Intelligent management method and system for access control equipment based on the Internet of Things

Through IoT technology and data analysis, the sub-regions of the cell are divided, outliers and historical data correlations are handled, the failure rate of access control equipment is predicted, and the maintenance cycle is adjusted. The problems of insufficient monitoring and fixed maintenance cycles in traditional access control equipment management are solved, and the problems of insufficient monitoring and fixed maintenance cycles are improved. Equipment stability and management efficiency.

CN117764562BActive Publication Date: 2024-11-01HUNAN KUNTIAN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410193378.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-21
Publication Date
2024-11-01
Estimated Expiration
2044-02-21

AI Technical Summary

Technical Problem

Traditional access control equipment management has insufficient monitoring and maintenance management of equipment working status, weak fault prediction capabilities, and fixed maintenance cycles are difficult to adjust according to actual conditions, resulting in high risk of equipment failure.

Method used

The Internet of Things technology is used to divide the cell sub-regions, and the LOF algorithm is used to process outliers and gray correlation analysis methods to mine historical data correlation, predict failure rates, adjust maintenance cycles, and form an intelligent access control equipment management method.

Benefits of technology

Through intelligent management methods, the equipment maintenance costs are reduced, the stability and reliability of the access control system are improved, and a more scientific and reasonable maintenance plan is achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117764562B_ABST
    Figure CN117764562B_ABST
Patent Text Reader

Abstract

The present invention discloses an intelligent management method and system for access control equipment based on the Internet of Things, aiming to improve the management efficiency and maintenance prediction capability of access control equipment. First, the data transmission distance information of the access control equipment in each sub-area of ​​the target community is obtained, and an access control equipment management system is constructed through the Internet of Things technology. The working data of the access control equipment is obtained in the system, and the LOF algorithm is used to perform outlier analysis to process the outliers. The associated data is obtained through the historical use and working data using the gray correlation analysis method. Based on the associated data and the working data after the outlier processing, the maintenance cycle of the access control equipment in each sub-area is predicted using the predicted failure rate data to form an intelligent maintenance management plan for the access control equipment. By integrating the Internet of Things technology and data analysis means, the method realizes the intelligent management of access control equipment, improves the management efficiency and the accuracy of equipment maintenance, and has broad application prospects.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of access control equipment management, and in particular to an access control equipment intelligent management method and system based on the Internet of Things. Background Art

[0002] With the development of society, access control equipment has been widely used in various places, such as residential areas, enterprises, schools, etc. However, there are some problems in the management of traditional access control equipment, including insufficient monitoring and maintenance management of the working status of the equipment, and weak prediction ability of equipment failure. Usually, the maintenance cycle of access control equipment is often too fixed, and it is difficult to make scientific and reasonable adjustments based on the actual working conditions and equipment health status.

[0003] The current access control equipment management method is often based only on traditional time scheduling and maintenance plans, and cannot achieve in-depth analysis of equipment working data. Therefore, a access control equipment management method that can fully utilize Internet of Things technology, data analysis and intelligent algorithms is needed to improve the intelligence and real-time nature of management and reduce the risk of equipment failure.

[0004] The present invention divides the community into sub-areas through the Internet of Things technology, uses the LOF algorithm to process the abnormal values ​​of the working data, and mines the correlation of historical data through the gray correlation analysis method, thereby realizing the intelligent management of access control equipment. The present invention effectively reduces the equipment maintenance cost and improves the stability and reliability of the access control system by comprehensively analyzing the equipment data, predicting the failure rate, and adjusting the maintenance cycle. Therefore, the present invention has significant innovation and practical value in the field of intelligent access control management. Summary of the invention

[0005] In order to solve at least one of the above technical problems, the present invention proposes an intelligent management method and system for access control equipment based on the Internet of Things.

[0006] The first aspect of the present invention provides an intelligent management method for access control equipment based on the Internet of Things, comprising:

[0007] Divide the target community into N sub-areas, obtain the data transmission distance information of the access control equipment in each sub-area, and build the access control equipment management system of the target community based on the Internet of Things technology;

[0008] Acquiring access control device working data based on the access control device management system, and performing outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data;

[0009] Obtain historical access control device usage data and working status data, analyze the correlation between the access control device usage and working status according to the grey correlation analysis method, and obtain correlation data;

[0010] Predicting the probability of failure of the access control device according to the associated data and the working data after outlier processing to obtain predicted failure rate data;

[0011] A maintenance period is determined for the access control equipment in each sub-area according to the predicted failure rate data, and a maintenance management plan for the access control equipment is obtained.

[0012] In this solution, the target cell is divided into N sub-areas, the data transmission distance information of the access control equipment in each sub-area is obtained, and the access control equipment management system of the target cell is constructed based on the Internet of Things technology, specifically:

[0013] S1, obtaining a plan view of a target cell, dividing the target cell into N sub-areas according to the plan view, obtaining data wireless transmission distance information of access control equipment and installation location information of access control equipment in each sub-area, wherein the data wireless transmission distance information includes transmission distance and communication strength;

[0014] S2, introducing a simulated annealing algorithm, presetting an initial temperature, cooling rate, and number of iterations of the simulated degradation algorithm, randomly generating a location of a data transfer server in each sub-region based on the initial temperature, cooling rate, and number of iterations, and obtaining an initial solution of the simulated annealing algorithm;

[0015] S3, calculating the Euclidean distance of the access control device in each sub-area to the corresponding initial solution, and determining the communication range of the access control device according to the transmission distance and communication strength of the access control device;

[0016] S4, constructing an objective function according to the Euclidean distance and the communication strength of the access control device, and generating a new solution of the simulated annealing algorithm according to the initial temperature and the cooling rate;

[0017] S5, according to the Metropolis criterion, calculate the probability of accepting the new solution. If the probability is greater than the preset value, replace the initial solution of the simulated annealing algorithm with the new solution, and calculate the objective function of the new solution. If the probability is less than the preset value, discard the new solution.

