Agricultural technology promotion cloud log management publishing system and method thereof

Abstract

The invention relates to the technical field of agriculture, and discloses an agricultural technology promotion cloud log management and release system and method, and the system comprises a cloud infrastructure layer which is configured with a plurality of cloud services for processing and storing data; the data processing layer is configured with a real-time data processing module and a data warehouse, and the real-time data processing module adopts Apache Kafka and Redis; the user interface layer is constructed by using a React framework and supports self-adaptive design; the security and privacy protection layer is used for implementing TLS and AES-256 encryption technologies and carrying out data tracking and verification by adopting a block chain technology; and an analysis and decision support layer. The pertinence and the effect of popularization measures are improved by generating highly personalized recommendations, the acceptance rate and the satisfaction degree of users are increased, in addition, the system can dynamically adjust the recommendations according to real-time environment data and user behaviors, agricultural decisions are more accurate, and the efficiency and the yield of agricultural production are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to an agricultural technology promotion cloud log management and publishing system and method thereof. Background Art

[0002] Agricultural technology extension is the process of applying the latest agricultural research results and technologies to actual agricultural production, with the aim of improving agricultural production efficiency and crop yields while reducing environmental impact. With the growth of the global population and the reduction of arable land, improving agricultural production efficiency and sustainability has become a top priority. Traditional agricultural technology extension methods rely on face-to-face training and paper material distribution, which is time-consuming, labor-intensive and inefficient; with the rapid development of information technology, especially the application of cloud computing, big data, artificial intelligence and other technologies, the methods and means of agricultural technology extension are undergoing revolutionary changes. Existing agricultural information systems are able to collect and process large amounts of agricultural data, such as meteorological data, soil data, crop growth data, etc., and provide decision support through data analysis.

[0003] Although existing agricultural information systems provide certain technical support for agricultural technology extension, they are insufficient in several key aspects. First, these systems often lack real-time data processing capabilities, which means that they cannot quickly process and feedback the latest collected agricultural data, such as immediate meteorological changes, soil moisture and other key parameters. This delay in data processing makes it impossible to provide real-time agricultural technology advice and early warning information, thereby failing to help farmers adjust agricultural activities in time to cope with sudden climate change or disease and pests; in addition, many existing systems adopt a standardized extension method, the so-called "one size fits all" model, which ignores the regional differences and individual differences in agricultural production. This approach fails to fully take into account factors such as the specific farm conditions, crop types, resource availability and personal preferences of different farmers, resulting in the agricultural technology measures promoted often not being applicable to all situations, and the effect is greatly reduced. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an agricultural technology promotion cloud log management and publishing system and method thereof, which solves the problems of insufficient real-time data processing capabilities and lack of targeted personalized promotion strategies in the existing agricultural information system.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an agricultural technology promotion cloud log management and publishing system and method thereof, including a cloud infrastructure layer, configured with a variety of cloud services for processing and storing data;

[0006] The data processing layer is equipped with a real-time data processing module and a data warehouse. The real-time data processing module uses Apache Kafka and Redis.

[0007] The user interface layer is built using the React framework and supports adaptive design;

[0008] Security and privacy protection layer, implementing TLS and AES-256 encryption technology, and using blockchain technology for data tracking and verification;

[0009] The analytics and decision support layer uses machine learning and deep learning technologies, including but not limited to TensorFlow and PyTorch;

[0010] System monitoring module, used for system performance monitoring and user behavior analysis;

[0011] User feedback and support module, used to collect and respond to user opinions and needs.

[0012] Preferably, the data processing layer uses a Kalman filter to perform data assimilation, and the formula of the Kalman filter is:

[0013]

[0014]

[0015] in, is the estimated state, z is the observed data, K is the Kalman gain, R k is the observation noise covariance.

[0016] Preferably, the user interface layer includes accessibility features, complies with WCAG 2.1 standards, and implements screen reader support and keyboard navigation.

[0017] Preferably, the security and privacy protection layer includes a role-based access control function, using OAuth2.0 and JWT for identity authentication and authorization.

[0018] Preferably, the analysis and decision support layer adopts collaborative filtering technology, and its algorithm formula is:

[0019]

[0020] Among them, ∑ v∈U sim(u,v) represents the similarity between users u and v, r v,i is the rating of item i by user v.

