Smart campus management dormitory maintenance method and system based on big data application

By obtaining and analyzing real-time monitoring data of dormitory equipment, building a knowledge graph, predicting faults and implementing operation and maintenance strategies, the problem of timely detection of dormitory equipment failures is solved, and maintenance efficiency and user experience are improved.

CN116976859BActive Publication Date: 2024-11-12HANGZHOU XUEWO NETWORK TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311006704.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-08-11
Publication Date
2024-11-12
Estimated Expiration
2043-08-11

AI Technical Summary

Technical Problem

The existing technology cannot detect dormitory equipment failure in a timely manner, resulting in delayed maintenance and affecting the use of teachers and students.

Method used

By obtaining real-time monitoring data of multiple distributed monitoring nodes, extracting and extending attribute information, building metadata and knowledge graphs, predicting and analyzing faults, executing operation and maintenance strategies, and realizing timely detection and prediction of faults.

Benefits of technology

Real-time discovery and prediction of faults is achieved, maintenance efficiency is improved, costs are reduced, and user experience is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116976859B_ABST
    Figure CN116976859B_ABST
Patent Text Reader

Abstract

The present invention discloses a smart campus management dormitory maintenance method and system based on big data application, which belongs to the field of smart campus technology and operation and maintenance technology. The present invention obtains real-time monitoring data of multiple distributed monitoring nodes to monitor whether dormitory equipment is faulty in real time, thereby ensuring real-time discovery of faults, thereby improving maintenance efficiency; metadata is obtained by expanding attribute information; and according to metadata, a knowledge graph corresponding to a single dormitory device is constructed, so that in the process of fault discovery, the cause of the fault can be more comprehensively understood, thereby improving efficiency and reducing costs in the process of real-time maintenance and maintenance; through the knowledge graph, predicting and analyzing single dormitory equipment failures not only ensures timely discovery of faults, but also predicts faults before they occur, avoiding the impact of equipment failures on use, improving efficiency, and further improving user experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of smart campus technology and operation and maintenance technology, and in particular to a smart campus management dormitory maintenance method and system based on big data application. Background Art

[0002] A smart campus is an intelligent campus, and also refers to a campus built according to intelligent standards, which realizes the organic connection between physical space and information space, so that anyone, at any time and in any place can easily obtain resources and services; a smart campus is usually composed of a campus infrastructure with sensor networks and intelligent hardware as the core, and an intelligent software system deployed on a cloud server in a data center.

[0003] In the field of dormitory maintenance management, the above-mentioned smart campus technology can realize the dispatch of maintenance tasks based on reports from maintenance personnel or students through the support platform and application platform, so that maintenance personnel can be dispatched to the site to carry out maintenance.

[0004] However, the existing technology is unable to detect faults in a timely manner, so when dormitory equipment fails, it is necessary to wait for warranty maintenance, which affects the use of teachers and students. Summary of the invention

[0005] In order to solve the problems of the prior art, the embodiment of the present invention provides a smart campus management dormitory maintenance method and system based on big data application. The technical solution is as follows:

[0006] On the one hand, a smart campus management dormitory maintenance method based on big data application is provided, the method is applied to a system including multiple distributed monitoring nodes, and the method includes:

[0007] Acquire real-time monitoring data of a plurality of distributed monitoring nodes, wherein the plurality of distributed monitoring nodes correspond to a single dormitory device;

[0008] Extracting and expanding the attribute information of the plurality of real-time monitoring data;

[0009] Constructing metadata corresponding to the real-time monitoring data according to the expanded attribute information;

[0010] According to the metadata, construct a knowledge graph corresponding to the single dormitory equipment;

[0011] Based on the knowledge graph, predict and analyze the equipment failure of the single dormitory;

[0012] According to the fault information of the single dormitory equipment, a corresponding operation and maintenance strategy is executed.

[0013] Optionally, before acquiring the real-time monitoring data of the multiple distributed monitoring nodes, the method further includes:

[0014] Dynamically configure the real-time monitoring data upload method corresponding to the distributed monitoring nodes.

