An intelligent central control system for commercial tablet computers

Abstract

The invention discloses an intelligent central control system for a commercial tablet computer, relates to the technical field of central control of commercial tablet computers, and is used to solve the problem of poor central control efficiency; it comprises a data synchronization module, a model algorithm analysis module, a central state synchronization module, and a central control module; the invention classifies data and sets synchronization rules for the tablet computer, uses a Merkle tree to identify data differences between devices, synchronizes changed data blocks, and applies an ARIMA model to perform time series analysis on network and system performance indicators to determine subsequent performance changes, then introduces an isolation forest algorithm to enhance the system's ability to detect abnormal points, can quickly locate and respond to performance abnormalities, improve the stability and reliability of the system, and continuously monitors the synchronization of performance indicators of the commercial tablet computer with actual operating conditions, obtains key control impact information in real time, thereby generating a central request control signal or a stable operation signal, and performing corresponding central control.

Description

Technical Field

[0001] The present invention relates to the technical field of central control of a commercial tablet computer, and more specifically, to an intelligent central control system of a commercial tablet computer. Background Art

[0002] As part of modern technology, commercial tablets have been widely used in various industries, from retail, medical to education and service industries. These devices not only undertake the functions of data input and display, but also become important tools for performing complex tasks and data processing. With the development of the Internet of Things (IoT) and artificial intelligence (AI), the demand for intelligent central control systems of commercial tablets is growing. These systems can integrate and manage data collected from various devices and sensors to achieve automated control and decision support.

[0003] Deficiencies in existing technologies: When commercial tablets process and transmit large amounts of data, delays are inevitable when data is synchronized between devices due to the tablet's processing power and memory limitations. Insufficient data transmission speed makes it difficult to support real-time data analysis and instant decision-making, especially in a multi-device environment. The requirements for data consistency and real-time updates are difficult to adapt to the processing power of existing tablets. In scenarios that require rapid business response, manual adjustments due to the lack of automatic control by an intelligent center are bound to result in errors and omissions, which in turn affects the efficiency of commercial tablet devices in data-intensive applications. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention classifies data and sets synchronization rules for tablet computers, uses Merkle trees to identify data differences between devices, synchronizes changed data blocks, and applies the ARIMA model to perform time series analysis on network and system performance indicators, so that future performance changes can be predicted. Then, the isolation forest algorithm is introduced to enhance the system's ability to detect abnormal points, and can quickly locate and respond to performance anomalies, improve the stability and reliability of the system, and continuously monitor the synchronization of performance indicators of commercial tablet computers with actual operating conditions, and obtain key control impact information in real time, thereby generating a central request control signal or a stable operation signal, and performing corresponding intelligent central control, so as to solve the problem of poor intelligent central control of commercial tablet computers proposed in the above-mentioned background technology, which affects the use efficiency.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent central control system for a commercial tablet computer includes a data synchronization module, a model algorithm analysis module, a central state synchronization module and a central control module, and each module is connected by a signal;

[0007] The data synchronization module is used to determine the usage scenarios of tablet computers in commercial environments and classify the data by business functions, set synchronization rules, use Merkle trees to identify data differences between commercial tablet computers, identify changed data blocks, and synchronize the different parts of the data blocks;

[0008] Model algorithm analysis module, which applies ARIMA model to perform time series analysis on network and system performance indicator data, and uses isolation forest algorithm to detect abnormal points in network and system performance indicator data;

[0009] A central state synchronization module is used to analyze the synchronization between the performance monitoring of the commercial tablet computer and the actual operating conditions, and obtain the control influence information generated during the performance state synchronization process of the commercial tablet computer;

[0010] The central control module is used to analyze the control impact information and generate different signals, and determine the central control strategy of the commercial tablet computer according to the generated different signals.

[0011] In a preferred embodiment, the specific steps for determining the usage scenario of a tablet computer in a commercial environment and classifying the data by business functions and setting synchronization rules are as follows:

[0012] Categorize and prioritize data based on business needs, and label data with different priorities based on business impact;

[0013] Set synchronization rules based on data classification and business impact. Synchronization rules include real-time synchronization, scheduled synchronization, and on-demand synchronization.

[0014] In a preferred embodiment, the Merkle tree is used to identify the data differences between the commercial tablet devices, identify the changed data blocks, and synchronize the different parts of the data blocks. The specific steps include:

[0015] Aggregate the data of each commercial tablet device as a data set and construct each Merkle tree to split the data set into data blocks;

[0016] Take the hash value of the data block as the leaf node, and recursively calculate the hash value of the parent node from bottom to top until the root node of the tree is formed. The hash value of each parent node is the combination of the hash values ​​of the two child nodes;

[0017] During the data synchronization process, the Merkle tree root hash values ​​on the two commercial tablet devices are compared. If the root hash values ​​are different, the hash values ​​of the child nodes are recursively compared downward until different leaf nodes are located.

