Security upgrading method and device for intelligent terminal

Abstract

The invention discloses a security upgrading method for an intelligent terminal, and the method comprises the steps: obtaining current terminal data and historical terminal data corresponding to the intelligent terminal when the intelligent terminal receives an upgrading instruction; fusing the current terminal data and the historical data by using a preset data fusion algorithm to obtain comprehensive terminal data corresponding to the intelligent terminal; analyzing and processing the integrated terminal data by using a preset analysis algorithm to determine a prediction failure rate corresponding to the intelligent terminal; formulating an upgrading strategy corresponding to the intelligent terminal according to a preset upgrading mechanism and the prediction failure rate; and upgrading the intelligent terminal according to the upgrading strategy. According to the method, intelligent decision making and risk prevention in the upgrading process of the intelligent terminal are achieved, through automatic failure prediction and risk assessment, the requirement for manual intervention is reduced, the operation and maintenance cost is reduced, and safe upgrading of the intelligent terminal in a complex environment is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method and device for security upgrade of smart terminals. Background Art

[0002] Software upgrades for smart terminals (such as IoT devices, smart home devices, industrial terminals, etc.) can improve the device's operating efficiency, response speed, and resource management capabilities. For example, they can reduce lag, extend battery life, or enhance multitasking capabilities, thereby ensuring smooth operation of the device in complex scenarios.

[0003] Traditional smart terminal upgrade systems have numerous limitations, making them difficult to meet the accuracy, security, and reliability demands of modern devices. First, traditional systems typically rely on a single criterion, such as device model or version number, to filter upgrades. This lacks flexibility and makes it impossible to precisely adapt to the needs of different regions, network environments, or hardware batches, leading to upgrade failures and compatibility issues.

[0004] Existing solutions for handling upgrade failures rely primarily on manual intervention, such as operations personnel manually stopping upgrades or rolling back the system. This approach is time-consuming and inefficient, and it cannot guarantee device availability after the rollback. This leads to a high risk of business interruption and significantly increased operations and maintenance costs. Furthermore, in the event of widespread upgrade failures, traditional upgrade systems lack an automatic circuit breaker mechanism, making it impossible to prevent the spread of failures in a timely manner, potentially triggering a cascading system crash.

[0005] Application Contents

[0006] The present application provides a method and device for securely upgrading a smart terminal, which is used to overcome the above-mentioned problems or at least partially solve the problems of lack of automatic fuse mechanism and high cost of manual intervention during the upgrade of traditional smart terminals.

[0007] In a first aspect, the present application provides a method for securely upgrading a smart terminal, comprising:

[0008] When the smart terminal receives the upgrade instruction, the current terminal data and historical terminal data corresponding to the smart terminal are obtained;

[0009] Using the preset data fusion algorithm, the current terminal data and historical data are integrated to obtain the comprehensive terminal data corresponding to the smart terminal;

[0010] Analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the predicted failure rate corresponding to the smart terminal;

[0011] Formulate upgrade strategies for smart terminals based on the preset upgrade mechanism and predicted failure rate;

[0012] Upgrade smart terminals according to the upgrade strategy.

[0013] In a second aspect, the present application provides a security upgrade device for a smart terminal, comprising:

[0014] a data acquisition module configured to acquire current terminal data and historical terminal data corresponding to the smart terminal when the smart terminal receives an upgrade instruction;

[0015] a comprehensive terminal data determination module configured to fuse current terminal data and historical data using a preset data fusion algorithm to obtain comprehensive terminal data corresponding to the smart terminal;

[0016] a prediction failure rate determination module configured to analyze and process the comprehensive terminal data using a preset analysis algorithm to determine a prediction failure rate corresponding to the smart terminal;

[0017] An upgrade strategy determination module is configured to formulate an upgrade strategy corresponding to the smart terminal based on a preset upgrade mechanism and a predicted failure rate;

[0018] The execution module is configured to upgrade the smart terminal according to the upgrade strategy.

[0019] In a third aspect, the present application provides a readable medium comprising execution instructions. When a processor of an electronic device executes the execution instructions, the electronic device executes any method described in the first aspect.

[0020] In a fourth aspect, the present application provides an electronic device comprising a processor and a memory storing execution instructions. When the processor executes the execution instructions stored in the memory, the processor executes any method described in the first aspect.

[0021] This application provides a method for securely upgrading smart terminals. When a smart terminal receives an upgrade instruction, it obtains current terminal data and historical terminal data corresponding to the smart terminal; uses a preset data fusion algorithm to fuse the current terminal data and historical data to obtain comprehensive terminal data corresponding to the smart terminal; uses a preset analysis algorithm to analyze and process the comprehensive terminal data to determine the predicted failure rate corresponding to the smart terminal; formulates an upgrade strategy corresponding to the smart terminal based on the preset upgrade mechanism and predicted failure rate; and upgrades the smart terminal based on the upgrade strategy. This application implements intelligent decision-making and risk prevention during the smart terminal upgrade process. Through automated failure prediction and risk assessment, it reduces the need for manual intervention, reduces operation and maintenance costs, and ensures the secure upgrade of smart terminals in complex environments.