[0015] Optionally, the acquiring real-time monitoring data of multiple distributed monitoring nodes includes:

[0016] Setting a central node of the plurality of distributed monitoring nodes and a data transmission strategy corresponding to the central node;

[0017] The real-time monitoring data is acquired according to the data transmission strategy.

[0018] Optionally, extracting the attribute information of the plurality of real-time monitoring data and expanding the attribute information includes:

[0019] Based on neural network, preset recognition model;

[0020] According to the recognition model, identifying attribute information in the real-time monitoring data from multiple dimensions;

[0021] The attribute information is expanded to obtain the expanded attribute information.

[0022] Optionally, constructing metadata corresponding to the real-time monitoring data according to the expanded attribute information includes:

[0023] According to the expanded attribute information, the source of the real-time monitoring data and the application scenario, setting a description model corresponding to the real-time monitoring data;

[0024] According to the description model, metadata corresponding to the real-time monitoring data is constructed.

[0025] Optionally, constructing the knowledge graph corresponding to the single dormitory equipment according to the metadata includes:

[0026] Calculate the relationship data between the single dormitory device and the real-time monitoring data time according to the metadata and the real-time monitoring data;

[0027] A knowledge graph corresponding to the single dormitory is constructed according to the metadata and the relationship data.

[0028] Optionally, the predicting and analyzing the single dormitory equipment failure based on the knowledge graph includes:

[0029] Set up the data extraction model;

[0030] According to the data extraction model, identifying target relationship data;

[0031] According to the purpose relationship data and the knowledge graph, a plurality of real-time monitoring data are identified;

[0032] Preset fault identification model;

[0033] The identified multiple real-time monitoring data are input into the fault identification model to obtain fault information, where the fault information is used to indicate whether the dormitory equipment is faulty and the cause of the fault.

[0034] Optionally, executing a corresponding operation and maintenance strategy according to the fault information of the single dormitory equipment includes:

[0035] The operation and maintenance strategy includes remote operation and maintenance and local operation and maintenance;

[0036] If remote operation and maintenance is required, the corresponding operation and maintenance strategy is executed according to the fault cause in the fault information;

[0037] If local operation and maintenance is required, locally available operation and maintenance resources are obtained, and operation and maintenance tasks are allocated according to the locally available operation and maintenance resources.

[0038] On the other hand, a smart campus management dormitory maintenance system based on big data application is provided, characterized in that the system includes multiple distributed monitoring nodes, and the method includes:

[0039] An acquisition device, used to acquire real-time monitoring data of a plurality of distributed monitoring nodes, wherein the plurality of distributed monitoring nodes correspond to a single dormitory device;

[0040] An extraction device, used to extract attribute information of the plurality of real-time monitoring data and expand it;

[0041] A construction device, used to construct metadata corresponding to the real-time monitoring data according to the expanded attribute information;

[0042] The construction device is also used to construct a knowledge graph corresponding to the single dormitory equipment according to the metadata;

[0043] An analysis device, used for predicting and analyzing the single dormitory equipment failure based on the knowledge graph;

[0044] The execution device is used to execute the corresponding operation and maintenance strategy according to the fault information of the single dormitory equipment.

[0045] Optionally, the execution device is specifically used for:

[0046] The operation and maintenance strategy includes remote operation and maintenance and local operation and maintenance;

[0047] If remote operation and maintenance is required, the corresponding operation and maintenance strategy is executed according to the fault cause in the fault information;

[0048] If local operation and maintenance is required, locally available operation and maintenance resources are obtained, and operation and maintenance tasks are allocated according to the locally available operation and maintenance resources.

[0049] The technical solution provided by the embodiment of the present invention has the following beneficial effects:

[0050] Acquire real-time monitoring data of a plurality of distributed monitoring nodes, wherein the plurality of distributed monitoring nodes correspond to a single dormitory device;

[0051] Extracting and expanding the attribute information of the plurality of real-time monitoring data;

[0052] Constructing metadata corresponding to the real-time monitoring data according to the expanded attribute information;

[0053] According to the metadata, construct a knowledge graph corresponding to the single dormitory equipment;

[0054] Based on the knowledge graph, predict and analyze the equipment failure of the single dormitory;

[0055] According to the fault information of the single dormitory equipment, a corresponding operation and maintenance strategy is executed.

