Intelligent security management and control system and method based on energy consumption big data analysis

Abstract

The invention relates to the technical field of Internet of Things application, in particular to an intelligent security management and control system and method based on energy consumption big data analysis, and the system comprises a TCP communication module, a data analysis processing module, an early warning module and a big data display module. Collecting a data packet in a TCP communication process in real time; the collected data is subjected to preprocessing of data cleaning, duplicate removal and formatting, the processed data is deeply analyzed, and key features are extracted; setting an early warning rule and a threshold value based on a data analysis result, monitoring TCP communication data in real time, and sending detected abnormal information to an upper computer; the big data visualization platform generates a chart of TCP communication data, a data analysis result and early warning information, and independently displays an abnormal information analysis result, so that normal data and abnormal data can be visually displayed through the big data visualization platform, and a manager can quickly and completely know the energy consumption condition.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things application technology, and in particular to an intelligent safety management and control system and method based on energy consumption big data analysis. Background Art

[0002] The intelligent energy consumption monitoring platform integrates a variety of advanced remote transmission equipment and technologies, and can monitor and analyze multiple key indicators such as electricity, water resources, temperature, and liquid level in real time. The platform includes multi-dimensional energy consumption data monitoring (power consumption, water resource management, ambient temperature control, liquid storage container monitoring), intelligent data analysis and early warning, flexible and convenient operation experience, efficient and stable communication guarantee, etc. It can be applied to multiple fields such as university logistics departments, manufacturing factories, commercial complexes, residential property management, and agricultural irrigation systems.

[0003] The prior art CN118628122A discloses an energy-saving and carbon-reduction management and control system based on big data technology, including: a data acquisition module: used to collect energy consumption data, environmental data and carbon emission data, including sensor units and other data sources; a data processing module: used to process the data collected by the data acquisition module; a prediction module: used to establish a carbon emission prediction model and predict energy consumption trends; an intelligent decision-making module: used to provide management and control decision support and help managers formulate energy-saving and carbon-reduction strategies; a visualization and reporting module: regularly generate consumption, carbon emissions and energy-saving and carbon-reduction effect visualization reports to improve energy utilization efficiency and reduce carbon emissions.

[0004] However, when the existing energy consumption control system cleans the collected data, it only denoises the collected data, and does not correct the detected abnormal values ​​or notify the abnormalities. As a result, the collected data may be missing during the denoising process, thereby affecting the accuracy and completeness of the collected data. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent safety management and control system and method based on energy consumption big data analysis, which solves the problem that the existing energy consumption management and control system only denoises the collected data during the cleaning process, and does not correct the detected abnormal values ​​and notify the abnormalities, resulting in the loss of collected data during the denoising process, thereby affecting the accuracy and completeness of the collected data.

[0006] To achieve the above-mentioned purpose, the present invention provides a smart safety management and control system based on energy consumption big data analysis, including a TCP communication module, a data analysis and processing module, an early warning module and a big data display module, wherein the data analysis and processing module receives data collected by the TCP communication module, the early warning module receives abnormal data output by the data analysis and processing module, and the big data display module receives data from the TCP communication module, the data analysis and processing module and the early warning module;

[0007] The TCP communication module is used to establish a data communication connection with a remote device and collect data in real time using the device standard protocol;

[0008] The data analysis and processing module is used to format and remove noise from the original data, filter abnormal data, and detect and filter abnormal data using a machine learning model;

[0009] The warning module is used to monitor according to the set warning rules and thresholds, and send the obtained warning information to the host computer;

[0010] The big data display module is used to display the analysis results in the form of visual charts and web pages, and intuitively display the energy consumption usage and abnormal energy consumption points.

