Intelligent property management system based on artificial intelligence

Abstract

The invention discloses an intelligent property management system based on artificial intelligence, and relates to the technical field of intelligent property, and the system comprises a data management center which is in communication connection with a data collection and transmission module, a fault recognition and diagnosis module, a knowledge graph auxiliary decision module, an intelligent repair customer service module and an equipment maintenance management module. And the data acquisition and transmission module is used for acquiring and preprocessing operation data of the facility equipment based on various sensors deployed on the property facility equipment. According to the invention, real-time analysis is carried out on facility equipment operation data through an artificial intelligence algorithm, potential faults can be identified in advance and early warning can be given out, fault expansion is avoided, fault causes are rapidly positioned, clear guidance is provided for maintenance personnel, maintenance time is shortened, a knowledge graph is combined with a fault identification result, a solution strategy and decision support are provided, and maintenance efficiency is improved. Maintenance personnel are helped to quickly make a reasonable maintenance plan, resource allocation is optimized, and the fault processing efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of smart property technology, and in particular to a smart property management system based on artificial intelligence. Background Art

[0002] With the continuous advancement of urbanization, a large number of people have poured into cities, the scale of cities has continued to expand, the number of various properties such as residential communities, commercial complexes, office buildings, etc. has increased sharply, and a large number of new property projects have continued to emerge, bringing huge business volume to the property management industry. Under the traditional property management model, there are many obstacles to information communication between property companies and owners, and between various departments within property companies. Moreover, when faced with such large-scale properties, the traditional property management model has become increasingly problematic with problems such as low efficiency and high management costs.

[0003] In the existing technology, property management relies on manual inspections, which makes it difficult to detect the operating status of facilities and equipment and provide fault warnings in real time and accurately, resulting in delayed responses to equipment failures and affecting the quality of property services. Therefore, how to use AI technology in combination with knowledge graphs to perform fault identification and analysis, identify potential problems in advance, and match effective decisions to achieve real-time monitoring and identification maintenance of equipment is the problem to be solved by the present invention. To this end, an intelligent property management system based on artificial intelligence is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent property management system based on artificial intelligence to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] An artificial intelligence-based smart property management system includes a data management center, which is communicatively connected to a data acquisition and transmission module, a fault identification and diagnosis module, a knowledge graph-assisted decision-making module, an intelligent repair customer service module, and an equipment maintenance and management module;

[0007] The data acquisition and transmission module collects and pre-processes the operating data of the facilities and equipment based on various sensors deployed on the property facilities and equipment, and transmits it to the data management center;

[0008] The fault identification and diagnosis module is used to analyze the collected operating data using artificial intelligence algorithms, identify potential faults of the equipment, and provide fault diagnosis results;

[0009] The knowledge graph-assisted decision-making module is used to combine knowledge graph technology and equipment fault identification results to provide fault resolution strategies and decision support;

[0010] The intelligent repair customer service module is used to provide intelligent repair and consulting services using the AI ​​customer service system. Users can report repairs or query device status through the app or voice assistant, improving user experience.

[0011] The equipment maintenance management module is used to be responsible for the daily maintenance plan formulation, maintenance task allocation and maintenance record management of the equipment, so as to achieve the standardization and systematization of equipment maintenance work.

[0012] A further improvement of the technical solution of the present invention is that the data acquisition and transmission module specifically includes:

[0013] Deploy corresponding sensors at key locations of various facilities and equipment in the property. The sensors collect operational data of the facilities and equipment, including current, voltage, temperature, pressure, and vibration, at a preset sampling frequency, and store the collected data in the form of digital signals in the sensor's built-in buffer area.

[0014] Preprocess the collected operational data of facilities and equipment, including data cleaning and normalization. Data cleaning involves using filtering algorithms to remove high-frequency noise. Missing values ​​are supplemented by using mean filling and interpolation methods based on data characteristics. Outliers are identified and corrected using statistical methods. Normalization is used to unify data of different dimensions into a specific range.

[0015] The pre-processed operation data of the facility equipment is transmitted to the data management center through wireless communication, and is classified and stored according to the equipment type and timestamp dimensions.

