Intelligent analysis method, system and equipment for performance data of terminal equipment and medium

Abstract

The invention provides an intelligent analysis method, system and device for performance data of terminal equipment and a medium, and belongs to the technical field of data acquisition and analysis. The method comprises the following steps: a cloud server manages a data acquisition rule, and terminal equipment obtains an association rule through an HTTP protocol; the equipment collects performance data in real time according to a rule by means of a monitoring Agent program, locally processes the performance data to generate a standardized event record, and reports the standardized event record to cloud message middleware through an MQTT protocol after compression. The cloud data processing service adopts hierarchical processing, is firstly cached in a local SQLite database, and is stored in a MySQL database after data cleaning, aggregation and repeated alarm. The method comprises the following steps of: establishing an index, synchronizing to Elasticsearch to establish an index, combining Kibana display and performing TensorFlow deep analysis to generate prediction and early warning information, and finally generating a structured analysis report based on a result, thereby realizing efficient and intelligent analysis of performance data of the terminal equipment.

Description

Technical Field

[0001] This invention belongs to the field of data acquisition and analysis technology, and more specifically relates to an intelligent analysis system, method, device and medium for terminal device performance data. Background Technology

[0002] With the rapid development of IoT and smart display technologies, the deployment scale of terminal devices such as central control screens, smart gateways, and outdoor large screens has grown exponentially. These devices are widely distributed and located in complex environments, ranging from digital signage in shopping mall chains to information screens in transportation hubs. Under traditional operation and maintenance models, when devices experience malfunctions such as playback stuttering, poor switching, CPU utilization exceeding 90%, or insufficient memory, troubleshooting and handling rely entirely on manual on-site intervention. This results in response delays of several hours or even days, a sharp increase in operation and maintenance costs, and an inability to achieve unified health status management for large-scale devices.

[0003] Existing technical solutions mostly employ passive response mechanisms, only notifying maintenance personnel with simple alarms after a fault occurs, lacking the ability to predict performance anomalies early and provide dynamic protection. For example, hardware performance degradation of outdoor large screens due to changes in ambient temperature, or playback anomalies caused by incompatibility issues with specific video decoders, cannot be effectively identified and warned against using established rules. This passive monitoring often leads to a continuous expansion of the fault's impact, resulting in prolonged business interruption and a significantly increased risk of commercial losses.

[0004] Furthermore, traditional relational database-based monitoring systems face significant bottlenecks when dealing with the high-frequency, multi-dimensional performance data generated by massive amounts of equipment. Daily device logs and performance metrics can reach terabyte levels, making it difficult for traditional architectures to support real-time data processing and multi-dimensional correlation analysis. Insufficient data storage and computing power prevents the accurate extraction of useful information from historical data, making it even more difficult to achieve root cause analysis of faults or determine performance degradation trends through multi-indicator fusion. For example, the playback data from 200 4K screens in a chain cinema requires real-time analysis of over 20 dimensions of correlation indicators. Traditional technical solutions are completely unable to meet such needs, resulting in a lack of data support and decision-making basis for overall risk control at the system level, creating significant data analysis blind spots. Summary of the Invention

[0005] To address the above issues, the present invention aims to provide a method, system, device, and medium for intelligent analysis of terminal device performance data. By using edge computing to achieve terminal data collection and compression, and combining multi-level cloud caching and machine learning analysis, a complete operation and maintenance system from real-time monitoring to predictive early warning is constructed, which significantly improves device management efficiency and reduces the risk of business interruption.

[0006] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a method for intelligent analysis of terminal device performance data, including: Data collection rules are managed by a cloud server, and terminal devices obtain data collection rules associated with their own device attributes from the cloud server via the HTTP protocol. The terminal device collects system performance data in real time according to data collection rules through the monitoring agent program, performs calculations and judgments locally on the device and generates standardized event records, processes the data through a compression algorithm to generate device data, and asynchronously reports it to the cloud message middleware via the MQTT protocol. Device data is consumed through the cloud data processing service message middleware. A hierarchical processing mechanism is adopted, first storing the device data in a local SQLite database, then aggregating duplicate alarms through a data cleaning pipeline, generating a unique valid event record and storing it in a MySQL database. The valid event records in the MySQL database are synchronized to the Elasticsearch search engine using data synchronization tools to build an index for device performance indicator analysis. Based on the device performance index analysis, the data is displayed using the Kibana data visualization platform, and the TensorFlow machine learning framework is used for in-depth analysis to identify device performance patterns and generate predictive warning information as the analysis results. Based on the analysis results, a structured analysis report is generated.

