Edge gateway notification method and device

Abstract

The invention relates to the technical field of communication, and particularly provides an edge gateway notification method and device, and the method comprises the following steps: S1, data collection and preprocessing; s2, training and optimizing a large model; s3, performing real-time data analysis and prediction; s4, generating an intelligent notification strategy; s5, data transmission and notification; and S6, feeding back and optimizing a mechanism. Compared with the prior art, the method has the advantages that a notification mechanism of the edge gateway can be optimized through a large model technology, and more efficient and accurate data transmission and notification services are realized, so that high requirements on real-time performance, safety and reliability in an internet of things environment are met.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and specifically provides an edge gateway notification method and device. Background Art

[0002] With the rapid development of IoT technology, edge computing has become an important bridge connecting the cloud and terminal devices. The edge gateway is the core component of edge computing, responsible for data collection, processing, forwarding and notification. However, traditional edge gateway notification methods are usually based on fixed rules and thresholds, which are difficult to meet the changing and complex application requirements in the IoT environment.

[0003] This year, big model technology has made significant progress in the field of artificial intelligence. Its powerful data processing and prediction capabilities provide new ideas for optimizing edge gateway notification methods. Through big model technology, historical data, real-time data, and device status information can be deeply learned and analyzed to predict data transmission needs and trends, so as to adjust notification strategies in advance and achieve more efficient and accurate data transmission and notification services.

[0004] How to optimize the notification mechanism of the edge gateway through big model technology to achieve more efficient and accurate data transmission and notification services to meet the high requirements of real-time, security and reliability in the Internet of Things environment is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] The present invention aims at the above-mentioned deficiencies of the prior art and provides a highly practical edge gateway notification method.

[0006] A further technical task of the present invention is to provide an edge gateway notification device that is reasonably designed, safe and applicable.

[0007] The technical solution adopted by the present invention to solve its technical problem is:

[0008] An edge gateway notification method comprises the following steps:

[0009] S1, data collection and preprocessing;

[0010] S2, large model training and optimization;

[0011] S3, real-time data analysis and prediction;

[0012] S4, intelligent notification strategy generation;

[0013] S5. Data transmission and notification;

[0014] S6. Feedback and optimization mechanism.

[0015] Furthermore, in step S1, the edge gateway collects real-time data, historical data, and device status information from the connected terminal devices, and performs data cleaning, format conversion, and compression to remove redundant, irrelevant, or erroneous data. At the same time, the collected data is labeled and classified, and the processed data is used as the original data for large model training.

[0016] Furthermore, in step S2, the preprocessed data is used to train the large model so that the large model can accurately predict the demand and trend of data transmission, and the large model is tuned according to the actual application scenario. The trained model is tested using the validation set to check whether various performance indicators are within an acceptable range, and multiple simulation verifications are performed to improve the accuracy.

[0017] Further, in step S3, the edge gateway inputs the real-time data into the trained big model, and the trained big model uses the real-time data processing framework to perform real-time analysis and prediction on the real-time data stream, and the big model displays the analysis results of the real-time data in a chart;

[0018] At the same time, it predicts the demand and trend of data transmission and generates corresponding prediction results, which are used to inform the generation of strategies.

[0019] Furthermore, in step S4, based on the prediction result of the large model, it is determined that an intelligent push is sent to the target, and the notification strategy is intelligently generated and adjusted to customize the personalized notification content;

[0020] Choose the appropriate time to send notifications based on device status, and dynamically configure the frequency, method, and content of notifications based on actual needs and feedback to meet the needs of different application scenarios.

[0021] Further, in step S5, according to the generated notification strategy, the edge gateway transmits the data to the cloud or other terminal devices. During the data transmission process, a security protection mechanism is adopted. When the data transmission is completed, the edge gateway sends a notification to the administrator or related devices according to the notification strategy, and selects the appropriate notification channel according to the recipient's preferences and actual conditions.

[0022] Further, in step S6, after receiving the notification, the notification strategy is fed back according to the actual situation, the edge gateway collects and analyzes the feedback data, adjusts the preference of the big model to generate the notification strategy, or uploads similar data through the edge gateway to fine-tune the big model, further optimizes the prediction ability and notification strategy of the big model, and directly adjusts the notification strategy according to the demand;

[0023] Filter edge gateway data, adjust notification policies, or retrain large models to adapt to device data based on notification content. Perform continuous pruning and quantization operations on large models based on actual application scenarios and performance requirements.