[0016] A further improvement of the technical solution of the present invention is that: the fault identification and diagnosis module includes a fault identification unit and a fault diagnosis unit;

[0017] The fault identification unit constructs a fault identification model based on a machine learning model, extracts fault features, and analyzes historical and real-time operating data of facility equipment to identify potential faults of the equipment;

[0018] The fault diagnosis unit is used to analyze fault characteristics through artificial intelligence algorithms based on the identified potential faults, quickly locate the cause of the fault, and quickly and accurately identify the cause of the fault.

[0019] A further improvement of the technical solution of the present invention is that the fault identification unit specifically includes:

[0020] Collect historical and real-time operating data of facilities and equipment, including multi-dimensional information such as current, voltage, temperature, pressure, and vibration collected by sensors. Data from different sources and formats are integrated to unify the data structure and format. The data is then standardized to eliminate dimensionality effects, ensuring that data with different characteristics are at the same level, forming a complete data set.

[0021] Based on the integrated data set, feature extraction is performed to obtain fault characteristics related to equipment failures, including current change amplitude, voltage fluctuation amplitude, temperature change rate, pressure fluctuation amplitude, and vibration frequency. Based on the operation and management requirements of the facility equipment, the corresponding allowable value of each fault characteristic is preset, and fault characteristics that deviate from the allowable value are marked to obtain a comprehensive feature data set.

[0022] Based on the characteristics of the facilities and equipment, a random forest-based machine learning model was selected as the basic architecture to build a fault identification model. Each fault feature was used as input, and whether it deviated from the allowable value was used as the output. The feature data set was divided into training, validation, and test sets. The selected random forest model was trained using the training set. By continuously adjusting the model parameters, the model gradually learned the patterns and regularities in the data on the training set. At the same time, the validation set was used to monitor model performance to prevent overfitting, and the test set was used to evaluate the trained model, thereby constructing the final fault identification model.

[0023] The built fault identification model is deployed to analyze real-time operation data, input the extracted fault features, and output the fault features that deviate from the allowable values. Fault features that deviate from the allowable values ​​are judged to have fault risks.

[0024] A further improvement of the technical solution of the present invention is that the fault diagnosis unit specifically includes:

[0025] Receive potential fault information output from the fault identification unit, including fault characteristics that deviate from the allowable value, and then parse the marked fault characteristics to analyze the specific manifestations of each fault characteristic;

[0026] Based on the analyzed fault features, an artificial intelligence algorithm is used to analyze the fault causes. A decision tree algorithm is selected to construct a tree structure based on the different values ​​of the fault features. This structure displays the mapping relationship between different feature combinations and fault causes. The input fault features are processed and analyzed, and matching and reasoning are performed within the existing fault knowledge base to quickly locate the cause of the fault and generate a list of fault causes.

[0027] The fault cause list generated by the artificial intelligence algorithm is evaluated and screened, and the frequency of occurrence of the fault cause in the historical operation data is comprehensively considered, combined with the actual operating environment and current working status of the facilities and equipment, to eliminate fault causes that are obviously inconsistent with the actual situation and form the final set of fault cause candidates.

[0028] A further improvement of the technical solution of the present invention is that: the knowledge graph decision-making auxiliary module includes a knowledge graph construction unit and a decision matching unit;

[0029] The knowledge graph construction unit is used to construct an equipment failure knowledge graph based on the type of property facilities and equipment, historical failure data, and maintenance experience. The graph includes the structural relationship, failure mode, and maintenance method information of the equipment, forming a comprehensive equipment failure knowledge base to provide knowledge support for fault handling and reduce misjudgments due to lack of experience.

[0030] The decision matching unit provides specific maintenance suggestions to maintenance personnel based on the knowledge graph and combined with the current fault identification and diagnosis results.

[0031] A further improvement of the technical solution of the present invention is that the knowledge graph construction unit specifically includes:

[0032] Collect data related to property facilities and equipment, including equipment type information, historical failure data, and maintenance experience records. Classify the data related to property facilities and equipment according to equipment type and failure mode to provide raw materials for building knowledge graphs.

[0033] Extract entities and relationships from the organized data. Entities include equipment, components, failure modes, and repair methods. Relationships include the structural relationships between equipment components, the relationship between failure modes and equipment, and the relationship between repair methods and failure modes. Use natural language processing (NLP) technology to identify entities and relationships and build a preliminary structured data framework.

[0034] Based on the extracted entities and relationships, we use graph database technology to construct an equipment failure knowledge graph. In the equipment failure knowledge graph, we use equipment, failure modes, and maintenance methods as nodes, and the relationships between nodes as edges. This framework builds the equipment failure knowledge graph and clearly displays the internal structural relationships of the equipment and the logical associations between failure modes and maintenance methods.

