Intelligent community comprehensive management platform based on big data analysis

Abstract

The invention relates to the technical field of data processing, in particular to a smart community comprehensive management platform based on big data analysis, which comprises a communication load analysis module for acquiring load data of a community network by analyzing the types and the number of various terminals accessed to a community base station within a preset time period; the special node positioning module identifies special network nodes in a community by dividing a special service IP (Internet Protocol), and monitors network behaviors of the special network nodes by setting a data acquisition rule; the monitoring terminal connection module is used for acquiring data of each monitoring terminal by being connected with a community monitoring network; and the comprehensive management module judges whether security vulnerabilities occur in community management or not by analyzing the matching degree among the access characteristics of the various terminals, the data traffic characteristics of the special nodes and the personnel flow characteristics, and outputs an alarm signal.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a smart community comprehensive management platform based on big data analysis. Background Art

[0002] Smart community is a new concept of community management based on information-based, intelligent social management and services. It realizes the modernization and intelligent management of the community by using new generation information technologies such as the Internet of Things, cloud computing, and mobile Internet. Smart community integrates a variety of information technologies, such as the Internet of Things, big data, and cloud computing. The comprehensive application of these technologies makes community management more intelligent and automated.

[0003] Managing outsiders in the community is an important function of the comprehensive management platform and is also the basis for ensuring community safety. Most existing management platforms use video management methods to collect facial information of people entering and leaving the community through face recognition technology, and determine whether to allow people to enter by comparing with the face database. This management method can only manage the entry and exit of people, but cannot manage the equipment carried by the entrants, or monitor some of the behaviors of the entrants, and cannot determine whether some of the behaviors of the entrants after entering are inconsistent with their registration information. For example, in some communities with express service points and takeaway service points, the existing management system cannot determine whether the entrants are related to the corresponding service points, whether the network data of the service points is normal, etc. These not only affect the safety of people in the community, but also the security of network resources in the community. Summary of the invention

[0004] The present invention analyzes the access load information of the community base station to obtain the load type and access time of the community base station, thereby realizing the monitoring of IoT devices in the community. By monitoring the devices in the community, some behaviors of the device carriers are indirectly monitored to determine whether their purpose and behavior of entering the community are related to their service work.

[0005] The technical solution proposed by the present invention is: a smart community comprehensive management platform based on big data analysis, including: A communication load analysis module, wherein the communication load analysis module obtains load data of the community network by analyzing the types and quantities of various terminals accessing the community base station within a preset time period; A special node positioning module, wherein the special node positioning module is configured to be able to identify and connect to a special network node; A monitoring terminal connection module, wherein the monitoring terminal module is connected to the community monitoring network and obtains data of each monitoring terminal; The integrated management module extracts various terminal access characteristics, special node data flow characteristics and personnel flow characteristics from the data obtained from the communication load analysis module, the special node positioning module and the monitoring terminal connection module, and determines whether there are security loopholes in the community management by analyzing the obtained data, and outputs an alarm signal.

[0006] Preferably, the communication load analysis module obtains the load data of the community network by analyzing the types and quantities of various terminals accessing the community base station within a preset time period, which is achieved through the following steps: According to a preset collection frequency, obtain community base station load data within a preset time length; the community base station includes a 5G base station and a 4G base station; Extracting the number of mobile network terminals connected to each base station from the base station load data; A clustering algorithm is used to identify type I network terminals and type II network terminals from base station load data; the type I network terminals include mobile phones and mobile computers, and the type II network terminals include mobile Internet of Things terminals.

[0007] Preferably, the method further includes: forming a network terminal vector by using the number of mobile network terminals accessed by the 5G base station and the 4G base station obtained at the same collection time point ;in, Respectively indicate time The number of network terminals connected to 5G base stations and the number of network terminals connected to 4G base stations, ,in Respectively represent the starting time and ending time of the preset time period; Obtaining the number of Class II network terminals accessing the community base station, the access time of each Class II network terminal, and the network access license ID of each Class II network terminal accessing the community base station from the base station load data; The network access permission ID and access time of each Class II network terminal constitute a network terminal identification vector ,in, Respectively represent The network access license ID of a Class II network terminal and the time of access to the community base station; Combine the network terminal vector and the network terminal identification vector into a long vector , used to monitor the access status of the second type of network terminals.

