is calculated through a graph algorithm, and the maintenance efficiency and the response speed are improved. In addition, the dynamic emergency plan reconstruction module flexibly deals with superposition of complex events, and the adaptability and processing capacity of emergency response are enhanced.

Description

Technical Field

[0001] The present invention relates to a smart property management system and method based on Internet of Things applications, belonging to the technical field of Internet of Things applications. Background Art

[0002] Property management systems are primarily used in large commercial buildings, industrial parks, residential communities, and other locations to monitor and manage the operating status of equipment (such as elevators, water pipes, and air conditioners). Traditional property management systems rely on manual inspections and device alarms to detect equipment failures, typically using a preset threshold alarm mode. Once the operating status of a device exceeds a preset threshold, the system triggers an alarm and issues a work order, requiring staff to conduct an inspection. However, this threshold-based detection method has several limitations.

[0003] First, threshold-based alarm systems often only respond when equipment anomalies are fully manifested, resulting in delayed fault detection. For example, abnormal current fluctuations in an elevator motor may not trigger an alarm initially until a serious fault occurs, delaying maintenance response. Second, in traditional systems, equipment status data, work order systems, and personnel scheduling modules are independent of each other, lacking effective dynamic linkage. For example, when a fire alarm sensor triggers an alarm, it cannot automatically generate other related work orders, such as elevator shutdowns, causing delays in emergency response. Furthermore, manual inspections and route planning often rely on staff experience and fail to fully consider the real-time status and location of equipment, resulting in ineffective movement and wasted time for maintenance personnel.

[0004] To address these issues, the industry has attempted to introduce intelligent scheduling systems and sensors for equipment status monitoring, but these systems still face the following problems: the path planning of intelligent scheduling systems is mostly based on static information and cannot be adjusted in real time; sensor-based monitoring still relies on manually set thresholds and lacks dynamic adjustment capabilities; traditional emergency plans are mostly fixed plans and cannot flexibly respond to the overlapping scenarios of multiple emergencies.

[0005] Therefore, how to realize intelligent fault prediction and work order generation based on real-time equipment status, how to effectively integrate equipment monitoring and personnel scheduling systems, and improve maintenance efficiency and emergency response capabilities have become the technical problems to be solved by the present invention. Summary of the Invention

[0006] The present invention provides a smart property management system and method based on Internet of Things applications, the main purpose of which is to solve the problems of lag in equipment status and work order generation, inefficiency in resource scheduling, and rigidity in emergency response.

[0007] To achieve the above objectives, the present invention provides a smart property management system based on the Internet of Things application, comprising:

[0008] The device status sensing module is used to collect at least two or more different types of operating status data of multiple devices in the property management area in real time;

[0009] An implicit work order generation engine is in communication with the device status perception module, configured to receive the operating status data and, based on a preset logic rule base, perform correlation analysis and dynamic weight calculation on the received multiple types of operating status data. When the results of the correlation analysis and dynamic weight calculation meet a preset trigger condition, an implicit work order corresponding to the device anomaly is generated. The generation of the implicit work order does not rely on the triggering of a single preset threshold, wherein the trigger condition is:

[0010]

[0011] Among them, S i represents the i-th type of operating status data, W i represents the dynamic weight corresponding to the i-th type of operating status data, n is the total number of types of collected operating status data, and T is the preset trigger threshold;

[0012] A work order-resource dynamic matching module is in communication with the implicit work order generation engine, and is used to receive the implicit work order and automatically match the optimal maintenance personnel for the implicit work order and generate a corresponding response path based on the pre-built topological relationship information of the equipment in the property management area and the skill tag information of the maintenance personnel;

[0013] The emergency logic reconstruction module is communicatively connected to the device status perception module and the implicit work order generation engine, and is used to receive the emergency event information collected by the device status perception module, and decompose the pre-set emergency plan into multiple dynamically combinable atomic operations. According to the received emergency event information, the module selects and combines the atomic operation library to form the optimal handling plan for the current emergency scenario.

[0014] Preferably, the implicit work order generation engine further includes a self-learning unit, which is configured to dynamically adjust the relevance weight corresponding to the j-th type of operating status data in the logic rule base according to feedback information on the completion effect of historical work orders using the following formula:

[0015]

[0016] in, It represents the weight of the j-th type of running status data after the t-th work order is completed. It represents the adjustment factor of the completion effect of the tth work order on the weight of the jth type of running status data, and α is the preset learning rate.

[0017] Preferably, when generating the corresponding response path, the work order-resource dynamic matching module uses the Dijkstra algorithm in graph theory to calculate the shortest path from the current maintenance personnel position to the target equipment position.