[0022] The further effects of the above-mentioned non-conventional preferred embodiment will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the existing technical solutions, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0024] Figure 1 A flowchart of a security upgrade method for a smart terminal provided in one embodiment of the present application;

[0025] Figure 2 A flowchart of another method for security upgrade of a smart terminal provided in one embodiment of the present application;

[0026] Figure 3 A flowchart of another method for security upgrade of a smart terminal provided in one embodiment of the present application;

[0027] Figure 4 This is a flowchart of another method for security upgrade of a smart terminal provided by an embodiment of the present application;

[0028] Figure 5 This is a schematic diagram of the structure of a security upgrade device for a smart terminal provided by an embodiment of the present application;

[0029] Figure 6 A schematic structural diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] Software upgrades for smart terminals (such as IoT devices, smart home devices, industrial terminals, etc.) can improve the device's operating efficiency, response speed, and resource management capabilities. For example, they can reduce lag, extend battery life, or enhance multitasking capabilities, thereby ensuring smooth operation of the device in complex scenarios.

[0032] Smart terminals are not limited to individual devices; they can also be multiple smart terminals within a region or network. This means that in some cases, smart terminals may be in a linked environment, where multiple devices work together to complete tasks or coordinate work. For example, in smart home systems, various devices (such as smart light bulbs, thermostats, and security cameras) are interconnected via a network, while in industrial automation systems, multiple terminal devices work together to ensure the smooth operation of the production line.

[0033] Traditional smart terminal upgrade systems have numerous limitations, making them difficult to meet the accuracy, security, and reliability demands of modern devices. First, traditional systems typically rely on a single criterion, such as device model or version number, to filter upgrades. This lacks flexibility and makes it impossible to precisely adapt to the needs of different regions, network environments, or hardware batches, leading to upgrade failures and compatibility issues.

[0034] In the absence of an automatic circuit breaker mechanism, once a terminal or a group of terminals fails, the problem may spread rapidly, causing problems on multiple terminal devices at the same time, and may even trigger a cascading collapse of the entire system, resulting in unpredictable risks and higher operation and maintenance costs.

[0035] Existing solutions for handling upgrade failures rely primarily on manual intervention, such as operations personnel manually stopping upgrades or rolling back the system. This approach is time-consuming and inefficient, and it cannot guarantee device availability after the rollback. This leads to a high risk of business interruption and significantly increased operations and maintenance costs. Furthermore, in the event of widespread upgrade failures, traditional upgrade systems lack an automatic circuit breaker mechanism, making it impossible to prevent the spread of failures in a timely manner, potentially triggering a cascading system crash.

[0036] To address this issue, the present invention proposes a method for securely upgrading a smart terminal, aiming to address the issues of traditional smart terminal upgrades lacking an automatic fuse mechanism and high manual intervention costs. In this embodiment, a method for securely upgrading a smart terminal includes:

[0037] Step 101: When the smart terminal receives an upgrade instruction, the current terminal data and historical terminal data corresponding to the smart terminal are obtained.

[0038] When a smart terminal receives an upgrade instruction, it first needs to obtain the current and historical terminal data associated with the terminal. Current terminal data includes real-time status information about the device at the time of the upgrade, such as hardware performance parameters, software version, network environment, and operation logs. This data reflects the device's current operating status, including whether the device is operating normally, any abnormal warnings, and hardware health.

[0039] When a smart terminal receives an upgrade instruction, it may encounter a variety of situations that can directly affect the success of the upgrade process. First, the device may be in normal working order, with no faults or anomalies. In this case, the upgrade process can usually proceed according to the planned process and requires no special handling. The system assesses the upgrade risk based on the device's current status and historical data, and decides whether to proceed based on factors such as device performance and network conditions.

[0040] However, the device may be in an abnormal state, such as a low battery, insufficient memory or storage space, an error or warning message during operation, or the device is currently performing a high-priority task. These factors may cause the upgrade process to encounter problems or even fail. In such cases, the system needs to use intelligent judgment to delay or pause the upgrade, or initiate other emergency response mechanisms, such as charging the smart terminal or clearing storage space.

[0041] Additionally, network stability may affect the upgrade process. If the device's connection is unstable or bandwidth is insufficient, the upgrade download process may be interrupted or delayed, or even fail. In this case, the system may delay the upgrade until network conditions improve, or switch to offline upgrade mode if it detects a network issue.

[0042] Historical terminal data includes the device's operational history over a period of time, such as previous upgrade records, failure logs, device fault history, and performance in different environments. This historical data helps analyze issues encountered during past upgrades, potential system compatibility issues, and vulnerable parts of the device.

[0043] Step 102: Utilize a preset data fusion algorithm to fuse the current terminal data and historical data to obtain comprehensive terminal data corresponding to the smart terminal.

[0044] Feature extraction algorithms extract key metrics or features from raw data. These typically include device hardware information (such as CPU usage, memory usage, and storage space), software status (such as operating system version, running applications, and error logs), network conditions (such as bandwidth and latency), and other environmental factors (such as battery level and device temperature). By extracting these features, complex data can be transformed into a form that is easier to process and analyze.

[0045] Next, the data fusion algorithm combines the extracted features of the current terminal data with those of historical data. To ensure the accuracy and representativeness of the fusion results, each data source is typically assigned a weight. These weights may be based on the importance of the data, the reliability of the data source, or the degree to which the data affects device performance. For example, if a device has exhibited frequent failures or performance issues in the past, the weight of this historical data may be increased to give it greater weight in the fusion process.