[0007] In an optional implementation, the step of managing data collection rules through a cloud server, and the terminal device obtaining data collection rules associated with its own device attributes from the cloud server via the HTTP protocol, includes: Create data collection rules on the cloud server. The data collection rules include CPU usage threshold, memory usage threshold, frame rate threshold, and decoding time threshold. Associate and bind data collection rules with device attributes, and publish the data collection rules; the device attributes include device model, device name, and device unique identifier; When a terminal device starts up, it retrieves published data collection rules that match its own attributes from the Nginx reverse proxy server via an HTTP request; the terminal device includes, but is not limited to, a central control screen, a smart gateway, and an outdoor screen.

[0008] In an optional implementation, the terminal device collects system performance data in real time according to data collection rules through a monitoring agent program, performs calculations and judgments locally on the device and generates standardized event records, processes the data using a compression algorithm to generate device data, and asynchronously reports it to the cloud message middleware via the MQTT protocol, including: On the terminal device, a locally deployed monitoring agent program loads data collection rules, monitors system performance indicators in real time, performs localized calculations and judgments based on the corresponding thresholds in the data collection rules, identifies abnormal system performance indicators, determines the type of abnormality, and generates standardized event records based on the device identifier of the terminal device; the system performance indicators include CPU utilization, memory usage, frame rate, and decoding time. The LZ4 compression algorithm is used to compress standardized event records to generate device data; The device data is published to the cloud-based RabbitMQ message middleware via the Paho MQTT client, and heartbeat packets containing device status information are sent periodically.

[0009] In an optional implementation, the device data consumed from the message middleware via the cloud data processing service employs a hierarchical processing mechanism. First, the device data is stored in a local SQLite database. Then, duplicate alarms are aggregated through a data cleaning pipeline to generate unique, valid event records, which are then stored in a MySQL database. This includes: Device data is obtained from the RabbitMQ message middleware through cloud data processing service and written to a local SQLite relational database for temporary caching; Establish an Apache Kafka data stream processing pipeline to clean and aggregate device data in an SQLite relational database based on device identifier, exception type, and time window dimensions; Merge multiple consecutive device data of the same anomaly type generated by the same device within a preset time window into a single valid event record; The deduplicated valid event records are persistently stored in a MySQL relational database.

[0010] In an optional implementation, the step of synchronizing valid event records from the MySQL database to the Elasticsearch search engine using a data synchronization tool to establish a device performance metric analysis index includes: Incrementally extract valid event records from a MySQL relational database using the Logstash data acquisition engine; Perform format conversion and field mapping on the extracted valid event records; Write the processed valid event records in batches to the specified index of the Elasticsearch distributed search engine.

[0011] In an optional implementation, the analysis index based on device performance indicators, combined with the Kibana data visualization platform for data display, and the TensorFlow machine learning framework for deep analysis, identifies device performance patterns and generates predictive warning information. The analysis results include: Based on the analysis of device performance indicators, valid event records are extracted from the Elasticsearch distributed search engine, device data is read from them, and a multi-dimensional visualization dashboard is built using the Kibana data visualization platform to generate visualization charts. The TensorFlow machine learning framework was used to analyze device data. The association rule algorithm was used to mine the spatiotemporal correlation between CPU usage and playback stuttering. The LSTM time series prediction algorithm was used to predict the hardware aging trend of the device based on the historical device data of the past 30 days, and hardware aging risk warning information was generated as the analysis result.

[0012] In an optional implementation, generating a structured analysis report based on the analysis results includes: The system periodically reads the analysis results and automatically calls the JasperReports reporting engine service via a RESTful API interface. It then combines the analysis results with the visualization charts generated by the Kibana data visualization platform to produce a structured analysis report, which is output in PDF format.