[0018] Preferably, the emergency logic reconstruction module also includes a conflict detection unit, which is used to detect whether there is a logical conflict between different atomic operations when forming an optimal handling plan based on the received emergency event information combination, and when there is a conflict, select the optimal atomic operation combination according to a preset priority rule.

[0019] Preferably, it also includes an equipment health scoring module, which is communicatively connected to the implicit work order generation engine and is used to perform health scoring on the equipment in the property management area based on the type and frequency of the generated implicit work orders and the completion effect of historical work orders, and dynamically update the health scoring results of the equipment.

[0020] Preferably, the operating status data collected by the equipment status perception module includes current data, vibration data, temperature data and pressure data.

[0021] Preferably, the preset trigger threshold T is determined after statistical analysis of historical equipment operation data and fault data.

[0022] Preferably, the mapping relationship between the equipment status combination and the work order type defined in the logic rule base includes: when the sum of the weight corresponding to the elevator motor current fluctuation and the weight corresponding to the abnormal access control switch frequency exceeds a preset value, an elevator transmission system inspection work order is generated.

[0023] Preferably, the atomic operations included in the atomic operation library include power off, starting the backup power supply and elevator forced landing; the equipment health scoring module is also used to generate predictive maintenance recommendations for the equipment based on the health scoring results of the equipment.

[0024] A smart property management method based on the Internet of Things application, characterized in that the method comprises the following steps:

[0025] S1, real-time collection of at least two or more different types of operating status data of multiple devices within the property management area;

[0026] S2: Receive the operating status data and, based on a preset logic rule library, perform correlation analysis and dynamic weight calculation on the received multiple types of operating status data. When the results of the correlation analysis and dynamic weight calculation meet a preset trigger condition, generate an implicit work order corresponding to the equipment abnormality. The generation of the implicit work order does not rely on the triggering of a single preset threshold.

[0027] S3, receiving the implicit work order, and automatically matching the optimal maintenance personnel for the implicit work order and generating a corresponding response path based on pre-built topological relationship information of the equipment in the property management area and the skill tag information of the maintenance personnel;

[0028] S4, receiving the emergency event information collected by the device status perception module, and decomposing the pre-set emergency plan into multiple dynamically combinable atomic operations, and selecting and combining the atomic operation library according to the received emergency event information to form the optimal disposal plan for the current emergency scenario.

[0029] Compared with the problems described in the background technology, the beneficial effects of the present invention are:

[0030] 1. By introducing an implicit work order generation mechanism based on state-to-work order mapping, this system breaks away from the traditional property management model of relying on fixed threshold alarms. Instead, it utilizes multi-dimensional correlation analysis of equipment states and dynamic weight calculation to trigger work order generation. This mechanism effectively avoids the problem of traditional technologies requiring intervention only after a fault has fully manifested. Instead, it provides timely warnings and automatically generates work orders when potential equipment anomalies occur. This threshold-free triggering method, based on dynamic state changes, eliminates reliance on single alarm signals or manual inspections, significantly improving the early identification of equipment faults and enhancing the system's response accuracy and flexibility.

[0031] 2. This solution's dynamic work order-resource matching module combines device topology information with maintenance personnel skill tags. Through intelligent scheduling, it automatically matches the most suitable personnel and uses graph algorithms to calculate the optimal response path. This intelligent allocation based on device location and personnel skills ensures efficient and accurate work order assignment, effectively avoiding errors caused by manual experience and intuition, and significantly improving work efficiency. The path optimization algorithm accurately calculates the shortest path, reducing unnecessary maintenance personnel movement and improving resource utilization. This, in practice, shortens system response time and improves execution effectiveness.

[0032] 3. This technical solution, through the emergency logic reconstruction module, proposes to disassemble the traditional overall emergency plan into dynamically combinable atomic operations, enabling the system to flexibly respond to a variety of complex scenarios (such as fire, elevator entrapment, power outages, etc.). Traditional emergency plans often struggle to cope with a variety of sudden and complex events due to their fixed processing steps. However, this solution, through atomic operations and real-time conflict detection, ensures that when faced with multiple emergency events, the optimal emergency plan can be automatically selected based on actual needs.

[0033] 4. As the system operates, the solution's self-learning mechanism dynamically adjusts the relevance weights of device status data based on historical work order feedback. This mechanism, through real-time data feedback, not only improves the accuracy of initial device fault identification but also enables self-optimization and adaptation to changes in device status over time. The introduction of this self-learning mechanism promotes the system's continuous evolution over the long term, enhancing its intelligence and responsiveness, and ensuring that the system can better respond to future equipment maintenance needs.

