ELECTRONIC APPARATUS FOR CRASH DATA ANALYSIS AND REPORTING BASED ON APPLICATION VERSION AND DOMAIN INFORMATION

Abstract

The present disclosure relates to adaptive learning systems for edge computing. Particularly, the present disclosure relates to an electronic apparatus designed for analyzing and reporting crash data based on application version and domain information to optimize edge device performance.

Specification

Description:Field of the Invention


The present disclosure provides an electronic apparatus for crash data analysis and reporting based on application version and domain information, specifically an adaptive learning system (100) for edge computing. The system includes a data acquisition module (102) configured to collect application version data from multiple edge devices (104). A crash detection unit (106) analyzes crash information, including crash types and domains, across these edge devices. A learning processor (108) generates diagnostic data by evaluating crash frequency and correlating it with application versions. A distribution engine (110) transmits updated diagnostic models to the edge devices based on the analysis, enabling improved crash prediction and response.
Background
The background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
Edge computing has become an essential component in modern computational systems, enabling processing to be carried out closer to data sources, such as Internet of Things (IoT) devices, rather than relying on centralized cloud servers. This decentralization of data processing offers numerous advantages, such as reducing latency, improving response times, and optimizing bandwidth usage. As a result, edge computing is widely implemented across various industries, including manufacturing, healthcare, and autonomous systems. However, the adoption of edge computing introduces several complexities, particularly in relation to managing and maintaining the operational integrity of a large number of edge devices distributed across multiple environments.
State-of-the-art systems typically utilize centralized control and diagnostic mechanisms to monitor the performance and operational status of edge devices. One such example is the centralized cloud-based diagnostics system that gathers data from edge devices for remote monitoring and maintenance purposes. However, such systems are associated with inherent drawbacks. Centralized diagnostic systems often experience significant delays in identifying issues with the devices due to the time required to transmit data to a remote cloud server. Such delays can result in prolonged downtime for edge devices, especially in time-sensitive applications such as autonomous vehicle systems or real-time industrial control systems. Furthermore, centralized systems also introduce concerns related to data security and privacy, as sensitive data from edge devices must be transmitted to remote servers, which may be susceptible to unauthorized access.
In addition to centralized diagnostic systems, traditional techniques employ static diagnostic models that are deployed across all edge devices uniformly. Such static models are developed based on predefined assumptions regarding the operational conditions and failure modes of edge devices. However, these static diagnostic models exhibit limitations in effectively handling the dynamic and heterogeneous nature of edge devices, which are often subjected to varying environmental conditions, usage patterns, and failure mechanisms. The uniform application of static models across diverse edge devices results in inaccurate diagnostics, leading to the misidentification of failure modes or the inability to detect certain failures in specific devices. As a result, the reliability and performance of edge devices are compromised, necessitating frequent manual intervention to address such issues.
Furthermore, contemporary diagnostic approaches for edge computing systems often rely on retrospective data analysis, wherein operational data from edge devices is collected over time and analyzed periodically. While such retrospective analysis may provide insights into long-term performance trends, such systems lack the capability to offer real-time diagnostics or adaptive learning mechanisms. This delay in diagnosis and troubleshooting can significantly impact the availability of critical applications that rely on continuous operation of edge devices, such as real-time video analytics in smart cities or healthcare monitoring systems. Additionally, retrospective diagnostic systems are often incapable of adapting to changes in application versions or hardware configurations of edge devices, resulting in outdated diagnostic models that fail to account for the latest updates or configurations of edge devices.
Moreover, the majority of conventional diagnostic systems for edge computing are unable to handle the increasing complexity associated with edge device ecosystems. With the proliferation of diverse edge devices across industries, traditional diagnostic systems struggle to scale effectively. The need to support a growing number of edge devices, each with varying hardware, software, and firmware configurations, introduces significant challenges in maintaining up-to-date diagnostic models. Manual updates to diagnostic models and intervention are typically required, resulting in substantial time and resource costs. Consequently, there is an urgent need for a more adaptive and scalable solution that can efficiently manage diagnostic processes for a large and diverse set of edge devices.