[0018] When a data block with a different hash value is identified, the data block is synchronized to another commercial tablet, and the hash value of the relevant node is updated and the hash values ​​of all affected parent nodes are recursively updated until the root node.

[0019] In a preferred embodiment, the ARIMA model is applied to perform time series analysis on network and system performance index data, and the isolation forest algorithm is used to detect abnormal points in the network and system performance index data. The specific steps are as follows:

[0020] Perform data cleaning to remove or correct missing, erroneous or abnormal data records;

[0021] First, use the ADF test method to check whether the data is stable. If the data is not stable, perform differential processing to convert the non-stationary time series into a stable time series through first-order or multi-order differences;

[0022] Apply the ARIMA model to the stationary time series data for time series analysis and predict the trend of network and system performance indicators;

[0023] Initialize the forest, set the number of trees and the number of samples per tree, and extract samples to construct isolated trees;

[0024] Randomly select a feature in the feature set, and randomly select a split value between the maximum and minimum values ​​of the randomly selected feature;

[0025] Divide the data into two subsets according to the split value, and repeat the process until each leaf node contains only one data point or the preset maximum tree depth is reached;

[0026] In each tree, calculate the path length from the root node to each leaf node;

[0027] The average path length between a given data point and all trees in the forest is used to calculate the anomaly score of the data point;

[0028] Set the anomaly score threshold based on business needs or experience. Points with scores higher than this threshold are marked as anomalies.

[0029] In a preferred embodiment, the method for analyzing the synchronization between the performance monitoring of a commercial tablet computer and the actual operating conditions and obtaining the control influence information generated during the synchronization of the performance status of the commercial tablet computer includes the following steps:

[0030] The control impact information includes performance update information and abnormal response information. The performance update information includes a baseline update fluctuation index, and the abnormal response information includes an abnormal detection response index.

[0031] The baseline update fluctuation index in the performance update information and the anomaly detection response index in the anomaly response information are combined to generate a central control coefficient;

[0032] The baseline update fluctuation index is directly proportional to the central control coefficient, and the anomaly detection response index is inversely proportional to the central control coefficient.

[0033] In a preferred embodiment, the control influence information is analyzed and different signals are generated, and the central control strategy of the commercial tablet computer is determined according to the generated different signals. The specific steps are as follows:

[0034] Comparing the central control coefficient with a preset control evaluation threshold;

[0035] If the central control coefficient is less than the control evaluation threshold, a central stable operation signal is generated and the central control continues without additional central strategy control;

[0036] If the central control coefficient is greater than or equal to the control evaluation threshold, a central request control signal is generated, control intervention is performed, and the central control strategy of the commercial tablet computer is adjusted.

[0037] The technical effects and advantages of the intelligent central control system of a commercial tablet computer of the present invention are as follows:

[0038] The present invention performs fine data classification and synchronization rule settings on tablet computers, uses Merkle trees to efficiently identify data differences between devices, and only synchronizes changed data blocks, thereby improving data synchronization efficiency and reducing network load. Then, the ARIMA model is used to perform time series analysis on network and system performance indicators, making future performance changes predictable, thereby optimizing resource allocation and maintenance plans. The introduction of the isolation forest algorithm further enhances the system's ability to detect anomalies, can quickly locate and respond to performance anomalies, and improve the stability and reliability of the system.

[0039] By continuously monitoring the synchronization of the performance indicators of commercial tablets with actual operating conditions, key control impact information can be obtained in real time, thereby generating central request control signals or stable operation signals. These signals provide accurate data support for decision makers, enabling them to adjust the central control strategy according to the current state of the system, ensuring efficient operation of the system and business continuity, significantly improving the operating efficiency and data processing capabilities of commercial tablets in complex business environments, and bringing significant efficiency improvements and performance optimization to the intelligent central control system of commercial tablets. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention is a schematic structural diagram of an intelligent central control system of a commercial tablet computer. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In order to achieve the above objectives, Figure 1 The present invention provides a schematic structural diagram of an intelligent central control system for a commercial tablet computer, which specifically includes a data synchronization module, a model algorithm analysis module, a central state synchronization module and a central control module, and each module is connected by a signal;

[0043] The data synchronization module is used to determine the usage scenarios of tablet computers in commercial environments and classify the data by business functions, set synchronization rules, use Merkle trees to identify data differences between commercial tablet computers, identify changed data blocks, and synchronize the different parts of the data blocks;

[0044] Model algorithm analysis module, which applies ARIMA model to perform time series analysis on network and system performance indicator data, and uses isolation forest algorithm to detect abnormal points in network and system performance indicator data;

[0045] A central state synchronization module is used to analyze the synchronization between the performance monitoring of the commercial tablet computer and the actual operating conditions, and obtain the control influence information generated during the performance state synchronization process of the commercial tablet computer;

[0046] The central control module is used to analyze the control impact information and generate different signals, and determine the central control strategy of the commercial tablet computer according to the generated different signals.