[0034] 5. The system uses the Equipment Health Scoring module to dynamically assess the health of each device based on the type, frequency, and completion of implicit work orders. This health assessment, based on device operational data, not only provides a data-driven basis for decision-making regarding equipment maintenance but also enables property managers to take timely action through predictive maintenance recommendations before actual equipment failures occur, avoiding unnecessary equipment downtime or repairs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is the intelligent optimization decision flow chart for emergency events of the present invention;

[0036] Figure 2 This is a flow chart for constructing and applying the equipment health scoring model of the present invention;

[0037] Figure 3 This is a flowchart of real-time monitoring of IoT device status and closed-loop management of work orders in the present invention;

[0038] Figure 4 This is a flowchart of the multi-algorithm dynamic scheduling driven by work order priority of the present invention.

[0039] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0040] 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.

[0041] The present application provides a smart property management system and method based on Internet of Things applications. The smart property management system based on Internet of Things applications includes:

[0042] The device status sensing module is used to collect at least two or more different types of operating status data of multiple devices in the property management area in real time;

[0043] An implicit work order generation engine is in communication with the device status perception module, configured to receive the operating status data and, based on a preset logic rule base, perform correlation analysis and dynamic weight calculation on the received multiple types of operating status data. When the results of the correlation analysis and dynamic weight calculation meet a preset trigger condition, an implicit work order corresponding to the device anomaly is generated. The generation of the implicit work order does not rely on the triggering of a single preset threshold, wherein the trigger condition is:

[0044]

[0045] Among them, S i represents the i-th type of operating status data, W i represents the dynamic weight corresponding to the i-th type of operating status data, n is the total number of types of collected operating status data, and T is the preset trigger threshold;

[0046] A work order-resource dynamic matching module is in communication with the implicit work order generation engine, and is used to receive the implicit work order and automatically match the optimal maintenance personnel for the implicit work order and generate a corresponding response path based on the pre-built topological relationship information of the equipment in the property management area and the skill tag information of the maintenance personnel;

[0047] The emergency logic reconstruction module is communicatively connected to the device status perception module and the implicit work order generation engine, and is used to receive the emergency event information collected by the device status perception module, and decompose the pre-set emergency plan into multiple dynamically combinable atomic operations. According to the received emergency event information, the module selects and combines the atomic operation library to form the optimal handling plan for the current emergency scenario.

[0048] Preferably, the implicit work order generation engine further includes a self-learning unit, which is configured to dynamically adjust the relevance weight corresponding to the j-th type of operating status data in the logic rule base according to feedback information on the completion effect of historical work orders using the following formula:

[0049]

[0050] Among them, It represents the weight of the j-th type of running status data after the t-th work order is completed. It represents the adjustment factor of the completion effect of the tth work order on the weight of the jth type of running status data, and α is the preset learning rate.

[0051] Preferably, when generating the corresponding response path, the work order-resource dynamic matching module uses the Dijkstra algorithm in graph theory to calculate the shortest path from the current maintenance personnel position to the target equipment position.

[0052] Preferably, the emergency logic reconstruction module also includes a conflict detection unit, which is used to detect whether there is a logical conflict between different atomic operations when forming an optimal handling plan based on the received emergency event information combination, and when there is a conflict, select the optimal atomic operation combination according to a preset priority rule.

[0053] Preferably, it also includes an equipment health scoring module, which is communicatively connected to the implicit work order generation engine and is used to perform health scoring on the equipment in the property management area based on the type and frequency of the generated implicit work orders and the completion effect of historical work orders, and dynamically update the health scoring results of the equipment.

[0054] Preferably, the operating status data collected by the equipment status perception module includes current data, vibration data, temperature data and pressure data.

[0055] Preferably, the preset trigger threshold T is determined after statistical analysis of historical equipment operation data and fault data.

[0056] Preferably, the mapping relationship between the equipment status combination and the work order type defined in the logic rule base includes: when the sum of the weight corresponding to the elevator motor current fluctuation and the weight corresponding to the abnormal access control switch frequency exceeds a preset value, an elevator transmission system inspection work order is generated.

[0057] Preferably, the atomic operations included in the atomic operation library include power off, starting the backup power supply and elevator forced landing; the equipment health scoring module is also used to generate predictive maintenance recommendations for the equipment based on the health scoring results of the equipment.