[0021] Preferably, the data processing layer is further configured with Apache Spark, which is used for big data processing and supports integrated operations of batch processing and stream processing.

[0022] Preferably, the system monitoring module uses Prometheus and Grafana for monitoring and analysis;

[0023] The Prometheus server is further configured with an alarm manager for generating alarms based on predefined performance thresholds and automatically sending notifications when the monitored indicators exceed the normal range;

[0024] The Grafana platform is configured with multiple dashboards for receiving data from the Prometheus server and visualizing the data through charts, meters, and log displays, and supports customized views for in-depth analysis of specific data.

[0025] Preferably, the security and privacy protection layer is further configured with:

[0026] Differential privacy technology is applied to data publishing and sharing to protect user privacy. The formula is:

[0027] Pr[K(D)∈S]≤e ∈ Pr[K(D′)∈S]+δ

[0028] Among them, K is the data query algorithm, D and D′ are adjacent data sets, ∈ is the privacy budget, and δ is the probability of privacy leakage.

[0029] Preferably, the user feedback and support module sets up an online feedback mechanism for collection;

[0030] The online feedback mechanism is provided with a feedback form directly accessed by the user interface, which is used to collect user experience feedback, function requests or error reports when using the system;

[0031] The feedback form includes, but is not limited to, a text input area, multiple choice questions, and a rating system, so that users can describe in detail the problems or suggestions they encounter.

[0032] A method for managing and publishing agricultural technology promotion cloud logs, comprising the following steps:

[0033] a. Collect agricultural technology data and process it in real time through Apache Kafka;

[0034] b. Use Kalman filter to assimilate data and update data model;

[0035] c. Generate personalized recommendations based on user data and agricultural technology data through machine learning models;

[0036] d. Display recommendation results through the user interface layer and receive user feedback to optimize the recommendation system.

[0037] The present invention provides an agricultural technology promotion cloud log management and publishing system and method thereof. It has the following beneficial effects:

[0038] 1. The present invention improves the pertinence and effectiveness of promotion measures by generating highly personalized recommendations, and increases user acceptance and satisfaction through customized agricultural management and technical solutions. In addition, the system can dynamically adjust recommendations based on real-time environmental data and user behavior, making agricultural decisions more accurate and greatly improving the efficiency and output of agricultural production.

[0039] 2. The present invention improves the accuracy and consistency of data by assimilating information from multiple data sources through the Kalman filter. This data assimilation technology is particularly important for modern agriculture that relies on accurate data to drive decision-making. It can effectively optimize prediction models and decision-making processes, thereby helping agricultural practitioners to better manage crop growth, pest and disease control, and resource allocation, and improve the predictability and sustainability of agricultural production.

[0040] 3. The present invention uses Prometheus and Grafana for in-depth performance monitoring and data visualization, timely identifies and responds to system performance issues, and maintains efficient operation of the system. At the same time, the implementation of security and privacy protection layers, such as TLS and AES-256 encryption and the application of blockchain technology, ensures the security and immutability of data, greatly enhancing the data security of the system and the user's trust in the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A perspective view of the present invention;

[0042] Figure 2 The figure is a flow chart of the method steps of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0044] Embodiment 1:

[0045] Please refer to the attached Figure 1 , an embodiment of the present invention provides an agricultural technology promotion cloud log management and publishing system, including:

[0046] The cloud infrastructure layer is configured with various cloud services for processing and storing data;

[0047] The data processing layer is equipped with a real-time data processing module and a data warehouse. The real-time data processing module uses Apache Kafka and Redis.

[0048] The user interface layer is built using the React framework and supports adaptive design;

[0049] Security and privacy protection layer, implementing TLS and AES-256 encryption technology, and using blockchain technology for data tracking and verification;

[0050] The analytics and decision support layer uses machine learning and deep learning technologies, including but not limited to TensorFlow and PyTorch;

[0051] System monitoring module, used for system performance monitoring and user behavior analysis;

[0052] User feedback and support module, used to collect and respond to user opinions and needs;

[0053] The data processing layer uses Kalman filter for data assimilation. The formula of Kalman filter is:

[0054]

[0055]

[0056] in, is the estimated state, z is the observed data, K is the Kalman gain, R k is the observation noise covariance;

[0057] The user interface layer includes accessibility features, adheres to WCAG 2.1 standards, and implements screen reader support and keyboard navigation;

