Internet-based intelligent operation and maintenance management system for smart parks

Abstract

An Internet-based intelligent operation and maintenance management system for a smart park relates to the field of park operation and maintenance technology, including an intelligent operation and maintenance management platform, wherein the intelligent operation and maintenance management platform is communicatively connected with a data acquisition module, an operation visualization module, an identity authentication module, and a service request feedback module; the data of each Internet of Things monitoring node and a user terminal of the target park are collected and encrypted and uploaded to the intelligent operation and maintenance management platform; a digital twin model of the target park is constructed; the user's identity is authenticated according to the identity authentication data of the user terminal; the current scene information of the digital twin model is constructed, and the digital twin model is monitored in real time. At the same time, the real-time monitoring results are corrected according to the service request data of the safety situation report type, and the recommended driving route is fed back for the service request data of the traffic recommendation type. If the recommended driving route does not meet the requirements, the user feature matching mechanism is started to generate the best driving route, thereby improving the efficiency of park management and user experience.

Description

Technical Field

[0001] The present invention relates to the field of park operation and maintenance technology, and in particular to an intelligent operation and maintenance management system for a smart park based on the Internet. Background Art

[0002] Prior art CN117196480B "A smart logistics park management system based on digital twin" includes a data acquisition module, a data processing module, a data storage module, and a data output module; the data acquisition module is used to collect real-time data of the warehouse; the data storage module is used to store the three-dimensional model data of the warehouse pre-established by the user and the historical data of the warehouse; the data processing module is used to establish a mapping relationship between the historical data and the three-dimensional model data, import the cargo location information into the three-dimensional model data, and finally prepare a target location report for cargo storage based on the three-dimensional model data, and generate a path planning report;

[0003] The prior art CN116227752B "A park facility management system based on the Internet of Things" includes: a model building module, which is used to collect park spatial data and establish a park digital twin model based on the park spatial data; an environmental monitoring module, which is set at a preset location point in the park and is used to monitor the environmental data of the preset location point in the park; a patrol module, which is used to obtain monitored patrol environment data according to a preset patrol route; an analysis and management module, which is used to predict the environmental data of a preset patrol route based on the park digital twin model, the environmental data of the preset location point and the preset patrol route, obtain predicted patrol environment data, and judge the status of the environmental monitoring module based on the comparison between the patrol environment data and the predicted patrol environment data;

[0004] At present, the problems faced by traditional park management include the lack of a management platform. Due to the lack of an overall plan for traditional parks, the system is isolated, making it difficult to manage and count park construction in a targeted manner, resulting in low work efficiency. Park operations generate a large amount of data, which managers are unable to efficiently integrate, analyze and count. The lack of an intelligent platform has led to employees spending a lot of manpower and material resources on internal information management and statistics, which undoubtedly increases the operating costs of the park and makes it impossible to better serve customers. The management methods are low. How to share and integrate resources and information, obtain park data in real time, and conduct statistics and analysis to improve user service experience are issues that we urgently need to solve. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent operation and maintenance management system for a smart park based on the Internet, including an intelligent operation and maintenance management platform, wherein the intelligent operation and maintenance management platform is communicatively connected with a data acquisition module, an operation visualization module, an identity authentication module and a service request feedback module;

[0006] The data acquisition module is used to collect multi-source heterogeneous data of each IoT monitoring node in the target park, as well as identity authentication data, location feature data and service request data of user terminals, and encrypt and upload them to the intelligent operation and maintenance management platform;

[0007] The operation visualization module is used to build a digital twin model of the target park;

[0008] The identity authentication module is used to authenticate the user according to the identity authentication data of the user terminal;

[0009] The service request feedback module is used to construct the current scene information of the digital twin model, monitor each three-dimensional model in the digital twin model in real time according to the current scene information, and perform correction operations on the real-time monitoring results according to the service request data of the safety situation report type, and feedback the service request data of the user consultation service type according to the current scene information, and feedback the recommended driving path for the service request data of the traffic recommendation type. If the recommended driving path does not meet the requirements, the user feature matching mechanism is started to generate the best driving path and feedback it to the user terminal.

[0010] Furthermore, the process in which the data collection module collects multi-source heterogeneous data of each IoT monitoring node of the target park and the identity authentication data, location feature data and service request data of the user terminal and encrypts and uploads them to the intelligent operation and maintenance management platform includes:

[0011] An intelligent operation and maintenance management platform is constructed based on blockchain technology. The intelligent operation and maintenance management platform is connected to a number of blockchain nodes, which are linked to each other to form a blockchain network. The blockchain nodes are connected to each IoT monitoring node and user terminal in the target park. The IoT monitoring node is used to collect multi-source heterogeneous data within its coverage area and mark the collection time and set the collection cycle. The user terminal is used to collect the user's identity authentication data, location feature data and service request data;

[0012] The public key and private key of the blockchain node corresponding to each IoT monitoring node and the user terminal are preset through an asymmetric encryption algorithm, and the multi-source heterogeneous data of the IoT monitoring node and the identity authentication data, location feature data and service request data of the user terminal are encrypted and transmitted to the blockchain node through the corresponding public key. The blockchain node decrypts the received multi-source heterogeneous data and identity authentication data, location feature data and service request data through the private key, and the accounting node and point-to-point communication protocol of the blockchain network are preset. The decrypted multi-source heterogeneous data and identity authentication data, location feature data and service request data are packaged into a new block through the accounting node, and the new block is broadcast to the entire blockchain network according to the point-to-point communication protocol, the new block is added to the end of the blockchain, and the block information in the new block is updated to the local blockchain copies of all blockchain nodes.

