Method and system for monitoring and adjusting aviation industry in real time based on large model
By using big models to conduct real-time monitoring and adjustment of data acquisition, preprocessing and deep learning technologies in the aviation industry, the problems of untimely information acquisition and low processing efficiency in the management methods of traditional aviation industry are solved, and real-time monitoring of flight status is achieved and forecasting, improving flight safety and operational efficiency.
Patent Information
- Application Number
- CN202411002578.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-26
AI Technical Summary
The traditional aviation industry management methods rely on manual monitoring, and there are problems such as untimely acquisition of information, low processing efficiency, and inaccurate adjustment strategies, which cannot meet the needs of efficient, safe and stable operation of the modern aviation industry.
Using real-time monitoring and adjustment methods based on large models, build large models through data acquisition and preprocessing and deep learning technologies, monitor and predict flight safety and delay risks in real time, formulate intelligent adjustment strategies, optimize flight plans and regularly update models to adapt to the industry change.
Real-time monitoring and prediction of flight status is realized, which reduces safety hazards and delay risks, improves flight safety and operation efficiency, and reduces operating costs.
Smart Images

Figure CN119028185A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of real-time monitoring and adjustment of the aviation industry, and in particular to a method and system for real-time monitoring and adjustment of the aviation industry based on a large model. Background Art
[0002] With the rapid development of the aviation industry, the number of flights continues to increase, and issues such as flight safety, flight efficiency, and service quality are becoming increasingly prominent. Traditional aviation industry management methods mostly rely on manual monitoring and adjustment, which have problems such as untimely information acquisition, low processing efficiency, and inaccurate adjustment strategies. They can no longer meet the needs of efficient, safe, and stable operations in the modern aviation industry.
[0003] In recent years, with the rapid development of technologies such as big data and artificial intelligence, big model technology has been widely used in many fields. By training a large amount of data, big models can achieve accurate prediction and intelligent adjustment of complex systems. However, in the aviation industry, real-time monitoring and adjustment methods based on big models have not been fully studied and applied.
[0004] Therefore, it is necessary to study a real-time monitoring and adjustment method based on large models to improve the operational efficiency of the aviation industry. Summary of the invention
[0005] The purpose of the present invention is to provide a method and system for real-time monitoring and adjustment of the aviation industry based on a large model, so as to solve the problems raised in the above-mentioned background technology.
[0006] To achieve the above object, the present invention provides the following technical solution: a method for real-time monitoring and adjustment of the aviation industry based on a large model, the method comprising the following steps:
[0007] Data collection and preprocessing: collecting operational data from the aviation industry, cleaning, integrating and standardizing the data;
[0008] Large model construction and training, using deep learning technology to learn the operating laws and characteristics of the aviation industry by training large amounts of data;
[0009] Real-time monitoring and prediction: using big models to monitor and predict the operation data of the aviation industry in real time, assess flight safety and delay risks, and predict future operation trends;
[0010] Intelligent adjustment strategy formulation: formulate targeted adjustment strategies based on the monitoring and prediction results of the big model to optimize flight plans and improve service quality;
[0011] System optimization and updating, including regular collection of new operational data, retraining and tuning of large models to adapt to the latest developments and changes in the aviation industry.
[0012] Preferably, the specific operations of data collection and preprocessing include:
[0013] Data sources include sensor data, user behavior data, and log data. The frequency of data collection can be based on the real-time requirements of the data, such as scheduled collection, real-time collection, or streaming collection. Data cleaning includes removing duplicate data, filling missing values, and processing outliers. Data integration combines data from different sources to form a unified data set. Data is converted into a unified format and dimension to facilitate subsequent analysis and processing.
[0014] Preferably, the specific operations of building and training a large model include:
[0015] Refined design and adjustment of the model, including selection of appropriate activation functions, optimization algorithms and loss functions, as well as model parameter initialization and regularization processing, can help improve the convergence speed and stability of the model, reduce the risk of overfitting, and enhance the performance of the model. The large model construction process includes model selection, network structure design, and parameter initialization. The optimization algorithms such as back propagation algorithm and gradient descent are used to minimize the error between the model's prediction results and the actual data by continuously adjusting the model's parameters.