[0008] Preferably, the special node positioning module identifies special network nodes in the community by dividing special service IPs, and monitors the network behavior of special network nodes by setting data acquisition rules, which is achieved through the following steps: The special node positioning module identifies the Internet access device's networking request and allocates a corresponding IP address according to the service type of the Internet access device; the service type includes community service business, express delivery business, and takeaway business; The express delivery business and takeaway business are classified as special businesses, and the IP addresses allocated for special businesses are classified as special business IPs; If the service type of the Internet access device is a special service, a special service IP is allocated to the corresponding Internet access device, and the device that uses the special service IP to access the Internet is a special node; Establish data acquisition rules for special business IPs, and acquire data of special nodes according to a preset acquisition frequency; the data acquisition rules include the type of data allowed to be acquired and the amount of data allowed to be acquired.

[0009] Preferably, the monitoring terminal module is connected to the community monitoring network and obtains data from each monitoring terminal through the following steps: Connect the monitoring terminal module to the community monitoring network; The monitoring data is obtained from the community monitoring network according to the standard communication protocol, and the monitoring data includes the video monitoring data, card swiping data and face recognition data of each monitoring terminal.

[0010] Preferably, the integrated management module extracts various terminal access features, special node data flow features and personnel flow features from the data acquired by the communication load analysis module, the special node positioning module and the monitoring terminal connection module, and is implemented by the following steps: Connect the communication load analysis module, the special node positioning module and the monitoring terminal connection module with the comprehensive management module; Set the data collection frequency, and obtain the data of the communication load analysis module, the special node positioning module and the monitoring terminal connection module according to the data collection frequency; The acquired data is divided into load data set, special node data set and monitoring data set.

[0011] Preferably, the step of dividing the acquired data into a load data set, a special node data set and a monitoring data set includes: The load data set is formed by using the network terminal vector, the network terminal identification vector and the long vector obtained from the communication load analysis module; The special node data set is formed by using the data of the special node obtained from the special node positioning module; The monitoring data set is formed by using the monitoring data obtained from the monitoring terminal module.

[0012] Preferably, the analysis of the acquired data to determine whether there is a security loophole in community management is achieved through the following steps: Obtain load data sets, special node data sets and monitoring data sets, and perform preprocessing; Extract the second-class network terminal access features, extract the special node data flow features, and extract the personnel flow features of the monitoring data to form the second-class network terminal access feature set, the special node data flow feature set and the personnel feature set; Determine whether the access characteristics of Class II network terminals, data traffic characteristics of special nodes, and personnel flow characteristics match, and determine whether management loopholes occur based on the matching results.

