Methods, systems, devices and media for enhancing the stability of IoT message processing

Abstract

This invention discloses a method, system, device, and medium for enhancing the stability of IoT message processing. The method includes: a data source sending data to a monitoring module; the monitoring module identifying and filtering the data; sending abnormal data to a compensation module for processing; sending abnormal data to an alarm module for policy-based alarms; sending normally flowing data directly to a business module for processing; if the business system encounters errors during processing, transferring these error data and related anomaly information to a data mining module; and distributing this data to various specialized mining sub-modules based on data characteristics and error types. This invention introduces advanced data mining algorithms such as TF-IDF to mine error keywords from error data and generate rules that can predict future errors. This targeted data mining method offers higher accuracy and intelligence compared to traditional statistical analysis or simple rule matching.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) information processing technology, and specifically to a method, system, device, and storage medium for enhancing the stability of IoT message processing. Background Technology

[0002] In complex scenarios where numerous terminals are connected to an Internet of Things (IoT) platform, the stability of data reporting and transmission faces multiple challenges. IoT platforms need to connect to various types of terminal devices, which vary significantly in performance. Some devices may possess powerful processing capabilities and stable communication modules, enabling efficient data processing and transmission; while others may be limited by factors such as cost and power consumption, resulting in relatively weaker performance and susceptibility to data processing delays and communication interruptions. In practical applications, network environments are often unstable and susceptible to various factors, such as signal interference, network congestion, and device movement. These factors can all lead to errors, failures, or malfunctions during data transmission, thereby affecting the overall performance of the IoT system.

[0003] Definitions:

[0004] Dead letter storage: When encountering data that cannot be processed, it is usually sent to the dead letter module for storage and recording, which facilitates subsequent troubleshooting.

[0005] TF-IDF: A statistical method used to assess the importance of a word to a document in a set of documents or a corpus. Summary of the Invention

[0006] The present invention proposes a method, system, device, and storage medium for enhancing the stability of IoT message processing, which can at least solve one of the technical problems in the background art.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] A method for enhancing the stability of IoT message processing includes the following steps:

[0009] The data source sends data to the monitoring module, which then identifies and filters the data.

[0010] Abnormal data is sent to the compensation module for processing.

[0011] Abnormal data will also be sent to the alarm module for policy-based alarms;

[0012] For data that is in normal flow, it is sent directly to the business module for processing.

[0013] If the business system encounters errors during processing, it will transfer these error data and related exception information to the data mining module.

[0014] The data mining module intelligently distributes these data to various specialized mining sub-modules based on data characteristics and error types.

[0015] The prediction rules generated by the data mining module, the penalty mechanism for devices, and the data put into the dead-letter storage module can be manually reviewed in the audit module to prevent misjudgments. If a misjudgment occurs, the rules and data can be adjusted in the audit module.

[0016] Furthermore, the alarm module analyzes and evaluates anomalies, and sends alarm notifications to relevant personnel based on preset thresholds or business rules combined with alarm policies.

[0017] Furthermore, the data source sends the data to the monitoring module, which then identifies and filters the data according to the following steps:

[0018] The monitoring module sets data failure rules. These rules read the message reporting time, compare it with the current time, and mark messages that exceed a preset time threshold as invalid.

[0019] The monitoring module is configured with a data missing rule. This rule will count the messages reported by each terminal and mark any messages that are not reported on time as missing.

[0020] The monitoring module sets error keywords, data sources, and data target prediction rules, and uses the rules provided by the data mining module to predict, identify, and filter the data.

[0021] Furthermore, the abnormal data is sent to the compensation module for processing, specifically including:

[0022] Based on the terminal identification information in the abnormal data, instructions are issued to the terminal to re-report missing, erroneous, or invalid data, thereby achieving proactive real-time data compensation.

[0023] Error and expired data are transferred to the dead letter storage module for archiving;

[0024] Data that fails to be processed by the business system is sent to the delay retry penalty module to penalize devices that fail to send data multiple times.