[0046] During the data fusion phase, the algorithm weights and combines current and historical data features according to pre-set rules to generate a comprehensive device data model. This comprehensive data model not only reflects the current state of the device but also encompasses its historical performance at different points in time and under different usage conditions. Ultimately, the resulting comprehensive device data effectively characterizes the overall health and operational capabilities of the device, providing accurate information for subsequent predictive analysis and risk assessment.

[0047] Step 103: Analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the prediction failure rate corresponding to the smart terminal.

[0048] The analysis algorithm receives integrated, integrated terminal data as input. This data typically includes information on multiple dimensions, including the device's real-time status, historical performance, hardware health, software version, and network conditions. This data may contain clues to potential issues during future device upgrades. Therefore, the analysis algorithm uses specific mathematical models or statistical methods to extract key information related to upgrade success or failure from this multi-dimensional data.

[0049] To predict the failure rate of smart device upgrades, analytical algorithms typically leverage techniques such as machine learning, regression analysis, or neural networks. By learning from historical upgrade data and device performance data, the algorithms can identify patterns and patterns in device failures under similar conditions. For example, devices with certain hardware configurations may be more prone to failure during an upgrade; or bandwidth issues may increase the probability of failure during an upgrade in certain network environments. By deeply analyzing this historical data, the model calculates a predicted failure rate for each device—the probability of failure under the current upgrade conditions.

[0050] This predicted failure rate isn't a simple number; it's derived from a combination of various factors, including the device's operating status, environmental factors, and historical performance. This means the predicted failure rate may vary depending on the device's state. For example, if the device's battery is low or its memory usage is high, the failure rate may increase significantly; whereas, with a stable network and good hardware, the failure rate may be lower.

[0051] Step 104: Formulate an upgrade strategy corresponding to the smart terminal based on the preset upgrade mechanism and predicted failure rate.

[0052] The system sets different threshold ranges based on the predicted failure rate. Each failure rate range corresponds to a different upgrade strategy. For example, if the predicted failure rate is low, the system can directly execute the standard upgrade process. In this case, no additional intervention is required during the upgrade process. The device can be upgraded in the usual way. The upgrade package will be transmitted through standard channels, and the system will complete the upgrade according to the established process.

[0053] However, when the predicted failure rate is high, the system may adopt a more cautious strategy. For example, during this phase, the system might send an early warning notification to the management center, alerting relevant operations personnel or users to potential risks while continuing the upgrade. This early warning mechanism allows for the preparation of response plans in advance, enabling a quick response when problems arise, and reducing losses caused by system failures.

[0054] In the most severe cases, when the predicted failure rate is particularly high, the system may immediately terminate the upgrade process, perform a rollback, or even stop all related upgrade tasks. At this point, the device upgrade risk is assessed to be too high, and any further upgrade operations could cause system failure or service interruption. Therefore, the safest option is to suspend all upgrade activities to avoid irreversible damage to the device or user services.

[0055] When formulating these upgrade policies, the system also considers various factors, including the device's hardware configuration, network conditions, and operating system version. Policies may be adjusted for specific device types or devices in specific environments. For example, for devices with poor battery life or insufficient storage space, the system may choose to reduce the size of the upgrade package to avoid loading too much data at once, or perform the upgrade in stages based on the device's current state to reduce the probability of upgrade failure.

[0056] Step 105: Upgrade the smart terminal according to the upgrade strategy.

[0057] Upgrading smart terminals according to the established upgrade strategy is not just a simple push of the upgrade package, but a combination of multiple factors such as the current status of the device, historical performance, network environment, etc., through flexible strategy adjustments to ensure that the upgrade process can adapt to different scenarios and achieve the best results.

[0058] Throughout the upgrade process, the system dynamically adjusts its upgrade strategy based on the device's specific conditions. For example, for devices with low battery, the system may postpone or delay the upgrade until the device has reached a certain charge level. For devices with limited network bandwidth, the system may choose to download the upgrade package in stages or upgrade when network conditions are stable. Each step is determined based on the device's real-time status and predicted failure risk, ensuring stability and security throughout the upgrade process.

[0059] In general, upgrading smart devices according to a defined upgrade strategy is a highly dynamic, flexible, and precise process that effectively mitigates potential risks while ensuring uninterrupted service. This refined upgrade process not only improves device operational efficiency but also significantly reduces the risk of service interruptions or hardware damage due to upgrade failures, thereby enhancing the user experience and overall device reliability.

[0060] Through the above technical solution, it can be seen that the beneficial effects of this embodiment are:

[0061] The embodiment of the present application provides a method for securely upgrading a smart terminal. When the smart terminal receives an upgrade instruction, the method obtains current terminal data and historical terminal data corresponding to the smart terminal; uses a preset data fusion algorithm to fuse the current terminal data and historical data to obtain comprehensive terminal data corresponding to the smart terminal; uses a preset analysis algorithm to analyze and process the comprehensive terminal data to determine the predicted failure rate corresponding to the smart terminal; formulates an upgrade strategy corresponding to the smart terminal based on the preset upgrade mechanism and predicted failure rate; and upgrades the smart terminal based on the upgrade strategy. The present application implements intelligent decision-making and risk prevention during the smart terminal upgrade process. Through automated failure prediction and risk assessment, it reduces the need for manual intervention, lowers operation and maintenance costs, and ensures the secure upgrade of smart terminals in complex environments.

[0062] Figure 1 What is shown is only a basic embodiment of a security upgrade method for a smart terminal of the present application. By performing certain optimization and expansion on this basis, other preferred embodiments of a security upgrade method for a smart terminal can be obtained.