[0013] Secondly, embodiments of this application also provide a terminal device performance data intelligent analysis system, including: The cloud-based rule management module, deployed on a cloud server, is used to create, store, and manage data collection rules, and to send rule configurations associated with device attributes to terminal devices via the HTTP protocol. The device-side data acquisition module, deployed on the terminal device, is used to load data acquisition rules, collect system performance data in real time, perform calculations and judgments locally and generate standardized event records, which are then processed by a compression algorithm and asynchronously reported via the MQTT communication protocol. The message middleware module uses RabbitMQ message middleware to receive and cache device data reported by terminal devices. The cloud-based data processing module, including the SQLite relational database, the Apache Kafka data stream processing platform, and the MySQL relational database, is used to consume device data from the message middleware module and perform hierarchical processing on the device data, including temporary caching, streaming cleaning, duplicate alarm aggregation, and persistent storage of valid event records. The data synchronization and analysis module, including the Logstash data acquisition engine, the Elasticsearch distributed search engine, and the TensorFlow machine learning framework, is used to synchronize valid event records in MySQL to the search engine, build an index for device performance indicator analysis, and perform in-depth analysis and prediction. The visualization and report generation module, including the Kibana data visualization platform and the JasperReports reporting engine, is used to provide multi-dimensional visualizations based on analysis results and automatically generate structured analysis reports containing charts and statistical conclusions.

[0014] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the intelligent analysis method for terminal device performance data as described in any of the above.

[0015] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the intelligent analysis method for terminal device performance data as described in any of the above embodiments.

[0016] As can be seen from the above technical solutions, the present invention has the following advantages: The intelligent analysis method for terminal device performance data provided in this application achieves full-process automation and intelligence in terminal device performance management by constructing a cloud-based collaborative intelligent analysis system. This method relies on edge computing to complete real-time data collection and preliminary judgment at the device end, significantly reducing network transmission pressure; it efficiently processes massive amounts of data through multi-level caching and streaming cleaning mechanisms, accurately aggregating abnormal events; it combines the Elasticsearch search engine and machine learning algorithms to deeply mine performance patterns, achieving a leap from real-time monitoring to risk prediction; and finally, it automatically generates structured reports combining data visualization and in-depth analysis, greatly improving the operational efficiency and reliability of large-scale terminal devices, and effectively reducing manual intervention costs and business interruption risks.

[0017] This application achieves automated centralized management and control of a large number of terminal devices by constructing a cloud-based collaborative intelligent management architecture. Employing a unified rule configuration and distribution mechanism, terminal devices can autonomously acquire data collection policies and execute monitoring tasks, significantly improving operational efficiency and effectively solving the management challenges brought about by the rapid increase in device scale.

[0018] This application employs a combination of edge computing and intelligent compression transmission. By preprocessing and compressing data on the device side, network bandwidth consumption is significantly reduced. Simultaneously, the cloud utilizes multi-level caching and data cleaning mechanisms to effectively reduce storage resource consumption, achieving efficient processing of massive amounts of device data.

[0019] This application establishes a complete data processing and analysis pipeline, enabling in-depth mining and intelligent analysis of equipment performance data. By combining a distributed search engine with machine learning algorithms, valuable information can be quickly extracted from massive amounts of data, revealing inherent patterns and potential problems in equipment performance, thus greatly enhancing data analysis and decision support capabilities.

[0020] This application utilizes advanced machine learning algorithms to achieve accurate prediction and early warning of equipment performance anomalies. By analyzing historical data trends and real-time operating status, it can promptly identify potential fault risks and generate early warning information, transforming equipment operation and maintenance from passive response to proactive prevention, effectively avoiding potential system failures.

[0021] This application comprehensively improves the reliability of equipment operation and business continuity by constructing a complete closed loop of monitoring, analysis, and early warning. From data collection to intelligent analysis, from anomaly early warning to report generation, a complete operation and maintenance support system is formed, providing all-round protection for the stable operation of large-scale equipment groups and significantly reducing the risk of business interruption. Attached Figure Description

[0022] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating the intelligent analysis method for terminal device performance data provided in this application.

[0024] Figure 2 A schematic diagram of the intelligent analysis system for terminal device performance data provided in this application.

[0025] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0026] The various embodiments of this disclosure will be described more fully in the detailed steps of the intelligent analysis method for terminal device performance data described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0027] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Please see Figure 1 The diagram shows a flowchart of a method for intelligent analysis of terminal device performance data in a specific embodiment. The method includes: S1: Data collection rules are managed through a cloud server. Terminal devices obtain data collection rules associated with their own device attributes from the cloud server via the HTTP protocol.