[0025] Furthermore, data that fails to be processed by the business system is sent to the delay retry penalty module to penalize devices that fail to send data multiple times. Specifically, this includes...

[0026] Failed messages are recorded in an error queue, and the dispatcher counts the number of failures for each message. Based on the number of failures, different lifespans are assigned to messages, with higher lifespans indicating more failures.

[0027] The dispatcher distributes these messages into queues with different delay levels according to their lifespans. The higher the lifespan, the longer the delay. Device messages that fail multiple times are penalized.

[0028] The delay program is responsible for listening to messages in these queues. For messages that have reached the delay requirement, they are sent to the retry queue for retry. If the retry still fails, the message is put back into the error queue.

[0029] Furthermore, the data mining module intelligently distributes this data to various specialized mining sub-modules based on data characteristics and error types, specifically including:

[0030] a) The error keyword data mining module uses the TF-IDF keyword mining algorithm to clean and segment the collected error and normal data, calculates the TF-IDF value of each word, and selects the top-ranking words as error keywords; it generates prediction rules for the data message, such as the following rule: when the keyword "null" appears in the data text, it is judged as abnormal data;

[0031] b) Data source mining module: collects error data and mines data source information, classifies data sources according to anomaly information, uses K-means clustering algorithm to cluster the frequency of anomaly data in data sources, divides data sources into high-quality data sources, low-quality data sources, and anomaly data sources, and generates prediction rules for the corresponding data sources.

[0032] c) Data target mining module: collects data targets and times that are prone to errors when issuing instructions, uses the Apriori algorithm to mine association rules on the collected data, and the algorithm will output a series of association rules to identify the error patterns of each device and generate error time rules that use the fitted ARIMA model to predict the error time in the future.

[0033] On the other hand, the present invention also discloses a system for enhancing the stability of IoT message processing, which is used to implement the above-mentioned method for enhancing the stability of IoT message processing, including a monitoring module, an error keyword data mining module, a data compensation module, an auditing module, and an alarm module;

[0034] The data source sends data to the monitoring module, which filters the data according to rules; normal data is sent to the business processing module, and abnormal data is sent to the compensation module.

[0035] The business system sends failed data during processing to the data compensation module, and error data and exception information to the data mining module;

[0036] The data compensation module performs proactive real-time compensation based on the cause of the anomaly;

[0037] Abnormal data is sent to the alarm module, and alarm notifications are sent to relevant personnel in accordance with the alarm policy.

[0038] The data mining module analyzes the data to generate prediction and identification rules;

[0039] The audit module manually reviews the prediction rules generated by the data mining module, the penalty mechanism for devices, and the data stored in the dead-letter storage module.

[0040] Furthermore, the system also includes a delay retry penalty module, which sends data that fails to be processed by the business system to the delay retry penalty module to penalize devices that fail to send data multiple times.

[0041] In another aspect, the present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method described above.

[0042] In another aspect, the present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method described above.

[0043] As can be seen from the above technical solution, the method for enhancing the stability of IoT message processing of the present invention has the following beneficial effects:

[0044] There is a lack of an automatic troubleshooting, compensation, and penalty mechanism to address processing failures caused by the uncertainties of the Internet of Things (IoT) in order to improve the stability and processing efficiency of message processing systems.

[0045] Business systems typically have retry mechanisms when handling errors. However, this invention provides a general and comprehensive dynamic adjustment strategy (such as a penalty mechanism) based on the number of device failures.

[0046] In IoT message processing systems, data mining techniques are rarely used to develop systems specifically designed to extract and generate predictive rules from erroneous data.

[0047] Active real-time data compensation based on terminal identifier.

[0048] Deep data mining and intelligent prediction enable preventative measures to reduce erroneous data generation and improve data processing efficiency and accuracy.

[0049] The integrated data filtering and real-time compensation mechanism ensures the integrity and timeliness of the data, avoiding business interruptions or decision-making errors caused by data errors or missing data.

[0050] Flexible penalty mechanisms and dynamic retry strategies improve the reliability and stability of data transmission.

[0051] The intelligent strategy of this method is auditable.