[0018] S6, looping through S4 to S5, and when the number of loops reaches the preset number of iterations of the simulated annealing algorithm, stopping the loop to obtain a final solution of the simulated annealing algorithm, wherein the final solution is the location of the data transfer server;

[0019] S7, analyzing the location of the data transfer server in each sub-area according to the simulated annealing algorithm, determining the setting location of the data terminal server in the target cell, and building a door access control equipment management system for the target cell based on the location of the data transfer server and the data terminal server in each sub-area and the Internet of Things technology.

[0020] In this solution, the access control device management system obtains the access control device working data, and performs outlier analysis on the working data based on the LOF algorithm to process the abnormal values ​​of the working data, specifically:

[0021] Based on the access control device management system, the access control device working data of each sub-area is obtained, where the access control device working data includes user access records and access control device status information of each access control device;

[0022] The LOF algorithm is introduced, and the parameters of the LOF algorithm are preset, wherein the parameters include the number of neighbors K and the distance measurement method, and the local outlier factor of each data point in the working data of the access control device is calculated based on the LOF algorithm;

[0023] Preset an outlier threshold, compare the local outlier factor of each data point with the preset outlier threshold, and mark the data point whose local outlier factor is greater than the preset outlier threshold as an outlier;

[0024] A data mean replacement operation is performed on the abnormal value to obtain the access control device working data of each sub-area after the data abnormal value is processed.

[0025] In this solution, the usage data and working status data of the historical access control equipment are obtained, and the correlation between the usage and working status of the access control equipment is analyzed according to the grey correlation analysis method to obtain the correlation data, which is specifically:

[0026] Obtaining historical usage data and working status data of access control equipment, wherein the usage data includes the access control switch frequency, and the working status data includes the normal working status and fault status of the access control;

[0027] Converting the usage data and the working status data into time series data, aligning the usage data and the working status data based on the time series, and standardizing the usage data and the working status data based on the Z-score method to obtain usage sequence data and working status sequence data;

[0028] Calculate the correlation coefficients of the usage sequence data and the working status sequence data according to the grey correlation analysis method, sort the correlation coefficients according to the time series, and obtain a correlation coefficient matrix;

[0029] The correlation level between the usage and working status of the access control device is determined according to the correlation coefficient matrix, and the correlation data between the usage and working status of the access control device is obtained, wherein the correlation data includes the correlation coefficient matrix and the correlation level.

[0030] In this solution, the failure probability of the access control device is predicted based on the associated data and the working data after the abnormal value processing to obtain the predicted failure rate data, which is specifically:

[0031] Building a fault probability prediction model for access control equipment based on LSTM, dividing the usage sequence data and the working status sequence data into a training set and a test set;

[0032] Select mean square error as the loss function of the model, select Adam optimization algorithm as the optimizer of the model, configure the loss function and optimizer into the model and compile the model;

[0033] The training set is imported into the fault probability prediction model for training, the associated data is used as the probability prediction basis of the prediction model, and the model parameters are updated through back propagation and gradient descent to reduce the loss function, thereby obtaining the trained fault probability prediction model;

[0034] Importing the test set into the trained fault occurrence probability model, evaluating the prediction ability of the model, and adjusting the model parameters according to the prediction ability;

[0035] According to the working data after outlier processing, the current usage data of the access control equipment in each sub-area is counted, and the current usage data is imported into the failure probability prediction model to predict the failure probability of the access control equipment in each sub-area and obtain the predicted failure rate data.

[0036] In this solution, the maintenance cycle of the access control equipment in each sub-area is determined according to the predicted failure rate data to obtain a maintenance management solution for the access control equipment, which is specifically:

[0037] Determine the maintenance level of the access control equipment in each sub-area according to the predicted failure rate data of the access control equipment in each sub-area of ​​the target community;

[0038] Determine the maintenance priority of the access control equipment in each sub-area according to the maintenance level to obtain a priority scheme;

[0039] The maintenance period of the access control equipment in each sub-area is determined based on the predicted failure rate data, and the maintenance period and the priority scheme are combined to obtain a maintenance management scheme for the access control equipment.

[0040] The second aspect of the present invention further provides an access control device intelligent management system based on the Internet of Things, the system comprising: a memory, a processor, the memory comprising an access control device intelligent management method program based on the Internet of Things, and when the access control device intelligent management method program based on the Internet of Things is executed by the processor, the following steps are implemented:

[0041] Divide the target community into N sub-areas, obtain the data transmission distance information of the access control equipment in each sub-area, and build the access control equipment management system of the target community based on the Internet of Things technology;

[0042] Acquiring access control device working data based on the access control device management system, and performing outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data;

[0043] Obtain historical access control device usage data and working status data, analyze the correlation between the access control device usage and working status according to the grey correlation analysis method, and obtain correlation data;

[0044] Predicting the probability of failure of the access control device according to the associated data and the working data after outlier processing to obtain predicted failure rate data;

[0045] A maintenance period is determined for the access control equipment in each sub-area according to the predicted failure rate data, and a maintenance management plan for the access control equipment is obtained.