[0011] The present invention also includes a smart safety management and control method based on energy consumption big data analysis, comprising the following steps:

[0012] Establish a TCP communication connection, use the standard protocol stack for data transmission, collect data packets in the TCP communication process in real time, and store the collected data packets;

[0013] The collected TCP communication data is pre-processed by data cleaning, deduplication and formatting, and the processed data is deeply analyzed through data mining and machine learning algorithms to extract key features;

[0014] Based on the data analysis results, set warning rules and thresholds, monitor TCP communication data in real time, and send detected abnormal information to the host computer;

[0015] The big data visualization platform generates charts of TCP communication data, data analysis results, and warning information, and independently displays abnormal information analysis results.

[0016] Among them, in “establishing a TCP communication connection, using a standard protocol stack for data transmission, collecting data packets in the TCP communication process in real time, and storing the collected data packets”, the method includes the following steps:

[0017] The client sends a SYN packet containing an initial sequence number to initiate a connection request to the server. After receiving the SYN packet, the server replies with a SYN-ACK packet containing its own initial sequence number. The client then sends an ACK packet to the server to confirm receipt of the server's SYN-ACK packet, and the TCP communication connection is successfully established.

[0018] After the TCP connection is established, the data is cached in the buffer of the protocol stack, and then sliced ​​according to the size of the maximum transmission unit. The TCP module adds header information to the data, and the data is entrusted to the IP module for encapsulation and transmission;

[0019] During data transmission, use a network packet capture tool to capture data packets containing source address, destination address, port number, and data content during TCP communication in real time;

[0020] The collected data packets are stored in the local database and distributed storage system.

[0021] Among them, in "pre-processing the collected TCP communication data by data cleaning, deduplication and formatting, and conducting in-depth analysis on the processed data through data mining and machine learning algorithms to extract key features", the steps include:

[0022] Remove invalid information, erroneous data and redundant data about null values, abnormal values ​​and duplicate data from the collected TCP communication data;

[0023] Format the cleaned and deduplicated data and convert it into a format suitable for subsequent analysis to keep the data consistent;

[0024] Use data mining and machine learning algorithms to conduct in-depth analysis of processed data and extract traffic patterns, response times, and abnormal behavior information from large amounts of data;

[0025] Based on the analysis results of data mining and machine learning algorithms, key features that affect network performance, service quality or security in TCP communication data are extracted.

[0026] Among them, in “based on the data analysis results, setting warning rules and thresholds, real-time monitoring of TCP communication data, and sending the detected abnormal information to the host computer”, the method also includes the following steps:

[0027] Extract historical TCP communication data and business demand data, analyze the distribution, trends and correlation of the data, and identify abnormal patterns that may lead to network performance degradation or security risks;

[0028] Based on the analysis results, formulate specific warning rules, clarify which data changes or combinations are considered abnormal, and set corresponding thresholds;

[0029] Design and deploy a system to monitor TCP communication data. The system collects, processes and analyzes TCP communication data in real time, and performs anomaly detection based on preset warning rules and thresholds.

[0030] The anomaly detection and alarm mechanism automatically analyzes TCP communication data, determines whether there is an anomaly based on the warning rules and thresholds, triggers an alarm immediately when an anomaly is detected, and generates an alarm record containing detailed information about the anomaly, timestamp, and data source;

[0031] The detected abnormal information is sent to the host computer through the communication channel.

[0032] Among them, in “designing and deploying a system for monitoring TCP communication data, the system collects, processes and analyzes TCP communication data in real time, and performs anomaly detection according to preset warning rules and thresholds”, the method includes:

[0033] Collect historical TCP communication data as a training set. The data contains both normal and abnormal situations. The model learns the characteristics of normal data and the characteristics of abnormal data.

[0034] Extract traffic size, number of packets, and connection duration from raw TCP communication data to reflect the inherent regularities and abnormal patterns of the data;

[0035] Use the extracted features and labels to train a machine learning model. During the training process, the model continuously adjusts its parameters to minimize the prediction error and learn the feature representation of normal data.

[0036] The performance of the model was evaluated through the cross-validation method, and the model was optimized by adjusting model parameters, increasing the number of features, and improving feature extraction methods based on the evaluation results.