[0052] The entire system operates without intruding on business systems.

[0053] Specifically, compared with the prior art, the main inventiveness of this invention lies in:

[0054] This invention introduces advanced data mining algorithms such as TF-IDF, specifically designed to extract erroneous keywords from erroneous data and generate rules that can predict future errors. This targeted data mining method offers higher accuracy and intelligence compared to traditional statistical analysis or simple rule matching.

[0055] This invention introduces a penalty mechanism based on the number of device failures and retry queues with different latency levels into the business system. This mechanism dynamically adjusts the retry strategy according to the device's performance.

[0056] This invention closely integrates anomaly detection, prediction, data filtering, and real-time compensation mechanisms, forming a closed-loop data processing flow with the original IoT data processing module.

[0057] Auditing can correct misjudgments. Attached Figure Description

[0058] Figure 1 This is a system block diagram of the present invention;

[0059] Figure 2 This is a schematic diagram of the delay retry penalty module of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 some embodiments of the present invention, but not all embodiments.

[0061] Due to performance differences among terminals and environmental instability, data transmission may encounter errors, failures, and invalidations, posing challenges to system stability and processing efficiency. To effectively address these issues and improve system performance, this invention proposes a system for enhancing the stability of IoT message processing, as follows:

[0062] The embodiments of the present invention can be used in various Internet of Things (IoT) data transmission systems, such as smart meter systems, smart lighting systems, and smart sensor lighting systems.

[0063] like Figure 1 As shown, this system includes a monitoring module, an error keyword data mining module, a data compensation module, an auditing module, a delay retry penalty module, and an alarm module.

[0064] The data source sends data to the monitoring module, which then filters the data according to rules. Normal data is sent to the business processing module, while abnormal data is sent to the compensation module.

[0065] The business system sends failed data during processing to the data compensation module, and error data and exception information to the data mining module.

[0066] The compensation module performs proactive real-time compensation based on the cause of the anomaly.

[0067] Abnormal data is sent to the alarm module, and alarm notifications are sent to relevant personnel in accordance with the alarm policy.

[0068] The data mining module analyzes the data to generate prediction and identification rules.

[0069] The audit module manually reviews the prediction rules generated by the data mining module, the penalty mechanism for devices, and the data stored in the dead-letter storage module.

[0070] Accordingly, the steps of the method for enhancing the stability of IoT message processing disclosed in this embodiment of the invention are as follows:

[0071] 1) The data source sends the data to the monitoring module, which then identifies and filters the data according to the following steps.

[0072] The monitoring module allows you to set data invalidation rules. These rules read the message reporting time, compare it with the current time, and mark messages that exceed a preset time threshold as invalid.

[0073] The monitoring module allows you to set rules for missing data. These rules will track the messages reported by each terminal, and any messages that are not reported on time will be marked as missing.

[0074] The monitoring module allows you to set error keywords, data sources, and data target prediction rules. It then uses rules provided by the data mining module to predict, identify, and filter data.

[0075] 2) These abnormal data will be sent to the compensation module for processing.

[0076] a) Based on the terminal identification information in the abnormal data, instructions are issued to make the terminal re-report missing, erroneous, or invalid data, thereby achieving proactive real-time data compensation.

[0077] b) Transfer erroneous and expired data to the dead letter storage module for archiving.

[0078] c) Send failed data from the business system to the delay retry penalty module to penalize devices that fail to send data multiple times. For example... Figure 2 As shown, the steps are as follows:

[0079] 1. Failed messages are recorded in an error queue, and the dispatcher counts the number of failures for each message. Based on the number of failures, a different lifespan is assigned to each message (initially 1, up to a maximum of 5), with a higher lifespan indicating more failures.

[0080] 2. The dispatcher distributes these messages into queues with different delay levels based on their lifetime values; the higher the lifetime value, the longer the delay. For example, messages with a lifetime value of 1 are sent to a queue with a delay of 3 seconds, while messages with a lifetime value of 3 are sent to a queue with a delay of 5 minutes. Multiple failed device messages are penalized.