[0058] A smart property management method based on the Internet of Things application, characterized in that the method comprises the following steps:

[0059] S1, real-time collection of at least two or more different types of operating status data of multiple devices within the property management area;

[0060] S2: Receive the operating status data and, based on a preset logic rule library, perform correlation analysis and dynamic weight calculation on the received multiple types of operating status data. When the results of the correlation analysis and dynamic weight calculation meet a preset trigger condition, generate an implicit work order corresponding to the equipment abnormality. The generation of the implicit work order does not rely on the triggering of a single preset threshold.

[0061] S3, receiving the implicit work order, and automatically matching the optimal maintenance personnel for the implicit work order and generating a corresponding response path based on pre-built topological relationship information of the equipment in the property management area and the skill tag information of the maintenance personnel;

[0062] S4, receiving the emergency event information collected by the device status perception module, and decomposing the pre-set emergency plan into multiple dynamically combinable atomic operations, and selecting and combining the atomic operation library according to the received emergency event information to form the optimal disposal plan for the current emergency scenario.

[0063] Example 1: In an industrial park, the property management team faces a series of challenges, including delayed response to equipment failures and inefficient staff scheduling. The complex is equipped with a variety of critical facilities, including elevators, water pipes, air conditioning systems, and fire protection facilities. Traditional property management methods rely on manual inspections and threshold alarms. When an abnormality occurs in the equipment, the system triggers an alarm and dispatches a work order based on the preset threshold. However, due to the lag between the equipment status monitoring and alarm system, many problems are not discovered in the early stages. Often, staff will not intervene to deal with the problem until the equipment has already suffered a more serious failure, resulting in longer repair response time and higher maintenance costs.

[0064] In this embodiment, the property management system utilizes an intelligent fault prediction and work order generation mechanism based on IoT technology. By installing multi-dimensional sensors (such as current sensors, temperature sensors, and vibration sensors) on various devices in the complex, the system can monitor the operating status of each device in real time. The collected data is not limited to a single threshold setting, but rather triggers work order generation through correlation analysis of the status. For example, during elevator maintenance, the current fluctuation data of the elevator motor, the on / off frequency of the access control system, and the vibration during elevator operation are all collected simultaneously. Traditional systems may trigger alarms based solely on abnormal current fluctuations, while ignoring the impact of other important data such as vibration and access control frequency. With this system, current fluctuations are combined with abnormal access control frequency. Through dynamic weight calculation, the system identifies possible transmission system problems in the elevator and automatically generates related work orders, such as an elevator transmission system inspection. This process does not rely on triggering a single threshold, but rather relies on correlation analysis of multiple data points to predict potential faults in advance.

[0065] Furthermore, after a work order is generated, the system automatically plans the optimal response path based on the equipment topology and the location of maintenance personnel. For example, suppose the elevator is located on the second underground floor of a complex, while the person responsible for maintaining it is currently on the fifth floor. Traditional systems may require personnel to manually calculate the path, resulting in ineffective trips to different floors and wasted time. This system, however, automatically calculates the shortest path using graph algorithms (such as the Dijkstra algorithm) and pushes real-time path planning to maintenance personnel, ensuring they can reach the location of the faulty equipment in the shortest possible time. This feature significantly improves maintenance response speed and reduces the complexity of manually calculating paths.

[0066] In terms of emergency response, this embodiment further optimizes traditional emergency plans. Imagine an elevator malfunction one night, and at the same time, a fire alarm sensor on a floor triggers an alarm. Traditional emergency plans cannot handle both types of emergencies simultaneously. However, this system uses an emergency logic reconstruction module to break down multiple atomic operations into independent units, such as powering off → activating the backup power supply and elevator forced landing. Using a real-time conflict detection mechanism, the system prioritizes the most urgent operation based on the actual situation, ensuring efficient and accurate emergency response.

[0067] Through the integrated application of these technical approaches, this embodiment significantly improves the early detection of faults, the intelligence of resource scheduling, and the adaptability of emergency response, overcoming the problems of delayed monitoring, inefficient scheduling, and rigid emergency response in traditional property management systems. In practice, property management personnel can be notified of equipment failures at the earliest stages of their occurrence, addressing potential issues promptly and preventing further losses caused by the spread of equipment failures. Furthermore, intelligent work orders and route planning significantly improve staff efficiency and significantly shorten response times. This not only improves equipment operational reliability but also optimizes property management costs and resource utilization.

[0068] Example 2: In this example, the device status sensing module primarily collects real-time status data for multiple devices within the property management area. Specifically, through multi-dimensional sensors (such as temperature sensors, current sensors, and vibration sensors), the system can collect multiple operating status data for devices, such as current values, temperature values, and vibration frequencies. Each piece of data is collected and uploaded to the data processing unit in real time via IoT sensors.

