An intelligent property management system and method

Abstract

The application relates to the technical field of property management, and discloses a property intelligent management system and method, which comprises a proprietor interaction interface, a property management interface and a data processing center; the data processing center collects data from a plurality of participating nodes in the property management range, and provides real-time property states and management decision support for proprietors and property management personnel. The system adopts a micro-service architecture, contains a plurality of service groups such as data collection, processing, analysis and decision support, and integrates a machine learning model to perform deep analysis and prediction. A communication interface layer provides a GraphQL interface and a WebSocket real-time message push service, and efficient interaction is realized. A data storage layer adopts Redis, PostgreSQL and Solr databases, and ensures data real-time performance. The system also has a cloud storage architecture, and ensures data safety and disaster recovery. A front adapter is used to establish communication with various property systems, and comprehensive data collection and integration are realized. The application improves property management efficiency, and realizes the intellectualization and refinement of property management.

Description

Technical Field

[0001] This invention relates to the field of property management technology, specifically to an intelligent property management system and method. Background Technology

[0002] With the acceleration of urbanization and the improvement of people's living standards, property management plays an increasingly important role in modern society. Current property management methods often rely on manual patrols, paper records, and verbal communication. These methods are not only inefficient but also prone to errors, failing to meet the needs of modern property management. In recent years, the rapid development of information technology, especially the rise of technologies such as the Internet, big data, cloud computing, and machine learning, has made intelligent property management possible.

[0003] Current property management faces numerous challenges. Firstly, regarding data collection, property managers need to manually record information such as equipment operating status, environmental parameters, and personnel activities. This is not only time-consuming and labor-intensive, but also makes it difficult to guarantee data accuracy and timeliness. For example, data such as elevator operating status, water and electricity meter readings, and temperature and humidity in public areas are often delayed and inaccurate if collected manually. Secondly, in terms of data processing and analysis, traditional property management methods lack efficient data processing tools and methods. The collected data is often scattered and inconsistently formatted, making effective integration and analysis difficult. This prevents property managers from accurately and promptly grasping the overall condition of the property and making it difficult to make scientific management decisions. For instance, predicting equipment failures and assessing maintenance needs often relies solely on experience without data analysis support, significantly reducing management efficiency and accuracy.

[0004] In terms of resident services, the current property management system also presents many inconveniences. Residents need to personally go to the property management office to inquire about property fees, report equipment repairs, etc., which not only wastes their time but also increases the workload of the property management office. At the same time, due to poor communication, residents are often not very satisfied with property management.

[0005] With the widespread application of IoT technology, various devices, sensors, and smart terminals within the property management scope generate a massive amount of data. This data contains rich information, such as equipment operating status, personnel activity patterns, and environmental change trends, which is of great significance for improving property management. However, how to efficiently collect, process, and analyze this data, and transform it into valuable management decisions, is a problem that traditional property management methods struggle to solve. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent property management system and method to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent property management system, comprising an owner interaction interface, a property management interface, and a data processing center for processing property data. The property data originates from multiple participating nodes within the property management scope, including residential buildings, commercial buildings, public facilities, and landscaped gardens. The data processing center provides data support for the owner interaction interface and the property management interface, enabling owners and property management personnel to monitor the property status in real time and make corresponding management decisions.

[0008] The data processing center comprises a communication interface layer, a service processing layer, a data access layer, and a data storage layer. The communication interface layer includes a gateway module, which provides connection services to the owner's interface and property management interface, establishing a data transmission channel. The service processing layer adopts a microservice architecture, providing the data processing center with data acquisition, processing, analysis, decision support, business logic processing, and basic service functions. The gateway module uses a dynamic routing mechanism to locate specific service instances within the service processing layer. The data storage layer is responsible for data storage, including real-time property status caching, persistent historical data storage, and index storage. The data access layer includes a connection pool management module, which establishes a connection channel between the service processing layer and the data storage layer, enabling secure and stable data read and write operations.