[0035] The constructed equipment failure knowledge graph is integrated into the property facility equipment management system. At the same time, with the introduction of new equipment, the emergence of new failure cases and the accumulation of maintenance experience, the knowledge graph is regularly updated and optimized to ensure the timeliness and accuracy of the knowledge base.

[0036] A further improvement of the technical solution of the present invention is that the decision matching unit specifically includes:

[0037] The decision matching unit receives the current fault identification result from the fault identification unit, clarifies the fault characteristics and the preliminary fault type, and obtains the detailed fault cause given by the fault diagnosis unit. Based on the constructed equipment fault knowledge graph, the decision matching unit performs correlation analysis between the current fault information and the equipment structure, fault mode, and maintenance method nodes in the knowledge graph.

[0038] Generate specific maintenance recommendations based on the results of information integration and correlation analysis. Based on the maintenance experience and methods stored in the knowledge graph and the characteristics of the current fault, recommend appropriate maintenance steps. Also, list the required maintenance tools and parts, specifying the models and specifications of the parts, to ensure maintenance personnel can prepare in advance and quickly carry out maintenance work.

[0039] The formulated maintenance suggestions will be fed back to maintenance personnel and management personnel. During the actual maintenance process, if the maintenance personnel find that the maintenance suggestions are unreasonable or encounter new problems, they will feed the information back to the decision matching unit. Based on the feedback information, combined with the knowledge graph and historical maintenance data, the maintenance suggestions will be optimized and adjusted.

[0040] A further improvement of the technical solution of the present invention is that the intelligent repair customer service module specifically includes:

[0041] Users initiate a repair request or consultation request by clicking on the repair portal on the app interface or waking up the voice assistant. In the app, users fill out the repair form, including the device type, description of the fault phenomenon, and location information. When using the voice assistant, users must clearly state their repair needs. The AI ​​customer service system receives the request in real time and establishes a connection between the user and the repair case.

[0042] The AI ​​customer service system processes the information provided by users. For repair requests, it uses natural language processing technology to extract information including device model and fault symptoms. Combined with the device fault knowledge base in the knowledge graph, it provides preliminary solutions. At the same time, it automatically records the repair time and fault description information and generates a repair work order.

[0043] After the repair work order is generated, the AI ​​customer service system automatically assigns the repair work order to the corresponding maintenance personnel and continues to follow up on the repair progress. After the repair is completed, the AI ​​customer service system sends a repair result notification to the user, informing the user that the equipment has been repaired and reminding the user to confirm.

[0044] A further improvement of the technical solution of the present invention is that the equipment maintenance management module specifically includes:

[0045] Develop a daily maintenance plan for the equipment based on the equipment type, operating environment, and historical maintenance records. Generate a personalized maintenance plan based on the equipment's specifications, manufacturer-recommended maintenance cycles, and the equipment's actual usage frequency and historical failure data.

[0046] The maintenance plan is broken down into specific maintenance tasks, and tasks are assigned to appropriate maintenance personnel based on their professional skills, workload, and geographic location. Maintenance personnel receive task push notifications via the app, with task details including equipment information, maintenance content, and deadlines.

[0047] After arriving at the site, maintenance personnel will perform maintenance tasks according to the requirements. During the maintenance process, the maintenance progress will be recorded in real time through the app, including the steps performed, potential problems found, and temporary measures taken. After the maintenance is completed, the maintenance personnel will fill out a detailed maintenance record, including the maintenance time, completion status, replaced parts, and follow-up suggestions, and then store the maintenance record in the database.

[0048] Regularly conduct data analysis on maintenance plans and execution records, optimize maintenance plans based on the analysis results, adjust maintenance cycles, task content or personnel allocation, and generate equipment maintenance reports based on data analysis results to provide a basis for management decisions.

[0049] Due to the adoption of the above technical solution, the present invention has the following technical advancements compared to the prior art:

[0050] 1. The present invention provides an artificial intelligence-based smart property management system. Through real-time analysis of facility and equipment operating data using artificial intelligence algorithms, it can identify potential faults in advance and issue early warnings to avoid fault escalation, quickly locate the cause of the fault, provide clear guidance for maintenance personnel, shorten maintenance time, and use knowledge graphs combined with fault identification results to provide solution strategies and decision support, helping maintenance personnel to quickly formulate reasonable maintenance plans, optimize resource allocation, and significantly improve fault handling efficiency.