[0013] Preferably, the determining whether the second-category network terminal access characteristics, special node data flow characteristics, and personnel flow characteristics match includes: Align the second-class network terminal access feature set, special node data flow feature set and personnel feature set on the time axis; Obtain network terminal access characteristics, the network terminal access characteristics including: the number of access terminals of a type , the access time point of the first type of network terminals, the number of second type of network terminals access , the time point at which the second-class network terminal accesses, and the time point corresponding to the maximum number of second-class network terminals accessing , Duration of the maximum number of accesses , the time point for the minimum number of Class II network terminals to access and the time it takes for the minimum number of accesses to increase to the maximum number of accesses , the increase in the number of Class II network terminals accessing ; Get the number of special node traffic, the special node traffic characteristics include: maximum traffic time point , the lowest flow time point , the length of time from the lowest flow time point to the maximum flow time point ; Obtain a personnel feature set and extract personnel flow features, which include the maximum personnel entry and exit time points within a preset time period. , arrive Number of external vehicles during the time period , arrive The number of inbound personnel during the time period ; if , then it is judged that the increase in the number of Class II network terminal accesses is related to the entry of outsiders, that is, the access characteristics of Class II network terminals match the characteristics of personnel flow, otherwise it is judged that there is a loophole in the management of outsiders, and an alarm message 1 is output; among them, and represents a time delay coefficient of one and a time threshold of one; if , then it is judged that the increase in the number of Class II network terminal accesses is related to the entry of outsiders, that is, the access characteristics of Class II network terminals match the characteristics of personnel flow; otherwise, it is judged that there is a loophole in the management of outsiders, and alarm information 1 is output; among them, and They represent vehicle weight, personnel weight and personnel quantity threshold respectively; if , it is judged that the increase in the flow of the special node is related to the increase in the number of Class II network terminal accesses; that is, the network terminal access characteristics match the flow characteristics of the special node; otherwise, it is judged that there are loopholes in the management of outsiders and network security management, and the alarm information 2 is output; where, and Represents time delay factor 2 and time threshold 2.

[0014] Preferably, a prediction model is pre-stored in the integrated management module, and the prediction model uses a random forest algorithm to predict the probability of external personnel management loopholes and network security management loopholes based on network terminal access characteristics, personnel flow characteristics, special node traffic characteristics, alarm information one and alarm information two.

[0015] Beneficial effects of the present invention: 1. The platform of the present invention analyzes the types and numbers of access terminals of base stations in the community, identifies special terminals (Internet of Things devices), and monitors network data of special places such as express stations and takeaway cabinets set up in the community by setting up special node positioning modules. The amount of Internet data is combined with the number and time of people entering the place to determine the relationship between the increase in the amount of Internet data at the place and the entry of people, and to determine whether there are abnormal Internet activities and abnormal people entering and leaving the place, so as to achieve comprehensive management of personnel safety and network security.

[0016] 2. The platform of the present invention uses the prediction model preset in the comprehensive management module to analyze the data of the communication load analysis module, the special node positioning module, and the monitoring terminal connection module, predict the probability of security vulnerabilities, and output alarm information. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a structural diagram of a smart community comprehensive management platform based on big data analysis of the present invention; Figure 2 The present invention is a flow chart of a method for determining security vulnerabilities in community management by the platform of the present invention. DETAILED DESCRIPTION

[0018] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0019] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0020] refer to Figure 1 and Figure 2 The technical solution provided by the present invention is: a smart community comprehensive management platform based on big data analysis, including: a communication load analysis module, a special node positioning module, a monitoring terminal connection module and a comprehensive management module.

[0021] Among them, the communication load analysis module is used to obtain the access data of the community base station; the special node positioning module is used to identify and connect special network nodes; the monitoring terminal module is used to connect to the community monitoring network and obtain the data of each monitoring terminal; the comprehensive management module is used to obtain the data of the communication load analysis module, the special node positioning module and the monitoring terminal connection module, and by analyzing the obtained data, it is determined whether there are security loopholes in the community management and output an alarm signal.

[0022] The integrated management module includes a processor and a memory connected to the processor, a communication module, a display terminal and an input terminal, and the display terminal and the input terminal are used for inputting data and outputting alarm signals.

[0023] The process of the communication load analysis module obtaining the 5G and / or 4G network terminal access data in the community is as follows: According to a preset collection frequency, obtain community base station load data within a preset time length; the community base station includes a 5G base station and a 4G base station; Extracting the number of mobile network terminals connected to each base station from the base station load data; Class I and Class II network terminals are identified from base station load data through clustering algorithms; Class I network terminals include mobile phones and mobile computers, and Class II network terminals include mobile Internet of Things terminals. Specifically, identification can be performed by identifying the connection frequency, data flow size, signal strength, and network access permission information of the device. Usually, the data flow of mobile phones is large and fluctuates frequently, while the data flow of Internet of Things devices is small and fluctuates less; the signal strength of Internet of Things devices is low, while the signal strength of mobile phones is high.