[0046] In this solution, the usage data and working status data of the historical access control equipment are obtained, and the correlation between the usage and working status of the access control equipment is analyzed according to the grey correlation analysis method to obtain the correlation data, which is specifically:

[0047] Obtaining historical usage data and working status data of access control equipment, wherein the usage data includes the access control switch frequency, and the working status data includes the normal working status and fault status of the access control;

[0048] Converting the usage data and the working status data into time series data, aligning the usage data and the working status data based on the time series, and standardizing the usage data and the working status data based on the Z-score method to obtain usage sequence data and working status sequence data;

[0049] Calculate the correlation coefficients of the usage sequence data and the working status sequence data according to the grey correlation analysis method, sort the correlation coefficients according to the time series, and obtain a correlation coefficient matrix;

[0050] The correlation level between the usage and working status of the access control device is determined according to the correlation coefficient matrix, and the correlation data between the usage and working status of the access control device is obtained, wherein the correlation data includes the correlation coefficient matrix and the correlation level.

[0051] In this solution, the failure probability of the access control device is predicted based on the associated data and the working data after the abnormal value processing to obtain the predicted failure rate data, which is specifically:

[0052] Building a fault probability prediction model for access control equipment based on LSTM, dividing the usage sequence data and the working status sequence data into a training set and a test set;

[0053] Select mean square error as the loss function of the model, select Adam optimization algorithm as the optimizer of the model, configure the loss function and optimizer into the model and compile the model;

[0054] The training set is imported into the fault probability prediction model for training, the associated data is used as the probability prediction basis of the prediction model, and the model parameters are updated through back propagation and gradient descent to reduce the loss function, thereby obtaining the trained fault probability prediction model;

[0055] Importing the test set into the trained fault occurrence probability model, evaluating the prediction ability of the model, and adjusting the model parameters according to the prediction ability;

[0056] According to the working data after outlier processing, the current usage data of the access control equipment in each sub-area is counted, and the current usage data is imported into the failure probability prediction model to predict the failure probability of the access control equipment in each sub-area and obtain the predicted failure rate data.

[0057] In this solution, the maintenance cycle of the access control equipment in each sub-area is determined according to the predicted failure rate data to obtain a maintenance management solution for the access control equipment, which is specifically:

[0058] Determine the maintenance level of the access control equipment in each sub-area according to the predicted failure rate data of the access control equipment in each sub-area of ​​the target community;

[0059] Determine the maintenance priority of the access control equipment in each sub-area according to the maintenance level to obtain a priority scheme;

[0060] The maintenance period of the access control equipment in each sub-area is determined based on the predicted failure rate data, and the maintenance period and the priority scheme are combined to obtain a maintenance management scheme for the access control equipment.

[0061] The present invention discloses an intelligent management method and system for access control equipment based on the Internet of Things, aiming to improve the management efficiency and maintenance prediction capability of access control equipment. First, the data transmission distance information of the access control equipment in each sub-area of ​​the target community is obtained, and an access control equipment management system is constructed through the Internet of Things technology. The working data of the access control equipment is obtained in the system, and the LOF algorithm is used to perform outlier analysis to process the outliers. The associated data is obtained through the historical use and working data using the gray correlation analysis method. Based on the associated data and the working data after the outlier processing, the maintenance cycle of the access control equipment in each sub-area is predicted using the predicted failure rate data to form an intelligent maintenance management plan for the access control equipment. By integrating the Internet of Things technology and data analysis means, the method realizes the intelligent management of access control equipment, improves the management efficiency and the accuracy of equipment maintenance, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flow chart of an intelligent management method for access control equipment based on the Internet of Things is shown in the present invention;

[0063] Figure 2 A flow chart showing the method of obtaining predicted failure rate data;

[0064] Figure 3 A flow chart showing a maintenance and management scheme for access control equipment obtained by the present invention is shown;

[0065] Figure 4 A block diagram of an Internet of Things-based access control equipment intelligent management system of the present invention is shown. DETAILED DESCRIPTION

[0066] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0068] Figure 1 The flowchart of the intelligent management method of access control equipment based on the Internet of Things of the present invention is shown.

[0069] like Figure 1 As shown, the first aspect of the present invention provides an intelligent management method for access control equipment based on the Internet of Things, comprising:

[0070] S102, dividing the target cell into N sub-areas, obtaining data transmission distance information of access control equipment in each sub-area, and building an access control equipment management system for the target cell based on the Internet of Things technology;

[0071] S104, acquiring access control device working data based on the access control device management system, and performing outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data;

[0072] S106, obtaining historical usage data and working status data of access control devices, analyzing the correlation between the usage and working status of the access control devices according to a grey correlation analysis method, and obtaining correlation data;

[0073] S108, predicting the probability of failure of the access control device according to the associated data and the working data after outlier processing, to obtain predicted failure rate data;

[0074] S110, determining a maintenance period for the access control equipment in each sub-area according to the predicted failure rate data, and obtaining a maintenance management plan for the access control equipment.

[0075] It should be noted that by dividing the target community into N sub-areas, we can understand the differences in each area in more detail, and supervise the access control equipment in each sub-area according to the actual situation; constructing an access control equipment management system based on the Internet of Things technology enables access control managers to remotely control access control equipment and improve management efficiency; since the data received by the access control equipment management system is transmitted wirelessly, the influence of the environment may cause transmission interference, which may lead to abnormal data in the access control equipment management system. The LOF algorithm is used to process the abnormal value of the access control equipment working data obtained from the access control equipment management system, which greatly improves the accuracy of the data and lays the foundation for subsequent data analysis; in the actual access control equipment management system, the data received by the access control equipment management system is transmitted wirelessly, which may cause transmission interference due to environmental influences, and thus lead to abnormal data in the access control equipment management system. In the use of access control equipment, the working condition of the access control equipment is often closely related to the use of the access control. The use and working condition of the access control equipment are correlated and analyzed by the grey correlation analysis method to identify the potential correlation between the use and working condition of the access control equipment, and the failure rate of the access control equipment in each sub-area is predicted through the potential correlation, and finally the maintenance cycle of the access control equipment in each sub-area is determined. The maintenance cycle can be determined according to the actual use of the access control equipment, which improves the flexibility of maintenance, minimizes the maintenance cost, and avoids unnecessary losses due to the failure of the access control equipment. The access control equipment includes the access control equipment and building access control equipment of each household in each sub-area of ​​the target community.