Another challenge in conventional systems pertains to the detection and analysis of device crashes, particularly in edge computing environments where real-time processing and reliability are paramount. Traditional systems are limited in their ability to quickly detect and analyze crashes across a wide array of devices. These systems often rely on manual log analysis or predefined error codes that do not account for new or previously unknown failure modes. Furthermore, conventional crash detection techniques do not effectively correlate crash data across multiple devices, resulting in isolated troubleshooting efforts that fail to consider patterns or commonalities in crash occurrences. As a result, the troubleshooting process becomes labor-intensive, time-consuming, and prone to errors.
In light of the above discussion, there exists an urgent need for solutions that overcome the problems associated with conventional systems and/or techniques for managing and diagnosing edge devices in edge computing environments.
All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.
Summary
Various objects, features, and advantages of the disclosed subject matter can be more fully appreciated with reference to the following detailed description of the disclosed subject matter when considered in connection with the following drawings, in which like reference numerals identify like elements.
The present disclosure provides an electronic apparatus for crash data analysis and reporting based on application version and domain information, specifically an adaptive learning system (100) for edge computing. The system includes a data acquisition module (102) configured to collect application version data from multiple edge devices (104). A crash detection unit (106) analyzes crash information, including crash types and domains, across these edge devices. A learning processor (108) generates diagnostic data by evaluating crash frequency and correlating it with application versions. A distribution engine (110) transmits updated diagnostic models to the edge devices based on the analysis, enabling improved crash prediction and response.
An objective of the present disclosure is to enable adaptive learning in edge computing systems by processing crash data and transmitting updated diagnostic models to edge devices. The system of the present disclosure aims to enhance the stability and performance of applications deployed on edge devices by efficiently managing crash detection and diagnostic data distribution.
In an aspect, the present disclosure provides an adaptive learning system for edge computing. The system comprises a data acquisition module to collect application version data from a plurality of edge devices. A crash detection unit is disposed in communication with the data acquisition module, said crash detection unit analyzes crash information including crash types and domains across the plurality of edge devices. A learning processor is arranged relative to the crash detection unit, said learning processor generates diagnostic data based on crash frequency and application versions from the crash detection unit. A distribution engine is interconnected with the learning processor, said distribution engine transmits updated diagnostic models to the plurality of edge devices within the adaptive learning system.
Furthermore, the adaptive learning system enables continuous collection of application performance data in addition to version data, which enhances diagnostic accuracy. The crash detection unit categorizes crash types into critical and non-critical based on their impact on device performance, which optimizes response strategies. Additionally, historical crash data is stored for comparison against current trends, contributing to improved crash trend analysis. The learning processor utilizes predictive capabilities to anticipate future crash patterns, enabling proactive diagnostics. Furthermore, the distribution engine sends real-time alerts to edge devices when an updated diagnostic model is available, ensuring timely updates.
Moreover, the adaptive learning system prioritizes updates to edge devices based on geographical region and device performance metrics, facilitating efficient resource allocation. The data acquisition module captures additional environmental data such as network conditions and device hardware specifications, further refining diagnostic precision. The crash detection unit evaluates crash severity based on the application domain and user impact on the edge device, enhancing diagnostic relevance. Lastly, the learning processor updates diagnostic models based on variations in crash types across different edge devices, ensuring adaptability across diverse device environments.

Brief Description of the Drawings


The features and advantages of the present disclosure would be more clearly understood from the following description taken in conjunction with the accompanying drawings in which:
FIG. 1 illustrates an adaptive learning system (100) for edge computing, in accordance with the embodiments of the present disclosure.
FIG. 2 illustrates sequential diagram of an adaptive learning system (100) for edge computing, in accordance with the embodiments of the present disclosure.
Detailed Description
The following is a detailed description of exemplary embodiments to illustrate the principles of the invention. The embodiments are provided to illustrate aspects of the invention, but the invention is not limited to any embodiment. The scope of the invention encompasses numerous alternatives, modifications and equivalent; it is limited only by the claims.
In view of the many possible embodiments to which the principles of the present discussion may be applied, it should be recognized that the embodiments described herein with respect to the drawing figures are meant to be illustrative only and should not be taken as limiting the scope of the claims. Therefore, the techniques as described herein contemplate all such embodiments as may come within the scope of the following claims and equivalents thereof.
The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different instances in the description and the figures may indicate similar or identical items.
Pursuant to the "Detailed Description" section herein, whenever an element is explicitly associated with a specific numeral for the first time, such association shall be deemed consistent and applicable throughout the entirety of the "Detailed Description" section, unless otherwise expressly stated or contradicted by the context.