[0047] Analyze the usage scenarios of tablet computers in commercial environments, such as inventory management, order processing, customer data updates, etc., determine the data that needs to be updated in real time and the data that can be processed later, and classify the business functions. Classify the data according to the business functions it supports, such as financial data, customer interaction data, inventory management data, etc.;

[0048] Define data priorities, classify and prioritize data according to business needs. Critical data (such as transaction records and inventory levels) enjoy higher synchronization priority. The specific steps are as follows:

[0049] Classify the collected data according to its business impact and mark it with different priorities. Business impact can be from financial analysis, that is, evaluating the factors that affect expected revenue, cost, and profit, risk assessment analysis, that is, identifying and evaluating potential risks and formulating response strategies, etc.

[0050] High priority (P1): data that directly affects business operations and customer satisfaction, such as transaction records and inventory levels;

[0051] Medium priority (P2): data that has an impact on business decisions but does not require immediate feedback, such as sales trend analysis;

[0052] Low priority (P3): data with little impact on the business and can be updated less frequently, such as historical transaction data and outdated customer feedback;

[0053] Synchronization rules are set based on data classification and business impact. P1 data is synchronized in real time to ensure timely data update regardless of network conditions. P2 data is synchronized on a scheduled basis and can be set to automatically update during non-peak hours to reduce network load. P3 data is synchronized on demand and is updated only when there is a specific need or when the system load is low.

[0054] Merkle tree technology is used to quickly detect and identify data differences between commercial tablet devices. Data differences are identified by comparing the root hash values ​​of the tree, and data snapshots of commercial tablet devices are compared to identify changed data blocks and synchronize the differences. The specific steps are as follows:

[0055] The data of each commercial tablet device is aggregated as a data set and constructed into its own Merkle tree. Each data set is divided into smaller data blocks. The size of each data block can be determined according to the actual application and data characteristics, such as 1KB or 10KB per block. A hash value is calculated for each data block. The hash function can be selected such as SHA-256 to ensure security and minimize conflicts.

[0056] Take the hash value of the data block as the leaf node, and recursively calculate the hash value of the parent node from bottom to top until the root node of the tree is formed. The hash value of each parent node is the combination of the hash values ​​of its two child nodes.

[0057] At the beginning of data synchronization, the Merkle tree root hash values ​​on the two commercial tablet devices are compared first. If the root hash values ​​are different, the hash values ​​of the child nodes are recursively compared downward until the specific different leaf nodes are located;

[0058] Perform data synchronization. When a data block with a different hash value is identified, the data block is synchronized to another device. After the data block is synchronized, the hash value of the relevant node is updated, and the hash values ​​of all affected parent nodes are recursively updated until the root node.

[0059] Through this method, the Merkle tree can not only synchronize data efficiently, but also ensure the security and integrity of the data. It is suitable for ensuring data consistency between commercial tablets in an environment with large and distributed data volumes.

[0060] The setup mechanism dynamically adjusts the priority of data synchronization according to the network status and system load to ensure optimal use of system resources. The specific steps are as follows:

[0061] Monitor the network status and system load of the commercial tablet computer intelligent central control system. Choose enterprise-level monitoring tools such as Zabbix. Monitoring tools can provide a wide range of monitoring functions, including network and system performance monitoring. For network traffic monitoring, you can use tools such as NetFlow or s-Flow to provide detailed network traffic data.

[0062] Deploy monitoring agents on commercial tablets to collect network and system performance data on the local computer. Use the bandwidth usage, latency, and packet loss rate in the collected data as network performance indicators; use CPU usage, memory usage, and storage I / O performance as system performance indicators.

