Whole-process monitoring and quality optimization method and system for intelligent property project

Abstract

The invention is suitable for the technical field of intelligent property, and provides an intelligent property project whole-process monitoring and quality optimization method and system, and the method comprises the steps: synchronously capturing a facility operation parameter set and an owner complaint work order set, and carrying out the standardization processing to form a standardized data stream; generating a quality scoring curve according to a preset period based on the data stream; identifying an abnormal time period by comparing a curve slope with a sudden drop threshold value, and extracting corresponding data to form a fault analysis basic data packet; constructing a fault conduction directed graph based on the data packet, identifying key nodes and generating an equipment parameter weight coefficient adjustment and sampling frequency optimization scheme; and updating the weight and adjusting the sampling strategy based on the scheme. According to the invention, the whole-course dynamic monitoring and accurate optimization of the property service quality are realized, and the management efficiency and the service quality are improved.

Description

Technical Field

[0001] This invention belongs to the field of smart property technology, and in particular relates to a method and system for full-process monitoring and quality optimization of smart property projects. Background Technology

[0002] With the rapid development of the Internet of Things, big data, and mobile internet technologies, smart property management, as an important direction for modern property management, is gradually replacing the traditional manual management model. Its core lies in using intelligent devices to monitor property facilities in real time and dynamically adjusting service quality based on resident feedback, thereby improving management efficiency, reducing operating costs, and enhancing the resident experience. Currently, most properties have introduced basic monitoring systems, collecting operating parameters of key facilities such as elevators and central air conditioning, and receiving resident complaints through mobile platforms, thus establishing a preliminary foundation for digital management.

[0003] The existing technology has the following technical problems: the facility operation parameters and owner complaint work orders are not effectively integrated, the data is fragmented and it is difficult to fully reflect the quality of property services; there is a lack of a dynamic quantitative evaluation mechanism for service quality, making it impossible to identify periods of abnormal quality in a timely manner; the analysis of faults is limited to the level of a single device and does not consider the fault transmission relationship between devices, resulting in a lack of systematic and targeted optimization decisions, making it difficult to fundamentally improve the stability of property service quality. Summary of the Invention

[0004] The purpose of this invention is to provide a method for full-process monitoring and quality optimization of smart property projects, aiming to solve the technical problems existing in the prior art as identified in the background art.

[0005] This invention is implemented as follows: a method for full-process monitoring and quality optimization of smart property projects, the method comprising:

[0006] Simultaneously capture the set of facility operation parameters of facilities within the property's jurisdiction, as well as the set of complaint work orders submitted by owners through mobile devices, and standardize the set of facility operation parameters and the set of complaint work orders to form a standardized data stream;

[0007] Based on the standardized data stream, a fusion analysis is performed to generate a quality score curve reflecting the quality of property services according to a preset cycle.

[0008] A sudden drop threshold is set, and the slope of each point of the quality score curve is compared with the sudden drop threshold to identify abnormal periods. The set of facility operation parameters and the set of complaint work orders corresponding to the abnormal period are extracted from the standardized data stream to form an abnormal subset of facility operation parameters and a feature set of complaint work orders, respectively. These are then packaged into a basic data package for fault analysis.

[0009] Based on the aforementioned fault analysis basic data package, a fault propagation directed graph is constructed, the in-degree value of all nodes in the fault propagation directed graph is calculated, key nodes are identified based on the in-degree value, and a system optimization decision including facility parameter weight coefficient adjustment scheme and sampling frequency optimization scheme is generated based on the in-degree value weight of the key nodes.

[0010] The weights are updated based on the facility parameter weight coefficient adjustment scheme, the quality score curve is readjusted, and the sampling strategy is adjusted based on the sampling frequency optimization scheme.

[0011] As a further aspect of the present invention, the formation of a standardized data stream specifically includes:

[0012] The system collects facility operation parameters in real time through IoT sensors, including: elevator operation parameters, abnormal door opening and closing frequency, central air conditioning operation parameters, water pump operation parameters, and access control operation parameters.

[0013] The system receives a set of complaint tickets, which includes: a unique facility ID, a complaint timestamp, a problem description, and a fault type tag.