[0051] 2. The present invention provides an intelligent property management system based on artificial intelligence. Through the data acquisition and transmission module, the operation data of facilities and equipment are accurately collected and transmitted. Combined with the early warning and precise positioning of the fault identification and diagnosis module, the occurrence of sudden equipment failures is reduced and the increase in maintenance costs caused by the expansion of faults is avoided. At the same time, intelligent maintenance plan formulation and task allocation ensure that equipment is maintained in a timely and effective manner, extend the service life of equipment, reduce the frequency of equipment replacement, and reduce equipment operation and maintenance costs as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0053] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0054] Figure 2 Schematic diagram of the working process of the fault diagnosis unit of the present invention. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] Example 1, as Figure 1 、 Figure 2 As shown, the present invention provides an artificial intelligence-based smart property management system, including a data management center, which is communicatively connected to a data acquisition and transmission module, a fault identification and diagnosis module, a knowledge graph-assisted decision-making module, an intelligent repair customer service module, and an equipment maintenance and management module;

[0057] The data acquisition and transmission module collects and pre-processes the operating data of the facilities and equipment based on various sensors deployed on the property facilities and equipment, and transmits it to the data management center. Corresponding sensors are deployed at key locations of various property facilities and equipment. For elevator equipment, current, voltage, temperature, vibration, and speed sensors are installed at key locations such as motors, cars, and tracks. For air-conditioning systems, current, voltage, pressure, and temperature sensors are arranged at locations such as compressors, condensers, and evaporators. The sensors collect operating data of the facilities and equipment, including current, voltage, temperature, pressure, and vibration, at a preset sampling frequency, and store the collected data in the form of digital signals in the sensor's own buffer area. The collected operating data of the facilities and equipment are pre-processed, including data cleaning and normalization steps. Data cleaning is performed, and high-frequency noise is removed using filtering algorithms. Missing values ​​are supplemented by mean filling and interpolation methods based on data characteristics. Outliers are identified and corrected based on statistical methods. Through normalization, data of different dimensions are unified into a specific range. The pre-processed operating data of the facilities and equipment are transmitted to the data management center via wireless communication and classified and stored according to the device type and timestamp dimensions.

[0058] The fault identification and diagnosis module is used to analyze the collected operating data using artificial intelligence algorithms, identify potential equipment faults, and provide fault diagnosis results. This helps identify potential equipment problems in advance, reduce the occurrence of sudden faults, and improve the reliability and stability of equipment operation. The fault identification and diagnosis module includes a fault identification unit and a fault diagnosis unit.

[0059] Among them, the fault identification unit builds a fault identification model based on the machine learning model, extracts fault features, and analyzes the historical operation data and real-time operation data of the facilities and equipment to identify potential faults of the equipment. It can issue early warnings before the fault occurs, so that property personnel can take measures in advance to avoid the expansion of the fault, reduce downtime and maintenance costs, and collect historical and real-time operation data of the facilities and equipment, covering multi-dimensional information of current, voltage, temperature, pressure and vibration collected by sensors, and integrate data from different sources and formats, unify the data structure and format, and then standardize the data to eliminate the dimensional effect, so that data with different features are at the same level to form a complete data set. Based on the integrated data set, feature extraction is performed to obtain fault features related to equipment failures, including current change amplitude, voltage fluctuation amplitude, temperature change rate, pressure fluctuation amplitude and vibration frequency, and preset the corresponding allowable values ​​of each fault feature according to the operation management requirements of the facilities and equipment, and mark the fault features that deviate from the allowable values. The feature dataset is obtained comprehensively. According to the characteristics of the facilities and equipment, a machine learning model based on random forest is selected as the basic architecture to build a fault identification model. Each fault feature is used as input, and whether it deviates from the allowable value is used as output. The feature dataset is divided into training set, validation set and test set. The selected random forest model is trained with the training set. By continuously adjusting the model parameters, the model gradually learns the patterns and rules in the data on the training set. At the same time, the validation set is used to monitor the model performance to prevent overfitting. The trained model is evaluated with the test set. The accuracy, recall rate and F1 value indicators are used to measure the model performance. If the model performance is not ideal, the reasons are analyzed and targeted optimization is carried out to improve the model's ability to fit the data and ensure that the model has high recognition accuracy and generalization ability. Then the final fault identification model is built and deployed. The real-time operation data is analyzed, the extracted fault features are input, and the fault features that deviate from the allowable value are output. The fault features that deviate from the allowable value are judged as having a fault risk.