[0063] Clean the network and system performance indicators collected by monitoring tools, remove or correct missing, erroneous or abnormal data records, ensure data quality, and generate additional features, such as hourly, daily, and weekly periodic indicators to capture periodic fluctuations;

[0064] Apply ARIMA model to perform time series analysis to predict the trend of network and system performance indicators;

[0065] The ARIMA model construction process is to first use methods such as ADF (Augmented Dickey-Fuller) test to check whether the data is stationary. If the data is not stationary, it is necessary to perform difference processing to convert the non-stationary time series into a stationary time series through first-order or multi-order differences;

[0066] Determine the parameters p, d, and q of the model. p is the number of autoregressive (AR) terms, which is determined by the ACF (autocorrelation function) and PACF (partial autocorrelation function) graphs. d is the number of differences, which is used to make the data stable. q is the number of moving average (MA) terms, which is determined by the ACF and PACF graphs. Autoregressive (AR) part: , the formula for the moving average (MA) part is: , the ARIMA model can be defined as: ,in, is the data value at time t, represents the AR partial coefficient, represents the white noise at time t, θ is used to represent the coefficient of the MA part, Represents the data value after d times difference;

[0067] Use the training data to fit the ARIMA model, and use residual tests (such as the Ljung-Box test) to check the model's fit to ensure that the residuals are white noise. The Ljung-Box test statistic calculation expression is: , where n is the sample size, represents the sample autocorrelation coefficient of lag k, where m is the number of lags;

[0068] After the Ljung-Box test is used to verify that the model fitting effect meets the standard, the trained ARIMA model is used to perform time series forecasting to determine the trend of performance indicators. That is, ARIMA can be used to predict the future trends of key performance indicators such as network bandwidth usage, CPU usage, and memory requirements.

[0069] By predicting future performance requirements, intelligent central control can adjust resource allocation in advance, such as expanding capacity or optimizing load balancing in advance, to cope with expected high-load periods. By promptly identifying trends that may lead to performance degradation, the system can intervene before the problem becomes serious, such as performing maintenance or reconfiguration, thereby improving system availability and stability.

[0070] Use the isolation forest algorithm to detect abnormal points in performance indicator data, extract or select key indicators that reflect system status from network and system performance indicators, such as CPU usage, and standardize the features of key indicators so that the mean of each feature is 0 and the variance is 1;

[0071] Build an isolation forest, initialize the forest, set the number of trees T and the number of samples per tree M. Common settings are 100 to 500 trees, and the number of samples per tree depends on the size of the dataset, but is usually less than 256;

[0072] For each tree, m samples are randomly selected and isolated trees are constructed;

[0073] Randomly select features, randomly select a feature in the feature set; randomly select a split value, randomly select a split value between the maximum and minimum values ​​of the feature;

[0074] Split the node, divide the data into two subsets according to the split value, and repeat this process until each leaf node contains only one data point or reaches the preset maximum tree depth;

[0075] Path length analysis: In each tree, the path length from the root node to each leaf node is calculated. Data points with shorter path lengths are more likely to be anomalies.

[0076] Normalized path length analysis, that is, for a given data point, the average path length of all trees in the forest is used to calculate its anomaly score. The calculation formula of the anomaly score s(x, n) is: , where E(h(x)) is the average path length of data point x in all trees, and c(n) is a normalization factor, usually the average path length in a completely balanced binary tree, calculated as: , where H(i) is the harmonic number of i, approximately equal to ln(i)+0.57.

[0077] To mark anomalies, first set a threshold, that is, set an anomaly score threshold based on business needs or experience. Points with scores higher than this threshold are marked as anomalies.

[0078] The Isolation Forest algorithm is used to monitor and identify abnormal behaviors in network traffic and hardware performance indicators, such as sudden increases in traffic and memory leaks. By detecting data patterns that are significantly different from normal patterns, the Isolation Forest helps identify potential security threats. Anomaly detection can quickly locate the source of system performance problems, such as an application consuming too many resources or misconfigured, allowing the maintenance team to respond and resolve the problem quickly.

[0079] The time series prediction capability of the ARIMA model enables the intelligent central control system of commercial tablet computers to predict performance requirements and potential problems during subsequent use, thereby making policy adjustments in advance, such as increasing server processing power or optimizing database queries. The real-time anomaly detection function of the isolation forest algorithm improves the system's response speed to emergencies, thereby reducing system downtime and potential business losses.

[0080] Performance monitoring is synchronized with actual operating conditions, which means that the settings and parameters of the monitoring system should be able to reflect and adapt to the current working environment and operating status of the central system in real time. This synchronization ensures that the performance monitoring data accurately represents the performance of the central system in actual use, allowing the operation and maintenance team to respond immediately to performance fluctuations, potential problems, or optimization opportunities. In actual operation, factors such as the workload, user activity, and network conditions of the central system may change continuously. If the performance monitoring settings are fixed, the monitoring results may not truly reflect the current system status, resulting in data interpretation errors, delayed or inaccurate responses.