[0009] The communication interface layer provides GraphQL interface and WebSocket real-time message push service for the owner interaction interface and property management interface, which are used for the interaction and command issuance of owners and property management personnel.

[0010] Preferably, the service processing layer includes a data acquisition service group, a data processing service group, a status monitoring service group, a decision support service group, and an infrastructure service group. The data acquisition service group is responsible for designing communication protocols with various property systems and building front-end adapters for receiving property data. The data processing service group is used to clean, integrate, transform, and standardize the data received by the data acquisition service group. The status monitoring service group is used to monitor changes in the property status in real time. The decision support service group provides management decision suggestions to property managers based on the property status and owner needs. The infrastructure service group is responsible for maintaining the operational stability of the entire service processing layer and the message transmission between services.

[0011] Preferably, the service processing layer further includes a machine learning service group, which integrates various machine learning models for in-depth analysis and prediction of property data. The machine learning service group includes a data preprocessing module, a model training module, a model inference module, and a model evaluation module. The data preprocessing module is responsible for extracting features from the raw property data and selecting input data associated with the machine learning models. The model training module trains various machine learning models based on the preprocessed data, including classification models, regression models, clustering models, and prediction models. The model inference module applies the trained models to perform real-time prediction and analysis of new property data. The model evaluation module periodically evaluates the model performance and optimizes or retrains the model based on the evaluation results.

[0012] Preferably, the machine learning service group is further integrated with the status monitoring service group and the decision support service group; in the status monitoring service group, the machine learning model is used to identify abnormal states, including identifying abnormal operating patterns of equipment through clustering models and predicting the occurrence time of equipment failures through prediction models; in the decision support service group, the machine learning model provides decision suggestions based on historical data and current status, including determining the priority of maintenance needs through classification models and predicting maintenance costs through regression models.

[0013] Preferably, the data acquisition service group includes an equipment data acquisition module, an environmental data acquisition module, a personnel activity data acquisition module, and an event data acquisition module; the equipment data acquisition module is responsible for collecting operational data of public facilities, including elevators and water and electricity meters; the environmental data acquisition module collects environmental parameters, including temperature, humidity, and air quality; the personnel activity data acquisition module records data on personnel entering and exiting and parking activities; and the event data acquisition module collects information on various events occurring within the property area.

[0014] The data processing service group includes a data cleaning module, a data integration module, a data transformation module, and a data standardization module. The data cleaning module is responsible for removing invalid and erroneous data. The data integration module integrates data from different sources. The data transformation module converts the data into a unified format. The data standardization module is used to process continuous numerical data using the Z-score standardization method, subtracting the mean from each numerical data point and dividing by its standard deviation, so that the processed data conforms to a standard normal distribution.

[0015] Preferably, the status monitoring service group includes an equipment status monitoring module, an environmental status monitoring module, a security monitoring module, and an emergency response module; the equipment status monitoring module monitors the operating status of public facilities in real time; the environmental status monitoring module monitors changes in environmental parameters; the security monitoring module is responsible for monitoring the security situation within the property area, including video surveillance and intrusion detection; and the emergency response module automatically triggers an emergency plan when an abnormal situation is detected.

[0016] Preferably, the data storage layer uses Redis as the real-time state cache database, PostgreSQL as the historical record persistence database, and Solr as the index storage database.

[0017] Preferably, the data storage layer is designed with a cloud storage architecture, which includes multiple data nodes and redundant nodes. The data nodes are responsible for data storage and access, while the redundant nodes are responsible for data backup and disaster recovery.

[0018] Preferably, the data acquisition service group includes front-end adapters for various property systems. The front-end adapters are used to establish communication mechanisms with the specific corresponding property systems, including the formulation of communication protocols, conversion of data formats, breakpoint resume, and status monitoring.