[0081] 3. The delay program is responsible for listening to messages in these queues. Messages that have reached the delay requirement are sent to the retry queue for retry. If the retry still fails, the message is put back into the error queue.

[0082] 3) Abnormal data will also be sent to the alarm module for policy-based alarms. The alarm module will analyze and evaluate the anomalies, and send alarm notifications to relevant personnel based on preset thresholds or business rules and alarm policies.

[0083] 4) For data in normal flow, it is directly sent to the business module for processing. If the business system encounters errors during processing, it will transfer these erroneous data and related exception information to the data mining module. This module intelligently distributes this data to various specialized mining sub-modules based on data characteristics and error types, for the following processing.

[0084] a) The error keyword data mining module uses the TF-IDF keyword mining algorithm to clean and segment the collected error and normal data, calculates the TF-IDF value of each word, and selects the top-ranking words as error keywords. It generates prediction rules for the data messages, such as the rule: when the keyword "null" appears in the data text, it is judged as abnormal data.

[0085] b) The data source mining module collects erroneous data and mines information from the data sources. Based on the anomaly information, the data sources are categorized, and the K-means clustering algorithm is used to cluster the frequency of anomaly data, classifying the data sources into high-quality data sources, low-quality data sources, and anomaly data sources. Prediction rules are then generated for the corresponding data sources. For example, data source number 1 is marked as an anomaly data source, and its data is likely to be abnormal; therefore, its data is sent to a low-priority thread for identification.

[0086] c) The data target mining module collects error-prone data targets and times when issuing commands. It uses the Apriori algorithm to mine association rules from the collected data, outputting a series of association rules, such as "The confidence level of 'Device A malfunctions between 3 PM and 4 PM, and Device B also malfunctions during this time period is 80%'." This identifies the error patterns of each device, such as periodic errors and trending errors. It then generates rules to predict error times in the future using a fitted ARIMA model. For example, if data target A is predicted to malfunction at 3 PM, the data will be sent to a low-priority thread.

[0087] 5) The prediction rules generated by the data mining module, the penalty mechanism for devices, and the data stored in the dead-letter storage module can be manually reviewed in the audit module to prevent misjudgments. If a misjudgment occurs, the rules and data can be adjusted in the audit module.

[0088] The following example uses the IoT data transmission system of a smart meter; under normal circumstances, a smart meter reports its energy consumption data every hour.

[0089] 1) Some electricity meters are installed in meter boxes in corners where network signals are poor. Data reported at the top of the hour may fail to reach the IoT system, resulting in missing data when calculating meter readings. This invention addresses this issue using the following method.

[0090] a) The monitoring system will collect data on the reporting status according to the preset data missing business rules. For example, the rule can be configured as follows: if no data is reported within 20 minutes, it will be marked as data missing.

[0091] (b) The monitoring system will send the meter terminal number and its corresponding time information for any meters that fail to report data on time to the data compensation module. This module will then issue instructions to prompt the relevant devices to proactively report their status information in order to complete the missing data.

[0092] 2) Due to network congestion, the data originally scheduled to be reported by the device at midnight was delayed by half an hour before being successfully reported. For the business system, since the device's information had far exceeded the predetermined reception time limit, it was considered invalid. This patent uses the following method to process this data.

[0093] a) The data source mining module will classify and mine data sources based on the timeout data sources and normal data sources provided by the business system, and categorize these data sources into low-quality data sources, high-quality data sources, etc.

[0094] b) The monitoring system will predict the data based on the data source classification rules provided by the data source mining module. If it is a low-quality data source, it is very likely that the reported data will be timed out, and then sent to a high-priority thread for judgment and processing.

[0095] c) After setting timeout rules in the monitoring system, the system compares the data reception time with the device reporting time. For data exceeding the preset threshold, the monitoring system will not send it directly to the business system, but will forward it to the data compensation module. The data compensation module will issue instructions to complete these expired data. At the same time, this timed-out data will also be sent to the dead-letter storage module for future viewing and analysis.