The present disclosure provides an electronic apparatus for crash data analysis and reporting based on application version and domain information, specifically an adaptive learning system (100) for edge computing. The system includes a data acquisition module (102) configured to collect application version data from multiple edge devices (104). A crash detection unit (106) analyzes crash information, including crash types and domains, across these edge devices. A learning processor (108) generates diagnostic data by evaluating crash frequency and correlating it with application versions. A distribution engine (110) transmits updated diagnostic models to the edge devices based on the analysis, enabling improved crash prediction and response.
Pursuant to the "Detailed Description" section herein, whenever an element is explicitly associated with a specific numeral for the first time, such association shall be deemed consistent and applicable throughout the entirety of the "Detailed Description" section, unless otherwise expressly stated or contradicted by the context.
As used herein, the term "adaptive learning system" refers to a system that enables continuous improvement through iterative processes based on collected data, typically from external sources, and analysis of said data. Such a system is employed to optimize performance, detect anomalies, and adjust its operation in response to changing conditions or patterns in data. In the context of edge computing, the adaptive learning system operates in a decentralized environment, where processing occurs on edge devices, which are computing devices located near the data source rather than relying on a central cloud or data center. The adaptive learning system for edge computing may process data from various applications, monitor device performance, detect system crashes, and generate diagnostic insights. The adaptive nature of such a system allows for the refinement of diagnostic models based on real-time feedback from multiple edge devices, enabling timely updates to address detected issues and improve operational stability across a network of devices.
As used herein, the term "data acquisition module" refers to a system component responsible for gathering data from external sources, in this case, from a plurality of edge devices. The data collected by said component typically includes application version information, device performance metrics, and other operational data that may be relevant to diagnosing issues on the edge devices. The data acquisition module operates continuously or periodically and communicates the collected data to subsequent components within the system for further analysis. Such a data collection process enables monitoring the performance of various applications deployed on different edge devices, identifying common issues or anomalies, and serving as the foundation for generating further diagnostic data. The data acquisition module works seamlessly within the adaptive learning system by ensuring accurate and timely collection of essential data from distributed edge devices, which can be leveraged by other system components to generate diagnostic models.
As used herein, the term "crash detection unit" refers to a system component responsible for identifying and analyzing crashes, or operational failures, occurring across a plurality of edge devices. Said crash detection unit processes crash-related data such as crash types, frequency, and affected application domains. By evaluating the nature and impact of crashes, the crash detection unit can categorize the crashes into various levels of severity and further classify them based on their underlying causes. Communication between the crash detection unit and the data acquisition module enables the crash detection unit to access a comprehensive dataset related to device performance and application versions. Furthermore, the crash detection unit may store historical crash data for comparison with current trends, allowing for an ongoing analysis of crash patterns and potential system vulnerabilities. The crash detection unit thereby contributes significantly to generating diagnostic data used by subsequent components within the system.
As used herein, the term "learning processor" refers to a component of the system responsible for processing crash-related data and deriving diagnostic information from said data. The learning processor interacts with the crash detection unit to receive information about crash occurrences, including crash frequency, application versions, and crash types. Said learning processor applies analytical techniques to identify patterns in the crash data and generate diagnostic insights that can help predict future issues or optimize system performance. The diagnostic data generated by the learning processor serves as the basis for updating diagnostic models, which are then distributed to edge devices within the network. Through continuous interaction with the crash detection unit and other system components, the learning processor adapts to changing system conditions, contributing to the dynamic and iterative nature of the adaptive learning system.
As used herein, the term "distribution engine" refers to a system component responsible for transmitting updated diagnostic models to a plurality of edge devices within the adaptive learning system. The distribution engine communicates with the learning processor, which generates the diagnostic models based on crash data analysis. Once said diagnostic models have been generated, the distribution engine ensures their distribution across the network of edge devices, enabling each device to update its diagnostic capabilities. In some embodiments, the distribution engine may prioritize updates to specific devices based on factors such as geographical location or device performance metrics. Additionally, the distribution engine may also send real-time alerts to edge devices when a new diagnostic model becomes available. Said distribution engine ensures that the entire network of edge devices benefits from the latest diagnostic insights and performance optimizations.