[0013] Furthermore, the process of running the visualization module to construct a digital twin model of the target park includes:

[0014] Obtain the physical entities of each building and infrastructure in the physical space of the target park, and at the same time obtain the multi-source heterogeneous data collected by the IoT monitoring nodes of each building and infrastructure and perform data format preprocessing to generate twin data;

[0015] The physical entities of each building and infrastructure are three-dimensionally modeled to generate a three-dimensional model, and the twin data is matched with the corresponding three-dimensional model to generate a digital twin model of the target park. At the same time, the location feature data of several user terminals are obtained, and the location information of several user terminals is displayed in real time on the digital twin model based on the location feature data.

[0016] Furthermore, the process of the identity authentication module authenticating the user according to the identity authentication data of the user terminal includes:

[0017] A user identity database is constructed, wherein the user identity database includes identity authentication data of several users, and the identity authentication data of the user received by the blockchain node is matched with the identity authentication data of several users in the user identity database for consistency. If the consistency match is successful, a user identity authentication success instruction is generated, and the user's service request data is fed back. If the consistency match fails, a user identity authentication failure instruction is generated, and the identity authentication failure instruction is sent to the user terminal.

[0018] Furthermore, the service request feedback module constructs the current scene information of the digital twin model, and the process of providing feedback on the service request data of the user consulting service class according to the current scene information includes:

[0019] Perform service request type analysis and attribute feature analysis on the user's service request data, extract the service request type, semantic attributes and numerical attributes of the service request data, and obtain the semantic attributes corresponding to each three-dimensional model in the digital twin model. Obtain the numerical attributes corresponding to each three-dimensional model according to the twin data corresponding to each three-dimensional model in the digital twin model, and obtain the estimated numerical attributes of each three-dimensional model. Construct the current scene information of the digital twin model according to the semantic attributes, numerical attributes and estimated numerical attributes corresponding to each three-dimensional model.

[0020] When the service request type of the service request data is a consulting service, the semantic attributes of the service request data are matched with the current scene information, and the numerical attributes and estimated numerical attributes of the three-dimensional model whose semantic attributes are consistent with the semantic attributes of the service request data are obtained and fed back to the user terminal.

[0021] Furthermore, the service request feedback module monitors each three-dimensional model in the digital twin model in real time according to the current scene information, and performs correction operations on the real-time monitoring results according to the service request data of the safety situation report type, including:

[0022] Preliminarily compare the difference between the numerical time series corresponding to each type of equipment data in the numerical attributes of each three-dimensional model in the current scene information and the estimated numerical time series corresponding to each type of equipment data in the estimated numerical attributes, obtain the numerical difference coefficient of each type of equipment data in the three-dimensional model, preset the numerical difference coefficient threshold, and if there is a type of equipment data in the three-dimensional model with a numerical difference coefficient greater than the numerical difference coefficient threshold, mark the type of equipment data as abnormal type equipment data, add an abnormal alarm label of the abnormal type equipment data to the three-dimensional model, and arrange maintenance personnel to perform emergency maintenance operations according to the abnormal alarm label of the abnormal type equipment data;

[0023] Match the semantic attributes and numerical attributes of the service request data with the current scene information, obtain a three-dimensional model in which the semantic attributes in the digital twin model are consistent with the semantic attributes of the service request data, and at the same time obtain the abnormal type device data in the service request data according to the numerical attributes of the service request data, and determine whether the three-dimensional model has an abnormal alarm label consistent with the abnormal type device data. If not, obtain the user's reputation value according to the user's historical service request data, and preset abnormal situations corresponding to different reputation values;

[0024] The abnormal situation corresponding to the current three-dimensional model is determined according to the user's reputation value, and maintenance personnel are arranged to perform emergency maintenance operations according to the emergency maintenance measures corresponding to the abnormal situation. At the same time, the maintenance personnel feedback the actual on-site situation of the three-dimensional model, and the user's reputation value is updated according to the actual on-site situation.