[0096] 3) Occasionally, due to differences in version and model, data format errors occur when electricity meters report data. Specifically, instead of transmitting integer data, some meters incorrectly transmit floating-point data, causing the business system to be unable to perform the correct data format conversion during processing. This patent uses the following method to address this issue.

[0097] a) The error keyword module uses TF-IDF to deeply compare the differences between normal and abnormal data and identify the characteristics of data containing floating-point types as error data sources. After manual auditing and confirmation of the rule, it is sent to the monitoring platform for entry and application.

[0098] b) The monitoring system predicts data based on the provided error keyword rules. If floating-point data appears, it is considered erroneous, and the message is filtered out. Simultaneously, it is sent to the data compensation module to allow the device to re-report the data.

[0099] 4) The IoT platform sends some instructions to the electricity meter. Due to network environment and other issues, the sending may fail. Continuously retrying the sending at regular intervals puts too much pressure on the platform. This patent uses the following method to handle this.

[0100] a) If sending data to the electricity meter frequently fails at 1 PM, the data will be sent to the data target mining module to collect the identifiers of error-prone meter devices and their sending times. This module will then mine error-prone data target rules, so that the next time data is sent to the meter at this time, a low-priority thread will be used, reducing system load.

[0101] b) Simultaneously, the message indicating a failed power generation is sent to the error queue. The dispatcher counts the number of failures for this message and assigns a lifespan of 1. The dispatcher then sends this message to a queue with a 3-second delay. After a 3-second delay, the delayer sends this message to the retry queue for a retry.

[0102] c) If data delivery still fails, the system will re-place the message in the error queue, assign it a lifespan of 2 by the dispatcher, and send it to a queue with a 1-minute delay. After the message is blocked for 1 minute, the system will send it back to the retry queue to attempt to resend it.

[0103] d) If the data is successfully sent, the processing flow ends; if it fails, continue with the above steps, sending the message to a queue with a higher latency level for blocking retry. This process aims to implement "punishing" delay processing for messages that fail to be sent multiple times, thereby reducing system load and optimizing system pressure.

[0104] 5) Rules for floating-point data keywords mined by the error keyword mining module, rules for low-quality data sources mined by the data source mining module, rules for error-prone data targets mined by the data target mining module, penalty mechanisms for failed meter delivery, and data deemed dead letters can all be manually reviewed in the audit module to prevent misjudgments. If a misjudgment occurs, the rules and data can be adjusted in the audit module.

[0105] In summary, the embodiments of this invention lack an automatic error correction, compensation, and penalty mechanism for processing failures caused by the uncertainties of the Internet of Things (IoT) to improve the stability and processing efficiency of the message processing system. Business systems typically have retry mechanisms when processing errors. However, the embodiments of this invention provide a general and comprehensive dynamic adjustment strategy (such as a penalty mechanism) based on the number of device failures. In IoT message processing systems, systems specifically designed to mine and generate predictive rules from error data are rare. Active real-time data compensation based on terminal identifiers is also addressed.

[0106] In another aspect, the present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method described above.

[0107] In another aspect, the present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method described above.

[0108] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform any of the methods for enhancing the stability of IoT message processing described above.

[0109] It is understood that the systems, devices, and storage media provided in the embodiments of the present invention correspond to the methods provided in the embodiments of the present invention, and the explanations, examples, and beneficial effects of the relevant content can be referred to the corresponding parts of the above methods.

