Adaptive Remote Communication Control System and Method Based on Large Model

Abstract

The present invention discloses an adaptive remote communication control system and method based on a large model, including modules such as communication data acquisition, large model analysis, adaptive control, fault detection and repair, interference suppression, and user interface. The large model has a multi-layer structure and can accurately predict communication quality. Each module has corresponding functions and performance indicators, such as the fault detection accuracy rate ≥ 95%, etc. There are also innovative formulas for channel selection, etc. The system has various optimization and guarantee functions, improving the accuracy and reliability of communication control; The present invention accurately predicts communication quality through the large model, and the multi-module collaborative optimization realizes efficient fault detection, repair, and interference suppression, guarantees data security, adapts to multiple devices and supports user customization, improving the quality, reliability, and user experience of remote communication, and promoting the development of the industry.

Description

Technical Field

[0001] The present invention relates to the technical field of remote communication control systems, and particularly to an adaptive remote communication control system and method based on large models. Background Art

[0002] With the rapid development of information technology, remote communication is increasingly widely used in various fields, covering aspects such as mobile communication and video calls in daily life, remote monitoring and intelligent control in the industrial field, and data transmission and remote collaboration in scientific research. However, the remote communication system faces many complex challenges during operation, which seriously affect the quality and reliability of communication and restrict the further development of related applications.

[0003] In traditional remote communication systems, data collection is often not comprehensive and accurate enough. Only some basic communication parameters, such as signal strength and bandwidth utilization rate, are concerned, while factors such as signal spectrum characteristics and channel fading characteristics, which have an important impact on communication quality, are ignored. This leads to an insufficient understanding of the communication state and makes it difficult to accurately predict and address potential problems. Moreover, the frequency and accuracy of data collection are also limited, unable to reflect the dynamic changes of the communication environment in real time and accurately, resulting in a lag in the system's response and adjustment when facing rapidly changing communication scenarios, affecting the continuity and stability of communication.

[0004] Regarding the analysis and prediction of communication quality, traditional methods lack effective model and algorithm support. Most rely on simple statistical analysis or experience-based judgment, making it difficult to uncover the deep rules and trends hidden in communication data. This results in inaccurate prediction of the change trend of communication quality and the inability to take effective optimization measures in advance, leading to significant fluctuations in communication quality. Especially in complex electromagnetic environments or network congestion situations, problems such as signal interruption, increased delay, and data packet loss are likely to occur, seriously affecting the user experience and the normal operation of services.

[0005] In terms of the control of communication parameters, traditional systems usually adopt fixed or simple rule-based adjustment strategies and cannot perform adaptive optimization according to the real-time communication state. For example, when facing changes in channel conditions, key parameters such as modulation mode and coding rate cannot be adjusted in a timely manner, resulting in low communication efficiency or degraded quality. Moreover, in multi-objective optimization, traditional methods are difficult to balance multiple interrelated quality indicators such as signal strength, signal-to-noise ratio, bandwidth utilization rate, and delay time, often focusing on one at the expense of another and unable to achieve the optimal overall communication quality.

[0006] Fault detection and repair are crucial aspects in remote communication systems, but traditional methods have many deficiencies. The accuracy of fault detection is relatively low, and it is difficult to promptly detect some potential fault hazards. Often, the fault is not addressed until it has severely affected communication. The repair mechanism is also not flexible and efficient enough. Usually, it requires manual intervention, and the repair time is relatively long, unable to meet application scenarios with high requirements for communication continuity. At the same time, for different types and severities of faults, there is a lack of intelligent classification and targeted handling strategies, further reducing the efficiency and success rate of fault repair.

[0007] In terms of interference handling, the traditional remote communication system has limited coping capabilities. With the substantial increase in wireless communication devices and the increasingly complex electromagnetic environment, various interference signals such as electromagnetic interference and co-channel interference have severely affected communication quality. The traditional interference suppression methods have poor effects and cannot effectively identify and adaptively suppress these interference signals, resulting in a decline in the clarity and stability of communication signals, affecting the accurate transmission of data and the reliability of communication.

[0008] In addition, the existing remote communication systems also have deficiencies in the user interface and user experience. The user interface is often not intuitive and friendly enough, making it difficult for users to understand the detailed information of communication status and quality indicators in real time. The operation is also not convenient enough. When users perform system parameter settings and control strategy selections, it is rather cumbersome, and there is a lack of personalized setting functions, unable to meet the needs of different users in different scenarios. At the same time, the system has poor adaptability to different devices, and the display effects and operation experiences on various terminal devices such as computers, tablets, and mobile phones are inconsistent, restricting the scope of use and flexibility of users.