[0025] Furthermore, the process of the service request feedback module feeding back the recommended driving route according to the current scene information and the service request data of the traffic recommendation category includes:

[0026] Match the semantic attributes of the service request data with the current scene information, obtain a three-dimensional model in the digital twin model whose semantic attributes are consistent with the semantic attributes of the service request data, mark the three-dimensional model as the target three-dimensional model, extract the location information of the user terminal in the digital twin model and several driving path segments between the target three-dimensional model, and simultaneously obtain the numerical attributes and estimated numerical attributes of several three-dimensional models included in several driving path segments in the current scene information, obtain the estimated driving time of several driving path segments in the current collection period according to the estimated numerical attributes, obtain the driving path segment distance between the location information of the user terminal and the target three-dimensional model from the several driving path segments The first ten driving paths with the shortest sum of the distances are selected, and the first ten driving paths are marked as candidate driving paths. At the same time, the randomness coefficients of the several driving path segments contained in each candidate driving path are obtained. According to the estimated driving time of the several driving path segments contained in each candidate driving path and the randomness coefficients of the several driving path segments, the stability level of each candidate driving path is obtained, and a stability level threshold is preset to screen out the candidate driving paths with a stability level greater than the stability level threshold. The candidate driving path with the highest stability level is screened out from the candidate driving paths as the recommended driving path. If there is no candidate driving path with a stability level greater than the stability level threshold, the user feature matching mechanism is started.

[0027] Furthermore, the process of obtaining the randomness coefficients of the plurality of driving path segments included in each of the to-be-selected driving paths includes:

[0028] According to the numerical attributes of each three-dimensional model in the current scene information, the pedestrian flow data and parking space usage data of each three-dimensional model are obtained, and the shortest distance between each three-dimensional model and several driving path segments included in each candidate driving path is obtained. According to the pedestrian flow data and parking space usage data of each three-dimensional model and the shortest distance between each three-dimensional model and several driving path segments, the randomness coefficient of several driving path segments included in each candidate driving path is obtained.

[0029] Furthermore, the process in which the service request feedback module starts the user feature matching mechanism, generates the best driving route and feeds back the route to the user terminal includes:

[0030] Extract the historical driving paths of several other user terminals from the local blockchain copy of the blockchain node to which the user terminal is communicatively connected, extract the shortest distance point from the historical driving path to the location information of the user terminal, mark the shortest distance point as the starting point, and mark the distance between the starting point and the location information as the starting point distance, extract the shortest distance point from the historical driving path to the target three-dimensional model of the user terminal, mark the shortest distance point as the end point, and mark the distance between the end point and the location information as the end point distance, screen out the top ten historical driving paths with the shortest sum of the starting point distance and the end point distance, mark the path between the starting point and the end point in the top ten historical driving paths as the target path, obtain the average driving time of several other user terminals on each target path, screen out the target path with the shortest average driving time, mark it as the optimal driving path, and feed it back to the user terminal.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows: the data acquisition module collects multi-source heterogeneous data (such as temperature, humidity, light intensity, etc.) from various IoT monitoring nodes in the target park, and collects identity authentication data, location feature data and service request data from user terminals, and encrypts these data and uploads them to the intelligent operation and maintenance management platform, thereby realizing secure data transmission, protecting user privacy and data security, and collecting rich and diverse data, which helps to understand the status of the park more comprehensively; the operation visualization module uses the collected data to build a digital twin model of the target park to realize the real-time operation status visualization of the park; the identity authentication module is used to verify the identity of the user, ensuring that only authenticated users can access the services provided by the system, and ensuring the security of data and resources; the service request feedback module provides corresponding services according to the user's request, such as real-time monitoring of each three-dimensional model in the digital twin model, correcting the monitoring results according to the security situation report, and providing feedback on the user's service request (such as consultation, traffic recommendation, etc.), which can dynamically adjust the service content according to the user's actual needs and improve the user experience. For traffic recommendation service requests, the best path can be provided according to the actual situation to improve the travel efficiency. At the same time, the user feature matching mechanism further improves the personalization of the service. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a schematic diagram of the Internet-based smart park intelligent operation and maintenance management system of an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0034] like Figure 1 As shown, the intelligent operation and maintenance management system of the smart park based on the Internet includes an intelligent operation and maintenance management platform, and the intelligent operation and maintenance management platform is communicatively connected with a data acquisition module, an operation visualization module, an identity authentication module and a service request feedback module;

[0035] The data acquisition module is used to collect multi-source heterogeneous data of each IoT monitoring node in the target park, as well as identity authentication data, location feature data and service request data of user terminals, and encrypt and upload them to the intelligent operation and maintenance management platform;

[0036] The operation visualization module is used to build a digital twin model of the target park;

[0037] The identity authentication module is used to authenticate the user according to the identity authentication data of the user terminal;

[0038] The service request feedback module is used to construct the current scene information of the digital twin model, monitor each three-dimensional model in the digital twin model in real time according to the current scene information, and perform correction operations on the real-time monitoring results according to the service request data of the safety situation report type, and feedback the service request data of the user consultation service type according to the current scene information, and feedback the recommended driving path for the service request data of the traffic recommendation type. If the recommended driving path does not meet the requirements, the user feature matching mechanism is started to generate the best driving path and feedback it to the user terminal.