[0014] The complaint work order set is structured and parsed, facility numbers are extracted and matched, and the problem description text is classified into predefined fault types;

[0015] The processed set of facility operation parameters and the set of complaint work orders are aligned by timestamp and merged into a standardized data stream with time series labels.

[0016] As a further aspect of the present invention, the step of generating a quality score curve reflecting the quality of property services at a preset period specifically includes:

[0017] Standardized data streams are divided into preset cycles, with each cycle containing a corresponding number of facility operation parameter records and associated work orders;

[0018] Calculate the facility health score and user satisfaction score within a preset period to generate a comprehensive quality score;

[0019] Connecting the comprehensive quality score points of 24 consecutive periods forms a quality score curve with timestamps.

[0020] As a further embodiment of the present invention, the packaging to form a basic data package for fault analysis specifically includes:

[0021] Calculate the slope of each adjacent point on the quality score curve and set a dynamic drop threshold. When the slope of any point is greater than the dynamic drop threshold, mark the time period adjacent to that point as an abnormal period.

[0022] Extract all facility operation parameters during the abnormal period, and remove normal facility operation data to form an abnormal subset of facility operation parameters;

[0023] Extract complaint work orders from abnormal periods, and extract the distribution of fault types and the characteristics of high-incidence facility areas to form a complaint work order feature set;

[0024] The abnormal subset of facility operation parameters and the feature set of complaint work orders are associated with each other through timestamps and compressed and packaged into a basic data package for fault analysis containing abnormal time period identifiers.

[0025] As a further aspect of the present invention, the generation of system optimization decisions, which includes a facility parameter weight coefficient adjustment scheme and a sampling frequency optimization scheme, specifically includes:

[0026] Parse the basic data packet for fault analysis, establish a set of facility nodes and a set of fault-related edges, and construct a weighted directed graph based on the physical connection relationship of facilities and historical fault logs;

[0027] Calculate the in-degree value of each node, select the top 10% of nodes by in-degree value as key nodes, and generate a facility parameter weight coefficient adjustment plan based on the in-degree value of the key nodes, thereby increasing the weight of the corresponding facility parameters of the key nodes based on the in-degree value.

[0028] A sampling frequency optimization scheme is generated, and the sampling frequency is increased based on the adjusted facility parameter weights for facilities associated with key nodes.

[0029] As a further embodiment of the present invention, the construction of the weighted directed graph specifically involves:

[0030] ;

[0031] in, As edge weight, it indicates that the fault is caused by the facility. Transmitted to facility The probability, These are the weighting coefficients for facility parameters. The physical connection strength between facilities is preset based on the connection method. This refers to the frequency of historical fault propagation.

[0032] Another objective of this invention is to provide a smart property project end-to-end monitoring and quality optimization system, the system comprising:

[0033] The standardized data stream generation module is used to simultaneously capture the set of facility operation parameters of facilities within the property's jurisdiction, as well as the set of complaint work orders submitted by owners through mobile terminals, and to standardize the set of facility operation parameters and the set of complaint work orders to form a standardized data stream.

[0034] The quality scoring curve analysis module is used to perform fusion analysis based on the standardized data stream and generate a quality scoring curve reflecting the quality of property services according to a preset period.

[0035] The abnormal period identification module is used to set a sudden drop threshold, compare the slope of each point of the quality score curve with the sudden drop threshold, identify abnormal periods, extract the facility operation parameter set and complaint work order set corresponding to the abnormal period from the standardized data stream, form an abnormal subset of facility operation parameters and a feature set of complaint work orders respectively, and package them into a basic data package for fault analysis.

[0036] The optimization decision generation module is used to construct a fault propagation directed graph based on the fault analysis basic data package, calculate the in-degree value of all nodes in the fault propagation directed graph, identify key nodes based on the in-degree value, and generate a system optimization decision including facility parameter weight coefficient adjustment scheme and sampling frequency optimization scheme based on the in-degree value weight of the key nodes.

[0037] The strategy adjustment module is used to update the weights based on the facility parameter weight coefficient adjustment scheme, readjust the quality score curve, and adjust the sampling strategy based on the sampling frequency optimization scheme.