[0076] According to an embodiment of the present invention, the target cell is divided into N sub-areas, the data transmission distance information of the access control equipment in each sub-area is obtained, and the access control equipment management system of the target cell is constructed based on the Internet of Things technology, specifically:

[0077] S1, obtaining a plan view of a target cell, dividing the target cell into N sub-areas according to the plan view, obtaining data wireless transmission distance information of access control equipment and installation location information of access control equipment in each sub-area, wherein the data wireless transmission distance information includes transmission distance and communication strength;

[0078] S2, introducing a simulated annealing algorithm, presetting an initial temperature, cooling rate, and number of iterations of the simulated degradation algorithm, randomly generating a location of a data transfer server in each sub-region based on the initial temperature, cooling rate, and number of iterations, and obtaining an initial solution of the simulated annealing algorithm;

[0079] S3, calculating the Euclidean distance of the access control device in each sub-area to the corresponding initial solution, and determining the communication range of the access control device according to the transmission distance and communication strength of the access control device;

[0080] S4, constructing an objective function according to the Euclidean distance and the communication strength of the access control device, and generating a new solution of the simulated annealing algorithm according to the initial temperature and the cooling rate;

[0081] S5, according to the Metropolis criterion, calculate the probability of accepting the new solution. If the probability is greater than the preset value, replace the initial solution of the simulated annealing algorithm with the new solution, and calculate the objective function of the new solution. If the probability is less than the preset value, discard the new solution.

[0082] S6, looping through S4 to S5, and when the number of loops reaches the preset number of iterations of the simulated annealing algorithm, stopping the loop to obtain a final solution of the simulated annealing algorithm, wherein the final solution is the location of the data transfer server;

[0083] S7, analyzing the location of the data transfer server in each sub-area according to the simulated annealing algorithm, determining the setting location of the data terminal server in the target cell, and building a door access control equipment management system for the target cell based on the location of the data transfer server and the data terminal server in each sub-area and the Internet of Things technology.

[0084] It should be noted that, due to the large scope of the target cell, the access control device data cannot be transmitted over long distances through wireless transmission, resulting in abnormal data transmission. Therefore, the simulated annealing algorithm is introduced to comprehensively consider the wireless transmission distance, communication strength and communication range of the access control device data in each sub-area, determine the data transfer server in each sub-area, and perform transfer operations on the access control device data in each sub-area, which helps to quickly and reliably transmit the data from the source to the destination; finally, the data of the data transfer server needs to be centrally operated, so the simulated annealing algorithm is used to analyze the location of the data transfer server in each sub-area, determine the setting location of the optimal data terminal server in the target cell, and build an access control device management system based on the Internet of Things according to the setting location of the server, so as to achieve the role of load balancing of multiple data servers, avoid overloading of a single server, and help improve the overall performance and stability of the system; the objective function comprehensively considers the transmission distance and communication strength of the access control device. The objective function is the sum of the communication strength of each access control device in a single sub-area multiplied by the Euclidean distance, which is the overall communication strength and transmission distance of the sub-area; the Metropolis criterion is a rule for accepting or rejecting state transfer. The simulated annealing algorithm is a global optimization algorithm that simulates the thermal motion of atoms in metals during cooling. The role of the Metropolis criterion in the simulated annealing algorithm is to accept or reject new states according to certain probability rules to perform random walks in the search space to find the global optimal solution.

[0085] According to an embodiment of the present invention, the access control device management system obtains access control device working data, and performs outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data, specifically:

[0086] Based on the access control device management system, the access control device working data of each sub-area is obtained, where the access control device working data includes user access records and access control device status information of each access control device;

[0087] The LOF algorithm is introduced, and the parameters of the LOF algorithm are preset, wherein the parameters include the number of neighbors K and the distance measurement method, and the local outlier factor of each data point in the working data of the access control device is calculated based on the LOF algorithm;

[0088] Preset an outlier threshold, compare the local outlier factor of each data point with the preset outlier threshold, and mark the data point whose local outlier factor is greater than the preset outlier threshold as an outlier;

[0089] A data mean replacement operation is performed on the abnormal value to obtain the access control device working data of each sub-area after the data abnormal value is processed.

[0090] It should be noted that outlier analysis of the working data of the access control device through the LOF algorithm can identify data points in the data set that have abnormal behavior relative to their surrounding neighborhoods. By identifying potential anomalies, the special circumstances and abnormal behaviors of the data set can be better understood; by accurately identifying outliers, the false alarm rate can be reduced to avoid incorrectly marking normal data as abnormal; the user access record includes entry and exit time, and the access control device status information includes the communication status with the access control device management system, and the access control opening and closing status information; the distance measurement method is Manhattan distance; the local outlier factor is the value obtained by comparing the local density of a data point with the local density of other points in the neighborhood.

[0091] According to an embodiment of the present invention, the acquisition of historical access control device usage data and working status data, and the analysis of the correlation between the access control device usage and working status according to the grey correlation analysis method to obtain the correlation data are specifically:

[0092] Obtaining historical usage data and working status data of access control equipment, wherein the usage data includes the access control switch frequency, and the working status data includes the normal working status and fault status of the access control;

[0093] Converting the usage data and the working status data into time series data, aligning the usage data and the working status data based on the time series, and standardizing the usage data and the working status data based on the Z-score method to obtain usage sequence data and working status sequence data;

[0094] Calculate the correlation coefficients of the usage sequence data and the working status sequence data according to the grey correlation analysis method, sort the correlation coefficients according to the time series, and obtain a correlation coefficient matrix;

[0095] The correlation level between the usage and working status of the access control device is determined according to the correlation coefficient matrix, and the correlation data between the usage and working status of the access control device is obtained, wherein the correlation data includes the correlation coefficient matrix and the correlation level.