[0039] It should be further explained that, in the specific implementation process, the data acquisition module collects multi-source heterogeneous data of each IoT monitoring node of the target park and the identity authentication data, location feature data and service request data of the user terminal and encrypts and uploads them to the intelligent operation and maintenance management platform, including:

[0040] An intelligent operation and maintenance management platform is constructed based on blockchain technology. The intelligent operation and maintenance management platform is communicatively connected with a number of blockchain nodes. The blockchain nodes are linked to each other to form a blockchain network. The blockchain nodes are communicatively connected with various IoT monitoring nodes and user terminals in the target park. The IoT monitoring nodes are used to collect multi-source heterogeneous data within their coverage area and mark the collection time, and set the collection cycle. The multi-source heterogeneous data collected by the IoT monitoring nodes include semantic attributes and numerical attributes of buildings or infrastructure. The user terminals are used to collect user identity authentication data, location feature data, and service request data;

[0041] The public key and private key of the blockchain node corresponding to each IoT monitoring node and the user terminal are preset through an asymmetric encryption algorithm, and the multi-source heterogeneous data of the IoT monitoring node and the identity authentication data, location feature data and service request data of the user terminal are encrypted and transmitted to the blockchain node through the corresponding public key. The blockchain node decrypts the received multi-source heterogeneous data and identity authentication data, location feature data and service request data through the private key, and the accounting node and point-to-point communication protocol of the blockchain network are preset. The decrypted multi-source heterogeneous data and identity authentication data, location feature data and service request data are packaged into a new block through the accounting node, and the new block is broadcast to the entire blockchain network according to the point-to-point communication protocol, the new block is added to the end of the blockchain, and the block information in the new block is updated to the local blockchain copies of all blockchain nodes.

[0042] It should be further explained that, in the specific implementation process, the user terminal includes mobile phones, laptops and other devices, and the user's identity authentication data includes user ID, static password: a password set by the user, usually a string of characters, security questions: security questions pre-set by the user and their answers, biometric features: such as fingerprints, facial recognition, iris scanning, voiceprint recognition, etc.;

[0043] The service request types of user service request data include: consulting services, safety situation reports and traffic recommendation categories. The consulting services include: information consultation on park policies, services, activities, etc., user complaints and suggestions on park services or facilities, environmental consulting requests, etc. Infrastructure requests include facility reservations: reservation requests for conference rooms, activity spaces, gyms and other facilities, equipment borrowing: borrowing requests for office equipment (such as laptops, projectors); safety situation reports include: reports on fires, medical emergencies, etc., abnormal reports on equipment operation data (such as generators, elevators and other equipment), abnormal network traffic reports, etc.; traffic recommendations include: requests to recommend the best path between the user's current location and the target location.

[0044] It should be further explained that, in the specific implementation process, the process of running the visualization module to build the digital twin model of the target park includes:

[0045] Obtain the physical entities of each building and infrastructure in the physical space of the target park, and at the same time obtain the multi-source heterogeneous data collected by the IoT monitoring nodes of each building and infrastructure and perform data format preprocessing to generate twin data;

[0046] The physical entities of each building and infrastructure are three-dimensionally modeled to generate a three-dimensional model, and the twin data is matched with the corresponding three-dimensional model to generate a digital twin model of the target park. At the same time, the location feature data of several user terminals are obtained, and the location information of several user terminals is displayed in real time on the digital twin model based on the location feature data.

[0047] It should be further explained that, in a specific implementation process, the process in which the identity authentication module authenticates the user according to the identity authentication data of the user terminal includes:

[0048] A user identity database is constructed, wherein the user identity database includes identity authentication data of several users, and the identity authentication data of the user received by the blockchain node is matched with the identity authentication data of several users in the user identity database for consistency. If the consistency match is successful, a user identity authentication success instruction is generated, and the user's service request data is fed back. If the consistency match fails, a user identity authentication failure instruction is generated, and the identity authentication failure instruction is sent to the user terminal.

[0049] It should be further explained that, in the specific implementation process, the service request feedback module constructs the current scene information of the digital twin model, and the process of providing feedback on the service request data of the user consulting service class according to the current scene information includes:

[0050] Performing service request type analysis and attribute feature analysis on the user's service request data, extracting the service request type, semantic attributes and numerical attributes of the service request data, wherein the semantic attributes include name: the name of the 3D model, such as building number, facility name, etc., 3D model type: the category of the 3D model, such as office building, residential building, park green space, etc., 3D model location: the specific location coordinates of the 3D model in the park, and 3D model purpose: the functional purpose of the 3D model, such as conference room, restaurant, parking lot, etc.;