FIG. 1 illustrates an adaptive learning system (100) for edge computing, in accordance with the embodiments of the present disclosure. In an embodiment, a data acquisition module (102) is included within the adaptive learning system (100) and is responsible for collecting application version data from a plurality of edge devices (104). Said data acquisition module (102) operates by establishing communication links with the edge devices (104), enabling continuous or periodic extraction of application version data. The data acquired by the data acquisition module (102) pertains to the specific versions of software applications running on the edge devices (104), which may include information such as version numbers, update statuses, and deployment histories. Said data acquisition module (102) collects data from a diverse array of edge devices (104) deployed across various operational environments, ensuring comprehensive data collection for further analysis. The data acquisition process may further include identifying discrepancies between different application versions, enabling the system to track inconsistencies across devices. The data acquisition module (102) thus serves as the initial data collection point in the adaptive learning system (100), providing essential information that is communicated to subsequent components, such as the crash detection unit (106), for further processing.
In an embodiment, the adaptive learning system (100) includes a crash detection unit (106) that is disposed in communication with the data acquisition module (102). Said crash detection unit (106) is responsible for analyzing crash information, which includes crash types and domains across the plurality of edge devices (104). Crash types may refer to the nature of operational failures, such as system freezes, application shutdowns, or hardware malfunctions, while crash domains relate to the specific areas of the edge devices (104) affected by said crashes, such as memory, processing units, or external interface failures. The crash detection unit (106) evaluates crash frequency, severity, and the circumstances leading to each crash, using the data collected by the data acquisition module (102). The crash detection unit (106) also categorizes crashes into distinct types for the purpose of analysis, which enables the identification of patterns or recurring issues within the edge devices (104). The crash detection unit (106) further communicates this processed crash information to the learning processor (108) for the generation of diagnostic data.
In an embodiment, a learning processor (108) is arranged relative to the crash detection unit (106) within the adaptive learning system (100). Said learning processor (108) receives crash data, including crash frequency and application versions, from the crash detection unit (106) and processes said data to generate diagnostic information. The learning processor (108) analyzes the correlation between crash occurrences and specific application versions, identifying patterns or trends that may indicate common causes of crashes. Said learning processor (108) processes large datasets of crash information across a variety of edge devices (104) to develop diagnostic insights that are representative of the entire network. The learning processor (108) may further refine diagnostic models by analyzing historical data and comparing it with current crash trends. The diagnostic data generated by the learning processor (108) is subsequently communicated to the distribution engine (110) for dissemination across the edge devices (104).
In an embodiment, the adaptive learning system (100) includes a distribution engine (110) that is interconnected with the learning processor (108). Said distribution engine (110) is responsible for transmitting updated diagnostic models generated by the learning processor (108) to the plurality of edge devices (104) within the system. The distribution engine (110) manages the dissemination of said diagnostic models, ensuring that each edge device (104) receives the relevant updates based on its application version and crash history. In some cases, the distribution engine (110) may prioritize updates based on criteria such as geographical location, device performance, or the severity of crashes experienced by specific edge devices (104). Said distribution engine (110) may also send real-time alerts to edge devices (104) when an updated diagnostic model is available, enabling rapid deployment of critical updates. The distribution engine (110) ensures that all edge devices (104) within the adaptive learning system (100) are equipped with the latest diagnostic capabilities derived from the processed crash data.
In an embodiment, the data acquisition module (102) is configured to continuously collect application performance data in addition to version data from the plurality of edge devices (104). Said data acquisition module (102) is designed to gather metrics that reflect how applications are functioning on each of the edge devices (104). Application performance data may include factors such as response times, latency, resource usage, error rates, and user interactions. This real-time or periodic data collection enables the system to monitor fluctuations in application performance that may be indicative of underlying issues such as crashes, memory leaks, or inefficient resource usage. In combination with version data, the continuous collection of performance data allows for a more comprehensive analysis of system health. By correlating performance metrics with application versions, the adaptive learning system (100) can determine whether specific software versions are contributing to degraded performance. This information is critical for understanding the impact of application updates on edge devices (104) and for generating diagnostic data that can help mitigate potential failures.