[0081] Monitor and analyze the performance status matching of the commercial tablet computer, and determine the synchronization between the performance monitoring of the commercial tablet computer and the actual operating conditions based on the monitoring and analysis results. The specific steps are as follows:

[0082] The central state synchronization module is used to monitor and analyze the synchronization between the performance monitoring of the commercial tablet computer and the actual operating conditions, and obtain the control impact information generated during the performance state synchronization process of the commercial tablet computer, and the control impact information includes performance update information and abnormal response information;

[0083] The performance update information includes a baseline update fluctuation index, and the abnormal response information includes an abnormal detection response index;

[0084] The baseline update fluctuation index in the performance update information is used to measure the degree of fluctuation of key performance indicators in the intelligent central control system of the commercial tablet computer relative to its dynamic baseline, and to analyze and evaluate the stability and consistency of system performance indicators;

[0085] The baseline update volatility index evaluates the central stability of commercial tablet computers by quantifying the degree of deviation of each performance indicator from its baseline. A smaller volatility index value indicates that the commercial tablet computer is running stably, the performance indicator fluctuates little, and is consistent with the expected baseline. By monitoring the statistical parameters of the degree of deviation (mean, variance, and skewness), the baseline update volatility index reflects different performance issues. For example, frequent large fluctuations may indicate potential hardware failures or configuration problems, and often show abnormal performance fluctuations before major failures occur. The baseline update volatility index can help the maintenance team take timely measures to avoid or mitigate the impact of failures by identifying these abnormal fluctuations in advance.

[0086] In the intelligent central control system of commercial tablet computers, the application of baseline update fluctuation index plays the following key roles:

[0087] Optimized performance monitoring: Provides a comprehensive performance measurement tool to help technical teams more accurately monitor and evaluate system performance, especially when the system is experiencing rapid changes or is under high load;

[0088] Support decision making: With a deep understanding of system performance fluctuations of commercial tablets, decision makers can better plan resource allocation, system upgrades or other maintenance activities to optimize system performance and reliability;

[0089] Dynamically adjust resources: With the dynamic update of the baseline update fluctuation index, the system can implement automated resource management strategies, such as automatically adjusting computing resource allocation based on current performance fluctuations and system load.

[0090] The baseline update volatility index is obtained as follows:

[0091] Get the key performance indicators. For each key performance indicator k, get the measured value of the key performance indicator at time t. , get the dynamic average value within a specific time window W The indicator deviation is calculated as follows: , where represents the deviation of the kth key performance indicator at time t, is the dynamic standard deviation of the key performance indicator;

[0092] Calculate the average deviation degree in a specific time window W. The calculation expression is: , calculate the index deviation variance value, the calculation expression is: , calculate the baseline update fluctuation index, the calculation expression is: .

[0093] It should be noted that the key performance indicators include at least one performance indicator data. The key performance indicators are determined based on the data in the network performance indicators or system performance indicators, such as bandwidth utilization, latency, etc., and the key performance indicators of different periods are selected according to different settings; the size of the time window is set according to actual needs, including multiple moments; the dynamic average and dynamic standard deviation are calculated by averaging and standard deviation of the measured values ​​obtained at all moments in the time window.

[0094] The abnormal detection response index in the abnormal response information is an indicator used to evaluate the efficiency and effectiveness of the intelligent central control system of commercial tablet computers in identifying and responding to abnormal behaviors. It measures the time required from the detection of the abnormality to the system's response to it (such as repair, alarm or other measures). It reflects the rapidity with which the control system detects the problem and takes measures. It evaluates the degree to which the performance returns to normal after the system responds. This not only involves the immediate effect of the response measures, but also includes the sustainability and stability of the long-term effects. The effects on the intelligent central control of commercial tablet computers are as follows:

[0095] Improve system stability: Through effective and timely exception response, the anomaly detection response index helps maintain the stable operation of the system. Abnormal situations such as hardware failures, software errors or security threats can be quickly identified and handled, reducing their impact on the overall system performance;

[0096] Optimize resource allocation: The Anomaly Detection Response Index helps management teams better understand how to allocate technical and human resources by monitoring the efficiency of anomaly responses. For example, if the response to a certain type of anomaly is not effective, it may be necessary to increase resources in this area or optimize the existing response strategy.

[0097] Improve fault recovery capabilities: The anomaly detection response index emphasizes the speed and effectiveness of fault recovery, helping system designers and operators improve fault recovery strategies, which is critical for business operations, especially in business environments with sensitive data or extremely high service continuity requirements.