[0024] The purpose of obtaining the access data of Class I network terminals is to determine the use of community base stations by outsiders entering the community. Provide data support for adjusting and managing the capacity of community base stations. By comparing the number of access to Class I network terminals and the number of access to Class II network terminals, it is determined whether the service personnel entering the community are performing work related to their service content. For example, a courier delivery person usually carries an IoT device and a mobile phone for express delivery in and out of the warehouse. If the increase in the number of IoT access devices matches the number of mobile phones connected at the same time (within the allowable error range), and the data communication time period of the IoT device and the mobile phone basically overlaps, it is determined that the entrant is engaged in express delivery; if the difference between the data communication time of the mobile phone and the data communication time of the IoT device exceeds 30 minutes, it is determined that the entrant has completed the service work, or has not performed the service work and is still staying in the community, which may pose a security risk.

[0025] The purpose of obtaining the second-class network terminal access data points is to determine the use of community base stations by special groups entering the community. The so-called special groups include couriers, salesmen, etc., because couriers use IoT devices to query express delivery at work, and salesmen use POS machines and other IoT devices to conduct transactions, etc. These outsiders often enter and exit the community and are familiar with the management staff, which can easily cause management paralysis and management loopholes.

[0026] Therefore, it is necessary to focus on monitoring the access data of the second type of network terminals, specifically: The number of mobile network terminals connected to the 5G base station and the 4G base station obtained at the same collection time point constitutes the network terminal vector ;in, Respectively indicate time The number of network terminals connected to 5G base stations and the number of network terminals connected to 4G base stations, ,in Respectively represent the starting time and ending time of the preset time period; Obtaining the number of Class II network terminals accessing the community base station, the access time of each Class II network terminal, and the network access license ID of each Class II network terminal accessing the community base station from the base station load data; The network access permission ID and access time of each Class II network terminal constitute a network terminal identification vector ,in, Respectively represent The network access license ID of a Class II network terminal and the time of access to the community base station; Combine the network terminal vector and the network terminal identification vector into a long vector Through this vector, the ID information and access time information of IoT devices accessing 4G base stations and 5G base stations in the community can be monitored. The number of IoT devices entering the community within a period of time can be obtained through statistics. The number of couriers and salesmen entering the community can be indirectly obtained through the number of IoT devices.

[0027] There are usually fixed express delivery and receiving points, express delivery lockers and takeaway lockers in the community. The entry and exit registration equipment and express delivery lockers in the delivery and receiving points need to be connected to the Internet (via wired or wireless connection). When the couriers enter, the Internet access data of these locations will increase (entry and exit processing and communication message sending are required). Therefore, by monitoring the Internet communication data of these locations, it is possible to determine whether the changes in the Internet communication data are related to the entry and exit of couriers and takeaway deliverymen.

[0028] The specific process is as follows: The Internet access device's networking request is identified through the special node positioning module, and the corresponding IP address is allocated according to the business type of the Internet access device; the business types include community service business, express delivery business, and takeaway business; the express delivery business and takeaway business are classified as special business, and the IP address allocated for the special business is classified as a special business IP; if the business type of the Internet access device is a special business, a special business IP is allocated to the corresponding Internet access device, and the device that accesses the Internet using the special business IP is a special node; establish data acquisition rules with the special business IP, and acquire data of the special node according to the preset collection frequency; the data acquisition rules include the type of data allowed to be acquired and the amount of data allowed to be acquired.

[0029] The monitoring terminal module is used to obtain surveillance videos of community entrances and exits and public areas, and image information of people and vehicles entering and leaving is obtained from the images. The target recognition algorithm YOLO can be used to identify the corresponding personnel and vehicle information, and the situation of people entering can be counted based on the recognition results, especially couriers, courier vehicles, takeaway personnel, etc.