[0016] Preferably, the specific operations of real-time monitoring and prediction include:
[0017] The real-time monitoring part reflects the operating status and performance of the system in real time by continuously collecting and processing data from various sensors and equipment. After pre-processing, the data is sent to the prediction model for analysis to derive prediction results for future trends. Advanced data collection and transmission technology is used to ensure the real-time and accuracy of data. By establishing an efficient data processing process, the raw data can be quickly converted into valuable information.
[0018] Preferably, the specific operations of the system optimization and update include:
[0019] Adopt a strategy of regularly updating data and regularly collect new operational data to retrain the large model so that it can adapt to the latest developments and changes in the aviation industry.
[0020] A real-time monitoring and adjustment system for the aviation industry based on a large model, the system consists of a data acquisition and preprocessing module, a large model construction and training module, a real-time monitoring and prediction module, an intelligent adjustment strategy formulation module, and a system optimization and update module;
[0021] Data collection and preprocessing module, which collects operational data of the aviation industry and cleans, integrates and standardizes the data;
[0022] The large model building and training module uses deep learning technology to learn the operating rules and characteristics of the aviation industry by training large amounts of data;
[0023] Real-time monitoring and prediction module, which uses big models to monitor and predict the operation data of the aviation industry in real time, evaluate flight safety and delay risks, and predict future operation trends;
[0024] Intelligent adjustment strategy formulation module, which formulates targeted adjustment strategies based on the monitoring and prediction results of the big model, optimizes flight plans and improves service quality;
[0025] System optimization and update module, including regular collection of new operating data, retraining and tuning of large models to adapt to the latest developments and changes in the aviation industry.
[0026] Preferably, the data sources of the data collection and preprocessing module include sensor data, user behavior data, and log data; the collection frequency is selected according to the real-time requirements of the data, such as scheduled collection, real-time collection, or streaming collection; data cleaning includes removing duplicate data, filling missing values, processing outliers, etc.; data integration is to merge data from different sources to form a unified data set; and the data is converted into a unified format and dimension to facilitate subsequent analysis and processing.
[0027] Preferably, the large model construction and training module performs refined design and adjustment of the model, including selecting appropriate activation functions, optimization algorithms and loss functions, and performing parameter initialization and regularization processing on the model, which helps to improve the convergence speed and stability of the model, reduce the risk of overfitting, and improve the performance of the model; the large model construction process includes model selection, network structure design, and parameter initialization; optimization algorithms such as back propagation algorithm and gradient descent are used to minimize the error between the model's prediction results and the actual data by continuously adjusting the model's parameters.
[0028] Preferably, the real-time monitoring and prediction module, the real-time monitoring part reflects the operating status and performance of the system in real time by continuously collecting and processing data from various sensors and devices. After pre-processing, the data is sent to the prediction model for analysis, so as to obtain the prediction results of future trends; it adopts advanced data collection and transmission technology to ensure the real-time and accuracy of data, and can quickly convert raw data into valuable information by establishing an efficient data processing process.
[0029] Preferably, the system optimization and update module adopts a strategy of regularly updating data, and retrains the large model by regularly collecting new operating data so that it can adapt to the latest developments and changes in the aviation industry.
[0030] Compared with the prior art, the present invention has the following beneficial effects:
[0031] The method and system for real-time monitoring and adjustment of the aviation industry based on a large model proposed in the present invention can monitor and predict flight status in real time, timely discover potential safety hazards and delay risks, formulate targeted adjustment strategies, effectively reduce the occurrence of flight delays and safety accidents, and improve the safety and operation efficiency of flights; by constructing a large model to conduct real-time analysis of the operation data of the aviation industry, quickly and accurately process flight operation data, realize real-time monitoring and adjustment of the aviation industry, improve the operation efficiency and service level of the aviation industry, and reduce operation costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION
[0033] In order to make the purpose and technical solution of the present invention clearly and completely described, and the advantages more clearly understood, the embodiments of the present invention are further described in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are part of the embodiments of the present invention, rather than all of the embodiments, and are only used to explain the embodiments of the present invention, and are not used to limit 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.