[0069] Each piece of status data collected by this module isn't simply a digital input; instead, the module adjusts the sensor's sensitivity and acquisition frequency based on the specific characteristics of the device. For example, for elevator equipment, the temperature sensor might collect data at a lower frequency, while the frequency of current data is dynamically adjusted based on the elevator's operating status. This module ensures the real-time and accuracy of device status data, forming the foundation of the implicit work order generation engine.

[0070] The implicit work order generation engine mainly receives data from the device status perception module and performs dynamic analysis based on a preset logical rule base. When multiple types of operating status data meet specific correlation analysis conditions, the system automatically generates implicit work orders related to device anomalies. Formula:

[0071]

[0072] In this formula: W i represents the dynamic weight of the i-th state data, which is gradually adjusted by the self-learning mechanism based on historical data; Si represents the value of the i-th state data, such as current, vibration, or temperature; T is a dynamically calculated trigger threshold, which is no longer a fixed setting, but is determined through statistical analysis based on the historical operation data and fault data of the equipment; n is the number of data types collected. In this formula, W i The value of is derived from historical work order completions and is dynamically adjusted through a self-learning mechanism. After each work order is completed, the system adjusts the weight of the associated status data based on the equipment's actual fault manifestations and maintenance effectiveness. For example, in elevator equipment fault diagnosis, changes in both current and vibration data may indicate a potential problem. By comprehensively considering the weights of these two data types, the system triggers a work order for an elevator drive system inspection when the weighted sum of current and vibration exceeds a set dynamic threshold.

[0073] The self-learning mechanism can continuously adjust the correlation weights corresponding to the equipment status data based on the feedback information of historical work orders. For example, the feedback data of the completion effect of historical work orders (such as the success rate of repairs, response time, etc.) will affect the weight adjustment, making the system more accurate and sensitive in fault identification. Whenever a new work order is completed, the system automatically adjusts W j To reflect the actual importance of the device status data. The formula is adjusted as follows:

[0074] W j (t+1)=W j (t)+α×E j (t),

[0075] Where: W j (t) is the weight of the j-th state data after the t-th work order; E j (t) is the feedback value of the tth work order; α is the preset learning rate, which controls the amplitude of weight adjustment. Through this dynamic learning mechanism, the system can continuously optimize the equipment condition monitoring strategy over time, thereby gradually improving the accuracy of equipment fault identification and the effectiveness of maintenance strategies in long-term operation.

[0076] The work order-resource dynamic matching module combines device topology information and maintenance personnel's skill tags. After generating a work order, the system automatically selects the most suitable maintenance personnel based on this information and plans a response path. Using graph algorithms (such as the Dijkstra algorithm), the system calculates the shortest path from the maintenance personnel's current location to the target device, reducing unnecessary movement and wasted time. For example, when an elevator malfunctions, the system not only automatically selects a person with elevator maintenance skills, but also calculates the shortest path from that person's current location to the location of the elevator malfunction and pushes it to that person in real time. This feature significantly improves resource utilization efficiency and response speed, avoiding the personnel scheduling errors and wasted time associated with traditional methods.

[0077] In terms of emergency response, the system uses an emergency logic reconstruction module, which breaks down traditional emergency plans into multiple atomic operations to ensure flexible response in the event of a superposition of multiple emergencies. Whenever the system receives multiple emergency events, it automatically selects the optimal operation from the atomic operation library and performs real-time conflict detection. For example, when a fire alarm and an elevator failure occur at the same time, the system will give priority to the elevator forced landing operation or the power off operation, rather than performing unrelated operations at the same time, thereby ensuring efficient and accurate emergency response. Through the above steps, this embodiment demonstrates how to optimize equipment monitoring, work order generation, and resource scheduling in the property management system by introducing Internet of Things technology, intelligent scheduling, graph algorithms, and self-learning mechanisms, thereby effectively improving the intelligence level and response efficiency of property management.

[0078] Example 3: This example combines Figures 1 to 4 , further explaining the specific workflow and optimization mechanism of the smart property management system based on Internet of Things applications.

[0079] like Figure 1 As shown in the figure, in this system, when an emergency occurs, the device status perception module first triggers the generation of a new work order. Subsequently, the system uses the urgency judgment node to classify the urgency of the work order based on information such as the work order type and device status. If the urgency of the event is high, the system will prioritize the optimal path algorithm to ensure a rapid response. If the urgency is medium, the load balancing algorithm is used to allocate tasks to ensure the rational use of resources. Work orders with lower urgency are optimized using the cost optimization algorithm and ultimately assigned to the corresponding device node to improve overall resource utilization efficiency. Each step ensures that the emergency event is handled promptly and accurately, improving the system's responsiveness and processing efficiency.