[0063] like Figure 2 FIG. 1 is another specific embodiment of a security upgrade method for a smart terminal according to the present application.

[0064] In this embodiment, a security upgrade method for a smart terminal includes the following steps:

[0065] Step 201: When the smart terminal receives an upgrade instruction, the current terminal data and historical terminal data corresponding to the smart terminal are obtained.

[0066] Step 202: Utilize a preset data fusion algorithm to fuse the current terminal data and the historical data to obtain comprehensive terminal data corresponding to the smart terminal.

[0067] Step 203: Using a feature extraction algorithm, determine the current data features corresponding to the current terminal data, and determine the historical data features corresponding to the historical terminal data.

[0068] For current terminal data, the feature extraction algorithm extracts a series of representative features from the device status acquired in real time. For example, the current terminal's hardware status (such as CPU utilization, memory usage, storage space, sensor data, etc.) and software status (such as the current operating system version, running applications, system logs, etc.) are very important features. These features directly reflect the performance and stability of the device when performing tasks and can help evaluate whether the device is currently suitable for upgrades. Through feature extraction, the system can simplify this real-time, multi-dimensional data into a few key indicators, such as resource utilization and system response time, thereby providing an intuitive reflection of the device's health status.

[0069] Next, for historical terminal data, feature extraction algorithms extract valuable information from the device's past operation history. This information may include historical upgrade records, past failure records, device lifecycle history, and device performance under different network conditions. Extracting historical data features primarily aims to identify potential issues or performance bottlenecks that the device has encountered in the past. For example, whether a device has experienced frequent failures under a specific hardware configuration, or whether upgrades frequently fail under a certain network environment, these historical data features help analyze potential weaknesses and risk points in the device, providing predictive insights into the current upgrade process.

[0070] Feature extraction algorithms typically use techniques such as signal processing, statistical analysis, or machine learning to transform raw data into representative feature vectors. These feature vectors can be numerical (such as CPU load percentage, memory usage, etc.) or categorical (such as the device's operating system type, network connection status, etc.). In this way, the algorithm can extract key information closely related to device performance, stability, and upgrade risks from complex raw data, thereby providing high-quality data support for subsequent data fusion and risk prediction.

[0071] Step 204: Determine the current data weight corresponding to the current data feature and determine the historical data weight corresponding to the historical data feature according to the preset weight determination rule.

[0072] For current data features, the system determines their corresponding weights based on the criticality and importance of the real-time data. Current data features typically reflect the immediate status of the device at the time of the upgrade, such as CPU usage, memory usage, network bandwidth, system load, device battery level, etc. These features can directly affect whether the device will malfunction or experience performance degradation during the upgrade process. Therefore, the system may assign higher weights to some important real-time data features, such as CPU load and memory usage, as they are directly related to the device's processing power and response speed. If the device's resources are limited or it is under high load, the system may postpone or stage the upgrade to avoid upgrade failure or system crash due to insufficient resources.

[0073] For historical data features, the system assigns weights based on the historical data's ability to predict the future performance of the device. Historical data features may include the device's past failure records, historical upgrade results, the device's usage cycle, and performance in specific environments (such as stability under different network conditions). These features help the system identify the long-term stability and potential risk factors of the device. For example, if a device has frequently encountered problems during past upgrades, or has a higher probability of failure in certain specific environments (such as low battery or unstable network environments), then historical data features may be given a higher weight. This is because historical data can reveal the performance of the device in similar situations, help predict future failure risks, and thus influence whether a more cautious upgrade strategy is adopted.

[0074] The weightings are determined not only by the importance of the features but also by the overall condition of the device, upgrade objectives, and environmental factors. The system can use data-driven learning algorithms or empirical data to determine these weights. For example, if a device has experienced numerous failures in the past, the weight of historical failure records may be increased to better reflect the device's risk level. For some newer models, current data may be more heavily relied upon, as historical records may be less valuable or inadequate.

[0075] Weights can be determined statically or dynamically. With static weighting, the system assigns weights based on preset rules such as device category and hardware specifications. With dynamic weighting, the system may adjust based on the device's actual usage and real-time data, ensuring that the influence of each feature is always consistent with the current state of the device. For example, if a device experiences frequent failures over a period of time, the system may automatically increase the weight of historical data to better assess the device's overall risk.

[0076] Step 205: Utilize the current data weight and the historical data weight to fuse the current terminal data and the historical terminal data to determine the comprehensive terminal data.

[0077] During the fusion process, the system performs a weighted merger of current terminal data and historical terminal data based on the previously determined current data weight and historical data weight. Specifically, during weighted fusion, the system combines current data and historical data through methods such as weighted average and weighted sum. The weight of current data and the weight of historical data are adjusted according to their respective importance and impact to ensure that the influence of each data source is appropriate. For example, in some cases, the current load condition of the equipment may be more important than the historical performance of the equipment, so the weight of the current data may be relatively large. In other cases, historical fault records may reveal potential long-term stability issues of the equipment, in which case the weight of historical data may be higher.

[0078] By weightedly fusing current and historical data, the system generates comprehensive terminal data, encompassing both immediate and long-term device performance. This comprehensive terminal data not only comprehensively assesses the current status of the device but also provides a more comprehensive perspective for device upgrade decisions, helping the system identify potential risks, optimize upgrade strategies, and ensure the security and stability of the upgrade process. This fused data is often used as the basis for subsequent analysis, supporting operations such as predicting failure rates and formulating upgrade strategies.