[0038] The beneficial effects of this invention are:

[0039] This invention provides a method and system for full-process monitoring and quality optimization of smart property projects. By synchronously capturing and standardizing the integration of facility operation parameters and resident complaint work orders, it breaks down data silos and achieves comprehensive and multi-dimensional perception of property service quality. The quality scoring curve generated based on standardized data flow dynamically reflects service quality trends and accurately identifies abnormal periods by combining sudden drop thresholds, enabling management to focus on problems promptly. By constructing a directed fault propagation graph, it deeply explores the fault correlations between devices and generates equipment parameter weight adjustment and sampling frequency optimization schemes based on the in-degree values ​​of key nodes, making optimization decisions more systematic and targeted. Simultaneously, by dynamically updating weights and adjusting sampling strategies, a closed-loop mechanism of monitoring-analysis-optimization-feedback is formed, effectively improving the real-time performance and accuracy of property service quality monitoring and the effectiveness of optimization measures. This continuously improves resident experience, reduces operational risks, and promotes the refined management level of smart property. Attached Figure Description

[0040] Figure 1 A flowchart illustrating the method for full-process monitoring and quality optimization of smart property projects provided in this embodiment of the invention;

[0041] Figure 2 A flowchart for forming a standardized data stream is provided as an embodiment of the present invention;

[0042] Figure 3 A flowchart for generating a quality score curve reflecting the quality of property services according to a preset period, provided in an embodiment of the present invention;

[0043] Figure 4 This is a flowchart illustrating the process of packaging and forming a basic data package for fault analysis, provided in an embodiment of the present invention.

[0044] Figure 5 A flowchart for generating a system optimization decision that includes a facility parameter weight coefficient adjustment scheme and a sampling frequency optimization scheme, provided in an embodiment of the present invention;

[0045] Figure 6 The structural block diagram of the smart property project full-process monitoring and quality optimization system provided in the embodiments of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0047] Figure 1 A flowchart of the smart property project full-process monitoring and quality optimization method provided in the embodiments of the present invention is shown below. Figure 1 As shown, the method includes:

[0048] S100, synchronously capture the set of facility operation parameters of facilities within the property's jurisdiction, as well as the set of complaint work orders submitted by owners through mobile terminals, and perform standardized processing on the set of facility operation parameters and the set of complaint work orders to form a standardized data stream;

[0049] This step uses an Internet of Things (IoT) sensor network to capture the real-time operational status of various key facilities within the property's jurisdiction. The parameters covered, such as elevator operating parameters, abnormal door opening and closing frequency, central air conditioning operating parameters, water pump operating parameters, and access control operating parameters, are all objective indicators that directly reflect the physical condition of the facilities. The real-time collection of these data can promptly capture subtle anomalies in the facilities, such as minor vibration changes in elevator operation or fluctuations in the temperature of the central air conditioning vents. These are often early signs of facility malfunctions.

[0050] At the same time, the system simultaneously receives a set of complaint work orders submitted by homeowners via mobile devices. These work orders contain information such as the unique identification number of the complained facility, the complaint timestamp, the problem description text, and the fault type tag. This provides direct feedback from homeowners on their subjective feelings about the quality of property services and can make up for the lack of attention to user experience in pure facility parameter monitoring.

[0051] To ensure effective synergy between these two types of data, the complaint work order set undergoes structured parsing. Facility numbers are extracted to achieve precise matching with specific facilities, preventing residents' feedback from being misrepresented and unable to be linked to specific facilities. For example, descriptions like "The east gate of the community is always malfunctioning" are matched to the corresponding access control facility through their numbers. Simultaneously, the problem description text is categorized into predefined fault types. This process aims to standardize data, transforming diverse natural language descriptions into standardized labels that the system can recognize. For instance, descriptions like "Air conditioner is not cooling" and "Air conditioner blows hot air" are uniformly categorized under the "cooling function malfunction" type, ensuring that different residents' feedback on the same type of problem can be grouped into the same category, facilitating subsequent statistics and analysis.