[0096] It should be noted that by using the grey correlation analysis method to conduct correlation analysis on the usage data and working status data of historical access control devices, the correlation relationship between the usage and working status of access control devices can be identified, which can effectively understand the impact of the usage of access control devices on the working status, and provide a prediction basis for subsequent fault prediction; the Z-score is a standardization method that converts data with different scales or different units into a standard normal distribution with the same mean and standard deviation, so that the values ​​of different variables can be compared and analyzed on the same scale; the elements in the correlation coefficient matrix represent the correlation coefficients between different sequences, that is, their degree of correlation, which helps to quantify the similarity between sequences and reflects the correlation relationship between the usage sequence data and the working status sequence data.

[0097] Figure 2 A flow chart of obtaining predicted failure rate data according to the present invention is shown.

[0098] According to an embodiment of the present invention, the probability of failure of the access control device is predicted based on the associated data and the working data after outlier processing to obtain predicted failure rate data, specifically:

[0099] S202, constructing a fault probability prediction model for the access control device based on LSTM, and dividing the usage sequence data and the working status sequence data into a training set and a test set;

[0100] S204, selecting mean square error as the loss function of the model, selecting Adam optimization algorithm as the optimizer of the model, configuring the loss function and the optimizer into the model to compile the model;

[0101] S206, importing the training set into the fault occurrence probability prediction model for training, using the associated data as the probability prediction basis of the prediction model, and updating the model parameters through back propagation and gradient descent to reduce the loss function, thereby obtaining a trained fault occurrence probability prediction model;

[0102] S208, importing the test set into the trained fault probability model, evaluating the prediction ability of the model, and adjusting the model parameters according to the prediction ability;

[0103] S210, collecting statistics on the current usage data of the access control equipment in each sub-area based on the working data after outlier processing, importing the current usage data into a failure probability prediction model, predicting the failure probability of the access control equipment in each sub-area, and obtaining predicted failure rate data.

[0104] It should be noted that a failure probability prediction model for access control equipment is constructed through an LSTM network, and the associated data is used as the prediction basis of the failure probability prediction model. The failure probability of the access control equipment in each sub-area is predicted based on the current usage data of the access control equipment in each sub-area. The equipment that may fail can be known in advance, and regular inspection and maintenance can be carried out to reduce sudden failures of the equipment and extend the service life of the equipment. Appropriate measures can be taken before the equipment fails to avoid downtime caused by equipment failure, which helps to ensure the normal operation of the access control equipment and improve the reliability and stability of the system.

[0105] Figure 3 The flowchart of the access control equipment maintenance management scheme obtained by the present invention is shown.

[0106] According to an embodiment of the present invention, the maintenance cycle of the access control equipment in each sub-area is determined according to the predicted failure rate data to obtain a maintenance management plan for the access control equipment, specifically:

[0107] S302, determining the maintenance level of the access control equipment in each sub-area of ​​the target community according to the predicted failure rate data of the access control equipment in each sub-area;

[0108] S304, determining the maintenance priority of the access control equipment in each sub-area according to the maintenance level, and obtaining a priority scheme;

[0109] S306, determining a maintenance period for access control equipment in each sub-area based on the predicted failure rate data, and combining the maintenance period with a priority scheme to obtain a maintenance management scheme for access control equipment.

[0110] It should be noted that by determining the maintenance priority and maintenance cycle of the access control equipment in each sub-area through the predicted failure rate data of the access control equipment in each sub-area, maintenance resources can be allocated more effectively, and high-priority equipment can receive more frequent and urgent maintenance, thereby optimizing overall resource utilization; determining the maintenance cycle and priority of access control equipment helps to reasonably arrange maintenance plans, reduce the frequency of emergency repairs, and thus reduce overall maintenance costs. Planning maintenance in advance can avoid additional costs incurred by emergency repairs.

[0111] According to an embodiment of the present invention, it also includes:

[0112] Based on the access control device management system, the usage data of the access control device of each household in each sub-area is obtained, and the usage frequency and usage time data of the access control device of each household are calculated and counted according to the usage data to obtain the usage characteristic data of the access control device;

[0113] Based on the K-means clustering algorithm, the classification level of the K-means clustering algorithm is set, and the access control device usage feature data is clustered according to the usage frequency to obtain usage frequency clustering data;

[0114] Perform thermal analysis on the usage time data in the access control device usage feature data to determine the usage hotspot time of each residential access control device and obtain the usage time characteristics of each residential access control device;

[0115] Classifying each residential user into a permanent user and a non-permanent user according to the usage frequency clustering data and the usage time characteristic data;

[0116] The maintenance cycle of the residential access control equipment corresponding to the non-resident user is reduced, which supplements the access control equipment maintenance management plan.

[0117] It should be noted that since some residential users in the target community are not permanent residents and since the maintenance and management resources of the target community's access control equipment are limited, the usage data of the access control equipment in each residence is obtained through the access control equipment management system. The access control equipment usage characteristic data is clustered according to the usage frequency based on the K-means clustering algorithm. The access control equipment with a usage frequency within a preset range is classified into one category, and the usage time of each household's access control equipment is analyzed. Based on the usage frequency clustering data and usage time characteristics of the access control equipment, it is determined whether each residential user is a permanent user or a non-permanent user. The maintenance cycle and maintenance frequency are reduced for non-permanent users, which further saves the target community's maintenance resources and maintenance costs for access control equipment.