[0079] Step 206: Analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the prediction failure rate corresponding to the smart terminal.

[0080] Step 207: Formulate an upgrade strategy corresponding to the smart terminal based on the preset upgrade mechanism and predicted failure rate.

[0081] Step 208: Upgrade the smart terminal according to the upgrade strategy.

[0082] The above technical solution demonstrates the beneficial effect of this embodiment: Data fusion, utilizing current and historical data weights, not only combines the device's real-time performance with historical records but also effectively balances the impact of different data sources, ensuring the system makes more accurate decisions. This process provides strong data support for secure upgrades of smart terminals, helping to achieve a smooth and reliable upgrade experience in complex environments and diverse usage scenarios.

[0083] like Figure 3 FIG. 1 is another specific embodiment of a security upgrade method for a smart terminal of the present application. This embodiment further describes the above embodiment.

[0084] In this embodiment, a security upgrade method for a smart terminal includes the following steps:

[0085] Step 301: When the smart terminal receives an upgrade instruction, the current terminal data and historical terminal data corresponding to the smart terminal are obtained.

[0086] Step 302: Utilize a preset data fusion algorithm to fuse the current terminal data and historical data to obtain comprehensive terminal data corresponding to the smart terminal.

[0087] Step 303: Analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the prediction failure rate corresponding to the smart terminal.

[0088] Step 304: Determine the upgrade data corresponding to the smart terminal.

[0089] Upgrade data refers to all key information related to the smart terminal upgrade process, including the upgrade package version, upgrade file size, and network conditions that may be affected during the upgrade. By collecting this upgrade data, the system can gain a comprehensive understanding of the upcoming upgrade content and associated potential risks. For example, changes in the upgrade package version, a significant increase in file size, or the quality of the network connection can all affect the smooth progress of the upgrade. Based on this data, the system can provide the necessary input for subsequent predictive analysis.

[0090] Step 305: Input the upgrade data and the integrated terminal data into a preset prediction model, so that the preset model outputs a predicted failure rate based on the upgrade data and the integrated terminal data.

[0091] Upgrade data and comprehensive terminal data are fed into a pre-set predictive model for processing. Predictive models are typically based on algorithms such as machine learning, deep learning, or statistical analysis, and can learn patterns and patterns in device upgrade failures from extensive historical data. Through training, the predictive model gradually establishes a relationship between upgrade data and terminal status (i.e., comprehensive terminal data) and upgrade failures. Specifically, the model may consider factors such as the device's hardware configuration, network status, system load, and historical failure history, extracting meaningful features to predict the device's failure risk under the current upgrade scenario.

[0092] The prediction model is constructed by determining the initial model; constructing a training data set for the initial model; the training data set includes training comprehensive data and training upgrade data of the training terminal; determining the annotation information corresponding to the training data set; the annotation information includes the actual failure rate of the training terminal; inputting the training comprehensive data and training upgrade data into the initial model so that the initial model outputs an initial prediction result; using the initial prediction result and the annotation information, determining the loss index of the initial model based on a preset loss function; when the loss index does not meet the training conditions, adjusting the hyperparameters of the initial model; when the loss index meets the training conditions, determining the initial model as the prediction model.

[0093] Determining the initial model typically requires selecting a suitable model structure. This initial model can be based on machine learning or deep learning, such as a decision tree, support vector machine, or neural network. This initial model is typically designed based on the characteristics of the problem and historical data. The model is typically chosen based on its ability to capture the complex nonlinear relationships and multidimensional data patterns that may arise during the equipment upgrade process.

[0094] Build a training dataset for the initial model. The training dataset includes two types of data: comprehensive training data for training terminals and training upgrade data. Comprehensive training data typically includes information such as the terminal device's hardware configuration, operating system version, historical fault records, and operating environment. This data helps the model understand the device's basic status and potential risks. Training upgrade data includes data related to upgrade operations, such as upgrade package version information and upgrade package data. This data provides the model with information about the upgrade process itself, helping it identify factors that may affect upgrade failures.

[0095] Determine the annotation information corresponding to the training dataset. This annotation information generally refers to the actual failure rate of the training terminal. Specifically, during the training and upgrade process, the device successfully completed the upgrade under certain conditions, and the specific probability of failure. This annotation information provides the model with learning objectives and is the foundation of supervised learning. This annotation information allows the model to understand the actual situation of device upgrade success or failure under given input conditions, thereby adjusting its internal parameters to minimize prediction error.

[0096] After the data is prepared, the training data and the training upgrade data are fed into the initial model, which learns and outputs initial predictions. The initial predictions are the model's predictions of the probability of success or failure for the device upgrade. During this stage, the model learns from the training data set and attempts to establish a correlation between input data and output results. However, since initial models are often unoptimized, the predictions may differ from actual results.

[0097] To further optimize the model, the initial prediction results and annotation information are used to determine the initial model's loss index based on a preset loss function. A loss function is a metric used to measure the difference between the prediction results and the true annotation information. Common loss functions include mean squared error and cross entropy. By calculating the loss function, the system can quantify the accuracy of the current model's predictions. A high loss index indicates that the model's predictive ability is weak and requires further optimization.