[0058] The security and privacy protection layer includes role-based access control, using OAuth2.0 and JWT for authentication and authorization;

[0059] The analysis and decision support layer uses collaborative filtering technology, and its algorithm formula is:

[0060]

[0061] Among them, ∑ v∈U sim(u,v) represents the similarity between users u and v, rv,i is the rating of user v on item i;

[0062] The data processing layer is further configured with Apache Spark, which is used for big data processing and supports integrated operations of batch processing and stream processing;

[0063] The system monitoring module uses Prometheus and Grafana for monitoring and analysis;

[0064] The Prometheus server is further configured with an alert manager to generate alerts based on predefined performance thresholds and automatically send notifications when the monitored metrics are outside the normal range;

[0065] Grafana platform, configured with multiple dashboards, receives data from Prometheus servers and visualizes the data through charts, meters, and log displays, supporting custom views for in-depth analysis of specific data;

[0066] The security and privacy protection layer is further configured with:

[0067] Differential privacy technology is applied to data publishing and sharing to protect user privacy. The formula is:

[0068] Pr[K(D)∈S]≤e ∈ Pr[K(D′)∈S]+δ

[0069] Among them, K is the data query algorithm, D and D′ are adjacent data sets, ∈ is the privacy budget, and δ is the probability of privacy leakage;

[0070] The user feedback and support module sets up an online feedback mechanism for collection;

[0071] The online feedback mechanism is equipped with a feedback form directly accessed by the user interface to collect user experience feedback, feature requests or error reports when using the system;

[0072] Feedback forms include, but are not limited to, text input areas, multiple choice questions, and rating systems to allow users to describe in detail their issues or suggestions.

[0073] Specifically, the system uses a comprehensive modular architecture to achieve data collection, processing, security management and user interaction to provide efficient agricultural technology promotion and decision support; the system first collects agricultural-related data through a variety of cloud services in the cloud infrastructure layer, and uses Apache Kafka and Redis to perform real-time data processing and storage in the data processing layer; these data are assimilated through the Kalman filter to optimize the accuracy and consistency of information to provide more accurate agricultural operation predictions and decision support, and the data processing results are passed to the user interface layer, which is built with the React framework and supports adaptive design to ensure that users can get the best experience no matter what device they use; the interface layer also includes barrier-free access functions and complies with the WCAG2.1 standard to ensure that all users can easily access and use the system; the security and privacy protection layer implements TLS and AES-256 encryption technology and blockchain technology to ensure the security and immutability of data, and uses OAuth2.0 and JWT for role-based access control to ensure that only authorized users can access The analysis and decision support layer applies advanced machine learning and deep learning technologies such as TensorFlow and PyTorch to provide personalized agricultural technology promotion suggestions through collaborative filtering algorithms. The algorithm calculates the recommendation score based on the similarity between users and historical interaction data, making the recommendation more accurate; the system monitoring module uses Prometheus and Grafana for performance monitoring and user behavior analysis, and promptly notifies system administrators of any problems that exceed predefined performance thresholds through the alarm manager, and deeply analyzes the system operation status through the visual dashboard provided by Grafana. Finally, the user feedback and support module sets up an online feedback mechanism to allow users to submit experience feedback or feature requests directly through the interface. These feedbacks are collected through text input areas, multiple-choice questions, and scoring systems, and are automatically classified and archived through natural language processing technology to quickly respond to user needs and continuously optimize system functions; this comprehensive and coordinated workflow not only improves system efficiency and user satisfaction, but also ensures data security and sustainable development of the system.

[0074] Embodiment 2:

[0075] Please see attached Figure 2 , a method for managing and publishing agricultural technology extension cloud logs, comprising the following steps:

[0076] a. Collect agricultural technology data and process it in real time through Apache Kafka;

[0077] b. Use Kalman filter to assimilate data and update data model;

[0078] c. Generate personalized recommendations based on user data and agricultural technology data through machine learning models;

[0079] d. Display recommendation results through the user interface layer and receive user feedback to optimize the recommendation system.