[0030] In a specific implementation, data collection rules are created through a dedicated configuration interface in the cloud server's management backend. For example, CPU utilization thresholds are set to 80%, memory usage thresholds to 70%, frame rate thresholds to 25fps, and decoding time thresholds to 50ms. These thresholds are set based on considerations of common terminal device performance standards and actual business needs to ensure effective detection of performance anomalies.

[0031] Then, the data collection rules are associated and bound to device attributes. Specifically, in the management backend, users can select device attribute information such as device model, device name, and device unique identifier through drop-down menus or search boxes to achieve precise matching between rules and specific devices. After completing the binding, clicking the "Publish" button will publish the data collection rules to the server, making them accessible to end devices.

[0032] When a terminal device (such as a central control screen, smart gateway, or outdoor large screen) starts up, its built-in network module automatically sends a request to the Nginx reverse proxy server via HTTP to retrieve data collection rules. The request carries the device's own attribute information, such as device model, name, and unique identifier.

[0033] When the Nginx reverse proxy server receives a request, it searches for a matching rule in the published data collection rules stored on the server based on the device's attribute information. If a matching rule is found, it is returned to the terminal device; otherwise, a default rule or a prompt message can be returned to the terminal device, informing it that no specific rule could be obtained.

[0034] S2: The terminal device collects system performance data in real time through the monitoring agent program according to the data collection rules, performs calculations and judgments locally on the device and generates standardized event records, processes the data through a compression algorithm to generate device data, and asynchronously reports it to the cloud message middleware via the MQTT protocol.

[0035] In a specific implementation, a monitoring agent program is deployed locally on the terminal device. This program is designed based on an edge computing architecture and aims to collect key performance indicators in real time while minimizing the impact on the device's performance. Once the device starts up and obtains the data collection rules, the monitoring agent program immediately loads these rules.

[0036] First, the system performance metrics are monitored in real time by a monitoring agent program. For example, data such as CPU usage, memory usage, frame rate, and decoding time can be obtained through system interfaces or specific monitoring tools. For frame rate monitoring, real-time frame rate data may be obtained by interacting with the display driver or video playback module; decoding time can be obtained by adding timing logic to key nodes of the decoding module.

[0037] Then, localized calculations and judgments are performed based on the corresponding thresholds in the data collection rules. For example, when CPU utilization exceeds 80%, it is judged as abnormal CPU utilization; when memory utilization exceeds 70%, it is judged as abnormal memory utilization, and so on. After identifying abnormal system performance indicators, the anomaly type is determined, such as "high CPU utilization" or "high memory utilization," and standardized event records are generated based on the device identifier of the terminal device. The record contains information such as device identifier, anomaly type, anomaly occurrence time, and specific performance indicator values ​​at the time of the anomaly.

[0038] At this point, the LZ4 compression algorithm is used to compress the standardized event records. The LZ4 compression algorithm is characterized by its fast compression speed and moderate compression ratio, making it suitable for rapid data processing when terminal device resources are limited. By calling the LZ4 algorithm library, the standardized event records are converted into compressed device data. Actual testing shows that this compression method can reduce data traffic by 70%, effectively preventing the monitoring program itself from becoming a performance burden.

[0039] Finally, configure the PahoMQTT client on the terminal device to publish the compressed device data to the RabbitMQ message middleware in the cloud. MQTT is a lightweight message transmission protocol suitable for use on devices with limited network conditions. When publishing data, set an appropriate QoS (Quality of Service) level to ensure reliable data transmission.

[0040] Meanwhile, the monitoring agent program periodically (e.g., every 30 seconds) sends heartbeat packets containing device status information to the cloud. The heartbeat packets include the device's current operating status (e.g., normal operation, abnormal operation, etc.), battery information (for mobile devices), network connection status, etc., so that the cloud can understand the device status in a timely manner.

[0041] S3: Consumes device data from the message middleware through cloud data processing services. It adopts a hierarchical processing mechanism, first storing device data in a local SQLite database, then aggregating duplicate alarms through a data cleaning pipeline, generating a unique valid event record, and storing it in a MySQL database.