[0110] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0111] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0112] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0113] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for enhancing the stability of message processing in the Internet of Things, characterized in that, Includes the following steps, The data source sends data to the monitoring module, which then identifies and filters the data. Abnormal data is sent to the compensation module for processing. Abnormal data will also be sent to the alarm module for policy-based alarms; For data that is in normal flow, it is sent directly to the business module for processing. If the business system encounters errors during processing, it will transfer these error data and related exception information to the data mining module. The data mining module intelligently distributes these data to various specialized mining sub-modules based on data characteristics and error types. The prediction rules generated by the data mining module, the penalty mechanism for the device, and the data put into the dead letter storage module are manually reviewed in the audit module to prevent misjudgment. If a misjudgment is found, the rules and data are adjusted in the audit module. The step of sending abnormal data to the compensation module for processing specifically includes, Based on the terminal identification information in the abnormal data, instructions are issued to the terminal to re-report missing, erroneous, or invalid data, thereby achieving proactive real-time data compensation. Error and expired data are transferred to the dead letter storage module for archiving; Data that fails to be processed by the business system is sent to the delay retry penalty module to penalize devices that fail to send data multiple times; specifically... include, Failed messages are recorded in an error queue, and the dispatcher counts the number of failures for each message. Different lifespans are assigned to messages based on the number of failures; the higher the lifespan, the more failures there are. The dispatcher distributes these messages into queues of different delay levels according to their lifespans. The higher the lifespan, the longer the delay. Device messages that fail multiple times are penalized. The delay program is responsible for listening to messages in these queues. For messages that have reached the delay requirement, they are sent to the retry queue for retry. If the retry still fails, the message is put back into the error queue.

2. The method for enhancing the stability of IoT message processing according to claim 1, characterized in that: It also includes an alarm module that analyzes and evaluates anomalies and sends alarm notifications to relevant personnel based on preset thresholds or business rules and alarm policies.

3. The method for enhancing the stability of IoT message processing according to claim 1, characterized in that: The data source sends data to the monitoring module, which then identifies and filters the data according to the following steps: The monitoring module sets data failure rules. These rules read the message reporting time, compare it with the current time, and mark messages that exceed a preset time threshold as invalid. The monitoring module is configured with a data missing rule. This rule will count the messages reported by each terminal and mark any messages that are not reported on time as missing. The monitoring module sets error keywords, data sources, and data target prediction rules, and uses the rules provided by the data mining module to predict, identify, and filter the data.

4. The method for enhancing the stability of IoT message processing according to claim 1, characterized in that: The data mining module intelligently distributes this data to various specialized mining sub-modules based on data characteristics and error types, specifically including: a) Error Keyword Data Mining Module: The collected error data and normal data are processed using the TF-IDF keyword mining algorithm. After cleaning and segmenting the data, the TF-IDF value of each word is calculated, and the top-ranking words are selected as error keywords. Generate prediction rules for data packets; b) Data source mining module: collects error data and mines data source information, classifies data sources according to anomaly information, uses K-means clustering algorithm to cluster the frequency of anomaly data in data sources, divides data sources into high-quality data sources, low-quality data sources, and anomaly data sources, and generates prediction rules for the corresponding data sources. c) Data target mining module: collects data targets and times that are prone to errors when issuing instructions, uses the Apriori algorithm to mine association rules on the collected data, and the algorithm will output a series of association rules to identify the error patterns of each device and generate error time rules that use the fitted ARIMA model to predict the error time in the future.

5. A system for enhancing the stability of IoT message processing, used to implement the method for enhancing the stability of IoT message processing as described in any one of claims 1-4, characterized in that: This includes a monitoring module, an error keyword data mining module, a data compensation module, an auditing module, and an alarm module; The data source sends data to the monitoring module, which filters the data according to rules; normal data is sent to the business processing module, and abnormal data is sent to the compensation module. The business system sends failed data during processing to the data compensation module, and error data and exception information to the data mining module; The data compensation module performs proactive real-time compensation based on the cause of the anomaly; Abnormal data is sent to the alarm module, and alarm notifications are sent to relevant personnel in accordance with the alarm policy. The data mining module analyzes the data to generate prediction and identification rules; The audit module manually reviews the prediction rules generated by the data mining module, the penalty mechanism for devices, and the data stored in the dead-letter storage module.

6. The system for enhancing the stability of IoT message processing according to claim 5, characterized in that: It also includes a delay retry penalty module, which sends data that fails to be processed by the business system to the delay retry penalty module to penalize devices that fail to send data multiple times.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 4.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the computer program is executed by the processor, it causes the processor to perform the steps of the method as described in any one of claims 1 to 4.

Images