[0024] Regularly pay attention to research progress and technological updates in the field of large models, and promptly apply new research results and technical means to the system.

[0025] An edge gateway notification device comprises: at least one memory and at least one processor;

[0026] The at least one memory is used to store a machine-readable program;

[0027] The at least one processor is used to call the machine-readable program to execute an edge gateway notification method.

[0028] Compared with the prior art, the edge gateway notification method and device of the present invention have the following outstanding beneficial effects:

[0029] (1) Significantly improve the real-time performance of data transmission. Through real-time analysis and prediction of real-time data by a large model, the present invention can predict the demand and trend of data transmission in advance and intelligently adjust the notification strategy. This prediction and adjustment mechanism can significantly reduce the delay of data transmission, improve the real-time performance of data transmission, and meet the high real-time requirements of IoT applications.

[0030] (2) Enhance the security of data transmission. Advanced security protection mechanisms, such as data encryption, access control, and intrusion detection, are used during data transmission to ensure the security and privacy of data during transmission. At the same time, the application of large model technology can timely detect potential security risks and abnormal behaviors, provide administrators with timely warnings and processing suggestions, and further enhance the security of data transmission.

[0031] (3) Improve reliability and stability. Through real-time data analysis and prediction, the present invention can timely discover potential safety hazards and failure risks, and provide administrators with timely warnings and processing suggestions. This warning and processing mechanism can reduce the system failure rate and improve the reliability and stability of the system. At the same time, the application of large model technology can also optimize notification strategies, reduce unnecessary notifications and interference, and further improve the stability of the system and user experience.

[0032] (4) Flexible configuration and scalability: It supports flexible notification policy configuration. Administrators can adjust the notification frequency, method, content and other parameters according to actual needs to meet the needs of different application scenarios. At the same time, the system also has good scalability and can easily integrate new functions and devices to meet changing business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Attached Figure 1 The invention is a flowchart of an edge gateway notification method. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] A best embodiment is given below:

[0037] like Figure 1 As shown, an edge gateway notification method in this embodiment has the following steps:

[0038] S1, data collection and preprocessing;

[0039] The edge gateway collects real-time data, historical data, device status and other information from the connected terminal devices, and performs pre-processing operations such as data cleaning, format conversion and compression to remove redundant, irrelevant or erroneous data to reduce the amount of data and noise, ensure the accuracy and consistency of the data, and mark and classify the collected data to facilitate subsequent data analysis and mining. This part of the data will be used as the original data for large model training.

[0040] S2, large model training and optimization;

[0041] Use preprocessed data to train the big model so that it can accurately predict the demand and trend of data transmission. At the same time, tune the big model according to the actual application scenario to improve the prediction accuracy and generalization ability. Train the big model with multiple batches of data to reduce the sensitivity of the big model to data sample differences, identify and reduce the impact of abnormal data, use the validation set to test the trained model, and check whether various performance indicators are within the acceptable range. Multiple simulations and validations improve the accuracy.

[0042] S3, real-time data analysis and prediction;

[0043] The edge gateway inputs real-time data into the trained big model, which uses the real-time data processing framework to perform real-time analysis and prediction on the real-time data stream. The big model displays the analysis results of the real-time data in charts; it also predicts the demand and trend of data transmission and generates corresponding prediction results. This result is used to inform the generation of strategies.

[0044] S4, intelligent notification strategy generation;

[0045] Based on the prediction results of the big model, it is determined when and where smart notifications need to be sent to which targets, and notification strategies are intelligently generated and adjusted to customize personalized notification content to ensure the accuracy and pertinence of notification information. The appropriate time to send notifications is selected based on factors such as device status to increase the opening rate and response rate of notifications. Based on actual needs and feedback, the frequency, method, content and other parameters of notifications are dynamically configured to meet the needs of different application scenarios.

[0046] S5. Data transmission and notification;

[0047] According to the generated notification strategy, the edge gateway transmits the data to the cloud or other terminal devices. During the data transmission process, advanced security protection mechanisms are used to ensure the security and privacy of the data. When the data transmission is completed, the edge gateway sends a notification to the administrator or related devices according to the notification strategy. According to the preferences and actual situation of the recipient, select the appropriate notification channel. For example, notification information can be sent through SMS, email, APP push, etc.