[0030] The integrated management module receives data from the load analysis module, the special node positioning module and the monitoring terminal connection module, analyzes and processes the data, and outputs corresponding alarm information through the display terminal.

[0031] The specific process is as follows: The communication load analysis module, the special node positioning module and the monitoring terminal connection module are connected to the comprehensive management module; the data collection frequency is set, and the data of the communication load analysis module, the special node positioning module and the monitoring terminal connection module are obtained according to the data collection frequency; the obtained data is divided into a load data set, a special node data set and a monitoring data set.

[0032] The network terminal vector, network terminal identification vector and long vector obtained from the communication load analysis module are used to form a load data set; the special node data obtained from the special node positioning module are used to form a special node data set; and the monitoring data obtained from the monitoring terminal module are used to form a monitoring data set.

[0033] Obtain the load data set, special node data set and monitoring data set, and perform preprocessing; extract the second-category network terminal access characteristics, extract the special node data flow characteristics, and extract the personnel flow characteristics of the monitoring data to form the second-category network terminal access feature set, special node data flow feature set and personnel feature set; determine whether the second-category network terminal access characteristics, special node data flow characteristics and personnel flow characteristics match, and determine whether there is a management loophole based on the matching results.

[0034] Align the second-class network terminal access feature set, special node data flow feature set and personnel feature set on the time axis; Obtain network terminal access characteristics, the network terminal access characteristics including: the number of access terminals of a type , the access time point of the first-class network terminal, the duration of the first-class network terminal accessing the community base station, the duration of the second-class network terminal accessing the community base station, and the number of second-class network terminals accessing the community base station , the time point at which the second-class network terminal accesses, and the time point corresponding to the maximum number of second-class network terminals accessing , Duration of the maximum number of accesses , the time point for the minimum number of Class II network terminals to access The time length for the minimum number of access terminals of the second category network to increase to the maximum number of access terminals , the increase in the number of Class II network terminals accessing .

[0035] Get the number of special node traffic, the special node traffic characteristics include: maximum traffic time point , the lowest flow time point , the length of time from the lowest flow time point to the maximum flow time point .

[0036] Obtain a personnel feature set and extract personnel flow features, which include the maximum personnel entry and exit time points within a preset time period. , arrive Number of external vehicles during the time period , arrive The number of inbound personnel during the time period .

[0037] if , then it is judged that the increase in the number of Class II network terminal accesses is related to the entry of outsiders, that is, the access characteristics of Class II network terminals match the characteristics of personnel flow, otherwise it is judged that there is a loophole in the management of outsiders, and an alarm message 1 is output; among them, and Represents a time delay coefficient of one and a time threshold of one.

[0038] if , then it is judged that the increase in the number of Class II network terminal accesses is related to the entry of outsiders, that is, the access characteristics of Class II network terminals match the characteristics of personnel flow; otherwise, it is judged that there is a loophole in the management of outsiders, that is, the increase in the number of IoT device accesses is much greater than the number of couriers and salesmen entering, and the comprehensive management module will output alarm information 1 to notify the management personnel to handle it; among them, and They represent vehicle weight, personnel weight and personnel quantity threshold respectively.

[0039] if , it is judged that the increase in traffic of special nodes is related to the increase in the number of Class II network terminal accesses; that is, the network terminal access characteristics match the traffic characteristics of special nodes; otherwise, it is judged that there are loopholes in the management of outsiders and network security management, that is, the network traffic increases abnormally, and there may be abnormal network activities. The comprehensive management module will output alarm information 2 to notify the management personnel to handle it; among them, and Represents time delay coefficient 2 and time threshold 2.

[0040] In the comprehensive management module, a prediction model based on the random forest algorithm is set up. Through the trained prediction model, the network terminal access characteristics, personnel flow characteristics, special node traffic characteristics, and the relationship between alarm information 1 and alarm information 2 are analyzed to predict the probability of external personnel management loopholes. and the probability of network security management breaches , respectively, with the set personnel management threshold and network security thresholds Compare, if It is judged that there is a personnel management loophole. If , it is judged that there is a network security management loophole.