[0051] The numerical attributes include: environmental attributes of the three-dimensional model, such as light intensity: light intensity at the location of the model, temperature: temperature at the location of the model, wind speed: wind speed at the location of the model, usage attributes of the three-dimensional model, such as operating capacity of the three-dimensional model, such as passenger flow or vehicle flow, equipment attributes of the three-dimensional model, such as power: rated power, current, voltage, frequency, etc. of the equipment of the three-dimensional model, energy consumption attributes of the three-dimensional model, such as power consumption: power consumption of the three-dimensional model or related equipment, water consumption: water consumption of the three-dimensional model or related equipment, etc.;

[0052] At the same time, the semantic attributes corresponding to each three-dimensional model in the digital twin model are obtained, and the numerical attributes corresponding to each three-dimensional model are obtained according to the twin data corresponding to each three-dimensional model in the digital twin model. At the same time, the estimated numerical attributes of each three-dimensional model are obtained, and the current scene information of the digital twin model is constructed according to the semantic attributes, numerical attributes and estimated numerical attributes corresponding to each three-dimensional model;

[0053] When the service request type of the service request data is a consulting service, the semantic attributes of the service request data are matched with the current scene information, and the numerical attributes and estimated numerical attributes of the three-dimensional model whose semantic attributes are consistent with the semantic attributes of the service request data are obtained and fed back to the user terminal.

[0054] It should be further explained that, in the specific implementation process, the process of obtaining the estimated numerical attributes of each 3D model includes:

[0055] Construct a numerical attribute prediction model based on deep learning, obtain multi-source heterogeneous data collected by each IoT node in several historical collection cycles as a training set and a test set, input the training set into the numerical attribute prediction model for training until the loss function training is stable, and save the model parameters, test the numerical attribute prediction model with the test set until it meets the preset requirements, and output the numerical attribute prediction model;

[0056] According to the numerical attribute prediction model, the estimated numerical time series sequence corresponding to the estimated numerical attributes of each three-dimensional model is output, and then the estimated numerical time series sequence corresponding to the estimated numerical attributes of each three-dimensional model is used as the personalized judgment data of each type of equipment data of each three-dimensional model, avoiding the use of fixed thresholds to judge whether each type of equipment in each three-dimensional model is faulty, reflecting the advantages of the Internet online system and ensuring the accuracy and real-time nature of the monitoring results.

[0057] It should be further explained that, in the specific implementation process, the service request feedback module monitors each three-dimensional model in the digital twin model in real time according to the current scene information, and at the same time corrects the real-time monitoring results according to the service request data of the safety situation report, including:

[0058] When the service request type of the service request data is a safety situation report type, a numerical time series sequence corresponding to each type of equipment data in the numerical attributes of each three-dimensional model in the current scene information is compared with an estimated numerical time series sequence corresponding to each type of equipment data in the estimated numerical attributes in advance, and a numerical difference coefficient of each type of equipment data in the three-dimensional model is obtained, and a numerical difference coefficient threshold is preset. If there is a type of equipment data in the three-dimensional model with a numerical difference coefficient greater than the numerical difference coefficient threshold, the type of equipment data is marked as abnormal type equipment data, and an abnormal alarm label of the abnormal type equipment data is added to the three-dimensional model, and maintenance personnel are arranged to perform emergency maintenance operations according to the abnormal alarm label of the abnormal type equipment data;

[0059] The calculation formula for obtaining the numerical difference coefficient of each type of equipment data in the three-dimensional model is:

[0060] ;

[0061] in, represents the numerical difference coefficient of the i-th type of equipment data in the three-dimensional model, Indicates the value of the i-th type of equipment data in the three-dimensional model at the t-th time. It represents the estimated value of the data of the i-th type of equipment in the three-dimensional model at the t-th time. represents the conversion coefficient, and n represents the total number of time series;

[0062] The semantic attributes and numerical attributes of the service request data are matched with the current scene information to obtain a three-dimensional model in which the semantic attributes in the digital twin model are consistent with the semantic attributes of the service request data. At the same time, the abnormal type equipment data in the service request data is obtained according to the numerical attributes of the service request data. The specific process is as follows: the numerical time series sequence corresponding to each type of equipment data in the numerical attributes of the three-dimensional model corresponding to the service request data is compared with the estimated numerical time series sequence corresponding to each type of equipment data in the estimated numerical attributes to obtain the numerical difference coefficient of each type of equipment data in the three-dimensional model, and a preset numerical difference coefficient threshold is set. If there is a type setting of the three-dimensional model When the numerical difference coefficient of the equipment data is greater than the numerical difference coefficient threshold, the equipment data of the type is marked as abnormal equipment data of the type, and it is determined whether the three-dimensional model has an abnormal alarm label consistent with the abnormal equipment data of the type. If not, the user's reputation value is obtained according to the user's historical service request data, and abnormal situations corresponding to different reputation values ​​are preset. The abnormal situation includes an abnormal situation that may be reported by the user, an abnormal situation that may be caused by a failure of the Internet of Things monitoring node corresponding to the three-dimensional model, an abnormal situation that may be reported by the user, and a combination of abnormal situations that may be caused by a failure of the Internet of Things monitoring node corresponding to the three-dimensional model, and corresponding emergency maintenance measures are set according to the abnormal situation;