[0118] According to an embodiment of the present invention, it also includes:

[0119] Link the target community’s video surveillance system to the access control equipment management system based on the Internet of Things to form the target community’s Internet of Things network;

[0120] Acquire video stream data of a target cell according to the Internet of Things network, extract video frames from the video stream data, and extract key features of the video frames based on an image recognition algorithm, wherein the key features include color information, object motion information, and illumination change information;

[0121] Predefine image features of emergency events, compare the key features with the image features of emergency events, determine whether an emergency event exists, and obtain a recognition result;

[0122] If an emergency event exists, determining the location and urgency of the emergency event based on the identification result, and determining the impact scope of the emergency event based on the location and urgency of the emergency event;

[0123] According to the influence range, a door access control operation is performed on the door access control equipment of the target cell within the influence range to obtain an emergency door access control equipment control strategy.

[0124] It should be noted that emergency incidents may occur in the target community. By integrating the community's video surveillance system into the access control equipment management system built based on the Internet of Things, an Internet of Things network is formed. The video stream data of the target community is obtained through the Internet of Things network, and the emergency incidents in the target community are identified based on the video stream data. The location, urgency, and impact range of the emergency incidents are determined, and finally a control strategy for the emergency access control equipment is formulated. According to the control strategy, the access control is released in the event of an emergency, which can greatly reduce the time for people to take shelter, maximize the safety of people, and enable emergency handling personnel to quickly reach the location of the incident for processing.

[0125] Figure 4 A block diagram of an Internet of Things-based access control equipment intelligent management system of the present invention is shown.

[0126] The second aspect of the present invention further provides an access control device intelligent management system 4 based on the Internet of Things, the system comprising: a memory 41, a processor 42, the memory comprising an access control device intelligent management method program based on the Internet of Things, the access control device intelligent management method program based on the Internet of Things being executed by the processor to implement the following steps:

[0127] Divide the target community into N sub-areas, obtain the data transmission distance information of the access control equipment in each sub-area, and build the access control equipment management system of the target community based on the Internet of Things technology;

[0128] Acquiring access control device working data based on the access control device management system, and performing outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data;

[0129] Obtain historical access control device usage data and working status data, analyze the correlation between the access control device usage and working status according to the grey correlation analysis method, and obtain correlation data;

[0130] Predicting the probability of failure of the access control device according to the associated data and the working data after outlier processing to obtain predicted failure rate data;

[0131] A maintenance period is determined for the access control equipment in each sub-area according to the predicted failure rate data, and a maintenance management plan for the access control equipment is obtained.

[0132] According to an embodiment of the present invention, the target cell is divided into N sub-areas, the data transmission distance information of the access control equipment in each sub-area is obtained, and the access control equipment management system of the target cell is constructed based on the Internet of Things technology, specifically:

[0133] S1, obtaining a plan view of a target cell, dividing the target cell into N sub-areas according to the plan view, obtaining data wireless transmission distance information of access control equipment and installation location information of access control equipment in each sub-area, wherein the data wireless transmission distance information includes transmission distance and communication strength;

[0134] S2, introducing a simulated annealing algorithm, presetting an initial temperature, cooling rate, and number of iterations of the simulated degradation algorithm, randomly generating a location of a data transfer server in each sub-region based on the initial temperature, cooling rate, and number of iterations, and obtaining an initial solution of the simulated annealing algorithm;

[0135] S3, calculating the Euclidean distance of the access control device in each sub-area to the corresponding initial solution, and determining the communication range of the access control device according to the transmission distance and communication strength of the access control device;

[0136] S4, constructing an objective function according to the Euclidean distance and the communication strength of the access control device, and generating a new solution of the simulated annealing algorithm according to the initial temperature and the cooling rate;

[0137] S5, according to the Metropolis criterion, calculate the probability of accepting the new solution. If the probability is greater than the preset value, replace the initial solution of the simulated annealing algorithm with the new solution, and calculate the objective function of the new solution. If the probability is less than the preset value, discard the new solution.

[0138] S6, looping through S4 to S5, and when the number of loops reaches the preset number of iterations of the simulated annealing algorithm, stopping the loop to obtain a final solution of the simulated annealing algorithm, wherein the final solution is the location of the data transfer server;

[0139] S7, analyzing the location of the data transfer server in each sub-area according to the simulated annealing algorithm, determining the setting location of the data terminal server in the target cell, and building a door access control equipment management system for the target cell based on the location of the data transfer server and the data terminal server in each sub-area and the Internet of Things technology.

[0140] According to an embodiment of the present invention, the access control device management system obtains access control device working data, and performs outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data, specifically:

[0141] Based on the access control device management system, the access control device working data of each sub-area is obtained, where the access control device working data includes user access records and access control device status information of each access control device;

[0142] The LOF algorithm is introduced, and the parameters of the LOF algorithm are preset, wherein the parameters include the number of neighbors K and the distance measurement method, and the local outlier factor of each data point in the working data of the access control device is calculated based on the LOF algorithm;

[0143] Preset an outlier threshold, compare the local outlier factor of each data point with the preset outlier threshold, and mark the data point whose local outlier factor is greater than the preset outlier threshold as an outlier;

[0144] A data mean replacement operation is performed on the abnormal value to obtain the access control device working data of each sub-area after the data abnormal value is processed.