[0080] like Figure 2 As shown, the equipment health score is a comprehensive assessment based on multiple factors, including work order type weight, work order frequency factor, historical completion coefficient, and time decay function. These factors are integrated into a scoring matrix to generate the equipment health score. The score automatically generates implicit work orders based on the actual equipment health and pushes them to maintenance personnel. Furthermore, the health score results can be used to generate maintenance strategies, helping property managers make effective maintenance decisions, extend equipment lifespan, and reduce failures.

[0081] like Figure 3As shown in the figure, after device status data is collected by sensor nodes and transmitted to the edge gateway, the system processes the data in real time and sends the analysis results to the health monitoring module. In this module, the system continuously monitors the health status of the devices and generates health analysis reports. Based on these reports, the system triggers the work order push (including path planning) module, which automatically optimizes the work order push path based on the device location and maintenance personnel's skills. This process ensures timely execution of maintenance tasks, and the progress of tasks can be tracked in real time through the on-site photo upload function.

[0082] like Figure 4 As shown in the figure, when a new work order arrives at the system, it first undergoes an urgency assessment, and based on the assessment results, determines the urgency of the work order. If the work order is urgent, the system uses an optimal path algorithm for path planning and assigns the task to device node A. If the urgency is medium, a load balancing algorithm is used to assign the task to device node B. For work orders with low urgency, the system uses a cost optimization algorithm to maximize the cost-effectiveness of task assignment, ultimately assigning the task to device node C.

[0083] Example 4: In this example, the formula In, W i : represents the dynamic weight of the i-th state data, dynamic weight W i It will be adjusted based on the feedback of the completion effect of the equipment's historical work orders. When the work order is generated, the weight reflects the impact of the status data on the health status of the equipment. The higher the weight, the greater the impact of the status data on fault identification. i : represents the value of the i-th state data, such as temperature, vibration, or current, collected in real time by sensors and uploaded to the system. T: represents the dynamic trigger threshold. This threshold is derived from statistical analysis of historical operating data and fault data, rather than a fixed threshold. Its function is to determine whether to initiate work order generation.

[0084] In this embodiment, the dynamic weight W i The value of will be adjusted continuously as the system runs. When a device failure occurs, W i The data will be gradually updated based on historical work order feedback, such as repair success rate, response time, and other factors. This adjustment ensures that the weight of each status data is flexible for different devices and scenarios, and accurately reflects the actual risk of failure.

[0085] The self-learning mechanism can dynamically adjust the weight of status data based on feedback from historical work orders, allowing the system to continuously optimize fault identification and work order generation strategies during long-term operation. Specifically, after each work order is completed, the system adjusts the weight of the status data based on the actual maintenance effect. The formula is as follows:

[0086] W j(t+1)=W j (t)+α×E j (t),

[0087] W j (t): represents the weight of the j-th state data after the t-th work order is completed; E j (t): represents the effect feedback value of the t-th work order, reflecting the maintenance effect, such as maintenance time, equipment recovery, etc.; α: learning rate, controlling the amplitude of weight adjustment; this formula dynamically adjusts the weight through the self-learning mechanism to ensure that the system can gradually adapt to the changes in the operating status of the equipment over time and improve the accuracy of fault identification. When the weight is updated, E j (t) will comprehensively consider the repair success rate, response time and equipment operation status after repair to avoid relying on a single indicator; after the work order is generated, the system will automatically calculate the response path to ensure that the maintenance personnel can reach the target equipment in the shortest time. This process involves graph algorithms, such as the Dijkstra algorithm, which is used to calculate the shortest path. In this embodiment, we further clarify the parameter definitions in the path planning process and their role in optimization. Each device has a location identifier in the system, and the devices are connected through a topology map. Each maintenance personnel also has a location identifier and is matched with the maintenance requirements of the equipment through skill tags; the input of the Dijkstra algorithm is the equipment topology map, the location of the maintenance personnel, the location of the equipment fault, and the skill tag information of the maintenance personnel. The algorithm ensures the real-time and accuracy of path planning by calculating the shortest path between the equipment and the maintenance personnel.

[0088] When emergencies occur, traditional systems typically rely on fixed emergency plans, which are unable to effectively cope with the accumulation of multiple complex events. In this embodiment, the emergency response logic is broken down into multiple atomic operations, and a real-time conflict detection mechanism is used to ensure flexible and accurate responses. Whenever the system receives multiple emergency events, it first classifies the tasks according to their urgency. The system selects the most urgent event for processing based on pre-set priority rules. To prevent conflicts between operations, the system detects the conflict nature of each operation in real time and prioritizes the operation combination with the least conflict.