[0056] 1. By acquiring real-time monitoring data from multiple distributed monitoring nodes, the dormitory equipment can be monitored in real time to ensure real-time discovery of faults, thereby improving maintenance efficiency;

[0057] 2. Metadata is obtained by expanding the attribute information; and based on the metadata, a knowledge graph corresponding to a single dormitory device is constructed, so that in the process of fault discovery, the cause of the fault can be more comprehensively understood, thereby improving efficiency and reducing costs in the process of real-time maintenance;

[0058] 3. Predicting and analyzing equipment failures in individual dormitories through knowledge graphs not only ensures timely discovery of failures, but also predicts failures before they occur, thus avoiding the impact of equipment failures on use, improving efficiency, and further improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 It is a flow chart of a dormitory maintenance method for smart campus management based on big data application provided by an embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of a smart campus management dormitory maintenance system based on big data application provided by an embodiment of the present invention;

[0062] Figure 3 It is a schematic diagram of a dormitory maintenance system for smart campus management based on big data application provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0064] Reference Figure 1 As shown, a smart campus management dormitory maintenance method based on big data application is provided, the method is applied to a system including multiple distributed monitoring nodes, and the method includes:

[0065] 101. Acquire real-time monitoring data of multiple distributed monitoring nodes, where the multiple distributed monitoring nodes correspond to a single dormitory device;

[0066] Specifically, in practical applications, the distributed monitoring nodes are deployed in a distributed manner, and the distributed deployment method may be:

[0067] For each dormitory equipment, such as power supply equipment, living equipment (such as air conditioners and access control) and network equipment, a corresponding monitoring node is set; the monitoring node is equipped with a network module;

[0068] For multiple monitoring nodes in a single dormitory, distributed deployment is achieved through network module self-subnet and IP address;

[0069] The multiple monitoring nodes broadcast their own network parameters and performance parameters to other nodes in real time; that is, for each monitoring node, through the broadcast, a monitoring node performance table is dynamically maintained, and the monitoring node performance table includes network parameters and performance parameters;

[0070] Within a preset time period, a monitoring node whose network parameters meet preset network conditions is selected as a data transmission node, if the monitoring node performance table indicates that the network parameters of the monitoring node are optimal;

[0071] Within a preset time period, a monitoring node whose performance parameters meet preset performance conditions is selected as an edge processing node, if the monitoring node performance table indicates that the performance parameters of the monitoring node are optimal;

[0072] The edge processing node obtains the edge processing algorithm or edge processing model from the server side through the data transmission node; through the edge processing algorithm or edge processing model, it realizes the processing of data and faults transmitted by other monitoring nodes, thereby ensuring accuracy through real-time updating of the edge processing algorithm or edge processing model, and realizing the improvement of response speed through edge computing.

[0073] 102. Extract attribute information of multiple real-time monitoring data and expand them;

[0074] 103. Construct metadata corresponding to the real-time monitoring data based on the expanded attribute information;

[0075] 104. Based on the metadata, construct the knowledge graph corresponding to a single dormitory device;

[0076] 105. Predict and analyze equipment failures in a single dormitory based on knowledge graph;

[0077] 106. Execute corresponding operation and maintenance strategies based on the fault information of individual dormitory equipment.

[0078] Optionally, before step 101, before obtaining real-time monitoring data of multiple distributed monitoring nodes, the method further includes:

[0079] Dynamically configure the real-time monitoring data upload method corresponding to the distributed monitoring nodes, and the upload object is the edge processing node.

[0080] The process can be specifically as follows:

[0081] Distributed monitoring nodes configure real-time monitoring data reporting conditions;

[0082] The monitoring data reporting condition can be that the data transmission node obtains it from the server side and then distributes it to other distributed monitoring nodes; the update time can be periodic, or it can be judged based on the feedback information after the fault repair. If the repair is unsuccessful, or there is a fault but the real-time monitoring data is not reported, it will be updated.