[0041] In the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0042] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0043] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any changes or modifications.

Claims

1. A smart community integrated management platform based on big data analysis, characterized in that: include: A communication load analysis module, wherein the communication load analysis module obtains load data of the community network by analyzing the types and quantities of various terminals accessing the community base station within a preset time period; A special node positioning module, which identifies special network nodes in the community by dividing special service IPs, and monitors the network behavior of special network nodes by setting data acquisition rules; A monitoring terminal connection module, wherein the monitoring terminal module obtains data of each monitoring terminal by connecting to the community monitoring network; The comprehensive management module extracts various terminal access characteristics, special node data flow characteristics and personnel flow characteristics from the data obtained from the communication load analysis module, the special node positioning module and the monitoring terminal connection module, analyzes the matching degree between the various terminal access characteristics, the special node data flow characteristics and the personnel flow characteristics, determines whether there are security loopholes in the community management, and outputs an alarm signal.

2. According to claim 1, a smart community comprehensive management platform based on big data analysis is characterized in that: The communication load analysis module obtains the load data of the community network by analyzing the types and quantities of various terminals accessing the community base station within a preset time period, and is implemented through the following steps: According to a preset collection frequency, obtain community base station load data within a preset time length; the community base station includes a 5G base station and a 4G base station; Extracting the number of mobile network terminals connected to each base station from the base station load data; A clustering algorithm is used to identify type I network terminals and type II network terminals from base station load data; the type I network terminals include mobile phones and mobile computers, and the type II network terminals include mobile Internet of Things terminals.

3. According to the smart community comprehensive management platform based on big data analysis as described in claim 2, It is characterized in that Also includes: The number of mobile network terminals connected to the 5G base station and the 4G base station obtained at the same collection time point constitutes the network terminal vector ;in, Respectively indicate time The number of network terminals connected to 5G base stations and the number of network terminals connected to 4G base stations, ,in Respectively represent the starting time and ending time of the preset time period; Obtaining the number of Class II network terminals accessing the community base station, the access time of each Class II network terminal, and the network access license ID of each Class II network terminal accessing the community base station from the base station load data; The network access permission ID and access time of each Class II network terminal constitute a network terminal identification vector ,in, Respectively represent The network access license ID of a Class II network terminal and the time of access to the community base station; Combine the network terminal vector and the network terminal identification vector into a long vector , used to monitor the access status of the second type of network terminals.

4. According to claim 3, a smart community integrated management platform based on big data analysis is characterized in that: The special node positioning module identifies special network nodes in the community by dividing special service IPs, and monitors the network behavior of special network nodes by setting data acquisition rules. This is achieved through the following steps: The special node positioning module identifies the Internet access device's networking request and allocates a corresponding IP address according to the service type of the Internet access device; the service type includes community service business, express delivery business, and takeaway business; The express delivery business and takeaway business are classified as special businesses, and the IP addresses allocated for special businesses are classified as special business IPs; If the service type of the Internet access device is a special service, a special service IP is allocated to the corresponding Internet access device, and the device that uses the special service IP to access the Internet is a special node; Establish data acquisition rules for special business IPs, and acquire data of special nodes according to a preset acquisition frequency; the data acquisition rules include the type of data allowed to be acquired and the amount of data allowed to be acquired.

5. According to claim 4, a smart community integrated management platform based on big data analysis is characterized in that: The monitoring terminal module is connected to the community monitoring network and obtains data from each monitoring terminal through the following steps: Connect the monitoring terminal module to the community monitoring network; The monitoring data is obtained from the community monitoring network according to the standard communication protocol, and the monitoring data includes the video monitoring data, card swiping data and face recognition data of each monitoring terminal.