[0060] The fault diagnosis unit is used to analyze fault characteristics based on the identified potential faults using an artificial intelligence algorithm, quickly locate the cause of the fault, quickly and accurately identify the cause of the fault, provide clear guidance to maintenance personnel, shorten maintenance time, and improve maintenance efficiency. It receives potential fault information output by the fault identification unit, including fault characteristics that deviate from the allowable value, and then parses the marked fault characteristics and analyzes the specific manifestations of each fault characteristic. Based on the parsed fault characteristics, it uses an artificial intelligence algorithm to analyze the cause of the fault. It selects a decision tree algorithm and constructs a tree structure based on different values ​​of the fault characteristics to display the mapping relationship between different feature combinations and fault causes. It processes and analyzes the input fault characteristics, performs matching and reasoning in an existing fault knowledge base, quickly locates the cause of the fault, and generates a fault cause list. The fault knowledge base stores a large number of historical fault cases and their corresponding fault characteristics and causes. By comparing with the data in the knowledge base, the possible cause of the current fault is quickly located. The fault cause list generated by the artificial intelligence algorithm is evaluated and screened. The frequency of occurrence of the fault cause in historical operating data is combined with the actual operating environment and current working status of the facility and equipment to eliminate fault causes that are obviously inconsistent with the actual situation and form a final set of candidate fault causes.

[0061] The knowledge graph-assisted decision-making module combines knowledge graph technology with equipment fault identification results to provide fault resolution strategies and decision support, helping property management and maintenance personnel quickly find the best solution and improve the accuracy of fault handling.

[0062] The intelligent repair customer service module is used to provide intelligent repair and consulting services using the AI ​​customer service system. Users can report repairs or check device status through the app or voice assistant, improving the user experience. Users can get feedback on device status and maintenance anytime and anywhere to ensure that problems are resolved in a timely manner.

[0063] The equipment maintenance management module is responsible for the formulation of daily maintenance plans, maintenance task allocation and maintenance record management of equipment, so as to standardize and systematize equipment maintenance work and ensure that the equipment is always in good operating condition.

[0064] Example 2, as Figure 1 、 Figure 2 As shown, based on Example 1, the present invention provides a technical solution: preferably, the knowledge graph decision-making assistance module includes a knowledge graph construction unit and a decision matching unit;

[0065] Among them, the knowledge graph construction unit is used to construct an equipment failure knowledge graph based on the type of property facilities and equipment, historical failure data and maintenance experience, including the structural relationship, failure mode and maintenance method information of the equipment, to form a comprehensive equipment failure knowledge base, provide knowledge support for fault handling, reduce misjudgment due to lack of experience, collect data related to property facilities and equipment, covering equipment type information, historical failure data and maintenance experience records, among which equipment type information includes the model, specifications, components of elevators, air conditioners, water pumps, etc. Historical failure data includes the time of failure, failure phenomenon, failure code, etc. Maintenance experience records include the operating steps of maintenance personnel, replaced parts, and the effect after maintenance, etc., and classify the data related to property facilities and equipment according to equipment type and failure mode to provide original materials for building a knowledge graph, extract entities and relationships from the sorted data, and entities It includes equipment, components, failure modes and maintenance methods. The relationships include the structural relationship between equipment components, the relationship between failure modes and equipment, and the relationship between maintenance methods and failure modes. Through natural language processing (NLP) technology, entities and relationships are identified, and a preliminary structured data framework is constructed. Based on the extracted entities and relationships, graph database technology is used to construct an equipment failure knowledge graph. In the equipment failure knowledge graph, equipment, failure modes, and maintenance methods are used as nodes, and the relationships between nodes are used as edges. The framework of the equipment failure knowledge graph is constructed to clearly display the internal structural relationship of the equipment and the logical association between failure modes and maintenance methods. The constructed equipment failure knowledge graph is integrated into the property facility equipment management system. At the same time, with the introduction of new equipment, the emergence of new failure cases and the accumulation of maintenance experience, the knowledge graph is regularly updated and optimized to ensure the timeliness and accuracy of the knowledge base.