[0083] Since the cloud has the advantage of big data processing, the accuracy can be further improved by updating the monitoring data reporting conditions in real time under the premise of big data processing.

[0084] Optionally, step 101 of acquiring real-time monitoring data of multiple distributed monitoring nodes includes:

[0085] 301. Setting a central node of multiple distributed monitoring nodes and a data transmission strategy corresponding to the central node;

[0086] The central node mentioned above is the data transmission node and edge processing node described in step 101.

[0087] Data transfer strategies include:

[0088] After the real-time monitoring data meets the reporting conditions, the distributed monitoring nodes establish an independent communication connection with the central node;

[0089] The central node stops broadcasting and receiving information from other distributed monitoring nodes;

[0090] Receive real-time monitoring data transmitted by the distributed monitoring node.

[0091] 302. Acquire real-time monitoring data according to the data transmission strategy.

[0092] Optionally, step 102 extracts attribute information of multiple real-time monitoring data and expands the information to include:

[0093] 401. Based on neural network, preset recognition model;

[0094] The neural network may be a self-learning text recognition model; the embodiment of the present invention does not limit the specific text recognition model and its training process.

[0095] 402. Identify attribute information in the real-time monitoring data from multiple dimensions according to the recognition model;

[0096] Among them, the attribute information includes the name of the component, operating status, maintenance record, type of real-time monitoring data (fault or non-fault), fault information and management information;

[0097] The fault information includes a description of the fault of the device;

[0098] The management information includes the update time and update content of the real-time monitoring data.

[0099] For some default contents, the preset values ​​are filled in.

[0100] 403. Expand the attribute information to obtain the expanded attribute information.

[0101] Specifically, the attribute information including the null value rate, unique value rate, number of columns, number of rows, etc. of the real-time monitoring data is expanded.

[0102] The real-time monitoring data uploaded by some distributed monitoring nodes also includes fault information corresponding to the edge processing algorithm or edge processing model. The above steps may also be:

[0103] Expand the attribute information of the edge processing algorithm or edge processing model, including accuracy, recall rate, AUC, f-1score, model parameters, model framework, etc.

[0104] By expanding the attribute information and obtaining the expanded attribute information, comprehensive acquisition of real-time monitoring data is achieved, thereby improving accuracy.

[0105] Optionally, step 103 constructs metadata corresponding to the real-time monitoring data according to the expanded attribute information, including:

[0106] 501. According to the expanded attribute information, the source of the real-time monitoring data, and the application scenario, a description model corresponding to the real-time monitoring data is set;

[0107] The application scenario includes a fault scenario, that is, the fault content indicated by the fault information.

[0108] The above description model may be implemented by setting a knowledge graph corresponding to the monitoring data, and the above process may be:

[0109] Obtain the correlation of all contents contained in the attribute information; the correlation may be preset by the system, such as setting the correlation between the name of the component, the operating status, the maintenance record, and the type of real-time monitoring data.

[0110] Identify the dimensions of the content contained in the attribute information. In practical applications, the name of the component, operating status, maintenance record, type of real-time monitoring data (fault or non-fault), fault information, and management information can be set as one dimension respectively;

[0111] In practical applications, if the contents represented by the dimensions are similar, such as the contents represented by the operating status and maintenance records are both abnormal operation of components, the two dimensions of operating status and maintenance records are merged to improve accuracy.

[0112] 502. Construct metadata corresponding to the real-time monitoring data according to the description model.

[0113] Through the schema, define multiple dimensions in the description model and build the initial knowledge graph;

[0114] Fill the initial knowledge graph with the content of the correlation and the attribute information corresponding to the dimension to complete the description of the dormitory equipment corresponding to the distributed monitoring node;

[0115] The filled knowledge graph is used as metadata corresponding to the real-time monitoring data.