[0034] Embodiment 1
[0035] See also Figure 1 The present invention provides a technical solution: a method for real-time monitoring and adjustment of the aviation industry based on a large model, the method comprising the following steps:
[0036] The data acquisition and preprocessing module is the foundation and key step of the entire technical solution. It is directly related to the accuracy and reliability of subsequent model construction. This module is further divided into two parts: data acquisition and data preprocessing.
[0037] In terms of data collection, we must first clarify the data source and collection method. The present invention will use different methods to collect all involved scene data according to different application scenarios. The data source may include sensor data, user behavior data, log data, etc. The collection frequency can be selected according to the real-time requirements of the data, such as timed collection, real-time collection or streaming collection. In the process of data collection, the present invention will also pay special attention to the integrity, accuracy and consistency of the data. Integrity refers to ensuring that all required data are collected without omissions; accuracy requires that the data truly reflects the actual situation without errors; consistency ensures that data from different sources can be unified in format, unit, etc., to facilitate subsequent processing and analysis.
[0038] More specifically, the data collection scope of the present invention covers flight information, meteorological data, airport facility usage, etc. Flight information includes flight number, take-off and landing time, aircraft type, passenger capacity, etc.; meteorological data includes wind speed, wind direction, visibility, cloud cover, etc.; airport facility usage includes runway usage, parking space usage, etc.
[0039] After the raw data is collected, it needs to be preprocessed. Data preprocessing is also an indispensable part, because the collected raw data often has problems such as inconsistent format, missing data, outliers, etc., so it needs to be cleaned, integrated and standardized. Data cleaning includes removing duplicate data, filling missing values, processing outliers, etc.; data integration is to merge data from different sources to form a unified data set; data standardization can normalize or standardize the data according to certain rules, and convert the data into a unified format and dimension for subsequent analysis and processing. In the preprocessing process, the present invention will fully consider the storage and management of the data. Since the amount of data may be very large, it is necessary to select a suitable storage medium and storage method to ensure the security and accessibility of the data. At the same time, the present invention will also establish specifications and processes for data management to ensure that the accuracy and consistency of the data are maintained for a long time.
[0040] Through data collection and preprocessing, high-quality data support can be provided for subsequent large-scale model construction and training, laying a solid foundation for the implementation of the entire technical solution.
[0041] Large model construction and training are the core links in the technical solution, which directly determine the performance and application effect of the model. The large model module is divided into two parts: large model construction and large model training.
[0042] In terms of large model construction, the present invention will select appropriate model structures and algorithms according to specific application scenarios and requirements. This includes but is not limited to deep learning models, machine learning algorithms, and traditional statistical models. In the process of building a large model, the present invention will fully consider factors such as model complexity, computing resources, and training time. Complexity determines the learning ability and generalization performance of the model, but too high complexity may lead to overfitting and waste of computing resources; computing resources limit the scale and training speed of the model, so it is necessary to weigh them according to actual conditions; training time affects the implementation cycle and cost of the entire technical solution, and is shortened as much as possible. In order to build a high-performance large model, the present invention will also fine-tune the model design and adjustment. This includes selecting appropriate activation functions, optimization algorithms, loss functions, etc., as well as performing model parameter initialization, regularization, and other processing. These measures help to improve the convergence speed and stability of the model, reduce the risk of overfitting, and thus improve the performance of the model.
[0043] The large model construction process includes steps such as model selection, network structure design, and parameter initialization. In terms of model selection, the present invention adopts deep learning technology, especially a combination model of recurrent neural network (RNN) and convolutional neural network (CNN), to make full use of the characteristics of sequence data and image data. In terms of network structure design, the present invention designs a multi-level neural network structure, including an input layer, a hidden layer, and an output layer, to achieve deep learning and feature extraction of complex data. In terms of parameter initialization, the present invention adopts random initialization or pre-trained model initialization to ensure that the initial state of the model has good generalization ability.