[0145] According to an embodiment of the present invention, the acquisition of historical access control device usage data and working status data, and the analysis of the correlation between the access control device usage and working status according to the grey correlation analysis method to obtain the correlation data are specifically:

[0146] Obtaining historical usage data and working status data of access control equipment, wherein the usage data includes the access control switch frequency, and the working status data includes the normal working status and fault status of the access control;

[0147] Converting the usage data and the working status data into time series data, aligning the usage data and the working status data based on the time series, and standardizing the usage data and the working status data based on the Z-score method to obtain usage sequence data and working status sequence data;

[0148] Calculate the correlation coefficients of the usage sequence data and the working status sequence data according to the grey correlation analysis method, sort the correlation coefficients according to the time series, and obtain a correlation coefficient matrix;

[0149] The correlation level between the usage and working status of the access control device is determined according to the correlation coefficient matrix, and the correlation data between the usage and working status of the access control device is obtained, wherein the correlation data includes the correlation coefficient matrix and the correlation level.

[0150] According to an embodiment of the present invention, the probability of failure of the access control device is predicted based on the associated data and the working data after outlier processing to obtain predicted failure rate data, specifically:

[0151] Building a fault probability prediction model for access control equipment based on LSTM, dividing the usage sequence data and the working status sequence data into a training set and a test set;

[0152] Select mean square error as the loss function of the model, select Adam optimization algorithm as the optimizer of the model, configure the loss function and optimizer into the model and compile the model;

[0153] The training set is imported into the fault probability prediction model for training, the associated data is used as the probability prediction basis of the prediction model, and the model parameters are updated through back propagation and gradient descent to reduce the loss function, thereby obtaining the trained fault probability prediction model;

[0154] Importing the test set into the trained fault occurrence probability model, evaluating the prediction ability of the model, and adjusting the model parameters according to the prediction ability;

[0155] According to the working data after outlier processing, the current usage data of the access control equipment in each sub-area is counted, and the current usage data is imported into the failure probability prediction model to predict the failure probability of the access control equipment in each sub-area and obtain the predicted failure rate data.

[0156] According to an embodiment of the present invention, the maintenance cycle of the access control equipment in each sub-area is determined according to the predicted failure rate data to obtain a maintenance management plan for the access control equipment, specifically:

[0157] Determine the maintenance level of the access control equipment in each sub-area according to the predicted failure rate data of the access control equipment in each sub-area of ​​the target community;

[0158] Determine the maintenance priority of the access control equipment in each sub-area according to the maintenance level to obtain a priority scheme;

[0159] The maintenance period of the access control equipment in each sub-area is determined based on the predicted failure rate data, and the maintenance period and the priority scheme are combined to obtain a maintenance management scheme for the access control equipment.

[0160] According to an embodiment of the present invention, it also includes:

[0161] Based on the access control device management system, the usage data of the access control device of each household in each sub-area is obtained, and the usage frequency and usage time data of the access control device of each household are calculated and counted according to the usage data to obtain the usage characteristic data of the access control device;

[0162] Based on the K-means clustering algorithm, the classification level of the K-means clustering algorithm is set, and the access control device usage feature data is clustered according to the usage frequency to obtain usage frequency clustering data;

[0163] Perform thermal analysis on the usage time data in the access control device usage feature data to determine the usage hotspot time of each residential access control device and obtain the usage time characteristics of each residential access control device;

[0164] Classifying each residential user into a permanent user and a non-permanent user according to the usage frequency clustering data and the usage time characteristic data;

[0165] The maintenance cycle of the residential access control equipment corresponding to the non-resident user is reduced, which supplements the access control equipment maintenance management plan.

[0166] According to an embodiment of the present invention, it also includes:

[0167] Link the target community’s video surveillance system to the access control equipment management system based on the Internet of Things to form the target community’s Internet of Things network;

[0168] Acquire video stream data of a target cell according to the Internet of Things network, extract video frames from the video stream data, and extract key features of the video frames based on an image recognition algorithm, wherein the key features include color information, object motion information, and illumination change information;

[0169] Predefine image features of emergency events, compare the key features with the image features of emergency events, determine whether an emergency event exists, and obtain a recognition result;

[0170] If an emergency event exists, determining the location and urgency of the emergency event based on the identification result, and determining the impact scope of the emergency event based on the location and urgency of the emergency event;

[0171] According to the influence range, a door access control operation is performed on the door access control equipment of the target cell within the influence range to obtain an emergency door access control equipment control strategy.