[0063] The calculation formula for obtaining the user's reputation value based on the user's historical service request data is:

[0064] ;

[0065] in, represents the reputation value of user j, Indicates the total number of service requests of user j whose service request type is security situation report. represents the total number of abnormal situations in which user j may report errors. represents the total number of combinations of possible abnormal situations of user error reporting by user j and possible abnormal situations of IoT monitoring node failure corresponding to the 3D model, is the conversion factor;

[0066] The abnormal situation corresponding to the current three-dimensional model is determined according to the user's reputation value, and maintenance personnel are arranged to perform emergency maintenance operations according to the emergency maintenance measures corresponding to the abnormal situation. At the same time, the maintenance personnel feedback the actual on-site situation of the three-dimensional model, and the user's reputation value is updated according to the actual on-site situation.

[0067] It should be further explained that, in the specific implementation process, the process of the service request feedback module feeding back the recommended driving route according to the current scene information and the service request data of the traffic recommendation class includes:

[0068] When the service request type of the service request data is a traffic recommendation type, the semantic attributes of the service request data are matched with the current scene information, and a three-dimensional model whose semantic attributes are consistent with the semantic attributes of the service request data in the digital twin model is obtained, and the three-dimensional model is marked as a target three-dimensional model, and several driving path segments between the location information of the user terminal in the digital twin model and the target three-dimensional model are extracted, and at the same time, the numerical attributes and estimated numerical attributes of several three-dimensional models included in the several driving path segments in the current scene information are obtained, and the estimated traffic flow time series sequence of several driving path segments in the current collection period is obtained according to the estimated numerical attributes, and the estimated driving time of several driving path segments in the current collection period is obtained according to the estimated traffic flow time series sequence, and the estimated driving time of several driving path segments in the current collection period is obtained from the several driving path segments. The top ten driving paths with the shortest sum of driving path segment distances between the location information of the user terminal and the target three-dimensional model are obtained, and the top ten driving paths are marked as candidate driving paths. At the same time, the randomness coefficients of the several driving path segments included in each candidate driving path are obtained. According to the estimated driving time of the several driving path segments included in each candidate driving path and the randomness coefficients of the several driving path segments, the stability level of each candidate driving path is obtained, and a stability level threshold is preset to screen out the candidate driving paths with a stability level greater than the stability level threshold. The candidate driving path with the highest stability level is screened out from the candidate driving paths as the recommended driving path. If there is no candidate driving path with a stability level greater than the stability level threshold, the user feature matching mechanism is started.

[0069] It should be further explained that, in the specific implementation process, the calculation formula for obtaining the stability level of each candidate driving path is:

[0070] ;

[0071] in, represents the stability level of the candidate driving path z, represents the estimated travel time of the pth driving path segment in the candidate driving path z, represents the randomness coefficient of the pth driving path segment in the candidate driving path z, represents the conversion factor, Indicates the number of driving path segments contained in the candidate driving path z.

[0072] It should be further explained that, in the specific implementation process, the process of obtaining the random coefficients of the several driving path segments included in each to-be-selected driving path includes:

[0073] According to the numerical attributes of each three-dimensional model in the current scene information, the pedestrian flow data and parking space usage data of each three-dimensional model are obtained, and the shortest distance between each three-dimensional model and several driving path segments included in each candidate driving path is obtained. According to the pedestrian flow data and parking space usage data of each three-dimensional model and the shortest distance between each three-dimensional model and several driving path segments, the randomness coefficient of several driving path segments included in each candidate driving path is obtained.

[0074] It should be further explained that, in the specific implementation process, according to the pedestrian flow data and parking space usage data of each three-dimensional model and the shortest distance between each three-dimensional model and several driving path segments, the calculation formula for obtaining the randomness coefficient of several driving path segments included in each selected driving path is:

[0075] ;

[0076] in, represents the randomness coefficient of the driving path segment e, represents the flow of people data of the three-dimensional model g, represents the parking space usage data of the three-dimensional model g, represents the shortest distance between the 3D model e and the driving path segment e, Represents the total number of 3D models, Indicates the conversion factor.

[0077] It should be further explained that, in the specific implementation process, if the recommended driving route does not meet the requirements, the user feature matching mechanism is started, and the process of generating the best driving route and feeding back to the user terminal includes:

[0078] Extract the historical driving paths of several other user terminals from the local blockchain copy of the blockchain node to which the user terminal is communicatively connected, extract the shortest distance point from the historical driving path to the location information of the user terminal, mark the shortest distance point as the starting point, and mark the distance between the starting point and the location information as the starting point distance, extract the shortest distance point from the historical driving path to the target three-dimensional model of the user terminal, mark the shortest distance point as the end point, and mark the distance between the end point and the location information as the end point distance, screen out the top ten historical driving paths with the shortest sum of the starting point distance and the end point distance, mark the path between the starting point and the end point in the top ten historical driving paths as the target path, obtain the average driving time of several other user terminals on each target path, screen out the target path with the shortest average driving time, mark it as the optimal driving path, and feed it back to the user terminal.