[0044] In terms of model training, the present invention improves the training efficiency and quality of the model by preparing sufficient training data and adopting appropriate training strategies, so that the model can better adapt to actual application scenarios.
[0045] The training of a large model is an iterative optimization process, the goal of which is to enable the model to accurately predict and analyze the operating data of the aviation industry. During the training process, the present invention uses optimization algorithms such as back propagation algorithm and gradient descent to minimize the error between the model's prediction results and the actual data by continuously adjusting the model's parameters. At the same time, the present invention also uses regularization, dropout and other technologies to prevent the model from overfitting and improve the generalization ability of the model.
[0046] Real-time monitoring and prediction are key links in the technical solution. They can achieve real-time tracking of system status and accurate prediction of future trends. This module is divided into two parts: real-time monitoring and predictive analysis. The real-time monitoring part continuously collects and processes data from various sensors and devices to reflect the operating status and performance of the system in real time. After preprocessing, these data are sent to the prediction model for analysis to obtain the prediction results of future trends.
[0047] Real-time monitoring is one of the important functions of the present invention. In terms of real-time monitoring, the present invention adopts advanced data acquisition and transmission technology to ensure the real-time and accuracy of data. At the same time, the present invention can quickly convert raw data into valuable information by establishing an efficient data processing process. In addition, by designing an intuitive visual interface, users can clearly understand the real-time status of the system.
[0048] The purpose of real-time monitoring is to track and evaluate the operating status of the aviation industry in real time. More specifically, by collecting data such as flight status, weather changes, and airport facility usage in real time, the big model can analyze and process these data in real time to promptly identify potential safety hazards and operational risks. For example, when bad weather occurs at an airport, the big model can monitor weather changes in real time, evaluate the impact on flights, and issue early warning information.
[0049] Predictive analysis is another important function of the present invention, which aims to predict the flight operation trend in the future based on historical data and current conditions. The big model can predict future flight delays, passenger flow changes, etc. by learning the rules and patterns in historical data. These prediction results can provide powerful decision support for airlines, helping them optimize flight plans, adjust resource allocation, and improve service quality.
[0050] The intelligent adjustment strategy formulation module includes multiple strategies, such as security adjustment strategy, efficiency improvement strategy, service quality improvement strategy, etc.
[0051] Based on the safety adjustment strategy, the big model can give targeted safety adjustment strategies for the safety hazards and operational risks found in real-time monitoring. For example, when it is predicted that a certain airport will have bad weather, the big model can suggest that airlines adjust flight plans in advance to avoid flight delays or cancellations. At the same time, the big model can also evaluate the safety of flights based on factors such as flight status and aircraft type, and make corresponding safety recommendations.
[0052] Based on efficiency improvement strategies, in order to improve the operating efficiency of the aviation industry, the big model can formulate efficiency improvement strategies based on the prediction and analysis results. For example, when it is predicted that the passenger flow will be large in a certain period of time, the big model can suggest that airlines increase flight frequency and optimize flight schedules to meet the travel needs of passengers. At the same time, the big model can also analyze the use of airport facilities and propose suggestions for optimizing airport resource allocation to improve the operating efficiency of the airport.
[0053] Based on the service quality improvement strategy, service quality is an important manifestation of the competitiveness of airlines. The big model can formulate a service quality improvement strategy by analyzing passenger needs, preferences and complaint data. For example, when it is found that passengers on a certain route are dissatisfied with the meal service, the big model can suggest that the airline adjust the meal types and flavors to improve passenger satisfaction. At the same time, the big model can also provide personalized service suggestions based on passengers' travel habits and preferences to enhance passenger loyalty and stickiness.
[0054] The model optimization and upgrade module is mainly used to continuously train and iterate the model. With the continuous development of the aviation industry, new operating data will continue to emerge. In order to maintain the accuracy and timeliness of the large model, the present invention adopts a strategy of regularly updating data. By regularly collecting new operating data, the large model is retrained to enable it to adapt to the latest developments and changes in the aviation industry.