[0052] Finally, the processed facility operation parameter set and complaint work order set are aligned by timestamp and merged into a standardized data stream with time series labels. The key to this step is to establish the correlation in the time dimension, because property problems often occur synchronously in time. For example, if the elevator operation parameters fluctuate abnormally within a certain period of time, it may be accompanied by complaints from owners about elevator malfunctions within the same period of time. The alignment of timestamps can clearly present this correlation, providing a temporal basis for subsequent analysis of the causal relationship between facility status and user experience.

[0053] like Figure 2 As shown, the formation of a standardized data stream specifically includes:

[0054] S110 collects facility operation parameters in real time through IoT sensors, including: elevator operation parameters, abnormal door opening and closing frequency, central air conditioning operation parameters, water pump operation parameters, and access control operation parameters;

[0055] S120 receives a set of submitted complaint work orders, including: the unique number of the complained facility, the complaint timestamp, the problem description text, and the fault type label;

[0056] S130: Perform structured parsing on the set of complaint work orders, extract facility numbers for matching, and classify the problem description text into predefined fault types;

[0057] S140 aligns the processed facility operation parameter set with the complaint work order set by timestamp and merges them into a standardized data stream with time series labels.

[0058] S200, Based on the standardized data stream, perform fusion analysis and generate a quality score curve reflecting the quality of property services according to a preset cycle;

[0059] The continuous data stream is segmented according to a preset cycle to establish a clear time granularity for property service quality assessment, avoiding the difficulty in capturing the phased characteristics of quality changes due to excessive data complexity. Within each cycle, facility operation parameter records and related complaint work orders for that period are integrated, ensuring that each assessment simultaneously covers both the objective condition of the facilities and the subjective feedback from residents.

[0060] Based on this, the calculation of facility health scores within a preset period essentially involves quantifying the overall operational status of the facility group and transforming dispersed facility parameters such as elevators, central air conditioning, and water pumps into comparable health indicators. The underlying logic is that the stable operation of facilities is the foundation of property service quality. By considering the deviation of each parameter from the benchmark value and the corresponding weight, it is possible to accurately reflect which facilities or parameters have a greater impact on overall health.

[0061] Meanwhile, the user satisfaction score supplements the evaluation from the perspective of homeowner experience. Even if facility parameters are within normal ranges, homeowners' actual feelings may still differ. By analyzing the severity of complaints and processing delays, service shortcomings that facility data cannot cover can be identified, such as homeowner dissatisfaction caused by untimely responses despite normal facility operation. Combining the facility health score with the user satisfaction score, and then introducing environmental compensation factors to generate a comprehensive quality score, aims to achieve a comprehensive evaluation. Environmental factors may temporarily affect service quality (such as a sudden increase in facility load due to extreme weather). Compensation factors can avoid excessive interference from such temporary factors in the quality assessment, making the score more closely reflect the actual service level.

[0062] Connecting the comprehensive quality score points of 24 consecutive periods forms a time-stamped quality score curve, transforming discrete periodic scores into a continuous trend graph. This visually presents the fluctuation pattern of property service quality over time, such as the quality difference between weekdays and weekends, and quality changes during morning and evening peak hours, providing a visual basis for identifying abnormal periods.

[0063] By integrating objective facility conditions with subjective user experience, a multi-dimensional quality assessment system has been constructed, enabling more comprehensive and multi-dimensional monitoring of property service quality. The pre-defined periodicity provides a clear time unit for quality assessment, facilitating timely tracking of quality changes and preventing problem accumulation. The calculation logic of the comprehensive quality score takes into account facility infrastructure, user experience, and environmental impact, ensuring that the score accurately reflects the actual service level and reducing misjudgments. The quality score curve formed over 24 periods transforms abstract quality data into an intuitive trend chart, clearly demonstrating the normal fluctuation patterns of quality and providing a benchmark for subsequent anomaly identification. When the curve shows abnormal fluctuations, the corresponding time period can be quickly located, providing a dynamic tracking tool for end-to-end monitoring.