[0079] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The intelligent operation and maintenance management system of the smart park based on the Internet is characterized by: It includes an intelligent operation and maintenance management platform, which is communicatively connected with a data acquisition module, an operation visualization module, an identity authentication module and a service request feedback module; The data acquisition module is used to collect multi-source heterogeneous data of each IoT monitoring node in the target park, as well as identity authentication data, location feature data and service request data of user terminals, and encrypt and upload them to the intelligent operation and maintenance management platform; The operation visualization module is used to build a digital twin model of the target park; The identity authentication module is used to authenticate the user according to the identity authentication data of the user terminal; The service request feedback module is used to construct the current scene information of the digital twin model, monitor each three-dimensional model in the digital twin model in real time according to the current scene information, and perform correction operations on the real-time monitoring results according to the service request data of the safety situation report class, and feedback the service request data of the user consultation service class according to the current scene information, and feedback the recommended driving path for the service request data of the traffic recommendation class. If the recommended driving path does not meet the requirements, the user feature matching mechanism is started to generate the best driving path and feedback it to the user terminal; Among them, the process of constructing the current scene information of the digital twin model and providing feedback on the service request data of the user consulting service class according to the current scene information includes: Perform service request type analysis and attribute feature analysis on the user's service request data, extract the service request type, semantic attributes and numerical attributes of the service request data, and obtain the semantic attributes corresponding to each three-dimensional model in the digital twin model. Obtain the numerical attributes corresponding to each three-dimensional model according to the twin data corresponding to each three-dimensional model in the digital twin model, and obtain the estimated numerical attributes of each three-dimensional model. Construct the current scene information of the digital twin model according to the semantic attributes, numerical attributes and estimated numerical attributes corresponding to each three-dimensional model. When the service request type of the service request data is a consulting service type, the semantic attributes of the service request data are matched with the current scene information, and the numerical attributes and estimated numerical attributes of the three-dimensional model whose semantic attributes are consistent with the semantic attributes of the service request data are obtained and fed back to the user terminal; The process of real-time monitoring of each 3D model in the digital twin model based on the current scene information and correcting the real-time monitoring results based on the service request data of the safety situation report includes: Preliminarily compare the difference between the numerical time series corresponding to each type of equipment data in the numerical attributes of each three-dimensional model in the current scene information and the estimated numerical time series corresponding to each type of equipment data in the estimated numerical attributes, obtain the numerical difference coefficient of each type of equipment data in the three-dimensional model, preset the numerical difference coefficient threshold, and if there is a type of equipment data in the three-dimensional model with a numerical difference coefficient greater than the numerical difference coefficient threshold, mark the type of equipment data as abnormal type equipment data, add an abnormal alarm label of the abnormal type equipment data to the three-dimensional model, and arrange maintenance personnel to perform emergency maintenance operations according to the abnormal alarm label of the abnormal type equipment data; Match the semantic attributes and numerical attributes of the service request data with the current scene information, obtain a three-dimensional model in which the semantic attributes in the digital twin model are consistent with the semantic attributes of the service request data, and at the same time obtain the abnormal type device data in the service request data according to the numerical attributes of the service request data, and determine whether the three-dimensional model has an abnormal alarm label consistent with the abnormal type device data. If not, obtain the user's reputation value according to the user's historical service request data, and preset abnormal situations corresponding to different reputation values; Determine the abnormal situation corresponding to the current 3D model according to the user's reputation value, and arrange maintenance personnel to perform emergency maintenance operations according to the emergency maintenance measures corresponding to the abnormal situation. At the same time, the maintenance personnel feedback the actual situation on site of the 3D model, and update the user's reputation value according to the actual situation on site; The process of recommending a driving route based on the current scene information and traffic recommendation service request data feedback includes: Match the semantic attributes of the service request data with the current scene information, obtain a three-dimensional model in the digital twin model whose semantic attributes are consistent with the semantic attributes of the service request data, mark the three-dimensional model as the target three-dimensional model, extract the location information of the user terminal in the digital twin model and several driving path segments between the target three-dimensional model, and simultaneously obtain the numerical attributes and estimated numerical attributes of several three-dimensional models included in several driving path segments in the current scene information, obtain the estimated driving time of several driving path segments in the current collection period according to the estimated numerical attributes, obtain the driving path segment distance between the location information of the user terminal and the target three-dimensional model from the several driving path segments The first ten driving paths with the shortest sum of the distances are selected, and the first ten driving paths are marked as candidate driving paths. At the same time, the randomness coefficients of the several driving path segments contained in each candidate driving path are obtained. According to the estimated driving time of the several driving path segments contained in each candidate driving path and the randomness coefficients of the several driving path segments, the stability level of each candidate driving path is obtained, and a stability level threshold is preset to screen out the candidate driving paths with a stability level greater than the stability level threshold. The candidate driving path with the highest stability level is screened out from the candidate driving paths as the recommended driving path. If there is no candidate driving path with a stability level greater than the stability level threshold, the user feature matching mechanism is started.