[0055] Embodiment 2
[0056] Based on the first embodiment, a real-time monitoring and adjustment system for the aviation industry based on a large model is proposed, which consists of a data acquisition and preprocessing module, a large model construction and training module, a real-time monitoring and prediction module, an intelligent adjustment strategy formulation module, and a system optimization and update module;
[0057] The data collection and preprocessing module collects operational data from the aviation industry and cleans, integrates and standardizes the data. Data sources include sensor data, user behavior data, and log data. The collection frequency is based on the real-time requirements of the data, and different methods such as scheduled collection, real-time collection, or streaming collection are selected. Data cleaning includes removing duplicate data, filling missing values, and processing outliers. Data integration combines data from different sources to form a unified data set. Data is converted into a unified format and dimension to facilitate subsequent analysis and processing.
[0058] The large model construction and training module uses deep learning technology to learn the operating laws and characteristics of the aviation industry by training large amounts of data; it conducts refined design and adjustment of the model, including selecting appropriate activation functions, optimization algorithms, and loss functions, as well as initializing and regularizing the model parameters, which helps to improve the convergence speed and stability of the model, reduce the risk of overfitting, and improve the performance of the model; the large model construction process includes model selection, network structure design, and parameter initialization; it uses optimization algorithms such as backpropagation algorithm and gradient descent to minimize the error between the model's predicted results and the actual data by continuously adjusting the model's parameters.
[0059] The real-time monitoring and prediction module uses large models to monitor and predict the operation data of the aviation industry in real time, evaluate flight safety and delay risks, and predict future operation trends. The real-time monitoring part continuously collects and processes data from various sensors and equipment to reflect the operating status and performance of the system in real time. After pre-processing, the data is sent to the prediction model for analysis to obtain prediction results for future trends. Advanced data collection and transmission technology is used to ensure the real-time and accuracy of data. By establishing an efficient data processing process, the raw data can be quickly converted into valuable information.
[0060] Intelligent adjustment strategy formulation module, which formulates targeted adjustment strategies based on the monitoring and prediction results of the big model, optimizes flight plans and improves service quality;
[0061] The system optimization and update module includes regularly collecting new operating data, retraining and tuning the large model, and adapting to the latest developments and changes in the aviation industry; adopting a strategy of regularly updating data, by regularly collecting new operating data, retraining the large model so that it can adapt to the latest developments and changes in the aviation industry.
[0062] 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. A method for real-time monitoring and adjustment of the aviation industry based on a large model, characterized by: The method comprises the following steps: Data collection and preprocessing: collecting operational data from the aviation industry, cleaning, integrating and standardizing the data; Large model construction and training, using deep learning technology to learn the operating laws and characteristics of the aviation industry by training large amounts of data; Real-time monitoring and prediction: using big models to monitor and predict the operation data of the aviation industry in real time, assess flight safety and delay risks, and predict future operation trends; Intelligent adjustment strategy formulation: formulate targeted adjustment strategies based on the monitoring and prediction results of the big model to optimize flight plans and improve service quality; System optimization and updating, including regular collection of new operational data, retraining and tuning of large models to adapt to the latest developments and changes in the aviation industry.
2. The method for real-time monitoring and adjustment of the aviation industry based on a large model according to claim 1 is characterized by: The specific operations of data collection and preprocessing include: Data sources include sensor data, user behavior data, and log data. The frequency of data collection can be based on the real-time requirements of the data, such as scheduled collection, real-time collection, or streaming collection. Data cleaning includes removing duplicate data, filling missing values, and processing outliers. Data integration combines data from different sources to form a unified data set. Data is converted into a unified format and dimension to facilitate subsequent analysis and processing.
3. The method for real-time monitoring and adjustment of the aviation industry based on a large model according to claim 1 is characterized by: The specific operations of building and training large models include: Refined design and adjustment of the model, including selection of appropriate activation functions, optimization algorithms and loss functions, as well as model parameter initialization and regularization processing, can help improve the convergence speed and stability of the model, reduce the risk of overfitting, and enhance the performance of the model. The large model construction process includes model selection, network structure design, and parameter initialization. The optimization algorithms such as back propagation algorithm and gradient descent are used to minimize the error between the model's prediction results and the actual data by continuously adjusting the model's parameters.