[0066] The decision matching unit, based on the knowledge graph and combined with the current fault identification and diagnosis results, provides maintenance personnel with specific maintenance recommendations, helping them quickly develop reasonable maintenance plans, optimize resource allocation, and improve the efficiency and quality of fault handling. The decision matching unit receives the current fault identification results from the fault identification unit, identifies the fault characteristics and the preliminary fault type, and obtains the detailed fault cause provided by the fault diagnosis unit. Based on the constructed equipment fault knowledge graph, the current fault information is correlated and analyzed with the equipment structure, fault mode, and maintenance method nodes in the knowledge graph. Based on the results of information integration and correlation analysis, specific maintenance recommendations are generated. Based on the maintenance experience and methods stored in the knowledge graph, corresponding maintenance steps are recommended based on the current fault characteristics. At the same time, a list of required maintenance tools and parts is listed, clarifying the models and specifications of the parts to ensure that maintenance personnel can prepare in advance and quickly carry out maintenance work. The formulated maintenance recommendations are fed back to maintenance personnel and management personnel. During the actual maintenance process, if maintenance personnel find that the maintenance recommendations are unreasonable or encounter new problems, they feedback this information to the decision matching unit. Based on this feedback information, combined with the knowledge graph and historical maintenance data, the maintenance recommendations are optimized and adjusted.

[0067] The intelligent repair customer service module specifically includes:

[0068] The user clicks on the repair portal or wakes up the voice assistant to initiate a repair or consultation request through the APP interface. In the APP, the user fills out the repair form, including the device type, fault phenomenon description and location information. When using the voice assistant, the user needs to clearly state the repair requirement. The AI ​​customer service system receives the request in real time and establishes an association between the user and the repair case. The AI ​​customer service system processes the information provided by the user. For repair requests, it uses natural language processing technology to extract information including device model and fault symptoms, and combines it with the device fault knowledge base in the knowledge graph to provide a preliminary solution. At the same time, it automatically records the repair time and fault description information and generates a repair work order. After the repair work order is generated, the AI ​​customer service system automatically assigns the repair work order to the corresponding maintenance personnel and continues to follow up on the repair progress. During the processing, the maintenance personnel can update the repair status in real time through the APP, including whether they have arrived at the site, are troubleshooting, and need to replace parts. After the repair is completed, the AI ​​customer service system sends a repair result notification to the user, informing the user that the device has been repaired and reminding the user to confirm.

[0069] The equipment maintenance management module specifically includes:

[0070] Develop a daily maintenance plan for the equipment based on the equipment type, operating environment, and historical maintenance records. Generate a personalized maintenance plan based on the equipment's specifications and the manufacturer's recommended maintenance cycle, combined with the equipment's actual usage frequency and historical fault data. For elevator equipment, a safety inspection is performed monthly, and in-depth maintenance is performed quarterly. For air-conditioning systems, inspections are performed twice a month in summer and once a month in winter. The maintenance plan covers the specific steps of the maintenance task, the list of required tools and materials, and the estimated time. The developed maintenance plan is broken down into specific maintenance tasks, and tasks are assigned to appropriate maintenance personnel based on their professional skills, workload, and geographic location. Maintenance personnel receive task push notifications through the APP, and task details include equipment After the maintenance personnel arrive at the site, they will perform the maintenance task requirements. During the execution process, the maintenance progress will be recorded in real time through the APP, including the steps executed, potential problems found, and temporary measures taken. After the maintenance is completed, the maintenance personnel will fill in a detailed maintenance record, including the maintenance time, completion status, replaced parts and subsequent suggestions, and then store the maintenance records in the database. Regular data analysis will be conducted on the maintenance plan and execution records. According to the analysis results, the maintenance plan will be optimized, and the maintenance cycle, task content or personnel configuration will be adjusted. At the same time, based on the data analysis results, an equipment maintenance report will be generated to provide a basis for management decision-making, ensure that the equipment is always in good operating condition, extend the equipment service life, and reduce operation and maintenance costs.