6. According to claim 5, a smart community integrated management platform based on big data analysis is characterized in that: The integrated management module extracts various terminal access features, special node data flow features and personnel flow features from the data obtained from the communication load analysis module, the special node positioning module and the monitoring terminal connection module, and is implemented through the following steps: Connect the communication load analysis module, the special node positioning module and the monitoring terminal connection module with the comprehensive management module; Set the data collection frequency, and obtain the data of the communication load analysis module, the special node positioning module and the monitoring terminal connection module according to the data collection frequency; The acquired data is divided into load data set, special node data set and monitoring data set.

7. According to claim 6, a smart community integrated management platform based on big data analysis is characterized in that: The step of dividing the acquired data into a load data set, a special node data set and a monitoring data set includes: The load data set is formed by using the network terminal vector, the network terminal identification vector and the long vector obtained from the communication load analysis module; The special node data set is formed by using the data of the special node obtained from the special node positioning module; The monitoring data set is formed by using the monitoring data obtained from the monitoring terminal module.

8. According to claim 7, a smart community integrated management platform based on big data analysis is characterized in that: The analysis of the acquired data to determine whether there are security loopholes in community management is achieved through the following steps: Obtain load data sets, special node data sets and monitoring data sets, and perform preprocessing; Extract the second-class network terminal access features, extract the special node data flow features, and extract the personnel flow features of the monitoring data to form the second-class network terminal access feature set, the special node data flow feature set and the personnel feature set; Determine whether the access characteristics of Class II network terminals, data traffic characteristics of special nodes, and personnel flow characteristics match, and determine whether management loopholes occur based on the matching results.

9. The smart community integrated management platform based on big data analysis according to claim 8 is characterized in that: The determining whether the second-category network terminal access characteristics, special node data flow characteristics, and personnel flow characteristics match includes: Align the second-class network terminal access feature set, special node data flow feature set and personnel feature set on the time axis; Obtain network terminal access characteristics, the network terminal access characteristics including: the number of access terminals of a type , the access time point of the first type of network terminals, the number of second type of network terminals access , the time point at which the second-class network terminal accesses, and the time point corresponding to the maximum number of second-class network terminals accessing , Duration of the maximum number of accesses , the time point for the minimum number of Class II network terminals to access and the time it takes for the minimum number of accesses to increase to the maximum number of accesses , the increase in the number of Class II network terminals accessing ; Get the number of special node traffic, the special node traffic characteristics include: maximum traffic time point , the lowest flow time point , the length of time from the lowest flow time point to the maximum flow time point ; Obtain a personnel feature set and extract personnel flow features, which include the maximum personnel entry and exit time points within a preset time period. , arrive Number of external vehicles during the time period , arrive The number of inbound personnel during the time period ; if , then it is judged that the increase in the number of Class II network terminal accesses is related to the entry of outsiders, that is, the access characteristics of Class II network terminals match the characteristics of personnel flow, otherwise it is judged that there is a loophole in the management of outsiders, and an alarm message 1 is output; among them, and represents a time delay coefficient of one and a time threshold of one; if , then it is judged that the increase in the number of Class II network terminal accesses is related to the entry of outsiders, that is, the access characteristics of Class II network terminals match the characteristics of personnel flow; otherwise, it is judged that there is a loophole in the management of outsiders, and alarm information 1 is output; among them, and They represent vehicle weight, personnel weight and personnel quantity threshold respectively; if , it is judged that the increase in the flow of the special node is related to the increase in the number of Class II network terminal accesses; that is, the network terminal access characteristics match the flow characteristics of the special node; otherwise, it is judged that there are loopholes in the management of outsiders and network security management, and the alarm information 2 is output; where, and Represents time delay coefficient 2 and time threshold 2.

10. The smart community integrated management platform based on big data analysis according to claim 9 is characterized in that: A prediction model is pre-stored in the comprehensive management module. The prediction model uses a random forest algorithm to predict the probability of external personnel management loopholes and network security management loopholes based on network terminal access characteristics, personnel flow characteristics, special node traffic characteristics, alarm information one and alarm information two.

Images