In an embodiment, the crash detection unit (106) further categorizes crash types into critical and non-critical based on their impact on device performance. Said crash detection unit (106) analyzes the severity of each crash and assigns a category based on the degree of performance degradation caused by the crash. Critical crashes may include instances where the edge device (104) experiences a complete shutdown, loss of data, or significant disruption in operation. Non-critical crashes, on the other hand, may involve temporary slowdowns, minor application failures, or errors that do not compromise the overall functionality of the device. The categorization process involves evaluating factors such as the duration of the crash, the components affected, and the recovery time required. The ability of the crash detection unit (106) to differentiate between critical and non-critical crashes enables the adaptive learning system (100) to prioritize responses and updates based on the severity of the issues encountered by the edge devices (104).
In an embodiment, the crash detection unit (106) is configured to store historical crash data for comparison against current crash trends. Said crash detection unit (106) retains information about previous crashes, including the types, frequency, severity, and conditions under which they occurred. The stored historical data provides a reference point for analyzing ongoing crash patterns across the plurality of edge devices (104). By comparing current crash data with historical records, the crash detection unit (106) can identify recurring issues or trends that may indicate deeper system flaws or emerging vulnerabilities. Historical crash data also allows for the detection of gradual changes in crash behavior, such as increased frequency or shifts in the types of crashes experienced. The ability to store and analyze historical crash data enhances the system's capability to anticipate future crashes and optimize the generation of diagnostic data by incorporating long-term insights into current assessments.
In an embodiment, the learning processor (108) utilizes machine learning algorithms to predict future crash patterns based on diagnostic data generated by the crash detection unit (106). Said learning processor (108) processes a vast dataset of crash occurrences, application performance data, and application version history, applying analytical techniques to identify correlations between specific factors and crash incidents. The learning processor (108) analyzes trends and anomalies within the data to develop predictive models that estimate the likelihood of future crashes. These models consider variables such as the frequency of past crashes, the types of applications running on the edge devices (104), and changes in the operational environment. By employing predictive analytics, the learning processor (108) can forecast potential crash scenarios, allowing the system to proactively adjust diagnostic models and suggest preventive measures. This capability significantly enhances the system's ability to minimize disruptions and maintain optimal performance across the network of edge devices (104).
In an embodiment, the distribution engine (110) is configured to send real-time alerts to edge devices (104) when a new diagnostic model is available. Said distribution engine (110) communicates with the learning processor (108) to determine when an updated diagnostic model has been generated and is ready for deployment. Upon identifying the availability of a new model, the distribution engine (110) sends alerts to the edge devices (104), notifying them of the update. The real-time alert functionality is crucial for ensuring that edge devices (104) are promptly informed of the availability of improved diagnostic capabilities, enabling them to take immediate action if necessary. The alert mechanism may also include detailed information about the nature of the update, such as the specific issues addressed or performance improvements provided by the new diagnostic model. By facilitating real-time communication between the system and the edge devices (104), the distribution engine (110) helps ensure timely deployment of diagnostic updates.
In an embodiment, the distribution engine (110) is further configured to prioritize updates to edge devices (104) based on geographical region and device performance metrics. Said distribution engine (110) assesses factors such as the location of each edge device (104), the severity of issues experienced, and the current performance status of the device. Based on these criteria, the distribution engine (110) determines which devices require immediate updates and prioritizes the deployment of new diagnostic models accordingly. Devices located in regions with high demand or those experiencing critical performance issues may receive updates sooner than devices in lower-priority areas or those with stable operation. The distribution engine (110) may also analyze network conditions to optimize the timing of updates, ensuring that updates are delivered efficiently without overloading the system. This targeted approach allows the adaptive learning system (100) to allocate resources effectively and respond to varying conditions across the network of edge devices (104).
In an embodiment, the data acquisition module (102) is configured to capture additional environmental data, including network conditions and device hardware specifications, from the plurality of edge devices (104). Said data acquisition module (102) collects information about the external factors that may affect the performance of applications running on the edge devices (104). Network conditions may include bandwidth availability, latency, and connectivity stability, while hardware specifications may involve details about the device's processing power, memory, and storage capacity. By gathering such environmental data, the data acquisition module (102) provides a more comprehensive dataset for the adaptive learning system (100) to analyze. This allows the system to correlate environmental factors with application performance and crash occurrences, identifying external influences that may contribute to issues on the edge devices (104). The ability to capture both application-specific and environmental data enhances the overall diagnostic capabilities of the system.