[0098] The anomaly detection response index is obtained as follows:

[0099] Get the time point set where the anomaly was detected ,in, Includes n time points when anomalies are detected, and obtains a set of time points for responding to anomalies ,in, Includes n time points for responding to anomalies, and calculates the response time difference for anomaly i , the calculation expression is: , where Indicates the time point of responding to exception i, Indicates the time point when anomaly i is detected, and calculates the response time consistency value. The calculation expression is: , where is the average response time difference;

[0100] Obtain the indicator value measured after the response measures are implemented , get the baseline value of the indicator before the abnormality occurs , calculate the response ratio, the expression is: , get the average response ratio of c responses, calculate the response value, and the calculation expression is: , calculate the anomaly detection response index, the calculation expression is: .

[0101] It should be noted that the average response ratio of c responses is obtained by predicting and analyzing the short-term effects to determine abnormal fluctuations, and the value of c is set according to actual needs;

[0102] The performance update information and the abnormal response information are combined to generate the central control coefficient, that is, the baseline update fluctuation index BUVI and the abnormal detection response index ADRI are obtained to jointly generate the central control coefficient. The central control coefficient is expressed as: , where is the central control coefficient, , The preset scaling coefficients for the baseline update volatility index BUVI and the anomaly detection response index ADRI, and , Both are greater than 0.

[0103] The specific method of jointly generating the central control coefficient may involve a variety of algorithms and models, depending on the actual situation and application requirements. This embodiment can use a weighted summation method to combine the baseline update fluctuation index and the anomaly detection response index to generate a comprehensive central control coefficient. This central control coefficient can be used as an input parameter for central control analysis to determine the stability of data transmission analysis of commercial tablet computers, thereby ensuring the stability of data transmission analysis through intelligent central control during subsequent monitoring.

[0104] It should be noted that the size of the preset proportional coefficient is to quantify each parameter to obtain a specific numerical value. In order to facilitate subsequent comparison, the size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding preset proportional coefficient for each group of sample data by technical personnel in this field. It is not unique, as long as it does not affect the proportional relationship between the parameter and the quantized numerical value. For example, the baseline update fluctuation index is proportional to the central control coefficient. The baseline update fluctuation index and the anomaly detection response index are normalized to have the same dimension and range. This can be achieved by subtracting the mean from the original data and dividing it by the standard deviation, or mapping the data to the range of [0, 1].

[0105] The larger the baseline update fluctuation index and the smaller the anomaly detection response index, the larger the jointly generated central control coefficient is, indicating that the central system of the commercial tablet computer has poor response effect and timeliness when facing performance fluctuations. It may be necessary to improve or optimize the central control system to enhance its stability and responsiveness, and conduct regular monitoring and analysis. According to the analysis results, adjust and optimize the system configuration and resource allocation, thereby improving the central system of the commercial tablet computer's ability to prevent potential failures, and enhancing business continuity and the overall reliability of the system;

[0106] The smaller the baseline update fluctuation index and the larger the anomaly detection response index, the smaller the jointly generated central control coefficient is, indicating that the central system of the commercial tablet computer is stable and responds quickly and effectively to anomalies, the system management and maintenance strategies are properly implemented, the system is properly configured, and can adapt to various situations. This is a healthy system state and should be maintained;

[0107] A low baseline update volatility index indicates that the system's performance fluctuations are small, that is, the system exhibits a high degree of stability during operation, and baseline indicators (such as CPU usage, memory usage, network latency, etc.) remain in a relatively constant range without large fluctuations, which means that the system can maintain consistent performance under different operating conditions;

[0108] A high anomaly detection response index indicates that the system is very effective in identifying and responding to anomalies. This means that once the system detects any behavior that deviates from normal operation, it can quickly take measures to repair or adjust it to minimize potential negative impacts. A high response index is usually associated with fast fault recovery time, efficient problem solving, and excellent maintenance practices.

[0109] Compare the generated central control coefficient with the preset control evaluation threshold to generate a central request control signal and a central stable operation signal;

[0110] After obtaining the central control coefficient, the central control coefficient is compared with the control evaluation threshold;

[0111] If the central control coefficient is greater than or equal to the control evaluation threshold, a central request control signal is generated, which indicates that the system performance fluctuates greatly or the response to the abnormality is not timely or effective enough. There may be insufficient resources, improper configuration, potential failures or performance bottlenecks, which require immediate attention and intervention, and adjustment of the central control strategy;

[0112] If the central control coefficient is less than the control evaluation threshold, a central stable operation signal is generated, which means that the system operates stably, performance fluctuations are small, and the response to abnormalities is fast and effective. The current configuration and resource allocation of the central system are appropriate and can meet operational requirements well, and no additional central strategy control is required.

[0113] It should be noted that by setting and calculating the control evaluation threshold, the generated central control coefficient can be effectively compared to help the central system allocate resources and optimize management. Setting reasonable thresholds can ensure that high-demand resources are given priority and improve the overall efficiency and stability of the central system. Relevant thresholds can be set and adjusted using statistical analysis, empirical methods or dynamic adjustment methods.