[0064] like Figure 3 As shown, the step of generating a quality score curve reflecting the quality of property services at a preset cycle specifically includes:

[0065] S210 divides the standardized data stream into preset cycles, with each cycle containing a corresponding number of facility operation parameter records and associated work orders;

[0066] S220: Calculate the facility health score and user satisfaction score within a preset period to generate a comprehensive quality score.

[0067] ;

[0068] in, The overall health score of the facility group For the number of monitored facilities, The number of monitoring parameter types for a single type of facility. For parameters The initial weights, For parameters The deviation between the measured value and the reference value, The transformation function from parameter bias to health loss

[0069] ;

[0070] in, The user satisfaction score This is the global work order impact coefficient. This represents the number of valid work orders within the current period. For work orders Severity weighting For work orders The delay from submission to response. For delayed penalty function;

[0071] ;

[0072] in, This is the overall quality score. Weighting of facility health Weighted by user satisfaction It is an environmental compensation factor.

[0073] S230 connects the comprehensive quality score points of 24 consecutive periods to form a quality score curve with timestamps.

[0074] S300, set a sudden drop threshold, compare the slope of each point of the quality score curve with the sudden drop threshold, identify abnormal time periods, extract the facility operation parameter set and complaint work order set corresponding to the abnormal time period from the standardized data stream, form an abnormal subset of facility operation parameters and a feature set of complaint work orders respectively, and package them into a fault analysis basic data package.

[0075] The slope of the quality score curve is calculated at each adjacent point to quantify the rate of quality change. The magnitude of the slope directly reflects the decline in property service quality within adjacent periods; a larger slope indicates faster quality deterioration and more urgent potential problems. Setting a dynamic threshold for sudden drops, rather than a fixed value, is to adapt to the quality fluctuation patterns under different scenarios. For example, the normal quality fluctuation range differs between weekdays and holidays, and the reasonable slope differs between peak hours and off-peak hours. The dynamic threshold can automatically adjust based on historical data and time period characteristics, avoiding misjudgments or omissions caused by fixed standards.

[0076] When the slope of a certain point exceeds the dynamic drop threshold, the adjacent time period is marked as an abnormal period. The purpose of this step is to accurately pinpoint the time range in which the problem occurs, transforming the vague "quality degradation" into a specific time interval, defining clear boundaries for subsequent data extraction, and improving analysis efficiency.

[0077] After identifying the abnormal period, all facility operation parameters within that period are extracted, and normal data is removed to form an abnormal subset of facility operation parameters. Irrelevant information is stripped away, focusing on facility anomaly signals that may cause quality degradation. Normal operation data can interfere with problem judgment, while the abnormal subset can directly point to parameters that deviate from the baseline value, such as abnormal vibration frequency in elevator operation or sudden pressure drop in water pumps, providing objective evidence for locating facility faults. At the same time, complaint work orders from the abnormal period are extracted, and the distribution of fault types (such as elevator malfunctions, air conditioner failures, etc.) and the characteristics of high-incidence facility areas (specifically down to buildings or facilities) are analyzed to form a complaint work order feature set. This operation transforms user feedback into clues for problem localization. Subjective complaints can resonate with objective facility parameters. For example, a concentration of complaints in a certain area may correspond to abnormal facility parameters in that area, thus cross-validating the problem from two dimensions: "user experience" and "facility status".

[0078] Finally, the abnormal subset of facility operation parameters and the feature set of complaint work orders are associated with timestamps and compressed and packaged into a basic data package for fault analysis. The purpose is to ensure the consistency of the two types of data in the time dimension, avoid analysis deviations caused by time misalignment, and at the same time retain the key information of the abnormal period, so as to provide a structured and related data foundation for the subsequent construction of a directed graph of fault propagation.

[0079] Dynamic thresholds ensure accurate anomaly identification, avoiding the limitations of fixed standards in complex scenarios while guaranteeing the accurate capture of periods of genuine quality deterioration, providing a reliable early warning mechanism for end-to-end monitoring. Precise labeling of abnormal periods narrows the scope of analysis, allowing property managers to focus on problem periods rather than blindly searching through massive amounts of data, significantly improving fault location efficiency. The linkage between anomaly subsets of facility parameters and complaint work order feature sets breaks the limitations of relying solely on facility data or user complaints. Objective data validates subjective feelings, and subjective feedback guides objective analysis, forming a comprehensive problem profile and clarifying the direction for quality optimization.