[0116] Metadata describes the information of monitoring data, increases the description dimension of monitoring data, and thus enhances the usability of monitoring data.

[0117] Optionally, step 104 constructs a knowledge graph corresponding to a single dormitory device according to the metadata, including:

[0118] 601. Calculate the relationship data between a single dormitory device and the real-time monitoring data time according to the metadata and the real-time monitoring data;

[0119] Specifically, based on NLP technology and knowledge graph, the graph relationship between all dormitory equipment in a single dormitory is constructed, and the relationship data is obtained;

[0120] The relationship data is used to indicate all dormitory devices that are affected when a fault occurs.

[0121] 602. Based on metadata and relational data, construct a knowledge graph corresponding to a single dormitory.

[0122] In practical applications, based on NLP technology, including named entity recognition, entity extraction, relationship extraction, relationship linking, entity disambiguation and other algorithms, the specific monitoring data corresponding to the metadata and relationship data are placed into the graph one by one according to the designed schema, and are increased and updated synchronously with the increase of access and production monitoring data.

[0123] Optional, see Figure 2 As shown, step 105 predicts and analyzes a single dormitory equipment failure based on the knowledge graph, including:

[0124] 701. Set a data extraction model. In practical applications, the data extraction model may be a text recognition model based on a neural algorithm, and the text recognition model may be a self-learning neural algorithm model.

[0125] The neural algorithm model in the above process is not limited in the specific training process and training method.

[0126] 702. Identify target relationship data according to the data extraction model; the target relationship data is monitoring data with similar attribute information or similar source information;

[0127] Similar attribute information or similar source information includes monitoring data from the same device, the same area, or the same system (such as power supply system, access control system, etc.);

[0128] Through self-learning neural algorithms, the extraction of purpose relationship data is achieved, which further improves the accuracy of recognition while saving labor costs.

[0129] 703. Based on the purpose relationship data and the knowledge graph, identify multiple real-time monitoring data; that is, identify multiple related real-time monitoring data.

[0130] 704. Preset fault identification model;

[0131] In practical applications, the fault identification model may be a Markov decision model, and the embodiment of the present invention does not limit the specific Markov decision model.

[0132] 705. Input the identified multiple real-time monitoring data into the fault identification model to obtain fault information, where the fault information is used to indicate whether the dormitory equipment is faulty and the cause of the fault.

[0133] Optionally, step 106 includes executing a corresponding operation and maintenance strategy according to the fault information of a single dormitory device:

[0134] The operation and maintenance strategies include remote operation and maintenance and local operation and maintenance;

[0135] If remote operation and maintenance is required, the corresponding operation and maintenance strategy will be executed according to the fault cause in the fault information;

[0136] If local operation and maintenance is required, obtain locally available operation and maintenance resources and allocate operation and maintenance tasks based on the locally available operation and maintenance resources.

[0137] The technical solution provided by the embodiment of the present invention obtains real-time monitoring data from multiple distributed monitoring nodes to monitor whether dormitory equipment is faulty in real time, thereby ensuring real-time discovery of faults and improving maintenance efficiency; metadata is obtained by expanding attribute information; and based on the metadata, a knowledge graph corresponding to a single dormitory device is constructed, so that in the process of fault discovery, the cause of the fault can be more comprehensively understood, thereby improving efficiency and reducing costs in the process of real-time warranty and maintenance; through the knowledge graph, a single dormitory equipment fault is predicted and analyzed, which not only ensures timely discovery of the fault, but also predicts the fault before it occurs, avoiding the impact of equipment failure on use, improving efficiency, and further improving user experience.

[0138] Reference Figure 3 As shown, a smart campus management dormitory maintenance system based on big data application is provided, characterized in that the system includes multiple distributed monitoring nodes, and the method includes:

[0139] An acquisition device, used to acquire real-time monitoring data of a plurality of distributed monitoring nodes, wherein the plurality of distributed monitoring nodes correspond to a single dormitory device;

[0140] An extraction device, used to extract attribute information of a plurality of real-time monitoring data and expand it;

[0141] A construction device, used to construct metadata corresponding to the real-time monitoring data according to the expanded attribute information;

[0142] The construction device is also used to construct a knowledge graph corresponding to a single dormitory device based on the metadata;

[0143] An analysis device, used to predict and analyze single dormitory equipment failures based on the knowledge graph;

[0144] The execution device is used to execute the corresponding operation and maintenance strategy according to the fault information of the single dormitory equipment.