[0071] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An artificial intelligence-based smart property management system, including a data management center, characterized by: The data management center is communicatively connected to a data acquisition and transmission module, a fault identification and diagnosis module, a knowledge graph-assisted decision-making module, an intelligent repair customer service module, and an equipment maintenance and management module; The data acquisition and transmission module collects and pre-processes the operating data of the facilities and equipment based on various sensors deployed on the property facilities and equipment, and transmits it to the data management center; The fault identification and diagnosis module is used to analyze the collected operating data using artificial intelligence algorithms, identify potential faults of the equipment, and provide fault diagnosis results; The knowledge graph-assisted decision-making module is used to combine knowledge graph technology and equipment fault identification results to provide fault resolution strategies and decision support; The intelligent repair customer service module is used to provide intelligent repair and consulting services using the AI ​​customer service system; The equipment maintenance management module is responsible for formulating daily maintenance plans for equipment, allocating maintenance tasks, and managing maintenance records.

2. The artificial intelligence-based smart property management system according to claim 1, characterized in that: The data acquisition and transmission module specifically includes: Deploy corresponding sensors at key locations of various facilities and equipment in the property. The sensors collect operational data of the facilities and equipment, including current, voltage, temperature, pressure, and vibration, at a preset sampling frequency, and store the collected data in the form of digital signals in the sensor's built-in buffer area. Pre-process the collected operational data of facilities and equipment, including data cleaning and normalization steps; The pre-processed operation data of the facility equipment is transmitted to the data management center through wireless communication, and is classified and stored according to the equipment type and timestamp dimensions.

3. The artificial intelligence-based smart property management system according to claim 1, characterized in that: The fault identification and diagnosis module includes a fault identification unit and a fault diagnosis unit; The fault identification unit constructs a fault identification model based on a machine learning model, extracts fault features, and analyzes historical and real-time operating data of facility equipment to identify potential faults of the equipment; The fault diagnosis unit is used to analyze fault characteristics and locate the cause of the fault based on the identified potential fault through an artificial intelligence algorithm.

4. The artificial intelligence-based smart property management system according to claim 3, characterized in that: The fault identification unit specifically includes: Collect historical and real-time operating data of facilities and equipment, including multi-dimensional information such as current, voltage, temperature, pressure, and vibration collected by sensors. The data from different sources and formats is integrated and standardized to form a complete data set. Based on the integrated data set, feature extraction is performed to obtain fault characteristics related to equipment failures, including current change amplitude, voltage fluctuation amplitude, temperature change rate, pressure fluctuation amplitude, and vibration frequency. Based on the operation and management requirements of the facility equipment, the corresponding allowable value of each fault characteristic is preset, and fault characteristics that deviate from the allowable value are marked to obtain a comprehensive feature data set. Based on the characteristics of the facilities and equipment, a random forest-based machine learning model was selected as the basic architecture to build a fault identification model. Each fault feature was used as input, and whether it deviated from the allowable value was used as output. The feature data set was divided into training, validation, and test sets. The training set was used to train the selected random forest model, the validation set was used to monitor model performance, and the test set was used to evaluate the trained model, thereby constructing the final fault identification model. The fault identification model constructed by deployment is used to analyze real-time operation data. The extracted fault features are input and the fault features that deviate from the allowable values ​​are output. Fault features that deviate from the allowable values ​​are judged to have fault risks.

5. The artificial intelligence-based smart property management system according to claim 4, characterized in that: The fault diagnosis unit specifically includes: Receive potential fault information output from the fault identification unit, including fault characteristics that deviate from the allowable value, and then parse the marked fault characteristics to analyze the specific manifestations of each fault characteristic; Based on the analyzed fault features, an artificial intelligence algorithm is used to analyze the fault causes. A decision tree algorithm is selected to construct a tree structure based on the different values ​​of the fault features. This structure displays the mapping relationship between different feature combinations and fault causes. The input fault features are processed and analyzed, and matching and reasoning are performed within the existing fault knowledge base to quickly locate the cause of the fault and generate a list of fault causes. The fault cause list generated by the artificial intelligence algorithm is evaluated and screened, and the frequency of occurrence of the fault cause in the historical operation data is comprehensively considered, combined with the actual operating environment and current working status of the facilities and equipment, to eliminate fault causes that are obviously inconsistent with the actual situation and form the final set of fault cause candidates.

6. The artificial intelligence-based smart property management system according to claim 3, characterized in that: The knowledge graph decision-making assistance module includes a knowledge graph construction unit and a decision matching unit; The knowledge graph construction unit is used to construct an equipment failure knowledge graph based on the type of property facilities and equipment, historical failure data, and maintenance experience, including the structural relationship, failure mode, and maintenance method information of the equipment, to form an equipment failure knowledge base; The decision matching unit provides specific maintenance suggestions to maintenance personnel based on the knowledge graph and combined with the current fault identification and diagnosis results.