[0037] In “a big data visualization platform generates a chart of TCP communication data, data analysis results, and warning information, and independently displays abnormal information analysis results”, the method includes the following steps:

[0038] The big data visualization platform collects data cleaning and format conversion of TCP communication data from network devices and server logs, and generates data analysis results including traffic trends, connection status, and performance parameters;

[0039] Based on the data analysis results, the big data visualization platform generates corresponding line graphs, bar graphs, and pie charts to display the characteristics, trends, and analysis results of TCP communication data;

[0040] For abnormalities or warning information detected during data analysis, the big data visualization platform will generate a special warning information chart that highlights the range of abnormal values ​​and the abnormal data characteristics of the occurrence time;

[0041] The big data visualization platform also provides an independent display area for displaying the results of abnormal information analysis. The area lists in detail all detected abnormal information, including abnormality type, occurrence time, and impact scope.

[0042] The present invention discloses an intelligent safety management and control system and method based on energy consumption big data analysis, including a TCP communication module, a data analysis and processing module, an early warning module and a big data display module. By establishing a TCP communication connection and using a standard protocol stack for data transmission, data packets in the TCP communication process are collected in real time, and the collected data packets are stored; the collected TCP communication data is pre-processed by data cleaning, deduplication and formatting, and the processed data is deeply analyzed through data mining and machine learning algorithms to extract key features; based on the data analysis results, early warning rules and thresholds are set, the TCP communication data is monitored in real time, and the detected abnormal information is sent to a host computer; a big data visualization platform generates charts of TCP communication data, data analysis results and early warning information, and independently displays the abnormal information analysis results, so that normal data and abnormal data can be intuitively displayed through the big data visualization platform, and management personnel can quickly and completely understand the energy consumption situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0044] Figure 1 It is a system diagram of the intelligent safety management and control system based on energy consumption big data analysis of the present invention.

[0045] Figure 2 It is a flow chart of an intelligent safety management and control method based on energy consumption big data analysis of the present invention.

[0046] Figure 3 The invention is a flow chart of establishing a TCP communication connection, using a standard protocol stack for data transmission, collecting data packets in the TCP communication process in real time, and storing the collected data packets.

[0047] Figure 4 The invention pre-processes the collected TCP communication data by data cleaning, deduplication and formatting, and conducts in-depth analysis on the processed data through data mining and machine learning algorithms to extract key features.

[0048] Figure 5The invention sets early warning rules and thresholds based on data analysis results, monitors TCP communication data in real time, and sends detected abnormal information to a host computer.

[0049] Figure 6 The invention designs and deploys a system for monitoring TCP communication data. The system collects, processes and analyzes TCP communication data in real time and performs abnormality detection according to preset warning rules and thresholds.

[0050] Figure 7 The big data visualization platform of the present invention generates charts of TCP communication data, data analysis results and warning information, and independently displays a flow chart of abnormal information analysis results.

[0051] In the figure: 101-TCP communication module, 102-data analysis and processing module, 103-early warning module, 104-big data display module. DETAILED DESCRIPTION

[0052] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0053] See also Figure 1 , Figure 1 It is a system diagram of the intelligent safety management and control system based on energy consumption big data analysis.

[0054] A smart safety management and control system based on energy consumption big data analysis, comprising a TCP communication module, a data analysis and processing module, an early warning module and a big data display module, wherein the data analysis and processing module receives data collected by the TCP communication module, the early warning module receives abnormal data output by the data analysis and processing module, and the big data display module receives data from the TCP communication module, the data analysis and processing module and the early warning module;

[0055] The TCP communication module is used to establish a data communication connection with a remote device and collect data in real time using the device standard protocol;

[0056] The data analysis and processing module is used to format and remove noise from the original data, filter abnormal data, and detect and filter abnormal data using a machine learning model;

[0057] The warning module is used to monitor according to the set warning rules and thresholds, and send the obtained warning information to the host computer;

[0058] The big data display module is used to display the analysis results in the form of visual charts and web pages, and intuitively display the energy consumption usage and abnormal energy consumption points.