[0145] Optionally, before acquiring the real-time monitoring data of the multiple distributed monitoring nodes, the method further includes:

[0146] In a single dormitory device respectively with

[0147] Dynamically configure the real-time monitoring data upload method corresponding to the distributed monitoring nodes.

[0148] Optionally, the acquisition device is used to:

[0149] Setting a central node of multiple distributed monitoring nodes and a data transmission strategy corresponding to the central node;

[0150] Obtain real-time monitoring data according to the data transmission strategy.

[0151] Optionally, the extraction device is used to:

[0152] Based on neural network, preset recognition model;

[0153] According to the recognition model, the attribute information in the real-time monitoring data is identified from multiple dimensions;

[0154] The attribute information is expanded to obtain the expanded attribute information.

[0155] Optionally, construct a device for:

[0156] According to the expanded attribute information, the source of the real-time monitoring data and the application scenario, a description model corresponding to the real-time monitoring data is set;

[0157] According to the description model, metadata corresponding to the real-time monitoring data is constructed.

[0158] Optionally, construct a device for:

[0159] Based on metadata and real-time monitoring data, calculate the relationship data of a single dormitory device and the time of real-time monitoring data;

[0160] Based on metadata and relational data, a knowledge graph corresponding to a single dormitory is constructed.

[0161] Optionally, the analysis device is specifically used for:

[0162] Set up the data extraction model;

[0163] According to the data extraction model, identify the target relational data;

[0164] Based on the purpose relationship data and knowledge graph, multiple real-time monitoring data are identified;

[0165] Preset fault identification model;

[0166] The identified multiple real-time monitoring data are input into the fault identification model to obtain fault information, which is used to indicate whether the dormitory equipment is faulty and the cause of the fault.

[0167] Optionally, the execution device is specifically used for:

[0168] The operation and maintenance strategies include remote operation and maintenance and local operation and maintenance;

[0169] If remote operation and maintenance is required, the corresponding operation and maintenance strategy will be executed according to the fault cause in the fault information;

[0170] If local operation and maintenance is required, obtain locally available operation and maintenance resources and allocate operation and maintenance tasks based on the locally available operation and maintenance resources.

[0171] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present invention, which will not be described in detail here.