[0172] The present invention discloses an intelligent management method and system for access control equipment based on the Internet of Things, aiming to improve the management efficiency and maintenance prediction capability of access control equipment. First, the data transmission distance information of the access control equipment in each sub-area of ​​the target community is obtained, and an access control equipment management system is constructed through the Internet of Things technology. The working data of the access control equipment is obtained in the system, and the LOF algorithm is used to perform outlier analysis to process the outliers. The associated data is obtained through the historical use and working data using the gray correlation analysis method. Based on the associated data and the working data after the outlier processing, the maintenance cycle of the access control equipment in each sub-area is predicted using the predicted failure rate data to form an intelligent maintenance management plan for the access control equipment. By integrating the Internet of Things technology and data analysis means, the method realizes the intelligent management of access control equipment, improves the management efficiency and the accuracy of equipment maintenance, and has broad application prospects.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0174] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0175] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0176] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0177] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0178] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent management method for access control equipment based on the Internet of Things, It is characterized in that The following steps are involved: Divide the target community into N sub-areas, obtain the data transmission distance information of the access control equipment in each sub-area, and build the access control equipment management system of the target community based on the Internet of Things technology; Acquiring access control device working data based on the access control device management system, and performing outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data; Obtain historical access control device usage data and working status data, analyze the correlation between the access control device usage and working status according to the grey correlation analysis method, and obtain correlation data; Predicting the probability of failure of the access control device according to the associated data and the working data after outlier processing to obtain predicted failure rate data; Determine the maintenance period for the access control equipment in each sub-area according to the predicted failure rate data, and obtain a maintenance management plan for the access control equipment; The acquisition of historical access control device usage data and working status data, and the analysis of the correlation between the access control device usage and working status according to the grey correlation analysis method to obtain correlation data are specifically: Obtaining historical usage data and working status data of access control equipment, wherein the usage data includes the access control switch frequency, and the working status data includes the normal working status and fault status of the access control; Converting the usage data and the working status data into time series data, aligning the usage data and the working status data based on the time series, and standardizing the usage data and the working status data based on the Z-score method to obtain usage sequence data and working status sequence data; Calculate the correlation coefficients of the usage sequence data and the working status sequence data according to the grey correlation analysis method, sort the correlation coefficients according to the time series, and obtain a correlation coefficient matrix; Determine the correlation level between the usage and working status of the access control device according to the correlation coefficient matrix, and obtain correlation data between the usage and working status of the access control device, wherein the correlation data includes the correlation coefficient matrix and the correlation level; The prediction of the failure probability of the access control device based on the associated data and the working data after the abnormal value processing to obtain the predicted failure rate data is specifically: Building a fault probability prediction model for access control equipment based on LSTM, dividing the usage sequence data and the working status sequence data into a training set and a test set; Select mean square error as the loss function of the model, select Adam optimization algorithm as the optimizer of the model, configure the loss function and optimizer into the model and compile the model; The training set is imported into the fault probability prediction model for training, the associated data is used as the probability prediction basis of the prediction model, and the model parameters are updated through back propagation and gradient descent to reduce the loss function, thereby obtaining the trained fault probability prediction model; Importing the test set into the trained fault occurrence probability model, evaluating the prediction ability of the model, and adjusting the model parameters according to the prediction ability; According to the working data after outlier processing, the current usage data of the access control equipment in each sub-area is counted, and the current usage data is imported into the failure probability prediction model to predict the failure probability of the access control equipment in each sub-area and obtain the predicted failure rate data.

2. According to claim 1, a method for intelligent management of access control equipment based on the Internet of Things, It is characterized in that The target cell is divided into N sub-areas, the data transmission distance information of the access control equipment in each sub-area is obtained, and the access control equipment management system of the target cell is constructed based on the Internet of Things technology, specifically: S1, obtaining a plan view of a target cell, dividing the target cell into N sub-areas according to the plan view, obtaining data wireless transmission distance information of access control equipment and installation location information of access control equipment in each sub-area, wherein the data wireless transmission distance information includes transmission distance and communication strength; S2, introducing a simulated annealing algorithm, presetting an initial temperature, cooling rate, and number of iterations of the simulated degradation algorithm, randomly generating a location of a data transfer server in each sub-region based on the initial temperature, cooling rate, and number of iterations, and obtaining an initial solution of the simulated annealing algorithm; S3, calculating the Euclidean distance of the access control device in each sub-area to the corresponding initial solution, and determining the communication range of the access control device according to the transmission distance and communication strength of the access control device; S4, constructing an objective function according to the Euclidean distance and the communication strength of the access control device, and generating a new solution of the simulated annealing algorithm according to the initial temperature and the cooling rate; S5, according to the Metropolis criterion, calculate the probability of accepting the new solution. If the probability is greater than the preset value, replace the initial solution of the simulated annealing algorithm with the new solution, and calculate the objective function of the new solution. If the probability is less than the preset value, discard the new solution. S6, looping through S4 to S5, and when the number of loops reaches the preset number of iterations of the simulated annealing algorithm, stopping the loop to obtain a final solution of the simulated annealing algorithm, wherein the final solution is the location of the data transfer server; S7, analyzing the location of the data transfer server in each sub-area according to the simulated annealing algorithm, determining the setting location of the data terminal server in the target cell, and building a door access control equipment management system for the target cell based on the location of the data transfer server and the data terminal server in each sub-area and the Internet of Things technology.

3. According to claim 1, a method for intelligent management of access control equipment based on the Internet of Things, It is characterized in that The access control device management system obtains access control device working data, and performs outlier analysis on the working data based on the LOF algorithm to process abnormal values ​​of the working data, specifically: Based on the access control device management system, the access control device working data of each sub-area is obtained, where the access control device working data includes user access records and access control device status information of each access control device; The LOF algorithm is introduced, and the parameters of the LOF algorithm are preset, wherein the parameters include the number of neighbors K and the distance measurement method, and the local outlier factor of each data point in the working data of the access control device is calculated based on the LOF algorithm; Preset an outlier threshold, compare the local outlier factor of each data point with the preset outlier threshold, and mark the data point whose local outlier factor is greater than the preset outlier threshold as an outlier; A data mean replacement operation is performed on the abnormal value to obtain the access control device working data of each sub-area after the data abnormal value is processed.

4. According to claim 1, a method for intelligent management of access control equipment based on the Internet of Things, It is characterized in that Determining the maintenance cycle for the access control equipment in each sub-area according to the predicted failure rate data to obtain the access control equipment maintenance management plan is specifically as follows: Determine the maintenance level of the access control equipment in each sub-area according to the predicted failure rate data of the access control equipment in each sub-area of ​​the target community; Determine the maintenance priority of the access control equipment in each sub-area according to the maintenance level to obtain a priority scheme; The maintenance period of the access control equipment in each sub-area is determined based on the predicted failure rate data, and the maintenance period and the priority scheme are combined to obtain a maintenance management scheme for the access control equipment.

5. An intelligent management system for access control equipment based on the Internet of Things, It is characterized in that The access control equipment intelligent management system based on the Internet of Things includes a storage device and a processor, the storage device includes a program of the access control equipment intelligent management method based on the Internet of Things as claimed in any one of claims 1 to 4, and the program of the access control equipment intelligent management method based on the Internet of Things is executed by the processor.