[0042] In this specific implementation, the cloud-based data processing service retrieves device data from the RabbitMQ message middleware through a dedicated message consumption interface. After obtaining the data, it is temporarily cached in a local SQLite relational database. This local SQLite database stores approximately three hours' worth of data, a balance between timely data processing and storage resources. During data writing, a suitable table structure is designed based on the data structure to ensure accurate and efficient data storage.

[0043] Next, an Apache Kafka data stream processing pipeline is established. This pipeline cleanses and aggregates device data in the SQLite relational database based on device identifier, exception type, and time window dimensions. For example, a time window of 5 minutes is set to process device data generated by the same device within a 5-minute period.

[0044] During data cleaning, data is filtered based on preset rules, such as removing data with incorrect formatting or that is incomplete. For aggregation operations, multiple consecutive instances of the same anomaly type generated by the same device within a preset time window are merged into a single valid event record. For example, if a device generates five consecutive "high CPU usage" anomaly records within five minutes, these are merged into a single record, which includes information such as the first occurrence time, the last occurrence time, and the number of occurrences.

[0045] Finally, the deduplicated valid event records are persistently stored in a MySQL relational database. MySQL databases have excellent data management and query performance, making them suitable for long-term storage of large amounts of data. During the storage process, a reasonable database table structure and indexes are designed based on the data characteristics and query requirements to facilitate subsequent data queries and analysis.

[0046] S4: Use data synchronization tools to synchronize valid event records from the MySQL database to the Elasticsearch search engine and build an index for device performance metric analysis.

[0047] In a specific implementation, valid event records are first incrementally extracted from a MySQL relational database using the Logstash data acquisition engine. The extraction time interval (e.g., every 10 minutes) and extraction conditions (e.g., only extracting data added or modified since the last extraction) are set in the Logstash configuration file to ensure the accuracy and efficiency of data extraction.

[0048] Then, the extracted valid event records undergo format conversion and field mapping. For example, the date format in the MySQL database is converted to an Elasticsearch-recognizable date format, and field names are mapped to names that conform to the Elasticsearch index specification. This step ensures that the data can be correctly written to Elasticsearch and facilitates subsequent queries and analysis.

[0049] Finally, the processed valid event records are written in batches to the specified index of the Elasticsearch distributed search engine. During the writing process, the batch write size and concurrency are reasonably set according to Elasticsearch cluster configuration and performance optimization principles to improve writing efficiency and avoid putting excessive pressure on the Elasticsearch cluster.

[0050] S5: Based on the analysis index of device performance indicators, the data is displayed using the Kibana data visualization platform, and the TensorFlow machine learning framework is used for in-depth analysis to identify device performance patterns and generate predictive warning information as the analysis results.

[0051] In a specific implementation, valid event records are extracted from the Elasticsearch distributed search engine based on device performance metric analysis indexes, and device data is read from them. A multi-dimensional visualization dashboard is built using the Kibana data visualization platform, such as creating a device health heatmap, using different colors and shades to represent the health status of different devices; and generating fault prediction curves to show the trend of device performance changes over time and the predicted time of fault occurrence. Through these visualizations, operations and maintenance personnel can intuitively understand the operating status of the devices.

[0052] Then, the TensorFlow machine learning framework was applied to analyze the device data. Specifically, association rule algorithms were used to mine the spatiotemporal correlation between CPU utilization and playback stuttering. For example, by analyzing a large amount of device data, it was found that when CPU utilization exceeded a certain threshold within a specific time period, the probability of playback stuttering increased significantly, thus providing a basis for optimizing device performance. The LSTM time series prediction algorithm was used to predict the hardware aging trend of the device based on the historical device data of the past 30 days.

[0053] The LSTM algorithm can effectively process time series data. By learning from historical data, it can predict the changing trends of equipment hardware performance indicators, provide early warning of hardware aging risks up to 8 hours in advance, and generate hardware aging risk warning information as analysis results to provide to maintenance personnel so that maintenance measures can be taken in a timely manner.

[0054] S6: Generate a structured analysis report based on the analysis results.

[0055] In a specific implementation, a scheduled task is first set (e.g., 2 AM every day) to periodically read the analysis results generated in step S5 through a dedicated script or program, including hardware aging risk warning information, equipment performance patterns, and other content.