[0059] In this embodiment: the intelligent TCP congestion control scheme is implemented based on the principle of obtaining the key characteristics of the user, obtaining the corresponding TCP flow request message through these characteristics, and then generating ISP resources to the buffer queue; the method dynamically adjusts the recommended congestion window of the TCP protocol layer control block according to the key characteristics of the user. Compared with the traditional static standard, this flexible allocation method can better adapt to the network needs of various users, thereby improving the available resources of effective users and the effective utilization of network resources.

[0060] Intelligent data analysis and processing: Use machine learning algorithms to conduct in-depth mining of TCP communication data, identify potential rules and patterns in the data, analyze key indicators such as data flow and response time in real time, evaluate network performance and service quality, mark and classify abnormal data, and provide data support for subsequent warnings.

[0061] Real-time warning: Based on the output of the intelligent data analysis and processing module, the warning threshold and rules are set. When data anomalies are detected, the warning mechanism is triggered immediately, and relevant personnel are notified via email, SMS, APP push, etc., and a warning history record query function is provided to facilitate the tracing and analysis of warning events.

[0062] Big data visualization display: Using advanced visualization technology, TCP communication data, data analysis results and warning information are intuitively displayed in the form of charts, dashboards, etc., supporting customized views and interactive operations. Users can adjust the display content and layout according to their needs. It provides data export function, which is convenient for users to use the displayed data for further analysis and reporting.

[0063] Can be used for business data analysis: Enterprises can use the big data visualization platform to intuitively display the collected data, help management quickly understand the operating status and existing problems, and provide support for decision-making.

[0064] See also Figures 2 to 7 , Figure 2 It is a flow chart of a smart safety management and control method based on energy consumption big data analysis of the present invention; Figure 3 It is a flowchart of the present invention for establishing a TCP communication connection, using a standard protocol stack for data transmission, collecting data packets in the TCP communication process in real time, and storing the collected data packets; Figure 4 The present invention performs data cleaning, deduplication and formatting preprocessing on the collected TCP communication data, performs in-depth analysis on the processed data through data mining and machine learning algorithms, and extracts the flow chart of key features; Figure 5It is a flowchart of the present invention that sets warning rules and thresholds based on data analysis results, monitors TCP communication data in real time, and sends detected abnormal information to a host computer; Figure 6 It is a flowchart of the present invention designing and deploying a system for monitoring TCP communication data, the system collects, processes and analyzes TCP communication data in real time, and performs abnormality detection according to preset warning rules and thresholds; Figure 7 The big data visualization platform of the present invention generates charts of TCP communication data, data analysis results and warning information, and independently displays a flow chart of abnormal information analysis results.

[0065] A smart safety management and control method based on energy consumption big data analysis includes the following steps:

[0066] S1: Establish a TCP communication connection, use the standard protocol stack for data transmission, collect data packets in the TCP communication process in real time, and store the collected data packets;

[0067] S11: The client sends a SYN packet containing an initial sequence number to initiate a connection request to the server. After receiving the SYN packet, the server replies with a SYN-ACK packet containing its own initial sequence number. The client then sends an ACK packet to the server to confirm receipt of the server's SYN-ACK packet, and the TCP communication connection is successfully established.

[0068] S12: After the TCP connection is established, the data is cached in the buffer of the protocol stack, and then sliced ​​according to the size of the maximum transmission unit. The TCP module adds header information to the data, and the data is entrusted to the IP module for encapsulation and transmission;

[0069] S13: During the data transmission process, a network packet capture tool is used to capture data packets including source address, destination address, port number, and data content in the TCP communication process in real time;

[0070] S14: Store the collected data packets in the local database and the distributed storage system.