[0080] like Figure 4 As shown, the packaging to form the basic data package for fault analysis specifically includes:

[0081] S310, calculate the slope of each adjacent point of the quality score curve and set a dynamic drop threshold. When the slope of any point is greater than the dynamic drop threshold, mark the time period adjacent to that point as an abnormal time period.

[0082] S320: Extract all facility operation parameters during the abnormal period, and form an abnormal subset of facility operation parameters after removing normal facility operation data;

[0083] S330: Extract complaint work orders during abnormal periods, and extract the distribution of fault types and the characteristics of high-incidence facility areas to form a complaint work order feature set;

[0084] S340 associates the abnormal subset of facility operation parameters with the feature set of complaint work orders through timestamps, and compresses and encapsulates them into a basic data package for fault analysis containing abnormal time period identifiers.

[0085] S400, based on the fault analysis basic data package, construct a fault propagation directed graph, calculate the in-degree value of all nodes in the fault propagation directed graph, identify key nodes based on the in-degree value, and generate a system optimization decision including facility parameter weight coefficient adjustment scheme and sampling frequency optimization scheme based on the in-degree value weight of the key nodes.

[0086] Parse the basic data packet for fault analysis, extract the facility information and fault correlation clues involved, establish a facility node set (i.e. all facilities that may participate in fault propagation) and a fault correlation edge set (i.e. the possible fault impact relationships between facilities), transform the scattered abnormal data into a structured relationship network, and make the originally implicit fault propagation path explicit.

[0087] Based on this, a weighted directed graph is constructed by combining the physical connections of facilities (such as the hard connection between water pumps and water supply pipes, and elevators and power supply systems) and historical fault logs (such as records of a certain type of fault that has often been transmitted from facility A to facility B in the past). The calculation of edge weights takes into account both the physical connection strength and the historical transmission frequency. The purpose is to quantify the possibility of a fault being transmitted from one facility to another. The closer the physical connection between facilities, the higher the basic probability of fault transmission. The risk of actual transmission will also increase for facility pairs that have frequently experienced transmission in the past. This dual consideration allows the directed graph to reflect the objective connection characteristics between facilities and to combine actual fault experience, making the model more in line with the real scenario of property operation.

[0088] The in-degree value essentially measures the total probability that a facility is affected by the failure of other facilities. The higher the in-degree value, the more easily the facility is affected by the anomalies of other facilities, or the more likely it is to become a convergence point of multiple failures, making it a weak link that needs to be focused on in the entire system.

[0089] Selecting the top 10% of nodes by in-degree value as key nodes aims to focus on the core impactors among numerous facilities, avoiding the inefficiency caused by evenly distributing resources, and ensuring that optimization measures directly target the facilities with the greatest impact on system quality. Based on the in-degree values ​​of key nodes, a facility parameter weighting adjustment scheme is generated, increasing the weight of their corresponding facility parameters. This is because the operational status of these key nodes has a more significant impact on the overall property service quality. Increasing their weight allows subsequent quality scoring curves to more accurately reflect anomalies in these nodes, preventing key issues from being masked by insufficient weight. Simultaneously, a sampling frequency optimization scheme is generated, increasing the sampling frequency for facilities associated with key nodes. This is because even minor anomalies in key nodes can trigger chain reactions; more frequent sampling can detect parameter fluctuations earlier, buying time for fault warnings and interventions. Adjusting the parameter sampling frequency from once per hour to once every 15 minutes allows for more timely detection of abnormal trends.

[0090] like Figure 5 As shown, the system optimization decision that generates the facility parameter weight coefficient adjustment scheme and the sampling frequency optimization scheme specifically includes:

[0091] S410 parses the basic data packet for fault analysis, establishes a set of facility nodes and a set of fault-related edges, and constructs a weighted directed graph based on the physical connection relationship of facilities and historical fault logs.