[0019] Preferably, a property intelligent management method is applied to the aforementioned property intelligent management system, the method comprising:

[0020] S1: Collect property data from multiple participating nodes within the property management scope through the data collection service group, including data on residential buildings, commercial buildings, public facilities, and landscaped areas;

[0021] S2: The data processing service team cleans, integrates, transforms, and standardizes the collected data;

[0022] S3: The status monitoring service group monitors the processed property data in real time and detects changes in the property status.

[0023] S4: Store the real-time monitored property status and processed historical data in the data storage layer;

[0024] S5: The data storage layer provides data read and write services to the service processing layer through the data access layer, and provides data support to the owner interaction interface and property management interface through the communication interface layer.

[0025] S6: Owners and property management personnel can view the property status in real time through the owner interaction interface and the property management interface, and make corresponding management decisions based on the provided data.

[0026] Compared with the prior art, the beneficial effects of the present invention are:

[0027] The system replaces current manual patrols and paper records with automated data collection and processing, significantly improving data accuracy and timeliness. Property managers can monitor property status in real time, including equipment operating status, environmental parameters, and personnel activities, enabling them to make faster and more scientific management decisions. The introduction of machine learning models allows the system to perform in-depth analysis and prediction of property data, such as equipment failure prediction and maintenance need assessment, further enhancing the precision of management.

[0028] The user interface design allows residents to easily check property fees and report equipment repairs online without having to visit the property management office, saving time and improving convenience. Real-time push notification services, such as GraphQL and WebSocket, ensure residents receive the latest notifications and instructions from property management promptly, enhancing the transparency and efficiency of communication.

[0029] The system adopts a microservice architecture, modularizing and service-oriented functions such as data acquisition, processing, analysis, and decision support, facilitating system expansion and maintenance. The data storage layer combines Redis real-time status caching, PostgreSQL historical record persistent storage, and Solr index storage, meeting efficient storage and retrieval needs for different data types and access requirements. The security monitoring module in the status monitoring service group monitors the security status within the property area in real time through video surveillance and intrusion detection, effectively preventing security incidents. The emergency response module enables the system to automatically trigger emergency plans when abnormal situations are detected, responding promptly to and handling emergencies, ensuring the safety of the property and its residents.

[0030] Automated and intelligent management methods reduce manual intervention and the use of paper documents, thereby lowering labor and material costs in property management. The application of cloud storage architecture makes data storage and backup more efficient and economical, further reducing data storage and management costs. Attached Figure Description

[0031] Figure 1 This is a structural diagram of an intelligent property management system according to the present invention;

[0032] Figure 2 A schematic diagram of the design for a machine learning service group;

[0033] Figure 3 This is a flowchart illustrating the steps of an intelligent property management method according to the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Please see Figure 1-3 This invention provides a technical solution: an intelligent property management system, which includes a homeowner interaction interface, a property management interface, and a data processing center. The homeowner interaction interface and the property management interface are used by homeowners and property management personnel respectively to view property status in real time, submit service requests, or perform management operations. The data processing center is the core of the system, responsible for collecting, processing, analyzing, and storing property data from multiple participating nodes within the property management area (such as residential buildings, commercial buildings, public facilities, and landscaping).

[0036] The data processing center consists of a communication interface layer, a service processing layer, a data access layer, and a data storage layer. The communication interface layer provides connection services for the owner interaction interface and the property management interface through a gateway module, and supports GraphQL interface for data query and WebSocket real-time message push service to enable real-time interaction and command issuance between owners and property management personnel.

[0037] The service processing layer adopts a microservice architecture to ensure high availability and scalability of the system. Specific service groups include:

[0038] Data Acquisition Service Group: Designs communication protocols for various property management systems (such as elevator monitoring systems, water and electricity meter reading systems, etc.) and builds front-end adapters to receive property data from these systems. For example, it communicates with the elevator monitoring system via the MQTT protocol to obtain real-time elevator operating status data.

[0039] Data Processing Service Group: This group cleans, integrates, transforms, and standardizes the collected data. For example, it uses data cleaning algorithms to remove invalid or erroneous data, converts the data into a unified JSON format, and employs Z-score standardization to process numerical data, ensuring consistency and comparability.