[0080] Specifically, through step a, the system automatically collects agricultural technical data from different sources, such as meteorological information, soil conditions, crop growth status, etc., and uses Apache Kafka to process these real-time data streams. Kafka's high throughput and low-latency processing capabilities ensure that the data can be processed and forwarded to the next processing stage quickly and continuously, thereby supporting real-time data-driven decision-making; then, in step b, the Kalman filter is used to assimilate the collected data. This process optimizes the accuracy and consistency of the data model by integrating historical data with new real-time data. The application of the Kalman filter improves the reliability of the prediction model because it dynamically adjusts the model parameters to adapt to new data inputs, greatly improving the response speed and efficiency of the decision support system; in step c, the system uses the updated The data model is combined with the user's historical behavior and preferences to generate personalized recommendations through a machine learning model. Here, machine learning models such as random forests or neural networks identify potential agricultural operations and decisions based on data features and user behaviors, and provide users with scientific crop management suggestions and technology promotion plans. This step not only enhances the relevance and personalization level of the recommendations, but also helps farmers and technicians achieve better crop management through data-driven insights; finally, in step d, these personalized recommendations are displayed through the user interface layer, and user feedback is collected. The design of the user interface layer supports interactivity and ease of use, ensuring that users can easily understand and operate the suggestions provided by the system. User feedback is collected by the system and used to further optimize the recommendation algorithm and user experience, forming a closed-loop improvement mechanism.

[0081] 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 agricultural technology promotion cloud log management and publishing system, characterized in that: include: The cloud infrastructure layer is configured with various cloud services for processing and storing data; The data processing layer is equipped with a real-time data processing module and a data warehouse. The real-time data processing module uses Apache Kafka and Redis. The user interface layer is built using the React framework and supports adaptive design; Security and privacy protection layer, implementing TLS and AES-256 encryption technology, and using blockchain technology for data tracking and verification; The analytics and decision support layer uses machine learning and deep learning technologies, including but not limited to TensorFlow and PyTorch; System monitoring module, used for system performance monitoring and user behavior analysis; User feedback and support module, used to collect and respond to user opinions and needs.

2. According to claim 1, an agricultural technology extension cloud log management and publishing system is characterized in that: The data processing layer uses a Kalman filter to perform data assimilation. The formula of the Kalman filter is: in, is the estimated state, z is the observed data, K is the Kalman gain, R k is the observation noise covariance.

3. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The user interface layer includes accessibility features, adheres to WCAG 2.1 standards, and implements screen reader support and keyboard navigation.

4. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The security and privacy protection layer includes role-based access control capabilities, using OAuth2.0 and JWT for authentication and authorization.

5. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The analysis and decision support layer adopts collaborative filtering technology, and its algorithm formula is: Among them, ∑ v∈U sim(u,v) represents the similarity between users u and v, r v,i is the rating of item i by user v.

6. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The data processing layer is further configured with Apache Spark, which is used for big data processing and supports integrated operations of batch processing and stream processing.

7. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The system monitoring module uses Prometheus and Grafana for monitoring and analysis; The Prometheus server is further configured with an alarm manager for generating alarms based on predefined performance thresholds and automatically sending notifications when the monitored indicators exceed the normal range; The Grafana platform is configured with multiple dashboards for receiving data from the Prometheus server and visualizing the data through charts, meters, and log displays, and supports customized views for in-depth analysis of specific data.

8. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The security and privacy protection layer is further configured with: Differential privacy technology is applied to data publishing and sharing to protect user privacy. The formula is: Pr[K(D)∈S]≤e ∈ Pr[K(D′)∈S]+δ Among them, K is the data query algorithm, D and D′ are adjacent data sets, ∈ is the privacy budget, and δ is the probability of privacy leakage.

9. The agricultural technology extension cloud log management and publishing system according to claim 1 is characterized in that: The user feedback and support module sets up an online feedback mechanism for collection; The online feedback mechanism is provided with a feedback form directly accessed by the user interface, which is used to collect user experience feedback, function requests or error reports when using the system; The feedback form includes, but is not limited to, a text input area, multiple choice questions, and a rating system, so that users can describe in detail the problems or suggestions they encounter.

10. A method for managing and publishing cloud logs for agricultural technology extension, according to an agricultural technology extension cloud log management and publishing system according to any one of claims 1 to 9, characterized in that: The following steps are involved: a. Collect agricultural technology data and process it in real time through Apache Kafka; b. Use Kalman filter to assimilate data and update data model; c. Generate personalized recommendations based on user data and agricultural technology data through machine learning models; d. Display recommendation results through the user interface layer and receive user feedback to optimize the recommendation system.

Images