[0172] It should be noted that: the smart campus dormitory management maintenance system based on big data application provided in the above embodiment only uses the division of the above functional modules as an example when executing the smart campus dormitory management maintenance method based on big data application. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above. In addition, the smart campus dormitory management maintenance system based on big data application and the method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0173] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0174] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A smart campus management dormitory maintenance method based on big data application, characterized in that: The method is applied to a system including a plurality of distributed monitoring nodes, and the method includes: Dynamically configure the real-time monitoring data upload method corresponding to the distributed monitoring nodes, and the upload object is the distributed monitoring node; Acquire real-time monitoring data of multiple distributed monitoring nodes, wherein the multiple distributed monitoring nodes correspond to a single dormitory device, and for each dormitory device, set a corresponding distributed monitoring node, wherein the multiple distributed monitoring nodes are self-organized through a network module to achieve distributed deployment; the multiple distributed monitoring nodes broadcast their own network parameters and performance parameters to other distributed monitoring nodes in real time; that is, for each distributed monitoring node, through the broadcast, dynamically maintain a monitoring node performance table, wherein the monitoring node performance table includes network parameters and performance parameters; Setting a central node of the plurality of distributed monitoring nodes and a data transmission strategy corresponding to the central node; the central node is a data transmission node and an edge processing node; According to the data transmission strategy, acquiring the real-time monitoring data; Extracting and expanding the attribute information of the plurality of real-time monitoring data, wherein the attribute information includes the name of the component, the operating status, the maintenance record, the type of the real-time monitoring data, the fault information and the management information; Constructing metadata corresponding to the real-time monitoring data according to the expanded attribute information; According to the metadata, construct a knowledge graph corresponding to the single dormitory equipment; Based on the knowledge graph, predict and analyze the equipment failure of the single dormitory; Execute corresponding operation and maintenance strategies according to the fault information of the single dormitory equipment; The step of constructing metadata corresponding to the real-time monitoring data according to the expanded attribute information includes: Setting a description model corresponding to the real-time monitoring data according to the expanded attribute information, the source of the real-time monitoring data, and an application scenario, wherein the application scenario includes the fault content indicated by the fault information; Constructing metadata corresponding to the real-time monitoring data according to the description model; Among them, within a preset time period, a distributed monitoring node whose performance parameters meet preset performance conditions is selected as an edge processing node, and a distributed monitoring node whose network parameters meet preset network conditions is selected as a data transmission node; The edge processing node obtains the edge processing algorithm or edge processing model from the server side through the data transmission node, and processes the data and faults transmitted by other monitoring nodes through the edge processing algorithm or the edge processing model; The step of constructing the knowledge graph corresponding to the single dormitory equipment according to the metadata includes: Calculating relationship data between the single dormitory device and the real-time monitoring data according to the metadata and the real-time monitoring data; Constructing a knowledge graph corresponding to the single dormitory according to the metadata and the relationship data; The predicting and analyzing the single dormitory equipment failure based on the knowledge graph includes: Set up the data extraction model; According to the data extraction model, identifying target relationship data; According to the purpose relationship data and the knowledge graph, a plurality of real-time monitoring data are identified; Preset fault identification model; The identified multiple real-time monitoring data are input into the fault identification model to obtain fault information, where the fault information is used to indicate whether the dormitory equipment is faulty and the cause of the fault.

2. The method according to claim 1, characterized in that The extracting and expanding the attribute information of the plurality of real-time monitoring data includes: Based on neural network, preset recognition model; According to the recognition model, identifying attribute information in the real-time monitoring data from multiple dimensions; The attribute information is expanded to obtain the expanded attribute information.

3. The method according to claim 2, characterized in that The executing a corresponding operation and maintenance strategy according to the fault information of the single dormitory equipment includes: The operation and maintenance strategy includes remote operation and maintenance and local operation and maintenance; If remote operation and maintenance is required, the corresponding operation and maintenance strategy is executed according to the fault cause in the fault information; If local operation and maintenance is required, locally available operation and maintenance resources are obtained, and operation and maintenance tasks are allocated according to the locally available operation and maintenance resources.

4. A system for implementing the smart campus dormitory maintenance method based on big data application as claimed in claim 1, characterized in that: The system comprises: An acquisition device, used to acquire real-time monitoring data of multiple distributed monitoring nodes; An extraction device, used to extract attribute information of the plurality of real-time monitoring data and expand it; A construction device, used to construct metadata corresponding to the real-time monitoring data according to the expanded attribute information; The construction device is also used to construct a knowledge graph corresponding to the single dormitory equipment according to the metadata; An analysis device, used for predicting and analyzing the single dormitory equipment failure based on the knowledge graph; An execution device, used for executing a corresponding operation and maintenance strategy according to the fault information of the single dormitory equipment; The step of constructing metadata corresponding to the real-time monitoring data according to the expanded attribute information includes: According to the expanded attribute information, the source of the real-time monitoring data and the application scenario, setting a description model corresponding to the real-time monitoring data; According to the description model, metadata corresponding to the real-time monitoring data is constructed.

5. The system according to claim 4, characterized in that The operation and maintenance strategy specifically used by the execution device includes remote operation and maintenance and local operation and maintenance; If remote operation and maintenance is required, the corresponding operation and maintenance strategy is executed according to the fault cause in the fault information; If local operation and maintenance is required, locally available operation and maintenance resources are obtained, and operation and maintenance tasks are allocated according to the locally available operation and maintenance resources.