7. The artificial intelligence-based smart property management system according to claim 6, characterized in that: The knowledge graph construction unit specifically includes: Collect data related to property facilities and equipment, including equipment type information, historical failure data, and maintenance experience records, and classify the data related to property facilities and equipment according to equipment type and failure mode; Extract entities and relationships from the organized data. Entities include equipment, components, failure modes, and repair methods. Relationships include the structural relationships between equipment components, the relationship between failure modes and equipment, and the relationship between repair methods and failure modes. Use natural language processing technology to identify entities and relationships and build a preliminary structured data framework. Based on the extracted entities and relationships, we use graph database technology to build an equipment failure knowledge graph. In the equipment failure knowledge graph, we use equipment, failure modes, and maintenance methods as nodes, and the relationships between nodes as edges to build the framework of the equipment failure knowledge graph. The constructed equipment failure knowledge graph is integrated into the property facility equipment management system. At the same time, with the introduction of new equipment, the emergence of new failure cases and the accumulation of maintenance experience, the knowledge graph is regularly updated and optimized.

8. The artificial intelligence-based smart property management system according to claim 7, characterized in that: The decision matching unit specifically includes: The decision matching unit receives the current fault identification result from the fault identification unit, clarifies the fault characteristics and the preliminary fault type, and obtains the detailed fault cause given by the fault diagnosis unit. Based on the constructed equipment fault knowledge graph, the decision matching unit performs correlation analysis between the current fault information and the equipment structure, fault mode, and maintenance method nodes in the knowledge graph. Generate specific maintenance suggestions based on the results of information integration and correlation analysis. Based on the maintenance experience and methods stored in the knowledge graph and the characteristics of the current fault, recommend corresponding maintenance steps. At the same time, list the required maintenance tools and parts, and clarify the models and specifications of the parts. The formulated maintenance suggestions will be fed back to maintenance personnel and management personnel. During the actual maintenance process, if the maintenance personnel find that the maintenance suggestions are unreasonable or encounter new problems, they will feed the information back to the decision matching unit. Based on the feedback information, combined with the knowledge graph and historical maintenance data, the maintenance suggestions will be optimized and adjusted.

9. The artificial intelligence-based smart property management system according to claim 1, characterized in that: The intelligent repair customer service module specifically includes: Users initiate a repair request or consultation request by clicking on the repair portal on the app interface or waking up the voice assistant. In the app, users fill out the repair form, including the device type, description of the fault phenomenon, and location information. When using the voice assistant, users must clearly state their repair needs. The AI ​​customer service system receives the request in real time and establishes a connection between the user and the repair case. The AI ​​customer service system processes the information provided by users. For repair requests, it uses natural language processing technology to extract information including device model and fault symptoms. Combined with the device fault knowledge base in the knowledge graph, it provides preliminary solutions. At the same time, it automatically records the repair time and fault description information and generates a repair work order. After the repair work order is generated, the AI ​​customer service system automatically assigns the repair work order to the corresponding maintenance personnel and continues to follow up on the repair progress. After the repair is completed, the AI ​​customer service system sends a repair result notification to the user, informing the user that the equipment has been repaired and reminding the user to confirm.

10. The artificial intelligence-based smart property management system according to claim 1, characterized in that: The equipment maintenance management module specifically includes: Develop a daily maintenance plan for the equipment based on the equipment type, operating environment, and historical maintenance records. Generate a personalized maintenance plan based on the equipment's specifications, manufacturer-recommended maintenance cycles, and the equipment's actual usage frequency and historical failure data. The maintenance plan is broken down into specific maintenance tasks, and tasks are assigned to appropriate maintenance personnel based on their professional skills, workload, and geographic location. Maintenance personnel receive task push notifications via the app. After arriving at the site, maintenance personnel will perform maintenance tasks according to the requirements. During the maintenance process, the maintenance progress will be recorded in real time through the APP. After the maintenance is completed, the maintenance personnel will fill in a detailed maintenance record, which will then be stored in the database. Regularly perform data analysis on maintenance plans and execution records, optimize maintenance plans based on the analysis results, adjust maintenance cycles, task content or personnel allocation, and generate equipment maintenance reports based on the data analysis results.

Images