In an embodiment, the crash detection unit (106) is configured to evaluate crash severity based on the application domain and user impact on the edge device (104). Said crash detection unit (106) analyzes crashes not only by their technical characteristics but also by considering the context in which the crashes occur. The application domain refers to the specific type of application running on the edge device (104), such as entertainment, communication, or business-related applications. Crashes that affect mission-critical applications, such as those used for business operations, may be classified as more severe compared to crashes in less essential applications. The crash detection unit (106) also evaluates how the crash impacts the end-user experience, including factors such as data loss, service interruption, or application downtime. By incorporating both the application domain and user impact into the severity evaluation, the crash detection unit (106) provides a more nuanced understanding of the consequences of each crash.
In an embodiment, the learning processor (108) is further configured to update the diagnostic models based on variance in crash types across different edge devices (104). Said learning processor (108) continuously monitors the crash data received from the plurality of edge devices (104) and analyzes the diversity of crash occurrences. Variations in crash types may arise due to differences in application versions, hardware configurations, or environmental factors affecting each edge device (104). The learning processor (108) identifies these variations and adjusts the diagnostic models accordingly, ensuring that the models remain relevant and effective across a wide range of device types and operating conditions. By accounting for the variance in crash data, the learning processor (108) enables the adaptive learning system (100) to maintain accurate and up-to-date diagnostic capabilities, even as the network of edge devices (104) evolves and expands. The updated diagnostic models are subsequently communicated to the distribution engine (110) for deployment across the network.
The disclosed electronic apparatus for crash data analysis and reporting is an adaptive learning system (100) tailored for edge computing environments, enabling real-time optimization of application performance across distributed edge devices. The system features a data acquisition module (102) that collects detailed application version data from a plurality of edge devices (104), which may vary in terms of software configurations and operational environments. This data is fed into a crash detection unit (106) that systematically analyzes crash types, domains, and other critical factors that influence system stability across the edge devices. By identifying patterns in crashes, the crash detection unit (106) helps in isolating issues specific to particular application versions or operational domains. The learning processor (108) plays a crucial role in processing crash frequency data and application version correlations, generating comprehensive diagnostic models that pinpoint the root causes of frequent crashes. These models are dynamic and evolve based on real-time data from the edge network. Once updated diagnostic models are generated, they are distributed back to the edge devices through a distribution engine (110), which ensures that the devices are equipped with the latest predictive models to mitigate crashes proactively. This closed-loop system enables continuous learning and adaptation, improving the reliability and efficiency of edge applications. By focusing on version-specific and domain-specific crash data, the apparatus ensures precise identification of vulnerabilities, offering targeted solutions that enhance overall system performance. This system is particularly suited for distributed environments, such as IoT networks, where maintaining consistent application uptime across diverse edge devices is essential.
FIG. 2 illustrates sequential diagram of an adaptive learning system (100) for edge computing, in accordance with the embodiments of the present disclosure. The sequential diagram illustrates the interaction between various components of an adaptive learning system (100) for edge computing. Edge devices (104) initially send application version data to the data acquisition module (102), which forwards the version data to the crash detection unit (106). Simultaneously, the edge devices (104) also send crash information, including crash types and domains, to the crash detection unit (106). The crash detection unit (106) analyzes the crash data and forwards the relevant information to the learning processor (108). The learning processor (108) processes this data to generate diagnostic insights, including frequency and causes of crashes. Once the diagnostic data is generated, the learning processor (108) sends updated diagnostic models to the distribution engine (110). Finally, the distribution engine (110) transmits these updated diagnostic models back to the edge devices (104), ensuring the entire system is informed of the latest diagnostic developments, helping mitigate and prevent future crashes or issues on the edge devices.
In an embodiment, the data acquisition module (102) of the adaptive learning system (100) collects application version data from a plurality of edge devices (104). The data acquisition module (102) interacts with each edge device (104) to retrieve information on the specific version of the software application running on the device. Such collected data helps establish a detailed understanding of the version distribution across the edge devices (104), allowing for identification of inconsistencies, outdated versions, or misconfigurations. Additionally, the continuous communication between the data acquisition module (102) and edge devices (104) helps track when updates occur, providing a historical record of version changes over time. The availability of such granular data on application versions allows subsequent system components to correlate this information with system performance and crash occurrences. As a result, the overall system is able to identify version-related patterns, such as whether specific versions are associated with increased crash frequencies or performance issues.