[0089] In the equipment health scoring module, the system assigns a health score based on equipment operating status data, historical work order completion status, and equipment maintenance frequency. This scoring mechanism not only predicts equipment health but also provides decision support for future maintenance tasks. The equipment health score is calculated using a weighted calculation of multiple factors, including the weight of each status data item, work order type and frequency, and historical maintenance results. The score can help property management personnel determine whether equipment requires proactive maintenance, thereby reducing the incidence of unexpected failures.

[0090] Example 5: In this example, the device status perception module is used to collect at least two different types of operating status data (such as current, temperature, and vibration) from multiple devices within the property management area in real time, and triggers implicit work order generation based on dynamic weight calculation. Unlike traditional systems, this solution does not rely on a single threshold trigger mechanism. Instead, it uses correlation analysis and dynamic weight calculation of multi-dimensional data (such as current and vibration data) to ensure that potential equipment anomalies are identified in their early stages.

[0091] Specifically, assuming that the system collects data from multiple devices (S i ), the weights of these data are calculated through the following process, W i : The dynamic weight of the i-th state data. This weight value is adjusted through a self-learning mechanism based on the completion results of historical work orders (such as maintenance time and success rate); T: The dynamic trigger threshold derived from statistical analysis of historical equipment operation data and fault data, used to determine whether an implicit work order needs to be generated; the generation of implicit work orders is based on the following formula:

[0092]

[0093] Among them, S i Indicates the real-time collected value of device status data (such as current, temperature, etc.), W i Indicates the dynamic weight corresponding to the state data. In the formula, W i The value of will be dynamically adjusted based on the feedback from historical work orders after each work order is generated, so that the system can adjust the influence of status data in a timely manner according to changes in device status.

[0094] After an implicit work order is generated, the system dynamically adjusts the weight of the status data through the self-learning unit. This adjustment is based on the completion results of historical work orders (such as fault repair time and repair success rate) and is performed using the following formula:

[0095] W j (t+1)=W j (t)+α×E j (t),

[0096] Among them, W j (t) is the weight of the j-th equipment status data after the t-th work order is completed, E j (t) represents the feedback effect (e.g., repair success rate) after the tth work order is completed, and α is the preset learning rate used to control the adjustment range. This dynamic adjustment mechanism ensures that the weight of device status data is gradually optimized over time, thereby improving the system's ability to predict device failures. These are all extended implementation methods known to those skilled in the art.

[0097] After a work order is generated, the system selects the optimal maintenance personnel based on the equipment topology information and the maintenance personnel's skill tag information through the work order-resource dynamic matching module, and generates a response path. Specifically, the system uses the Dijkstra algorithm in the graph algorithm to calculate the shortest path from the maintenance personnel's location to the target equipment location based on the distance between the maintenance personnel's current location and the equipment fault location. The path planning process is as follows: input data: the maintenance personnel's current location, the equipment fault location, the maintenance personnel's skill tag information, and the equipment topology map; calculation process: the Dijkstra algorithm is used to calculate the shortest path from the maintenance personnel's current location to the faulty equipment location, ensuring that the maintenance personnel can reach the fault location in the shortest time and reducing unnecessary travel time; this path planning function significantly improves maintenance efficiency and avoids the empirical and inefficient path planning in traditional systems.

[0098] When an emergency occurs, the emergency logic reconstruction module of this embodiment breaks down the traditional emergency plan into multiple atomic operations, and the system can select and execute the most appropriate operation plan according to the specific circumstances of the emergency. Each operation unit in the atomic operation library (such as power off, starting the backup power supply, equipment restart, etc.) will be dynamically combined according to the priority rules to ensure the accuracy and efficiency of the emergency response. In the face of multiple superpositions of emergency events, the system will use a real-time conflict detection mechanism to give priority to the operations most relevant to the current event and avoid executing conflicting operations. For example, when an elevator failure and a fire alarm occur at the same time, the system will give priority to the elevator forced landing operation or the emergency power off operation, and will not execute all operations at the same time, thereby ensuring the optimal allocation of resources and time.

[0099] The equipment health scoring module conducts health assessments on the equipment within the property management area, and the scoring is based on factors such as equipment operating status data, completion of historical work orders, and equipment maintenance frequency. The health score of each device is calculated through weighted calculation based on historical work order data, and the scoring result is used to determine whether predictive maintenance or early intervention is required. The health scoring process includes scoring factors: such as equipment operating status (temperature, current, vibration, etc.), maintenance frequency, historical completion status (repair success rate, etc.); scoring model: using a weighted model to weight and combine various factors to generate a health score for the equipment; the equipment health score provides property management personnel with powerful decision-making support, helping them to take necessary maintenance measures before equipment failure occurs, thereby avoiding the spread of failures and extending the service life of the equipment. These are all extended implementation methods that are known to ordinary technicians in this field.