4. The method for real-time monitoring and adjustment of the aviation industry based on a large model according to claim 1 is characterized by: The specific operations of real-time monitoring and prediction include: The real-time monitoring part reflects the operating status and performance of the system in real time by continuously collecting and processing data from various sensors and equipment. After pre-processing, the data is sent to the prediction model for analysis to derive prediction results for future trends. Advanced data collection and transmission technology is used to ensure the real-time and accuracy of data. By establishing an efficient data processing process, the raw data can be quickly converted into valuable information.
5. The method for real-time monitoring and adjustment of the aviation industry based on a large model according to claim 1 is characterized by: The specific operations of the system optimization and update include: Adopt a strategy of regularly updating data and regularly collect new operational data to retrain the large model so that it can adapt to the latest developments and changes in the aviation industry.
6. A system for real-time monitoring and adjustment of the aviation industry based on a large model according to any one of claims 1 to 5, characterized in that: The system consists of a data acquisition and preprocessing module, a large model building and training module, a real-time monitoring and prediction module, an intelligent adjustment strategy formulation module, and a system optimization and update module; Data collection and preprocessing module, which collects operational data of the aviation industry and cleans, integrates and standardizes the data; The large model building and training module uses deep learning technology to learn the operating rules and characteristics of the aviation industry by training large amounts of data; Real-time monitoring and prediction module, which uses big models to monitor and predict the operation data of the aviation industry in real time, evaluate flight safety and delay risks, and predict future operation trends; Intelligent adjustment strategy formulation module, which formulates targeted adjustment strategies based on the monitoring and prediction results of the big model, optimizes flight plans and improves service quality; System optimization and update module, including regular collection of new operating data, retraining and tuning of large models to adapt to the latest developments and changes in the aviation industry.
7. The real-time monitoring and adjustment system for the aviation industry based on a large model according to claim 6 is characterized by: The data collection and preprocessing module, the data sources include sensor data, user behavior data, and log data; The frequency of data collection can be selected based on the real-time requirements of the data, such as scheduled collection, real-time collection, or streaming collection. Data cleaning includes removing duplicate data, filling missing values, and processing outliers. Data integration is the process of combining data from different sources to form a unified data set; converting data into a unified format and dimension to facilitate subsequent analysis and processing.
8. The real-time monitoring and adjustment system for the aviation industry based on a large model according to claim 6 is characterized by: The large model construction and training module performs refined design and adjustment of the model, including selecting appropriate activation functions, optimization algorithms and loss functions, and performing parameter initialization and regularization processing on the model, which helps to improve the convergence speed and stability of the model, reduce the risk of overfitting, and improve the performance of the model; the large model construction process includes model selection, network structure design, and parameter initialization; optimization algorithms such as back propagation algorithm and gradient descent are used to minimize the error between the model's prediction results and the actual data by continuously adjusting the model's parameters.
9. The real-time monitoring and adjustment system for the aviation industry based on a large model according to claim 6 is characterized by: The real-time monitoring and prediction module, the real-time monitoring part reflects the operating status and performance of the system in real time by continuously collecting and processing data from various sensors and devices. After pre-processing, the data is sent to the prediction model for analysis, thereby obtaining the prediction results of future trends; We use advanced data collection and transmission technologies to ensure the real-time and accuracy of data, and by establishing efficient data processing processes, we can quickly convert raw data into valuable information.
10. The real-time monitoring and adjustment system for the aviation industry based on a large model according to claim 6 is characterized by: The system optimization and update module adopts a strategy of regularly updating data. By regularly collecting new operating data, the large model is retrained to enable it to adapt to the latest developments and changes in the aviation industry.
Citation Information
Cited By
Big data-based aviation information management platform, application and method thereof
CN119938760A