[0114] According to the generated central request control signal or central stable operation signal, corresponding signal processing and feedback control can be performed;

[0115] When a central request control signal is generated, a detailed performance diagnosis is immediately performed to find the cause of the high CCC value, such as resource bottlenecks, abnormal loads, or configuration errors. Based on the diagnosis results, necessary resources (such as CPU, memory expansion), load balancing settings, or network configuration optimization are added.

[0116] Automatically adjust system configuration or resource allocation according to preset rules. For example, scale cloud infrastructure resources through automated scripts or management software, and use intelligent monitoring tools to dynamically adjust system performance settings to reduce immediate load pressure.

[0117] For example, introduce intelligent load balancing, especially in a multi-device environment, and implement intelligent load balancing technology to ensure that data processing and transmission tasks are evenly distributed among devices to avoid overloading any single device;

[0118] Use policy-based routing algorithms to dynamically route data requests and processing tasks based on the processing capabilities and current load of the devices. For example, dynamically assign tasks based on the real-time performance data of the devices. This can be based on simple conditions such as "if the CPU utilization of device A is > 80%, then route the new task to device B";

[0119] Monitor the operation status of the entire system, especially the load conditions of each device and the efficiency of processing tasks, and adjust the load balancing configuration and strategy according to the monitoring results to improve the overall performance and response speed of the system.

[0120] When the central stable operation signal is generated, it indicates that the current system status is good and no immediate intervention is required, but the following strategies can be implemented to maintain the optimal state of the system:

[0121] Continue to implement comprehensive system monitoring to ensure that any minor performance changes or potential problems are captured in a timely manner. Analyze historical performance data to find optimization points, improve system efficiency, and reduce the probability of future problems.

[0122] Regularly perform central system maintenance, such as updating software, clearing cache, checking central system logs, etc., to prevent performance from gradually declining, and update and optimize existing central system control strategies, such as adjusting automated maintenance scripts, improving resource allocation algorithms, etc.

[0123] It should be noted that the threshold information in this embodiment is pre-set by professionals and will not be explained in detail here. Some parameter English letters in the embodiments have the same situation, but different meanings are explained when used, which will not be explained one by one here.

[0124] The present invention performs fine data classification and synchronization rule settings on tablet computers, uses Merkle trees to efficiently identify data differences between devices, and only synchronizes changed data blocks, thereby improving data synchronization efficiency and reducing network load. Then, the ARIMA model is used to perform time series analysis on network and system performance indicators, making future performance changes predictable, thereby optimizing resource allocation and maintenance plans. The introduction of the isolation forest algorithm further enhances the system's ability to detect anomalies, can quickly locate and respond to performance anomalies, and improve the stability and reliability of the system.

[0125] By continuously monitoring the synchronization of the performance indicators of commercial tablets with actual operating conditions, key control impact information can be obtained in real time, thereby generating central request control signals or stable operation signals. These signals provide accurate data support for decision makers, enabling them to adjust the central control strategy according to the current state of the system, ensuring efficient operation of the system and business continuity, significantly improving the operating efficiency and data processing capabilities of commercial tablets in complex business environments, and bringing significant efficiency improvements and performance optimization to the intelligent central control system of commercial tablets.