[0056] Then, the JasperReports reporting engine service is automatically invoked via the RESTful API interface to combine the analysis results with the visualization charts generated by the Kibana data visualization platform. During the invocation process, according to the JasperReports template design specifications, the analysis result data is populated into the corresponding report template positions, while the visualization charts are embedded into the report as images.

[0057] Finally, a structured analysis report is generated and output in PDF format. The output PDF report contains detailed information on equipment performance analysis, visualization charts, and risk warning information, providing equipment management and maintenance personnel with comprehensive and intuitive equipment performance analysis data, significantly reducing the difficulty of equipment management and maintenance.

[0058] In this embodiment, an edge computing architecture is used to deploy an agent program on the terminal to collect key indicators. Combined with heartbeat packets and compression algorithms, data traffic is effectively reduced, thus reducing the performance burden of the monitoring program on the device. Through the construction of a distributed data platform, a multi-level caching mechanism is established between local SQLite data for the past 3 hours and historical data from the cloud ES cluster. A data cleaning pipeline is designed to automatically filter duplicate alarms. An intelligent analysis engine is built based on Elasticsearch, and Kibana is used to realize visualizations such as device health heatmaps. Machine learning algorithms are used to identify the correlation between CPU usage and playback stuttering, providing an early warning of hardware aging risks up to 8 hours in advance. Overall, the difficulty of device management and maintenance is significantly reduced, and efficient collection, accurate analysis, and intelligent presentation of device performance data are achieved.

[0059] like Figure 2 As shown, the following are embodiments of the intelligent analysis system for terminal device performance data provided in this disclosure. This system and the intelligent analysis method for terminal device performance data in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the intelligent analysis system for terminal device performance data, please refer to the embodiments of the intelligent analysis method for terminal device performance data described above.

[0060] A terminal device performance data intelligent analysis system, comprising: The cloud-based rule management module, deployed on a cloud server, is used to create, store, and manage data collection rules, and to send rule configurations associated with device attributes to terminal devices via the HTTP protocol.

[0061] The device-side data acquisition module, deployed on the terminal device, is used to load data acquisition rules, collect system performance data in real time, perform calculations and judgments locally, generate standardized event records, process them through a compression algorithm, and then asynchronously report them via the MQTT communication protocol.

[0062] The message middleware module uses RabbitMQ message middleware to receive and cache device data reported by terminal devices.

[0063] The cloud-based data processing module, including the SQLite relational database, the Apache Kafka data stream processing platform, and the MySQL relational database, is used to consume device data from the message middleware module and perform hierarchical processing on the device data, including temporary caching, streaming cleansing, duplicate alarm aggregation, and persistent storage of valid event records.

[0064] The data synchronization and analysis module, including the Logstash data acquisition engine, the Elasticsearch distributed search engine, and the TensorFlow machine learning framework, is used to synchronize valid event records in MySQL to the search engine, build an index for device performance indicator analysis, and perform in-depth analysis and prediction.

[0065] The visualization and report generation module, including the Kibana data visualization platform and the JasperReports reporting engine, is used to provide multi-dimensional visualizations based on analysis results and automatically generate structured analysis reports containing charts and statistical conclusions.

[0066] The intelligent analysis system for terminal device performance data provided in this embodiment achieves real-time collection and localized processing of device performance data by deploying a terminal edge computing agent. It combines the MQTT protocol and compression algorithm to complete efficient data transmission, utilizes a multi-level cloud caching architecture and Kafka stream processing pipeline to clean and aggregate massive amounts of data, and performs in-depth analysis and trend prediction based on the Elasticsearch search engine and TensorFlow machine learning framework. Finally, it outputs visualized analysis results through an automated report generation system, forming a complete closed loop from data collection to intelligent early warning. This significantly improves the operation and maintenance efficiency of large-scale terminal devices, reduces the cost of manual intervention, and realizes a shift from a passive response to a proactive prevention operation and maintenance model.

[0067] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0068] The intelligent analysis method for terminal device performance data provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0069] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0070] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0071] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0072] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0073] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0074] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0075] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0076] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0077] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0078] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0079] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0080] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0081] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0082] The aforementioned electronic device realizes the intelligent analysis method for terminal device performance data of this application. It achieves localized collection and processing of device performance data by deploying a terminal edge computing agent, completes efficient data transmission by combining the MQTT protocol and compression algorithm, constructs a cloud multi-level caching architecture and Kafka stream processing pipeline to achieve massive data cleaning and aggregation, and performs deep learning and trend prediction based on the Elasticsearch and TensorFlow intelligent analysis platform. Finally, it outputs multi-dimensional analysis results through an automated report generation system. It achieves the beneficial effects of reducing cloud load and network transmission costs, improving data processing efficiency and storage utilization, realizing accurate early warning and predictive maintenance of equipment failures, and significantly improving the management efficiency and business continuity of large-scale terminal devices.