[0098] When the model's loss index does not meet the preset training conditions, it is necessary to adjust the initial model's hyperparameters, such as the learning rate, regularization coefficient, and number of neural network layers. By adjusting these hyperparameters, you can change the model's learning rate, complexity, and ability to fit the training data, helping the model better adapt to the data and reducing prediction errors. Hyperparameter adjustment typically involves methods such as cross-validation to verify the effectiveness of different hyperparameter configurations and ensure that the model can demonstrate good generalization capabilities across different datasets.

[0099] When the loss index meets the training conditions, the initial model is determined to be a predictive model and can be put into practical use. At this point, the predictive model has been trained on a large amount of data and parameter adjustments, and can accurately predict the probability of failure during the equipment upgrade process when faced with new data.

[0100] After inputting upgrade data and comprehensive device data into the prediction model, the model infers the patterns learned during training and outputs a predicted failure rate. The predicted failure rate is a numerical value that indicates the probability of a device failing under the current upgrade conditions. For example, if comprehensive device data indicates a device with high CPU load, near-full memory usage, and poor network conditions, the model may predict a high probability of upgrade failure for that device. Conversely, if the device is in good condition and has a stable network, the predicted failure rate may be lower.

[0101] The predicted failure rate isn't a simple binary judgment (success or failure), but rather a probabilistic assessment based on data analysis. This assessment provides a more nuanced and flexible basis for decision-making, helping the system formulate more precise upgrade strategies in practice. If the predicted failure rate is high, the system may implement strategies such as delayed upgrades, phased upgrades, and downgrades to reduce the risk of failure. If the predicted failure rate is low, the upgrade can proceed according to the standard process.

[0102] Step 306: Formulate an upgrade strategy corresponding to the smart terminal based on the preset upgrade mechanism and predicted failure rate.

[0103] Step 307: Upgrade the smart terminal according to the upgrade strategy.

[0104] The above technical solution demonstrates the beneficial effects of this embodiment: through this data-analysis-based prediction mechanism, smart terminals can more intelligently identify and address potential upgrade risks, improving the success rate of the upgrade process and device stability. Overall, using a pre-set analysis algorithm for failure prediction not only effectively improves the accuracy of device upgrades but also strongly supports the system's adaptability and fault response capabilities.

[0105] like Figure 4FIG. 1 is another specific embodiment of a security upgrade method for a smart terminal of the present application. This embodiment further describes the above embodiment.

[0106] Step 401: When the smart terminal receives an upgrade instruction, the current terminal data and historical terminal data corresponding to the smart terminal are obtained.

[0107] Step 402: Utilize a preset data fusion algorithm to fuse the current terminal data and the historical data to obtain comprehensive terminal data corresponding to the smart terminal.

[0108] Step 403: Analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the prediction failure rate corresponding to the smart terminal.

[0109] Step 404: Formulate an upgrade strategy corresponding to the smart terminal based on the preset upgrade mechanism and predicted failure rate.

[0110] Step 405: Determine a threshold range corresponding to the prediction failure rate, and determine a corresponding upgrade mechanism according to the threshold range.

[0111] After the smart terminal receives the upgrade instruction and calculates the predicted failure rate, in order to ensure the efficiency and safety of the upgrade process, a reasonable threshold range can be set and the corresponding upgrade mechanism can be determined accordingly.

[0112] The threshold intervals include the first interval, the second interval, the third interval and the fourth interval. When the predicted failure rate is in the first interval, the upgrade process of the smart terminal is executed; when the predicted failure rate is in the second interval, an early warning notification is sent to the management center and the smart terminal is upgraded; when the predicted failure rate is in the third interval, the service degradation mechanism is activated; when the predicted failure rate is in the fourth interval, the upgrade process of the smart terminal is terminated.

[0113] Specifically, the threshold range is divided into four levels, each corresponding to a different escalation mechanism. These mechanisms are designed to take appropriate measures based on the risk level of the device, ensuring the smooth completion of the upgrade process while minimizing the risk of system crashes or business interruptions caused by failures.

[0114] When a device's predicted failure rate falls within the first range, the risk of upgrade failure is low, and the system can proceed with the upgrade according to normal procedures. The upgrade process for smart terminals is carried out, requiring no special intervention. The upgrade package is directly downloaded and installed, and a full or incremental upgrade is performed. Under normal operating conditions, the upgrade has a high probability of success, and the system can proceed smoothly according to plan.

[0115] When a device's predicted failure rate falls within the second range, the risk of upgrade failure is relatively high, but still within an acceptable range. To mitigate this risk, the system should adopt a more cautious strategy, sending an early warning notification to the management center, alerting them to the device's upgrade status. While the upgrade can proceed despite a medium predicted failure rate, the management center can conduct additional monitoring of the device to ensure a prompt response and take corrective action if any anomalies arise during the upgrade process.

[0116] When the predicted failure rate of a device falls into the third range, the risk of device upgrade failure increases significantly. At this point, the system should take more conservative and preventive measures and initiate a service degradation mechanism.

[0117] Specifically, the service degradation mechanism includes: determining a preset concurrency threshold; limiting the upgrade concurrency corresponding to the smart terminal to the concurrency threshold, and using a weighted sliding window algorithm to calculate the current failure rate corresponding to the smart terminal; when the current failure rate is in the third or fourth interval, terminating the upgrade process and performing a rollback operation.