[0092] S420, Calculate the in-degree value of each node:

[0093] ;

[0094] in, For facilities The weighted in-degree value, For possible to Facility nodes that transmit faults For the fault from Transmitted to The right of the border;

[0095] The top 10% of nodes by in-degree value are selected as key nodes, and a facility parameter weight coefficient adjustment scheme is generated based on the in-degree value of the key nodes. The weight of the corresponding facility parameters of the key nodes is increased based on the in-degree value.

[0096] S430 generates a sampling frequency optimization scheme, which increases the sampling frequency for facilities associated with key nodes based on the adjusted facility parameter weights.

[0097] The construction of the weighted directed graph specifically involves:

[0098] ;

[0099] in, As edge weight, it indicates that the fault is caused by the facility. Transmitted to facility The probability, These are the weighting coefficients for facility parameters. The physical connection strength between facilities is preset based on the connection method. This refers to the frequency of historical fault propagation.

[0100] S500 updates the weights based on the facility parameter weight coefficient adjustment scheme, readjusts the quality score curve, and adjusts the sampling strategy based on the sampling frequency optimization scheme.

[0101] Figure 6 The structural block diagram of the smart property project full-process monitoring and quality optimization system provided in the embodiments of the present invention is as follows: Figure 6 As shown, the system includes:

[0102] The standardized data stream generation module 100 is used to simultaneously capture the set of facility operation parameters of facilities within the property's jurisdiction, as well as the set of complaint work orders submitted by owners through mobile terminals, and to standardize the set of facility operation parameters and the set of complaint work orders to form a standardized data stream.

[0103] The quality scoring curve analysis module 200 is used to perform fusion analysis based on the standardized data stream and generate a quality scoring curve reflecting the quality of property services according to a preset period.

[0104] The abnormal period identification module 300 is used to set a sudden drop threshold, compare the slope of each point of the quality score curve with the sudden drop threshold, identify abnormal periods, extract the facility operation parameter set and complaint work order set corresponding to the abnormal period from the standardized data stream, form an abnormal subset of facility operation parameters and a feature set of complaint work orders respectively, and package them into a fault analysis basic data package.

[0105] The optimization decision generation module 400 is used to construct a fault propagation directed graph based on the fault analysis basic data package, calculate the in-degree value of all nodes in the fault propagation directed graph, identify key nodes based on the in-degree value, and generate a system optimization decision including facility parameter weight coefficient adjustment scheme and sampling frequency optimization scheme based on the in-degree value weight of the key nodes.

[0106] The strategy adjustment module 500 is used to update the weights based on the facility parameter weight coefficient adjustment scheme, readjust the quality score curve, and adjust the sampling strategy based on the sampling frequency optimization scheme.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for full-process monitoring and quality optimization of smart property projects, characterized in that: The method includes: Simultaneously capture the set of facility operation parameters of facilities within the property's jurisdiction, as well as the set of complaint work orders submitted by owners through mobile devices, and standardize the set of facility operation parameters and the set of complaint work orders to form a standardized data stream; Based on the standardized data stream, a fusion analysis is performed to generate a quality score curve reflecting the quality of property services according to a preset cycle. A sudden drop threshold is set, and the slope of each point of the quality score curve is compared with the sudden drop threshold to identify abnormal periods. The set of facility operation parameters and the set of complaint work orders corresponding to the abnormal period are extracted from the standardized data stream to form an abnormal subset of facility operation parameters and a feature set of complaint work orders, respectively. These are then packaged into a basic data package for fault analysis. Based on the aforementioned fault analysis basic data package, a fault propagation directed graph is constructed, the in-degree value of all nodes in the fault propagation directed graph is calculated, key nodes are identified based on the in-degree value, and a system optimization decision including facility parameter weight coefficient adjustment scheme and sampling frequency optimization scheme is generated based on the in-degree value weight of the key nodes. The weights are updated based on the facility parameter weight coefficient adjustment scheme, the quality score curve is readjusted, and the sampling strategy is adjusted based on the sampling frequency optimization scheme.