[0071] In this embodiment, a TCP communication connection is established: first, the client initiates a connection request to the server by sending a SYN packet containing an initial sequence number. After receiving the SYN packet, the server will reply with a SYN-ACK packet containing its own initial sequence number to confirm that it has received the client's request and agrees to establish a connection. Finally, the client sends an ACK packet to the server to confirm that it has received the server's SYN-ACK packet. At this point, the TCP communication connection is successfully established.

[0072] Use standard protocol stack for data transmission: After the TCP connection is established, both parties start to transmit data through the standard protocol stack. The data is first cached in the buffer of the protocol stack, and then sliced ​​according to the size of the MTU (maximum transmission unit) to ensure that the data can be transmitted smoothly on the network. Next, the TCP module adds header information to the data, including sequence number, checksum, etc., to ensure the integrity and reliability of the data. Finally, the data is entrusted to the IP module for encapsulation and transmission.

[0073] Real-time collection of data packets during TCP communication: During data transmission, use network packet capture tools or write special programs to capture data packets during TCP communication in real time. These data packets contain key information such as source address, destination address, port number, data content, etc., which are crucial for subsequent data analysis and processing.

[0074] Storing collected data packets: The collected data packets need to be stored in a timely manner for subsequent data analysis, processing or visualization. The storage method can be a local database, distributed storage system or cloud storage, etc. The specific choice depends on factors such as data volume, storage requirements and processing performance. During the storage process, it is necessary to ensure the integrity and security of the data to avoid data loss or leakage.

[0075] S2: The collected TCP communication data is pre-processed by data cleaning, deduplication and formatting, and the processed data is deeply analyzed through data mining and machine learning algorithms to extract key features:

[0076] S21: removing invalid information, erroneous data and redundant data about null values, abnormal values ​​and duplicate data from the collected TCP communication data;

[0077] S22: Format the cleaned and deduplicated data to convert the data into a format suitable for subsequent analysis to keep the data consistent;

[0078] S23: Use data mining and machine learning algorithms to conduct in-depth analysis of the processed data and extract traffic patterns, response times, and abnormal behavior information from large amounts of data;

[0079] S24: Extract key features in TCP communication data that affect network performance, service quality, or security based on the analysis results of the data mining and machine learning algorithms.

[0080] In this embodiment:

[0081] Data cleaning: First, the collected TCP communication data is cleaned comprehensively. This step mainly removes invalid information, erroneous data and redundant data in the data, such as null values, abnormal values, duplicate data, etc. Through data cleaning, the data quality of subsequent analysis can be ensured and the accuracy and reliability of the analysis can be improved.

[0082] Data deduplication: Based on data cleaning, further deduplication is performed on the data. Since TCP communication data may contain a large amount of duplicate data, these duplicate data will interfere with subsequent data analysis and feature extraction. Therefore, data deduplication can effectively reduce data redundancy and improve the efficiency of data analysis.

[0083] Data formatting: Next, the cleaned and deduplicated data is formatted. Data formatting is to convert data into a format suitable for subsequent analysis, such as converting timestamps into a standard time format, converting numeric data into a numeric range suitable for analysis, etc. Data formatting can ensure the consistency and comparability of data, providing a basis for subsequent data mining and machine learning algorithms.

[0084] Application of data mining and machine learning algorithms: After data preprocessing is completed, data mining and machine learning algorithms are used to conduct in-depth analysis of the processed data. These algorithms can automatically extract useful information and patterns from large amounts of data, such as traffic patterns, response times, abnormal behaviors, etc. By applying these algorithms, the potential laws and features in the data can be revealed, providing strong support for subsequent feature extraction and data analysis.

[0085] Key feature extraction: Finally, based on the analysis results of data mining and machine learning algorithms, key features in TCP communication data are extracted. These features may be important factors affecting network performance, service quality or security, such as specific traffic patterns, abnormal response time, etc. By extracting key features, scientific basis and decision support can be provided for subsequent network performance optimization, service quality improvement or security warning.