[0118] During large-scale smart device upgrades, numerous devices are typically upgraded simultaneously, potentially leading to insufficient network bandwidth, excessive server load, or other resource bottlenecks. If the predicted failure rate of a device is high, you may need to limit the number of devices upgrading simultaneously. In this case, the system will limit the number of smart device upgrades based on a pre-set concurrency threshold. For example, the system might set a concurrency threshold of 100 devices. When this threshold is reached, new upgrade requests are temporarily queued and resumed when system resources allow.

[0119] Limit the number of concurrent upgrades for smart devices to the concurrency threshold to ensure that the system is not overloaded by too many devices upgrading simultaneously. By adjusting the concurrency threshold, the system reduces the load on the network and server, ensuring that the number of devices upgraded at any one time is within a reasonable range, and avoiding failures caused by excessive load.

[0120] After controlling the number of concurrent requests, the system continues to monitor the device upgrade status and calculates the upgrade failure rate in real time. Using a weighted sliding window algorithm, the system calculates the current failure rate for each smart terminal. This algorithm, a data processing algorithm based on a time window, continuously updates the data within the window to reflect the latest device upgrade status. During each time period, the system collects and calculates records of device upgrade successes and failures, assigning higher weights to failures to accurately identify potential risks in the system.

[0121] If the current failure rate calculated using the weighted sliding window falls within the third or fourth range (i.e., the device has a high risk of upgrade failure), the system immediately takes protective measures, terminates the upgrade process, and performs a rollback. A rollback restores the device to its pre-upgrade stable state to prevent device malfunction or system crashes caused by upgrade failures.

[0122] When a device's predicted failure rate falls within the fourth range, the risk of upgrade failure is extremely high, and the system should immediately implement the most stringent measures. In this case, the system should terminate the upgrade process for the smart device to prevent more serious consequences from a failed upgrade. For example, the smart device may already be unstable, or the network environment may be extremely unsuitable for an upgrade. In such cases, forcing the upgrade will not only fail to improve device performance, but may also cause system crashes or service interruptions. Therefore, the system should pause the upgrade process and decide whether to retry the upgrade after completing risk assessment and optimization measures.

[0123] Step 406: Determine an upgrade strategy based on the upgrade mechanism and the preset upgrade method.

[0124] Based on the upgrade mechanism, the system needs to consider upgrade strategies for devices in different risk ranges. For example, when the predicted failure rate is in a low range, the upgrade can proceed smoothly according to the normal process. In the medium risk range, the system may adopt a more conservative strategy, such as upgrading in batches or adding additional monitoring and early warning during the upgrade process. In the high risk range, it is necessary to activate the downgrade mechanism to limit the number of concurrent operations, reduce the load, or even postpone certain upgrade operations. In the extremely high risk range, the system will immediately terminate the upgrade and roll back the operation. These upgrade mechanisms, based on different risk assessments, determine the initial framework of the upgrade strategy.

[0125] The preset upgrade method will also affect the specific implementation of the policy. The preset upgrade methods usually include full upgrade, incremental upgrade, and phased upgrade. Full upgrade is suitable for situations with low risk, good equipment conditions, and a stable network environment, and can complete all updates at once; incremental upgrade is suitable for situations with high resource requirements or the need to minimize network burden. It reduces data transmission volume by only updating the changed parts; phased upgrade is suitable for complex environments, especially when there are a large number of devices or limited network bandwidth. It can split the upgrade process into multiple stages, gradually advancing, reducing system pressure, and allowing evaluation and adjustment at each stage.

[0126] Step 407: Upgrade the smart terminal according to the upgrade strategy.

[0127] The above technical solution demonstrates the beneficial effects of this embodiment: by dividing the predicted failure rate into different threshold intervals and developing corresponding upgrade mechanisms and strategies for each interval, the system can dynamically adjust the upgrade process based on real-time data. This strategy not only effectively reduces the risk of upgrade failure but also ensures that the smart terminal remains in optimal operating condition during the upgrade process through timely adjustments and optimizations, thereby improving device stability and reliability.

[0128] like Figure 5 The figure shows a specific embodiment of a security upgrade device for a smart terminal of the present application. Figures 1 to 4 A physical device for a security upgrade method for a smart terminal. Its technical solution is essentially the same as that of the above embodiment, and the corresponding descriptions in the above embodiment are also applicable to this embodiment. In this embodiment, a security upgrade device for a smart terminal includes:

[0129] The data acquisition module 501 is configured to acquire current terminal data and historical terminal data corresponding to the smart terminal when the smart terminal receives the upgrade instruction;

[0130] The comprehensive terminal data determination module 502 is configured to fuse the current terminal data and the historical data using a preset data fusion algorithm to obtain comprehensive terminal data corresponding to the smart terminal;

[0131] The prediction failure rate determination module 503 is configured to analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the prediction failure rate corresponding to the smart terminal;

[0132] The upgrade strategy determination module 504 is configured to formulate an upgrade strategy corresponding to the smart terminal according to a preset upgrade mechanism and a predicted failure rate;

[0133] The execution module 505 is configured to upgrade the smart terminal according to the upgrade strategy.

[0134] Figure 6 : This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0135] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0136] Memory is used to store execution instructions. Specifically, execution instructions are computer programs that can be executed. Memory can include internal memory and non-volatile memory, and provides execution instructions and data to the processor.