[0083] The storage medium provided in this application stores a program product capable of implementing an intelligent analysis method for terminal device performance data.

[0084] Intelligent analysis methods for terminal device performance data include: Data collection rules are managed by a cloud server, and terminal devices obtain data collection rules associated with their own device attributes from the cloud server via the HTTP protocol. The terminal device collects system performance data in real time according to data collection rules through the monitoring agent program, performs calculations and judgments locally on the device and generates standardized event records, processes the data through a compression algorithm to generate device data, and asynchronously reports it to the cloud message middleware via the MQTT protocol. Device data is consumed through the cloud data processing service message middleware. A hierarchical processing mechanism is adopted, first storing the device data in a local SQLite database, then aggregating duplicate alarms through a data cleaning pipeline, generating a unique valid event record and storing it in a MySQL database. The valid event records in the MySQL database are synchronized to the Elasticsearch search engine using data synchronization tools to build an index for device performance indicator analysis. Based on the device performance index analysis, the data is displayed using the Kibana data visualization platform, and the TensorFlow machine learning framework is used for in-depth analysis to identify device performance patterns and generate predictive warning information as the analysis results. Based on the analysis results, a structured analysis report is generated.

[0085] In some possible implementations, the intelligent analysis method for terminal device performance data of this disclosure can be implemented as a program product, which includes program code. When the program product is run on a terminal device, the program code is used to cause the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0086] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0087] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent analysis of terminal device performance data, characterized in that, include: Data collection rules are managed by a cloud server, and terminal devices obtain data collection rules associated with their own device attributes from the cloud server via the HTTP protocol. The terminal device collects system performance data in real time according to data collection rules through the monitoring agent program, performs calculations and judgments locally on the device and generates standardized event records, processes the data through a compression algorithm to generate device data, and asynchronously reports it to the cloud message middleware via the MQTT protocol. Device data is consumed through the cloud data processing service message middleware. A hierarchical processing mechanism is adopted, first storing the device data in a local SQLite database, then aggregating duplicate alarms through a data cleaning pipeline, generating a unique valid event record and storing it in a MySQL database. The valid event records in the MySQL database are synchronized to the Elasticsearch search engine using data synchronization tools to build an index for device performance indicator analysis. Based on the device performance index analysis, the data is displayed using the Kibana data visualization platform, and the TensorFlow machine learning framework is used for in-depth analysis to identify device performance patterns and generate predictive warning information as the analysis results. Based on the analysis results, a structured analysis report is generated.

2. The intelligent analysis method for terminal device performance data according to claim 1, characterized in that, The process of managing data collection rules via a cloud server, whereby terminal devices obtain data collection rules associated with their own device attributes from the cloud server via the HTTP protocol, includes: Create data collection rules on the cloud server. The data collection rules include CPU usage threshold, memory usage threshold, frame rate threshold, and decoding time threshold. Associate and bind data collection rules with device attributes, and publish the data collection rules; the device attributes include device model, device name, and device unique identifier; When a terminal device starts up, it retrieves published data collection rules that match its own attributes from the Nginx reverse proxy server via an HTTP request; the terminal device includes, but is not limited to, a central control screen, a smart gateway, and an outdoor screen.

3. The intelligent analysis method for terminal device performance data according to claim 2, characterized in that, The terminal device collects system performance data in real time according to data collection rules through a monitoring agent program, performs calculations and judgments locally on the device, generates standardized event records, processes the data using a compression algorithm, generates device data, and asynchronously reports it to the cloud message middleware via the MQTT protocol, including: On the terminal device, a locally deployed monitoring agent program loads data collection rules, monitors system performance indicators in real time, performs localized calculations and judgments based on the corresponding thresholds in the data collection rules, identifies abnormal system performance indicators, determines the type of abnormality, and generates standardized event records based on the device identifier of the terminal device; the system performance indicators include CPU utilization, memory usage, frame rate, and decoding time. The LZ4 compression algorithm is used to compress standardized event records to generate device data; The device data is published to the cloud-based RabbitMQ message middleware via the Paho MQTT client, and heartbeat packets containing device status information are sent periodically.