[0086] S3: Based on the data analysis results, set warning rules and thresholds, monitor TCP communication data in real time, and send detected abnormal information to the host computer;

[0087] S31: Extract historical TCP communication data and business demand data, analyze the distribution, trend and correlation of the data, and identify abnormal patterns that may cause network performance degradation or security risks;

[0088] S32: Based on the analysis results, formulate specific warning rules, clarify which data changes or combinations are considered abnormal, and set corresponding thresholds;

[0089] S33: Design and deploy a system to monitor TCP communication data. The system collects, processes and analyzes TCP communication data in real time, and performs anomaly detection based on preset warning rules and thresholds.

[0090] S331: Collect historical TCP communication data as a training set. The data includes both normal and abnormal situations. The model learns the characteristics of normal data and the characteristics of abnormal data.

[0091] S332: extracting the flow size, the number of data packets, and the connection duration from the original TCP communication data to reflect the inherent regularity and abnormal pattern of the data;

[0092] S333: Use the extracted features and labels to train a machine learning model. During the training process, the model continuously adjusts its parameters to minimize the prediction error and learn the feature representation of normal data;

[0093] S334: Evaluate the performance of the model through a cross-validation method, and optimize the model by adjusting model parameters, increasing the number of features, and improving the feature extraction method according to the evaluation results;

[0094] S34: The anomaly detection and alarm mechanism automatically analyzes TCP communication data, determines whether there is an anomaly based on the warning rules and thresholds, and immediately triggers an alarm when an anomaly is detected, generating an alarm record containing detailed information about the anomaly, timestamp, and data source;

[0095] S35: Send the detected abnormal information to the host computer through the communication channel.

[0096] In this embodiment:

[0097] Interpretation of data analysis results: First, we conduct an in-depth interpretation of the previous data analysis results to identify possible abnormal patterns or key indicators in the TCP communication data. These analysis results will serve as an important basis for setting warning rules and thresholds to ensure that the warning system can accurately identify and respond to potential network problems.

[0098] Warning rules and threshold setting: Based on the data analysis results, develop detailed warning rules and set reasonable thresholds. Warning rules should clearly define which data changes or combinations are considered abnormal, and thresholds are used to quantify the standards for these abnormalities. For example, you can set a warning to be triggered when the traffic exceeds a certain value, or set an alarm to be issued when the response time exceeds a certain range.

[0099] Real-time monitoring system design: Next, design a system that can monitor TCP communication data in real time. The system should have the ability to collect, process and analyze real-time data in order to detect and respond to abnormal changes in a timely manner. At the same time, the system should also have high reliability and stability to ensure continuous and stable operation in a complex network environment.

[0100] Abnormal information detection and identification: The real-time monitoring system should integrate an abnormal information detection and identification module. This module can automatically analyze TCP communication data and determine whether there is an abnormality based on the preset warning rules and thresholds. Once an abnormality is detected, the system should immediately generate abnormal information and prepare to send it to the host computer.

[0101] Abnormal information is sent to the host computer: Finally, the detected abnormal information is sent to the host computer through a safe and reliable communication channel. As a monitoring and management center, the host computer can receive and display these abnormal information so that relevant personnel can take timely measures to deal with them. At the same time, the host computer can also record the historical data of abnormal information to provide a basis for subsequent analysis and improvement.

[0102] S4: The big data visualization platform generates charts of TCP communication data, data analysis results, and warning information, and independently displays abnormal information analysis results;

[0103] S41: The big data visualization platform collects data cleansing and format conversion of TCP communication data from network devices and server logs, and generates data analysis results including traffic trends, connection status, and performance parameters;

[0104] S42: Based on the data analysis results, the big data visualization platform generates corresponding line graphs, bar graphs, and pie charts to display the characteristics, trends, and analysis results of the TCP communication data;

[0105] S43: For abnormalities or warning information detected during data analysis, the big data visualization platform will specifically generate warning information charts that highlight the range of abnormal values ​​and the abnormal data characteristics of the occurrence time;

[0106] S44: The big data visualization platform will also provide an independent display area for displaying the results of abnormal information analysis. The area lists in detail all detected abnormal information, including abnormality type, occurrence time, and impact scope.