[0048] S6, feedback and optimization mechanism;

[0049] After receiving the notification, the notification strategy is fed back according to the actual situation. The edge gateway collects and analyzes the feedback data, and can adjust the preference of the large model to generate the notification strategy or upload similar data through the edge gateway to fine-tune the large model, further optimize the prediction ability and notification strategy of the large model, and directly adjust the notification strategy according to the needs, which is more adaptable. At the same time, according to the content of this step notification, the edge gateway data can be filtered, the notification strategy can be adjusted, or the large model can be retrained to adapt to the device data. According to the actual application scenario and performance requirements, the large model is continuously pruned and quantized to further reduce the model size and computational complexity.

[0050] Regularly pay attention to research progress and technological updates in the field of large models, and promptly apply new research results and technical means to the system to improve the system's intelligence level and performance.

[0051] Based on the above method, an edge gateway notification device in this embodiment includes: at least one memory and at least one processor;

[0052] The at least one memory is used to store a machine-readable program;

[0053] The at least one processor is used to call the machine-readable program to execute an edge gateway notification method.

[0054] The above-mentioned specific implementations are only specific cases of the present invention. The patent protection scope of the present invention includes but is not limited to the above-mentioned specific implementations. Any technical solutions that conform to the above-mentioned specific implementations of the present invention and any appropriate changes or substitutions made by ordinary technicians in the relevant technical field shall fall within the patent protection scope of the present invention.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An edge gateway notification method, characterized in that: The steps are as follows: S1, data collection and preprocessing; S2, large model training and optimization; S3, real-time data analysis and prediction; S4, intelligent notification strategy generation; S5. Data transmission and notification; S6. Feedback and optimization mechanism.

2. The edge gateway notification method according to claim 1, characterized in that: In step S1, the edge gateway collects real-time data, historical data, and device status information from the connected terminal devices, and performs data cleaning, format conversion, and compression to remove redundant, irrelevant, or erroneous data. At the same time, the collected data is labeled and classified, and the processed data is used as the original data for large model training.

3. The edge gateway notification method according to claim 2, characterized in that: In step S2, the preprocessed data is used to train the large model so that the large model can accurately predict the demand and trend of data transmission. The large model is tuned according to the actual application scenario, and the trained model is tested using the validation set to check whether various performance indicators are within an acceptable range. Multiple simulations and verifications are performed to improve the accuracy.

4. The edge gateway notification method according to claim 3, characterized in that: In step S3, the edge gateway inputs the real-time data into the trained big model. The trained big model uses the real-time data processing framework to perform real-time analysis and prediction on the real-time data stream. The big model displays the analysis results of the real-time data in a chart. At the same time, it predicts the demand and trend of data transmission and generates corresponding prediction results, which are used to inform the generation of strategies.

5. The edge gateway notification method according to claim 4, characterized in that: In step S4, based on the prediction results of the big model, it is determined that intelligent push notifications are sent to the target, notification strategies are intelligently generated and adjusted, and personalized notification content is customized; Choose the appropriate time to send notifications based on device status, and dynamically configure the frequency, method, and content of notifications based on actual needs and feedback to meet the needs of different application scenarios.

6. The edge gateway notification method according to claim 5, characterized in that: In step S5, according to the generated notification strategy, the edge gateway transmits the data to the cloud or other terminal devices. During the data transmission process, a security protection mechanism is adopted. When the data transmission is completed, the edge gateway sends a notification to the administrator or related devices according to the notification strategy, and selects the appropriate notification channel according to the recipient's preferences and actual situation.

7. The edge gateway notification method according to claim 6, characterized in that: In step S6, after receiving the notification, the notification strategy is fed back according to the actual situation. The edge gateway collects and analyzes the feedback data, adjusts the preference of the big model to generate the notification strategy, or uploads similar data through the edge gateway to fine-tune the big model, further optimize the prediction ability and notification strategy of the big model, and directly adjust the notification strategy according to the needs; Filter edge gateway data, adjust notification policies, or retrain large models to adapt to device data based on notification content. Perform continuous pruning and quantization operations on large models based on actual application scenarios and performance requirements. Regularly pay attention to research progress and technological updates in the field of large models, and promptly apply new research results and technical means to the system.

8. An edge gateway notification device, characterized in that: include: at least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is configured to call the machine-readable program to execute the method according to any one of claims 1 to 7.

Images