[0137] In one possible implementation, a processor reads corresponding execution instructions from a non-volatile memory into a memory and then executes them. Alternatively, the processor may obtain corresponding execution instructions from other devices to logically form a security upgrade device for a smart terminal. The processor executes the execution instructions stored in the memory to implement a security upgrade method for a smart terminal provided in any embodiment of the present application through the execution of the execution instructions.

[0138] The above application Figure 5 The method performed by a security upgrade device for an intelligent terminal provided in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0139] The steps of the method disclosed in the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0140] The embodiment of the present application also proposes a readable medium, which stores an execution instruction. When the stored execution instruction is executed by the processor of the electronic device, the electronic device can execute a security upgrade method for a smart terminal provided in any embodiment of the present application, and is specifically used to execute the following Figure 1 or Figure 2 or Figure 3 or Figure 4 The method shown.

[0141] The electronic device in each of the aforementioned embodiments may be a computer.

[0142] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods or computer program products. Therefore, the present application may adopt a completely hardware embodiment, a completely software embodiment, or a combination of software and hardware.

[0143] The various embodiments in this application are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the partial description of the method embodiments.

[0144] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0145] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A security upgrade method for an intelligent terminal, characterized in that: include: When the smart terminal receives the upgrade instruction, the current terminal data and historical terminal data corresponding to the smart terminal are obtained; Using a preset data fusion algorithm, the current terminal data and the historical data are fused to obtain comprehensive terminal data corresponding to the smart terminal; Analyzing and processing the comprehensive terminal data using a preset analysis algorithm to determine the predicted failure rate corresponding to the smart terminal; Formulate an upgrade strategy corresponding to the smart terminal according to a preset upgrade mechanism and the predicted failure rate; The smart terminal is upgraded according to the upgrade strategy.

2. The method according to claim 1, characterized in that The fusing of the current terminal data and the historical data using a preset data fusion algorithm to obtain comprehensive terminal data corresponding to the smart terminal includes: Determine the current data features corresponding to the current terminal data and determine the historical data features corresponding to the historical terminal data using a feature extraction algorithm; Determine the current data weight corresponding to the current data feature and the historical data weight corresponding to the historical data feature according to a preset weight determination rule; The current terminal data and the historical terminal data are fused using the current data weight and the historical data weight to determine the comprehensive terminal data.

3. The method according to claim 2, characterized in that The analyzing and processing the comprehensive terminal data using a preset analysis algorithm to determine the predicted failure rate corresponding to the smart terminal includes: Determining upgrade data corresponding to the smart terminal; The upgrade data and the integrated terminal data are input into a preset prediction model, so that the preset model outputs the predicted failure rate according to the upgrade data and the integrated terminal data.

4. The method according to claim 3, characterized in that Also includes: Determine the initial model; Constructing a training data set for the initial model; The training data set includes comprehensive training data and training upgrade data of the training terminal; Determining labeling information corresponding to the training data set; The annotation information includes the actual failure rate of the training terminal; Inputting the training comprehensive data and the training upgraded data into the initial model so that the initial model outputs an initial prediction result; Determining a loss index of the initial model based on a preset loss function using the initial prediction result and the annotation information; When the loss index does not meet the training conditions, adjusting the hyperparameters of the initial model; When the loss index meets the training condition, the initial model is determined as the prediction model.

5. The method according to claim 1, wherein Formulating an upgrade strategy corresponding to the smart terminal according to the preset upgrade mechanism and the predicted failure rate includes: Determining a threshold interval corresponding to the prediction failure rate, and determining the corresponding upgrade mechanism according to the threshold interval; The upgrade strategy is determined based on the upgrade mechanism and the preset upgrade method.

6. The method according to claim 5, characterized in that The threshold intervals include a first interval, a second interval, a third interval, and a fourth interval, and determining the corresponding upgrade mechanism according to the threshold intervals includes: When the predicted failure rate is within the first interval, executing an upgrade process of the smart terminal; When the predicted failure rate is within the second interval, sending an early warning notification to a management center and upgrading the smart terminal; When the predicted failure rate is within the third interval, initiating a service degradation mechanism; When the predicted failure rate is in the fourth interval, the upgrade process of the smart terminal is terminated.

7. The method according to claim 6, characterized in that The initiation of the service degradation mechanism includes: Determine the preset concurrency threshold; Limiting the concurrent number of upgrades corresponding to the smart terminal to a concurrent number threshold, and calculating the current failure rate corresponding to the smart terminal using a weighted sliding window algorithm; When the current failure rate is in the third interval or the fourth interval, the upgrade process is terminated and a rollback operation is performed.

8. A security upgrade device for an intelligent terminal, characterized in that: include: a data acquisition module configured to acquire current terminal data and historical terminal data corresponding to the smart terminal when the smart terminal receives an upgrade instruction; a comprehensive terminal data determination module, configured to fuse the current terminal data and the historical data using a preset data fusion algorithm to obtain comprehensive terminal data corresponding to the smart terminal; a prediction failure rate determination module, configured to analyze and process the comprehensive terminal data using a preset analysis algorithm to determine the prediction failure rate corresponding to the smart terminal; An upgrade strategy determination module is configured to formulate an upgrade strategy corresponding to the smart terminal according to a preset upgrade mechanism and the predicted failure rate; An execution module is configured to upgrade the smart terminal according to the upgrade strategy.

9. A computer-readable storage medium storing a computer program, characterized in that: The computer program is used to execute the security upgrade method for a smart terminal as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the security upgrade method for a smart terminal as described in any one of claims 1 to 7.

Images