2. The method according to claim 1, characterized in that, The formation of a standardized data stream specifically includes: The system collects facility operation parameters in real time through IoT sensors, including: elevator operation parameters, abnormal door opening and closing frequency, central air conditioning operation parameters, water pump operation parameters, and access control operation parameters. The system receives a set of complaint tickets, which includes: a unique facility ID, a complaint timestamp, a problem description, and a fault type tag. The complaint work order set is structured and parsed, facility numbers are extracted and matched, and the problem description text is classified into predefined fault types; The processed set of facility operation parameters and the set of complaint work orders are aligned by timestamp and merged into a standardized data stream with time series labels.

3. The method according to claim 2, characterized in that, The generation of a quality score curve reflecting the quality of property services according to a preset cycle specifically includes: Standardized data streams are divided into preset cycles, with each cycle containing a corresponding number of facility operation parameter records and associated work orders; Calculate the facility health score and user satisfaction score within a preset period to generate a comprehensive quality score; Connecting the comprehensive quality score points of 24 consecutive periods forms a quality score curve with timestamps.

4. The method according to claim 3, characterized in that, The packaging process forms the basic data package for fault analysis, specifically including: Calculate the slope of each adjacent point on the quality score curve and set a dynamic drop threshold. When the slope of any point is greater than the dynamic drop threshold, mark the time period adjacent to that point as an abnormal period. Extract all facility operation parameters during the abnormal period, and remove normal facility operation data to form an abnormal subset of facility operation parameters; Extract complaint work orders from abnormal periods, and extract the distribution of fault types and the characteristics of high-incidence facility areas to form a complaint work order feature set; The abnormal subset of facility operation parameters and the feature set of complaint work orders are associated with each other through timestamps and compressed and packaged into a basic data package for fault analysis containing abnormal time period identifiers.

5. The method according to claim 4, characterized in that, The system optimization decision, which generates a scheme for adjusting facility parameter weight coefficients and a scheme for optimizing sampling frequency, specifically includes: Parse the basic data packet for fault analysis, establish a set of facility nodes and a set of fault-related edges, and construct a weighted directed graph based on the physical connection relationship of facilities and historical fault logs; Calculate the in-degree value of each node, select the top 10% of nodes by in-degree value as key nodes, and generate a facility parameter weight coefficient adjustment plan based on the in-degree value of the key nodes, thereby increasing the weight of the corresponding facility parameters of the key nodes based on the in-degree value. A sampling frequency optimization scheme is generated, and the sampling frequency is increased based on the adjusted facility parameter weights for facilities associated with key nodes.

6. The method according to claim 5, characterized in that, The construction of the weighted directed graph specifically involves: ； in, As edge weight, it indicates that the fault is caused by the facility. Transmitted to facility The probability, These are the weighting coefficients for facility parameters. The physical connection strength between facilities is preset based on the connection method. This refers to the frequency of historical fault propagation.

7. A smart property project end-to-end monitoring and quality optimization system, characterized in that: The system includes: The standardized data stream generation module is used to simultaneously capture the set of facility operation parameters of facilities within the property's jurisdiction, as well as the set of complaint work orders submitted by owners through mobile terminals, and to standardize the set of facility operation parameters and the set of complaint work orders to form a standardized data stream. The quality scoring curve analysis module is used to perform fusion analysis based on the standardized data stream and generate a quality scoring curve reflecting the quality of property services according to a preset period. The abnormal period identification module is used to set a sudden drop threshold, compare the slope of each point of the quality score curve with the sudden drop threshold, identify abnormal periods, extract the facility operation parameter set and complaint work order set corresponding to the abnormal period from the standardized data stream, form an abnormal subset of facility operation parameters and a feature set of complaint work orders respectively, and package them into a basic data package for fault analysis. The optimization decision generation module is used to construct a fault propagation directed graph based on the fault analysis basic data package, calculate the in-degree value of all nodes in the fault propagation directed graph, identify key nodes based on the in-degree value, and generate a system optimization decision including facility parameter weight coefficient adjustment scheme and sampling frequency optimization scheme based on the in-degree value weight of the key nodes. The strategy adjustment module is used to update the weights based on the facility parameter weight coefficient adjustment scheme, readjust the quality score curve, and adjust the sampling strategy based on the sampling frequency optimization scheme.

Images