[0100] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart property management system based on Internet of Things applications, characterized by: include: The device status sensing module is used to collect at least two or more different types of operating status data of multiple devices in the property management area in real time; An implicit work order generation engine is in communication with the device status perception module, configured to receive the operating status data and, based on a preset logic rule base, perform correlation analysis and dynamic weight calculation on the received multiple types of operating status data. When the results of the correlation analysis and dynamic weight calculation meet a preset trigger condition, an implicit work order corresponding to the device anomaly is generated. The generation of the implicit work order does not rely on the triggering of a single preset threshold, wherein the trigger condition is: Among them, S i represents the i-th type of operating status data, W i represents the dynamic weight corresponding to the i-th type of operating status data, n is the total number of types of collected operating status data, and T is the preset trigger threshold; A work order-resource dynamic matching module is in communication with the implicit work order generation engine, and is used to receive the implicit work order and automatically match the optimal maintenance personnel for the implicit work order and generate a corresponding response path based on the pre-built topological relationship information of the equipment in the property management area and the skill tag information of the maintenance personnel; The emergency logic reconstruction module is communicatively connected to the device status perception module and the implicit work order generation engine, and is used to receive the emergency event information collected by the device status perception module, and decompose the pre-set emergency plan into multiple dynamically combinable atomic operations. According to the received emergency event information, the module selects and combines the atomic operation library to form the optimal handling plan for the current emergency scenario.

2. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: The implicit work order generation engine further includes a self-learning unit, which is configured to dynamically adjust the relevance weight corresponding to the j-th type of operating status data in the logic rule base according to feedback information on completion results of historical work orders using the following formula: in, It represents the weight of the j-th type of running status data after the t-th work order is completed. It represents the adjustment factor of the completion effect of the tth work order on the weight of the jth type of running status data, and α is the preset learning rate.

3. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: When generating the corresponding response path, the work order-resource dynamic matching module uses the Dijkstra algorithm in graph theory to calculate the shortest path from the current maintenance personnel position to the target equipment position.

4. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: The emergency logic reconstruction module also includes a conflict detection unit, which is used to detect whether there is a logical conflict between different atomic operations when forming an optimal handling plan based on the received emergency event information combination, and when there is a conflict, select the optimal atomic operation combination according to a preset priority rule.

5. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: It also includes an equipment health scoring module, which is in communication with the implicit work order generation engine and is used to score the health of equipment in the property management area based on the type and frequency of the generated implicit work orders and the completion effect of historical work orders.

6. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: The operating status data collected by the equipment status perception module includes current data, vibration data, temperature data and pressure data.

7. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: The preset trigger threshold T is determined after statistical analysis of historical equipment operation data and fault data.

8. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: The mapping relationship between the device status combination and the work order type defined in the logic rule library includes: when the sum of the weight corresponding to the elevator motor current fluctuation and the weight corresponding to the abnormal access control switch frequency exceeds a preset value, an elevator transmission system inspection work order is generated.

9. The smart property management system based on the Internet of Things application according to claim 1 is characterized in that: The atomic operations included in the atomic operation library include power off, starting the backup power supply and elevator forced landing; the equipment health scoring module is also used to generate predictive maintenance recommendations for the equipment based on the health scoring results of the equipment.

10. A smart property management method based on Internet of Things applications, characterized in that: The method comprises the following steps: S1, real-time collection of at least two or more different types of operating status data of multiple devices within the property management area; S2: Receive the operating status data and, based on a preset logic rule library, perform correlation analysis and dynamic weight calculation on the received multiple types of operating status data. When the results of the correlation analysis and dynamic weight calculation meet a preset trigger condition, generate an implicit work order corresponding to the equipment abnormality. The generation of the implicit work order does not rely on the triggering of a single preset threshold. S3, receiving the implicit work order, and automatically matching the optimal maintenance personnel for the implicit work order and generating a corresponding response path based on pre-built topological relationship information of the equipment in the property management area and the skill tag information of the maintenance personnel; S4, receiving the emergency event information collected by the device status perception module, and decomposing the pre-set emergency plan into multiple dynamically combinable atomic operations, and selecting and combining the atomic operation library according to the received emergency event information to form the optimal disposal plan for the current emergency scenario.

Images