2. The Internet-based intelligent operation and maintenance management system for smart parks according to claim 1 is characterized in that: The process of the data acquisition module collecting multi-source heterogeneous data of each IoT monitoring node in the target park and the identity authentication data, location feature data and service request data of the user terminal and encrypting and uploading them to the intelligent operation and maintenance management platform includes: An intelligent operation and maintenance management platform is constructed based on blockchain technology. The intelligent operation and maintenance management platform is connected to a number of blockchain nodes, which are linked to each other to form a blockchain network. The blockchain nodes are connected to each IoT monitoring node and user terminal in the target park. The IoT monitoring node is used to collect multi-source heterogeneous data within its coverage area and mark the collection time and set the collection cycle. The user terminal is used to collect the user's identity authentication data, location feature data and service request data; The public key and private key of the blockchain node corresponding to each IoT monitoring node and the user terminal are preset through an asymmetric encryption algorithm, and the multi-source heterogeneous data of the IoT monitoring node and the identity authentication data, location feature data and service request data of the user terminal are encrypted and transmitted to the blockchain node through the corresponding public key. The blockchain node decrypts the received multi-source heterogeneous data and identity authentication data, location feature data and service request data through the private key, and the accounting node and point-to-point communication protocol of the blockchain network are preset. The decrypted multi-source heterogeneous data and identity authentication data, location feature data and service request data are packaged into a new block through the accounting node, and the new block is broadcast to the entire blockchain network according to the point-to-point communication protocol, the new block is added to the end of the blockchain, and the block information in the new block is updated to the local blockchain copies of all blockchain nodes.

3. The Internet-based intelligent operation and maintenance management system for smart parks according to claim 2 is characterized in that: The process of running the visualization module to build a digital twin model of the target park includes: Obtain the physical entities of each building and infrastructure in the physical space of the target park, and at the same time obtain the multi-source heterogeneous data collected by the IoT monitoring nodes of each building and infrastructure and perform data format preprocessing to generate twin data; The physical entities of each building and infrastructure are three-dimensionally modeled to generate a three-dimensional model, and the twin data is matched with the corresponding three-dimensional model to generate a digital twin model of the target park. At the same time, the location feature data of several user terminals are obtained, and the location information of several user terminals is displayed in real time on the digital twin model based on the location feature data.

4. The Internet-based intelligent operation and maintenance management system for smart parks according to claim 3 is characterized in that: The process of the identity authentication module authenticating the user according to the identity authentication data of the user terminal includes: A user identity database is constructed, wherein the user identity database includes identity authentication data of several users, and the identity authentication data of the user received by the blockchain node is matched with the identity authentication data of several users in the user identity database for consistency. If the consistency match is successful, a user identity authentication success instruction is generated, and the user's service request data is fed back. If the consistency match fails, a user identity authentication failure instruction is generated, and the identity authentication failure instruction is sent to the user terminal.

5. The Internet-based intelligent operation and maintenance management system for smart parks according to claim 4 is characterized in that: The process of obtaining the random coefficients of several driving path segments included in each candidate driving path includes: According to the numerical attributes of each three-dimensional model in the current scene information, the pedestrian flow data and parking space usage data of each three-dimensional model are obtained, and the shortest distance between each three-dimensional model and several driving path segments included in each candidate driving path is obtained. According to the pedestrian flow data and parking space usage data of each three-dimensional model and the shortest distance between each three-dimensional model and several driving path segments, the randomness coefficient of several driving path segments included in each candidate driving path is obtained.

6. The Internet-based intelligent operation and maintenance management system for smart parks according to claim 5 is characterized in that: The process in which the service request feedback module starts the user feature matching mechanism, generates the best driving path and feeds back to the user terminal includes: Extract the historical driving paths of several other user terminals from the local blockchain copy of the blockchain node to which the user terminal is communicatively connected, extract the shortest distance point from the historical driving path to the location information of the user terminal, mark the shortest distance point as the starting point, and mark the distance between the starting point and the location information as the starting point distance, extract the shortest distance point from the historical driving path to the target three-dimensional model of the user terminal, mark the shortest distance point as the end point, and mark the distance between the end point and the location information as the end point distance, screen out the top ten historical driving paths with the shortest sum of the starting point distance and the end point distance, mark the path between the starting point and the end point in the top ten historical driving paths as the target path, obtain the average driving time of several other user terminals on each target path, screen out the target path with the shortest average driving time, mark it as the optimal driving path, and feed it back to the user terminal.

Images