[0040] Status Monitoring Service Group: Monitors changes in the property's status in real time, including equipment operating status, environmental parameters (such as temperature and humidity), and personnel activity. For example, it monitors the security situation within the property in real time through surveillance cameras and intrusion detection systems.

[0041] Decision Support Services Group: Based on the property's condition and residents' needs, this group provides management decision-making advice to property managers. For example, it analyzes historical data using machine learning algorithms to predict when equipment malfunctions will occur, or prioritizes repair requests based on residents' repair reports.

[0042] Infrastructure Services Group: Responsible for maintaining the operational stability of the entire service processing layer and message passing between services. For example, using message queues to implement asynchronous communication between services ensures high system throughput and low latency.

[0043] The data access layer includes a connection pool management module, which establishes a secure and stable data read / write channel between the service processing layer and the data storage layer. The data storage layer is responsible for data storage and management.

[0044] The present invention will be further described below with reference to Examples 1 to 3:

[0045] Example 1:

[0046] In the service processing layer, a machine learning service group was further added to enhance the ability to deeply analyze and predict property data. This machine learning service group integrates multiple machine learning models and is subdivided into data preprocessing, model training, model inference, and model evaluation modules. The specific implementation methods of each module are as follows:

[0047] Data preprocessing module: This module first extracts features from the raw property data, selecting input features that are relevant to the machine learning model based on the characteristics of the property data. For example, it extracts key parameters such as operating time, temperature, and pressure from equipment operation logs as features.

[0048] Model training module: Based on the preprocessed data, this module trains various machine learning models, including but not limited to classification models (such as random forest, support vector machine), regression models (such as linear regression, neural network), clustering models (such as K-means, DBSCAN) and prediction models (such as time series analysis models).

[0049] Taking equipment failure prediction as an example, a prediction model is trained using historical failure data and normal operation data. The model can learn the characteristic change patterns before equipment failure.

[0050] Model Inference Module: This module applies a trained model to perform real-time predictions and analysis of new property data. For example, by inputting real-time collected equipment operation data into a fault prediction model, the model can output the probability of equipment failure within a future period.

[0051] Clustering models can be used to perform cluster analysis on the operating status of equipment, identify abnormal operating patterns, and issue timely warnings.

[0052] Model evaluation module: Regularly evaluates model performance, using metrics such as cross-validation, accuracy, recall, and F1 score to measure the model's predictive effectiveness.

[0053] Based on the evaluation results, the model can be optimized, such as by adjusting model parameters, selecting a more suitable algorithm, or by retraining the model to maintain its predictive accuracy when the model performance deteriorates.

[0054] The Machine Learning Service Group is tightly integrated with the Status Monitoring Service Group and the Decision Support Service Group, as specifically implemented below:

[0055] In the status monitoring service group:

[0056] Clustering models are used to analyze the operating status of equipment, identifying normal and abnormal patterns. For example, the DBSCAN clustering algorithm can identify abnormal stop patterns in elevator operation, allowing maintenance personnel to be notified promptly for inspection. Predictive models are applied to predict the occurrence time of equipment failures, enabling advance planning of maintenance schedules and minimizing the impact of unexpected failures on residents' lives.

[0057] In the decision support service group:

[0058] Prioritize maintenance requests using classification models. For example, based on factors such as the severity and scope of the reported repairs, a random forest classification model can be used to categorize maintenance requests into three levels: urgent, general, and deferred, allowing for the rational allocation of maintenance resources. Use regression models to predict maintenance costs. By analyzing historical maintenance records for data such as maintenance expenses and material consumption, a regression model can be trained to predict the costs of future maintenance tasks, providing a basis for budget management.