[0126] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0127] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0128] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0129] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0130] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0131] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent central control system for a commercial tablet computer, characterized in that: It includes a data synchronization module, a model algorithm analysis module, a central state synchronization module and a central control module, and each module is connected by signals; The data synchronization module is used to determine the usage scenarios of tablet computers in commercial environments and classify the data by business functions, set synchronization rules, use Merkle trees to identify data differences between commercial tablet computers, identify changed data blocks, and synchronize the different parts of the data blocks; Model algorithm analysis module, which applies ARIMA model to perform time series analysis on network and system performance indicator data, and uses isolation forest algorithm to detect abnormal points in network and system performance indicator data; A central state synchronization module is used to analyze the synchronization between the performance monitoring of the commercial tablet computer and the actual operating conditions, and obtain the control influence information generated during the performance state synchronization process of the commercial tablet computer; A central control module is used to analyze the control influence information and generate different signals, and determine the central control strategy of the commercial tablet computer according to the generated different signals; It is used to determine the usage scenarios of tablet computers in commercial environments, classify data by business functions, and set synchronization rules. The specific steps are as follows: Categorize and prioritize data based on business needs, and label data with different priorities based on business impact; Set synchronization rules based on data classification and business impact. Synchronization rules include real-time synchronization, scheduled synchronization, and on-demand synchronization. The method is used to analyze the synchronization between the performance monitoring of the commercial tablet computer and the actual operating conditions, and obtain the control influence information generated during the synchronization process of the performance status of the commercial tablet computer, including the following steps: The control impact information includes performance update information and abnormal response information. The performance update information includes a baseline update fluctuation index, and the abnormal response information includes an abnormal detection response index. The baseline update fluctuation index in the performance update information and the anomaly detection response index in the anomaly response information are combined to generate a central control coefficient; The baseline update fluctuation index is directly proportional to the central control coefficient, and the abnormal detection response index is inversely proportional to the central control coefficient; The baseline update fluctuation index indicates the degree of fluctuation of the key performance indicators in the intelligent central control system of the commercial tablet computer relative to the dynamic baseline; The anomaly detection response index indicates the stability of the intelligent central control system of the commercial tablet computer in identifying and responding to abnormal behaviors; The baseline update volatility index is obtained as follows: Get the key performance indicators. For each key performance indicator k, get the measured value of the key performance indicator at time t. , get the dynamic average value within the time window W The indicator deviation is calculated as follows: , where represents the deviation of the kth key performance indicator at time t, is the dynamic standard deviation of the key performance indicator k; Calculate the average deviation degree in the time window W. The calculation expression is: , calculate the index deviation variance value, the calculation expression is: , calculate the baseline update fluctuation index, the calculation expression is: ; The anomaly detection response index is obtained as follows: Get the time point set where the anomaly was detected ,in, Includes n time points when anomalies are detected, and obtains a set of time points for responding to anomalies ,in, Includes n time points for responding to exceptions, and calculates the response time difference for exception i , the calculation expression is: , where Indicates the time point of responding to exception i, Indicates the time point when anomaly i is detected, and calculates the response time consistency value. The calculation expression is: , where is the average response time difference; Obtain the indicator value measured after the response measures are implemented , get the baseline value of the indicator before the abnormality i occurs , calculate the response ratio, the expression is: , get the average response ratio of c responses, calculate the response value, and the calculation expression is: , calculate the anomaly detection response index, the calculation expression is: .

2. The intelligent central control system of a commercial tablet computer according to claim 1, characterized in that: Use Merkle tree to identify data differences between commercial tablet devices, identify changed data blocks, and synchronize the different parts of the data blocks. The specific steps include: Aggregate the data of each commercial tablet device as a data set and construct each Merkle tree to split the data set into data blocks; Take the hash value of the data block as the leaf node, and recursively calculate the hash value of the parent node from bottom to top until the root node of the tree is formed. The hash value of each parent node is the combination of the hash values ​​of the two child nodes; During the data synchronization process, the Merkle tree root hash values ​​on the two commercial tablet devices are compared. If the root hash values ​​are different, the hash values ​​of the child nodes are recursively compared downward until different leaf nodes are located. When a data block with a different hash value is identified, the data block is synchronized to another commercial tablet, and the hash value of the relevant node is updated and the hash values ​​of all affected parent nodes are recursively updated until the root node.

3. The intelligent central control system of a commercial tablet computer according to claim 2, characterized in that: The ARIMA model is used to perform time series analysis on network and system performance indicator data, and the isolation forest algorithm is used to detect abnormal points in network and system performance indicator data. The specific steps are as follows: Perform data cleaning to remove or correct missing, erroneous or abnormal data records; First, use the ADF test method to check whether the data is stable. If the data is not stable, perform differential processing to convert the non-stationary time series into a stable time series through first-order or multi-order differences; Apply the ARIMA model to the stationary time series data for time series analysis and predict the trend of network and system performance indicators; Initialize the forest, set the number of trees and the number of samples per tree, and extract samples to construct isolated trees; Randomly select a feature in the feature set, and randomly select a split value between the maximum and minimum values ​​of the randomly selected feature; Divide the data into two subsets according to the split value, and repeat the process until each leaf node contains only one data point or the preset maximum tree depth is reached; In each tree, calculate the path length from the root node to each leaf node; The average path length between a given data point and all trees in the forest is used to calculate the anomaly score of the data point; Set the anomaly score threshold based on business needs or experience. Points with scores higher than this threshold are marked as anomalies.

4. The intelligent central control system of a commercial tablet computer according to claim 3, characterized in that: The control impact information is analyzed and different signals are generated. The central control strategy of the commercial tablet computer is determined according to the generated different signals. The specific steps are as follows: Comparing the central control coefficient with a preset control evaluation threshold; If the central control coefficient is less than the control evaluation threshold, a central stable operation signal is generated and the central control continues without additional central strategy control; If the central control coefficient is greater than or equal to the control evaluation threshold, a central request control signal is generated, control intervention is performed, and the central control strategy of the commercial tablet computer is adjusted.

Images