[0107] In this embodiment,

[0108] Data collection and preprocessing: First, the big data visualization platform needs to collect TCP communication data from various data sources, which may include network devices, server logs, etc. The collected data needs to be preprocessed, including data cleaning, format conversion, etc., to ensure the quality and consistency of the data and provide a basis for subsequent analysis and visualization.

[0109] Data analysis and result generation: The preprocessed data will be sent to the data analysis module, which uses various data analysis algorithms and technologies (such as statistical analysis, machine learning, etc.) to deeply mine TCP communication data and generate data analysis results including traffic trends, connection status, performance parameters, etc. These results will serve as an important basis for generating charts.

[0110] Chart generation and visualization: Based on the data analysis results, the big data visualization platform will generate corresponding charts, such as line charts, bar charts, pie charts, etc., to intuitively display the characteristics, trends and analysis results of TCP communication data. These charts can not only help users quickly understand the data, but also discover potential anomalies and problems.

[0111] Warning information chart generation: For abnormalities or warning information detected in data analysis, the big data visualization platform will generate warning information charts. These charts will highlight the characteristics of abnormal data, such as the range of abnormal values, the time of occurrence, etc., so that users can quickly locate and deal with these abnormal situations.

[0112] Independent display of abnormal information analysis results: In addition to generating charts, the big data visualization platform also provides an independent display area or interface specifically for displaying abnormal information analysis results. This area lists all detected abnormal information in detail, including abnormality type, occurrence time, impact range, etc., as well as suggestions or solutions given by the system. In this way, users can understand the abnormal situation in the current network environment at a glance and take appropriate measures to deal with it.

[0113] What is disclosed above is only one or more preferred embodiments of the present application, and cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A smart safety management and control system based on energy consumption big data analysis, characterized by: It includes a TCP communication module, a data analysis and processing module, an early warning module and a big data display module, wherein the data analysis and processing module receives the data collected by the TCP communication module, the early warning module receives the abnormal data output by the data analysis and processing module, and the big data display module receives the data of the TCP communication module, the data analysis and processing module and the early warning module; The TCP communication module is used to establish a data communication connection with a remote device and collect data in real time using the device standard protocol; The data analysis and processing module is used to format and remove noise from the original data, filter abnormal data, and detect and filter abnormal data using a machine learning model; The warning module is used to monitor according to the set warning rules and thresholds, and send the obtained warning information to the host computer; The big data display module is used to display the analysis results in the form of visual charts and web pages, and intuitively display the energy consumption usage and abnormal energy consumption points.

2. A smart safety management and control method based on energy consumption big data analysis, using the smart safety management and control system based on energy consumption big data analysis as claimed in claim 1, characterized in that: The steps include: Establish a TCP communication connection, use the standard protocol stack for data transmission, collect data packets in the TCP communication process in real time, and store the collected data packets; The collected TCP communication data is pre-processed by data cleaning, deduplication and formatting, and the processed data is deeply analyzed through data mining and machine learning algorithms to extract key features; Based on the data analysis results, set warning rules and thresholds, monitor TCP communication data in real time, and send detected abnormal information to the host computer; The big data visualization platform generates charts of TCP communication data, data analysis results, and warning information, and independently displays abnormal information analysis results.

3. The intelligent safety management and control method based on energy consumption big data analysis according to claim 1 is characterized in that: In "establishing a TCP communication connection, using a standard protocol stack for data transmission, collecting data packets in the TCP communication process in real time, and storing the collected data packets", the method includes the following steps: The client sends a SYN packet containing an initial sequence number to initiate a connection request to the server. After receiving the SYN packet, the server replies with a SYN-ACK packet containing its own initial sequence number. The client then sends an ACK packet to the server to confirm receipt of the server's SYN-ACK packet, and the TCP communication connection is successfully established. After the TCP connection is established, the data is cached in the buffer of the protocol stack and then sliced ​​according to the size of the maximum transmission unit. The TCP module adds header information to the data, and the data is entrusted to the IP module for encapsulation and transmission; During data transmission, use a network packet capture tool to capture data packets containing source address, destination address, port number, and data content during TCP communication in real time; The collected data packets are stored in the local database and distributed storage system.