In an embodiment, the data acquisition module (102) of the adaptive learning system (100) is further configured to continuously collect application performance data in addition to version data from the plurality of edge devices (104). By collecting performance data, the data acquisition module (102) enables the system to monitor metrics such as response time, memory usage, CPU load, and error rates. This continuous data stream helps in identifying performance degradation that could indicate potential issues or areas needing improvement. Furthermore, by combining performance data with application version data, the system can pinpoint specific versions of an application that may contribute to poor performance. Collecting this data in real-time or near real-time enables the adaptive learning system (100) to respond dynamically to performance changes, providing subsequent system components with a comprehensive dataset that integrates both application behavior and versioning information. This holistic view of system operations improves diagnostic accuracy and allows for more informed system adjustments.
In an embodiment, the crash detection unit (106) of the adaptive learning system (100) further categorizes crash types into critical and non-critical based on their impact on device performance. Said categorization enables the system to assess the severity of each crash based on factors such as whether the crash leads to a complete system halt, data corruption, or minor disruptions. Critical crashes may include scenarios where core functions of the edge device (104) are interrupted, leading to a total loss of functionality, while non-critical crashes may involve temporary slowdowns or recoverable application errors. The crash detection unit (106) uses this classification to prioritize the attention given to various types of crashes, focusing on those that cause the most severe performance degradation. This classification process also informs the subsequent generation of diagnostic data, allowing the learning processor (108) to differentiate between types of failures and to adjust the system response based on crash severity.
In an embodiment, the crash detection unit (106) of the adaptive learning system (100) is configured to store historical crash data for comparison against current crash trends. The stored crash data includes details such as the time of occurrence, crash type, affected application version, and impact on system performance. The availability of historical data allows the system to detect recurring issues, trace patterns over time, and analyze trends in crash behavior. By comparing new crash events with past data, the crash detection unit (106) helps identify whether a current crash is an isolated incident or part of a larger pattern affecting multiple devices. Such historical comparisons also allow for identifying newly emerging issues that may not have been present in previous datasets, facilitating quicker responses to emerging system vulnerabilities. The ability to reference historical crash data ensures more informed diagnostics and helps track the long-term health of the edge devices (104).
In an embodiment, the learning processor (108) of the adaptive learning system (100) utilizes machine learning algorithms to predict future crash patterns based on diagnostic data collected from the crash detection unit (106). By analyzing crash frequency, types, application versions, and device environments, the learning processor (108) identifies correlations between certain variables and crash occurrences. Said learning processor (108) uses machine learning to detect patterns in crash behavior that may not be immediately apparent through simple data analysis. Over time, the learning processor (108) refines its predictive models to estimate the likelihood of future crashes based on current system conditions and trends. The predictive models generated allow the system to take preemptive actions, such as adjusting application configurations or alerting administrators before a crash occurs. This proactive approach helps reduce downtime and improves the overall stability of the system by preventing potential crashes before they occur.
In an embodiment, the distribution engine (110) of the adaptive learning system (100) is configured to send real-time alerts to edge devices (104) when a new diagnostic model is available. The real-time alerts are triggered when the learning processor (108) generates an updated diagnostic model based on the latest crash data or performance trends. The distribution engine (110) transmits said alerts to the plurality of edge devices (104), notifying them of the availability of the new diagnostic model. This alert system allows the edge devices (104) to implement the updated model without delays, ensuring that the most current diagnostic capabilities are applied to detect and mitigate potential issues. The real-time nature of these alerts ensures that the edge devices (104) are kept up-to-date with the latest system optimizations, reducing the risk of outdated diagnostics affecting system performance or stability. The alerts may also provide details about the changes in the diagnostic model.