4. The intelligent analysis method for terminal device performance data according to claim 3, characterized in that, The device data consumed through the cloud data processing service message middleware adopts a hierarchical processing mechanism. First, the device data is stored in a local SQLite database. Then, duplicate alarms are aggregated through a data cleaning pipeline to generate unique valid event records, which are then stored in a MySQL database. This includes: Device data is obtained from the RabbitMQ message middleware through cloud data processing service and written to a local SQLite relational database for temporary caching; Establish an Apache Kafka data stream processing pipeline to clean and aggregate device data in an SQLite relational database based on device identifier, exception type, and time window dimensions; Merge multiple consecutive device data of the same anomaly type generated by the same device within a preset time window into a single valid event record; The deduplicated valid event records are persistently stored in a MySQL relational database.

5. The intelligent analysis method for terminal device performance data according to claim 4, characterized in that, The process of synchronizing valid event records from the MySQL database to the Elasticsearch search engine using a data synchronization tool to establish an index for device performance metric analysis includes: Incrementally extract valid event records from a MySQL relational database using the Logstash data acquisition engine; Perform format conversion and field mapping on the extracted valid event records; Write the processed valid event records in batches to the specified index of the Elasticsearch distributed search engine.

6. The intelligent analysis method for terminal device performance data according to claim 5, characterized in that, The analysis index based on device performance indicators, combined with the Kibana data visualization platform for data display, and the TensorFlow machine learning framework for deep analysis, identifies device performance patterns and generates predictive warning information. The analysis results include: Based on the analysis of device performance indicators, valid event records are extracted from the Elasticsearch distributed search engine, device data is read from them, and a multi-dimensional visualization dashboard is built using the Kibana data visualization platform to generate visualization charts. The TensorFlow machine learning framework was used to analyze device data. The association rule algorithm was used to mine the spatiotemporal correlation between CPU usage and playback stuttering. The LSTM time series prediction algorithm was used to predict the hardware aging trend of the device based on the historical device data of the past 30 days, and hardware aging risk warning information was generated as the analysis result.

7. The intelligent analysis method for terminal device performance data according to claim 6, characterized in that, The generation of a structured analysis report based on the analysis results includes: The system periodically reads the analysis results and automatically calls the JasperReports reporting engine service via a RESTful API interface. It then combines the analysis results with the visualization charts generated by the Kibana data visualization platform to produce a structured analysis report, which is output in PDF format.

8. A terminal device performance data intelligent analysis system, characterized in that, The system employs the intelligent analysis method for terminal device performance data as described in any one of claims 1 to 7; The system includes: The cloud-based rule management module, deployed on a cloud server, is used to create, store, and manage data collection rules, and to send rule configurations associated with device attributes to terminal devices via the HTTP protocol. The device-side data acquisition module, deployed on the terminal device, is used to load data acquisition rules, collect system performance data in real time, perform calculations and judgments locally and generate standardized event records, which are then processed by a compression algorithm and asynchronously reported via the MQTT communication protocol. The message middleware module uses RabbitMQ message middleware to receive and cache device data reported by terminal devices. The cloud-based data processing module, including the SQLite relational database, the Apache Kafka data stream processing platform, and the MySQL relational database, is used to consume device data from the message middleware module and perform hierarchical processing on the device data, including temporary caching, streaming cleaning, duplicate alarm aggregation, and persistent storage of valid event records. The data synchronization and analysis module, including the Logstash data acquisition engine, the Elasticsearch distributed search engine, and the TensorFlow machine learning framework, is used to synchronize valid event records in MySQL to the search engine, build an index for device performance indicator analysis, and perform in-depth analysis and prediction. The visualization and report generation module, including the Kibana data visualization platform and the JasperReports reporting engine, is used to provide multi-dimensional visualizations based on analysis results and automatically generate structured analysis reports containing charts and statistical conclusions.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the intelligent analysis method for terminal device performance data as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent analysis method for terminal device performance data as described in any one of claims 1 to 7.

Images