[0059] Example 2:

[0060] The data acquisition service group includes:

[0061] Equipment data acquisition module: By installing sensors or smart meters on public facilities (such as elevators, water and electricity meters), this module collects real-time operational status data of the equipment, such as the number of elevator trips, operating time, and fault codes, as well as water and electricity meter readings. The data is transmitted to a central data server via wired or wireless means to ensure its real-time performance and accuracy.

[0062] Environmental data acquisition module: Deploy environmental monitoring sensors, such as temperature and humidity sensors and air quality monitors, in key areas within the property to collect environmental parameters periodically or in real time. The collected data includes temperature, humidity, PM2.5 concentration, CO concentration, etc., used to assess indoor environmental comfort and air quality.

[0063] Personnel activity data collection module: Utilizing access control systems, parking management systems, etc., this module records personnel entry and exit records and parking activity data, including entry and exit times, personnel identities, and vehicle information. Data analysis allows for understanding personnel flow patterns and optimizing access control management and parking resource allocation.

[0064] Event Data Collection Module: Establishes an event reporting system that allows property staff or residents to report various events occurring within the property area, such as facility damage, safety hazards, and community activities, via mobile applications, web pages, etc. Event data includes information such as event type, time of occurrence, location, and description, providing a basis for property management decision-making.

[0065] The data processing service group includes:

[0066] Data cleaning module: This module inspects the collected raw data, removing invalid data (such as null values ​​and duplicate values) and erroneous data (such as values ​​outside the reasonable range). It applies data validation rules to ensure the integrity and accuracy of the data.

[0067] Data integration module: Integrates data from different sources (such as equipment, environment, personnel activities, and events) to establish a unified data warehouse. Through data association technology, related data items are linked to form a complete data view.

[0068] Data conversion module: Converts data in different formats into a unified format to facilitate subsequent data processing and analysis. For example, it unifies time data into the "YYYY-MM-DD HH:MM:SS" format and numerical data into floating-point or integer types.

[0069] Data Standardization Module: This module employs Z-score standardization to process continuous numerical data. For each numerical data point, its mean and standard deviation are calculated. The mean is then subtracted from the data, and the result is divided by the standard deviation. Standardized data conforms to a standard normal distribution, which helps improve the accuracy and reliability of subsequent data analysis.

[0070] The status monitoring service group includes:

[0071] Equipment status monitoring module: Monitors the operating status of public facilities (such as elevators, water pumps, and lighting systems) in real time, and predicts equipment failure risks through data analysis. When an abnormal condition occurs, an alarm mechanism is immediately triggered to notify maintenance personnel for handling.

[0072] Environmental status monitoring module: Monitors changes in environmental parameters (such as temperature, humidity, and air quality), and triggers an early warning mechanism when the parameters exceed preset thresholds. For example, when the indoor temperature exceeds 30°C, the air conditioning system is automatically turned on to lower the temperature; when the PM2.5 concentration exceeds the standard, the air purification equipment is activated.

[0073] Security monitoring module: Utilizing video surveillance cameras and intrusion detection systems, it monitors the security situation within the property area in real time. When abnormal behavior is detected (such as unauthorized entry or theft of items), a security alarm is immediately triggered, and security personnel are notified to handle the situation.

[0074] Emergency Response Module: Based on the preset emergency plan, the emergency response process is automatically triggered when an abnormal situation is detected (such as fire, flood, equipment failure, etc.). Emergency response includes activating emergency broadcasts, issuing evacuation instructions, and deploying emergency resources to ensure the safety of personnel and the protection of property.

[0075] The data acquisition service group, data processing service group, and status monitoring service group together constitute the core of the property data management system, providing comprehensive, accurate, and real-time data support for property management and improving the efficiency and level of property management.

[0076] Example 3:

[0077] The data storage layer uses Redis as the real-time state cache database:

[0078] Leveraging Redis's key-value storage capabilities, this system stores real-time status data that requires rapid access within the property management system, such as equipment operating status and environmental parameters. It uses a client library provided by Redis (such as Jedis) to interact with the Redis server.