In an embodiment, the distribution engine (110) of the adaptive learning system (100) is further configured to prioritize updates to edge devices (104) based on geographical region and device performance metrics. The prioritization ensures that devices in regions experiencing higher demand or those encountering critical issues receive diagnostic updates sooner than devices with stable performance or lower priority regions. The distribution engine (110) assesses factors such as the current performance state of the edge devices (104), the severity of issues experienced, and geographical demand before deploying updates. This selective approach allows the adaptive learning system (












I/We Claims


1. An adaptive learning system (100) for edge computing, comprising:
a data acquisition module (102) configured to collect application version data from a plurality of edge devices (104);
a crash detection unit (106) disposed in communication with said data acquisition module (102), said crash detection unit (106) configured to analyze crash information including crash types and domains across said plurality of edge devices (104);
a learning processor (108) arranged relative to said crash detection unit (106), said learning processor (108) configured to generate diagnostic data based on crash frequency and application versions from said crash detection unit (106); and
a distribution engine (110) interconnected with said learning processor (108), said distribution engine (110) being configured to transmit updated diagnostic models to said plurality of edge devices (104) within said adaptive learning system (100).
2. The adaptive learning system (100) of claim 1, wherein said data acquisition module (102) is configured to continuously collect application performance data in addition to version data from said plurality of edge devices (104).
3. The adaptive learning system (100) of claim 1, wherein said crash detection unit (106) further categorizes crash types into critical and non-critical based on impact on device performance.
4. The adaptive learning system (100) of claim 1, wherein said crash detection unit (106) is configured to store historical crash data for comparison against current crash trends.
5. The adaptive learning system (100) of claim 1, wherein said learning processor (108) utilizes machine learning algorithms to predict future crash patterns based on said diagnostic data.
6. The adaptive learning system (100) of claim 1, wherein said distribution engine (110) is configured to send real-time alerts to edge devices (104) when a new diagnostic model is available.
7. The adaptive learning system (100) of claim 1, wherein said distribution engine (110) is further configured to prioritize updates to edge devices (104) based on geographical region and device performance metrics.
8. The adaptive learning system (100) of claim 1, wherein said data acquisition module (102) is configured to capture additional environmental data, including network conditions and device hardware specifications.
9. The adaptive learning system (100) of claim 1, wherein said crash detection unit (106) is configured to evaluate crash severity based on the application domain and user impact on the edge device (104).
10. The adaptive learning system (100) of claim 1, wherein said learning processor (108) is further configured to update the diagnostic models based on variance in crash types across different edge devices (104).




The present disclosure relates to adaptive learning systems for edge computing. Particularly, the present disclosure relates to an electronic apparatus designed for analyzing and reporting crash data based on application version and domain information to optimize edge device performance.
, Claims:I/We Claims


1. An adaptive learning system (100) for edge computing, comprising:
a data acquisition module (102) configured to collect application version data from a plurality of edge devices (104);
a crash detection unit (106) disposed in communication with said data acquisition module (102), said crash detection unit (106) configured to analyze crash information including crash types and domains across said plurality of edge devices (104);
a learning processor (108) arranged relative to said crash detection unit (106), said learning processor (108) configured to generate diagnostic data based on crash frequency and application versions from said crash detection unit (106); and
a distribution engine (110) interconnected with said learning processor (108), said distribution engine (110) being configured to transmit updated diagnostic models to said plurality of edge devices (104) within said adaptive learning system (100).
2. The adaptive learning system (100) of claim 1, wherein said data acquisition module (102) is configured to continuously collect application performance data in addition to version data from said plurality of edge devices (104).
3. The adaptive learning system (100) of claim 1, wherein said crash detection unit (106) further categorizes crash types into critical and non-critical based on impact on device performance.
4. The adaptive learning system (100) of claim 1, wherein said crash detection unit (106) is configured to store historical crash data for comparison against current crash trends.
5. The adaptive learning system (100) of claim 1, wherein said learning processor (108) utilizes machine learning algorithms to predict future crash patterns based on said diagnostic data.
6. The adaptive learning system (100) of claim 1, wherein said distribution engine (110) is configured to send real-time alerts to edge devices (104) when a new diagnostic model is available.
7. The adaptive learning system (100) of claim 1, wherein said distribution engine (110) is further configured to prioritize updates to edge devices (104) based on geographical region and device performance metrics.
8. The adaptive learning system (100) of claim 1, wherein said data acquisition module (102) is configured to capture additional environmental data, including network conditions and device hardware specifications.
9. The adaptive learning system (100) of claim 1, wherein said crash detection unit (106) is configured to evaluate crash severity based on the application domain and user impact on the edge device (104).
10. The adaptive learning system (100) of claim 1, wherein said learning processor (108) is further configured to update the diagnostic models based on variance in crash types across different edge devices (104).

Documents