4. The intelligent safety management and control method based on energy consumption big data analysis according to claim 1 is characterized in that: In "pre-processing the collected TCP communication data by cleaning, deduplication and formatting, and performing in-depth analysis on the processed data through data mining and machine learning algorithms to extract key features", the steps include: Remove invalid information, erroneous data and redundant data about null values, abnormal values ​​and duplicate data from the collected TCP communication data; Format the cleaned and deduplicated data and convert it into a format suitable for subsequent analysis to keep the data consistent; Use data mining and machine learning algorithms to conduct in-depth analysis of processed data and extract traffic patterns, response times, and abnormal behavior information from large amounts of data; Based on the analysis results of data mining and machine learning algorithms, key features that affect network performance, service quality or security in TCP communication data are extracted.

5. The intelligent safety management and control method based on energy consumption big data analysis according to claim 1 is characterized in that: In "based on the data analysis results, setting warning rules and thresholds, real-time monitoring of TCP communication data, and sending detected abnormal information to the host computer", the method also includes the following steps: Extract historical TCP communication data and business demand data, analyze the distribution, trends and correlation of the data, and identify abnormal patterns that may lead to network performance degradation or security risks; Based on the analysis results, formulate specific warning rules, clarify which data changes or combinations are considered abnormal, and set corresponding thresholds; Design and deploy a system to monitor TCP communication data. The system collects, processes and analyzes TCP communication data in real time, and performs anomaly detection based on preset warning rules and thresholds. The anomaly detection and alarm mechanism automatically analyzes TCP communication data, determines whether there is an anomaly based on the warning rules and thresholds, triggers an alarm immediately when an anomaly is detected, and generates an alarm record containing detailed information about the anomaly, timestamp, and data source; The detected abnormal information is sent to the host computer through the communication channel.

6. A smart safety management and control method based on energy consumption big data analysis as claimed in claim 5, characterized in that: In "Designing and deploying a system for monitoring TCP communication data, the system collects, processes and analyzes TCP communication data in real time, and performs anomaly detection according to preset warning rules and thresholds", the method includes: Collect historical TCP communication data as a training set. The data contains both normal and abnormal situations. The model learns the characteristics of normal data and the characteristics of abnormal data. Extract traffic size, number of packets, and connection duration from raw TCP communication data to reflect the inherent regularities and abnormal patterns of the data; Use the extracted features and labels to train a machine learning model. During the training process, the model continuously adjusts its parameters to minimize the prediction error and learn the feature representation of normal data. The performance of the model was evaluated through the cross-validation method, and the model was optimized by adjusting model parameters, increasing the number of features, and improving feature extraction methods based on the evaluation results.

7. The intelligent safety management and control method based on energy consumption big data analysis according to claim 1 is characterized in that: In "The big data visualization platform generates charts of TCP communication data, data analysis results and warning information, and independently displays abnormal information analysis results", the method includes the following steps: The big data visualization platform collects data cleaning and format conversion of TCP communication data from network devices and server logs, and generates data analysis results including traffic trends, connection status, and performance parameters; Based on the data analysis results, the big data visualization platform generates corresponding line graphs, bar graphs, and pie charts to display the characteristics, trends, and analysis results of TCP communication data; For abnormalities or warning information detected during data analysis, the big data visualization platform will generate a special warning information chart that highlights the range of abnormal values ​​and the abnormal data characteristics of the occurrence time; The big data visualization platform also provides an independent display area for displaying the results of abnormal information analysis. The area lists in detail all detected abnormal information, including abnormality type, occurrence time, and impact scope.

Images