[0079] In practice, the system is configured with a Redis server cluster to improve data access speed and availability. Reasonable expiration times are set to ensure the timeliness of cached data.

[0080] PostgreSQL is used as the historical data persistence database:

[0081] Leveraging the relational database features of PostgreSQL, historical data from the property management system can be stored, such as equipment operation records, event logs, and personnel activity records. Database operations can be performed using PostgreSQL's official client libraries (such as JDBC) or ORM frameworks (such as Hibernate).

[0082] In practice, a reasonable database table structure is designed, and indexes are created to optimize query performance. PostgreSQL's backup and recovery mechanisms are utilized to ensure data reliability and security.

[0083] Solr is used as the index storage database:

[0084] Leveraging Solr's full-text search capabilities, text data such as documents and logs in the property management system are indexed and stored for rapid retrieval. Solr's APIs (such as SolrJ for Java) are used for index creation, querying, and management.

[0085] In practice, the system configures a Solr cluster, defines index fields and query rules. The accuracy of search results is ensured by periodically updating the index.

[0086] The data storage layer utilizes cloud storage services provided by cloud service providers, constructing a cloud storage architecture comprising multiple data nodes and redundant nodes. Data nodes are responsible for data storage and access, distributing access pressure through load balancing technology. Redundant nodes are responsible for data backup and disaster recovery, employing distributed file systems (such as Hadoop HDFS) or replication mechanisms provided by cloud storage services to ensure data reliability and availability.

[0087] Data Acquisition Service Group: Develops front-end adapters for various property management systems (such as elevator monitoring systems, access control systems, environmental monitoring systems, etc.) to implement communication mechanisms with specific property management systems. Based on the communication protocols and data formats of the property management systems, adapters are developed using appropriate programming languages ​​(such as Java, Python) and communication libraries (such as Netty, Twisted).

[0088] The specific implementation of the front adapter includes:

[0089] Communication protocol development: Negotiate with the property system supplier to determine the protocol and format for data exchange.

[0090] Data format conversion: Implement data format conversion in the adapter to convert the raw data of the property system into a format that the system can recognize.

[0091] Resume interrupted data transmission: Implements the function of resuming interrupted data transmission during the data transmission process to ensure the integrity and continuity of the data.

[0092] Status monitoring: The adapter periodically reports the communication status and data transmission progress to the data acquisition service group in order to promptly detect and handle communication failures.

[0093] This invention also includes a property intelligent management method, which is applied to the aforementioned property intelligent management system, and is implemented as follows:

[0094] S1: Data Acquisition Service Group collects property data.

[0095] The data acquisition service team collects property data in real time or periodically by deploying various sensors, smart devices, and front-end adapters within the property management scope, including residential buildings, commercial buildings, public facilities, and landscaped areas.

[0096] For example, in residential buildings, smart meters and water meters collect data on water and electricity consumption; in commercial buildings, access control systems collect data on people entering and exiting; in public facilities, environmental monitoring sensors collect data on temperature, humidity, air quality, and other data; and in gardens and landscapes, cameras collect security monitoring videos of the park.

[0097] Communication protocols such as MQTT and HTTP are used to ensure efficient and stable data transmission. The front-end adapter is responsible for interfacing with different property management systems, enabling data format conversion and communication protocol adaptation.

[0098] S2: Data processing service group processes data.

[0099] After receiving the collected raw data, the data processing service team first performs data cleaning to remove invalid, erroneous, or duplicate data. Next, the data is integrated into a structured format for easier subsequent processing. Then, the data is converted into specific formats, such as JSON or XML, as needed. Finally, continuous numerical data is standardized, for example using Z-score standardization, to ensure data comparability and analytical accuracy.

[0100] S3: Status monitoring service group monitors property status.

[0101] The property status monitoring service team detects changes in property status by monitoring processed property data in real time. For example, by monitoring elevator operation data, it can promptly detect elevator malfunctions or abnormal conditions; by monitoring environmental data, it can promptly detect excessive air quality or abnormal temperature and humidity; and by monitoring security data, it can promptly detect intrusions or abnormal situations. Using technologies such as threshold setting, trend analysis, and pattern recognition, it achieves intelligent monitoring and early warning of property status.

[0102] S4: Data storage layer stores data.

[0103] Real-time monitored property status and processed historical data are stored in the data storage layer. Redis is used as the real-time status cache database for rapid response to query requests; PostgreSQL is used as the historical record persistence database to ensure long-term data preservation and traceability; and Solr is used as the index storage database to enable fast retrieval of text data. Distributed storage and redundant backup technologies are employed to ensure high data availability and security. A reasonable database table structure and indexing strategy are designed to optimize data query performance.

[0104] S5: The data storage layer provides data read and write services.

[0105] The data storage layer provides data read and write services to the service processing layer through the data access layer. The service processing layer can access data in the storage layer via API interfaces or database connection pools. Simultaneously, the data storage layer also provides data support to the owner's interaction interface and property management interface through the communication interface layer. RESTful APIs, GraphQL, and other interface technologies are used to enable flexible data access and querying. SSL / TLS encryption technologies are used to ensure the security of data transmission.

[0106] S6: Owners and property management personnel review the property status and make decisions.

[0107] Owners and property management personnel can view the property status in real time through the owner interaction interface and the property management interface. The owner interaction interface can be a mobile application, a webpage, or a smart terminal device, providing convenient property information inquiry and repair services. The property management interface is a more professional platform, providing comprehensive property management functions and data analysis tools.

[0108] We employ responsive design and cross-platform development technologies to ensure a user-friendly and compatible interface. We utilize data visualization techniques to visually represent complex property data in charts, reports, and other formats, helping owners and property managers quickly understand the property's status and make appropriate management decisions. For example, we adjust irrigation plans for the landscaping based on environmental data; schedule maintenance plans based on elevator operation data; and optimize access control management based on personnel entry and exit data.

[0109] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0110] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A property intelligent management system, characterized in that: It includes an owner interaction interface, a property management interface, and a data processing center for processing property data. The property data comes from multiple participating nodes within the property management scope, including residential buildings, commercial buildings, public facilities, and landscape. The data processing center provides data support for the owner interaction interface and the property management interface so that owners and property management personnel can keep abreast of the property status in real time and make corresponding management decisions. The data processing center includes a communication interface layer, a service processing layer, a data access layer, and a data storage layer; the communication interface layer includes a gateway module, which provides connection services to the owner interaction interface and the property management interface, and establishes a data transmission channel; The service processing layer adopts a microservice architecture, providing the data processing center with data collection, processing, analysis, decision support, business logic processing, and basic service functions. The gateway module locates the specific service instance in the service processing layer through a dynamic routing mechanism. The data storage layer is responsible for data storage, including real-time status caching of the property, persistent storage of historical records, and index storage. The data access layer includes a connection pool management module, which is used to establish a connection channel between the service processing layer and the data storage layer, enabling secure and stable data read and write operations between the two. The communication interface layer provides GraphQL interface and WebSocket real-time message push service for the owner interaction interface and property management interface, which are used for the interaction and command issuance of owners and property management personnel.

2. The intelligent property management system according to claim 1, characterized in that: The service processing layer includes a data acquisition service group, a data processing service group, a status monitoring service group, a decision support service group, and an infrastructure service group. The data acquisition service team is responsible for designing communication protocols with various property management systems and building front-end adapters for receiving property data; The data processing service group is responsible for cleaning, integrating, transforming, and standardizing the data received by the data acquisition service group; the status monitoring service group is responsible for monitoring changes in the property's status in real time; the decision support service group provides management decision-making suggestions to property managers based on the property's status and the needs of the owners; and the infrastructure service group is responsible for maintaining the operational stability of the entire service processing layer and the communication between services.

3. The intelligent property management system according to claim 2, characterized in that: The service processing layer further includes a machine learning service group, which integrates multiple machine learning models for in-depth analysis and prediction of property data. The machine learning service group includes a data preprocessing module, a model training module, a model inference module, and a model evaluation module. The data preprocessing module is responsible for extracting features from the raw property data and selecting input data associated with the machine learning model. The model training module trains various machine learning models based on preprocessed data, including classification models, regression models, clustering models, and prediction models; the model inference module applies the trained models to perform real-time prediction and analysis of new property data; and the model evaluation module periodically evaluates model performance and optimizes or retrains the models based on the evaluation results.

4. The intelligent property management system according to claim 3, characterized in that: The machine learning service group is further integrated with the status monitoring service group and the decision support service group. In the status monitoring service group, machine learning models are used to identify abnormal states, including identifying abnormal operating patterns of equipment through clustering models and predicting the occurrence time of equipment failures through predictive models. In the decision support service group, machine learning models provide decision recommendations based on historical data and current status, including determining the priority of maintenance needs through classification models and predicting maintenance costs through regression models.

5. A property intelligent management system according to claim 2, characterized in that: The data acquisition service group includes an equipment data acquisition module, an environmental data acquisition module, a personnel activity data acquisition module, and an event data acquisition module. The equipment data acquisition module is responsible for collecting operational data of public facilities, including elevators and water and electricity meters. The environmental data acquisition module collects environmental parameters, including temperature, humidity, and air quality. The personnel activity data acquisition module records data on personnel entry and exit and parking activities. The event data acquisition module collects information on various events occurring within the property area. The data processing service group includes a data cleaning module, a data integration module, a data conversion module, and a data standardization module; The data cleaning module is responsible for removing invalid and erroneous data; the data integration module integrates data from different sources. The data transformation module converts the data into a uniform format; the data standardization module is used to process continuous numerical data using the Z-score standardization method, subtracting the mean from each numerical data point and dividing by its standard deviation, so that the processed data conforms to a standard normal distribution.

6. The intelligent property management system according to claim 2, characterized in that: The status monitoring service group includes an equipment status monitoring module, an environmental status monitoring module, a safety monitoring module, and an emergency response module; the equipment status monitoring module monitors the operational status of public facilities in real time; The environmental status monitoring module monitors changes in environmental parameters; the security monitoring module is responsible for monitoring the security situation within the property area, including video surveillance and intrusion detection; and the emergency response module automatically triggers emergency plans when abnormal situations are detected.

7. The intelligent property management system according to claim 1, characterized in that: The data storage layer uses Redis as the real-time state cache database, PostgreSQL as the historical record persistence database, and Solr as the index storage database.

8. The intelligent property management system according to claim 7, characterized in that: The data storage layer is designed with a cloud storage architecture, which includes multiple data nodes and redundant nodes. The data nodes are responsible for data storage and access, while the redundant nodes are responsible for data backup and disaster recovery.

9. A property intelligent management system according to claim 5, characterized in that: The data acquisition service group includes front-end adapters for various property systems. The front-end adapters are used to establish communication mechanisms with the specific property systems, including the formulation of communication protocols, conversion of data formats, breakpoint resume, and status monitoring.

10. A method for intelligent property management, characterized in that, Applied to the property intelligent management system as described in any one of claims 1 to 9, the method comprises: S1: Collect property data from multiple participating nodes within the property management scope through the data collection service group, including data on residential buildings, commercial buildings, public facilities, and landscaped areas; S2: The data processing service team cleans, integrates, transforms, and standardizes the collected data; S3: The status monitoring service group monitors the processed property data in real time and detects changes in the property status. S4: Store the real-time monitored property status and processed historical data in the data storage layer; S5: The data storage layer provides data read and write services to the service processing layer through the data access layer, and provides data support to the owner interaction interface and property management interface through the communication interface layer; S6: Owners and property management personnel can view the property status in real time through the owner interaction interface and the property management interface, and make corresponding management decisions based on the provided data.

Images