[0009] In summary, the traditional remote communication control technology has been difficult to meet the modern society's requirements for high-quality, high-efficiency, and highly reliable remote communication. To overcome these problems, there is an urgent need for an adaptive remote communication control system and method based on large models. By introducing advanced technologies and innovative algorithms, it can achieve comprehensive and accurate monitoring and adaptive optimization of the communication process, improve communication quality and reliability, and provide more stable and efficient remote communication support for various applications. Summary of the Invention

[0010] The adaptive remote communication control system and method based on large models proposed by the present invention aim to solve the problems mentioned in the above existing technologies.

[0011] To achieve the above objectives, the present invention adopts the following technical solutions: An adaptive remote communication control system based on large models, comprising:

[0012] A communication data acquisition module, which is used to collect various types of data in the remote communication process in real time, including signal strength, signal-to-noise ratio, bandwidth utilization rate, data transmission rate, delay time, packet loss rate, signal spectrum characteristics, and channel fading characteristics. The data acquisition frequency is not less than 10 times per second, and the accuracy of data acquisition reaches within ±0.3%.

[0013] A large model analysis module, connected to the communication data acquisition module, uses a large model based on deep learning to analyze the collected communication data. The large model has a multi-layer neural network structure, including at least 8 hidden layers, and the number of neurons in each hidden layer is not less than 256. By learning a large amount of historical communication data, it can accurately predict the change trend of communication quality, and the prediction accuracy is not less than 85% on the validation set.

[0014] In the communication quality prediction, the prediction formula is used: Q t+1 = σ(W × X t + b), where Q t+1 is the predicted value of communication quality at time t + 1, σ is the ReLU activation function, W is the weight matrix, X t is the communication data feature vector at time t, including various collected data and processed features, and b is the bias vector. By continuously training and optimizing W and b, the prediction accuracy is improved.

[0015] An adaptive control module, based on the analysis results of the large model, formulates an adaptive control strategy to adjust communication parameters in real time, including modulation mode, coding rate, transmission power, bandwidth allocation, and channel selection, to optimize communication quality. Ensure that the signal strength is stable within the set range, the fluctuation amplitude does not exceed ±3dB, the signal-to-noise ratio is increased to not less than 20dB, the bandwidth utilization rate is increased to not less than 80%, the delay time is controlled within not more than 100ms, and the packet loss rate is reduced to not more than 1%.

[0016] In channel selection, the following selection formula based on channel quality assessment is used:

[0017] C i = α × S i + β × N i + γ × B i

[0018] where C i is the comprehensive evaluation value of the i-th channel, S i is the signal strength index of this channel, N i is the signal-to-noise ratio index, B i is the bandwidth availability index, and α, β, and γ are weight coefficients, which are determined according to actual needs and experience. By calculating the C i value of each channel, select the channel with the largest C i for communication.

[0019] The fault detection and repair module monitors the anomalies of communication data in real time. By establishing a fault diagnosis model, it can identify communication faults in a timely manner, such as signal interruption, severe interference, and equipment failure. The detection accuracy rate for common faults is not less than 95%. When a fault is detected, it automatically activates the repair mechanism, attempts to switch to the backup communication link, adjusts communication parameters, and restarts relevant equipment for repair. The repair success rate is not less than 90%, and it issues a fault alarm in a timely manner, with the alarm response time not exceeding 1 second.

[0020] In fault diagnosis, the following fault judgment formula based on probability statistics is adopted:

[0021]

[0022] Where P(F) is the probability of the occurrence of fault F, n(F) is the number of times fault F is detected within a certain period of time, and n(T) is the total number of detections. When P(F) exceeds the set threshold, it is judged that fault F has occurred.

[0023] The interference suppression module is used to identify and suppress various interference signals in the communication process in real time, such as electromagnetic interference and co-channel interference. By adopting an adaptive filtering algorithm and spectrum analysis technology, it can effectively reduce the impact of interference on communication quality and improve the clarity and stability of the signal. The improvement amplitude of the signal-to-noise ratio after interference suppression is not less than 5 dB.

[0024] In adaptive filtering, the following filtering coefficient update formula is adopted:

[0025] w n+1 =w n +μ×e n ×x n

[0026] Where w n+1 is the filtering coefficient vector for the (n + 1)-th iteration, w n is the filtering coefficient vector for the n-th iteration, μ is the step size factor, e n is the error signal, and x n is the input signal vector. By continuously updating the filtering coefficient, the effective suppression of interference signals is achieved.

[0027] The user interface module provides an intuitive communication status monitoring interface for users, displaying real-time communication data, quality index trend charts, and fault alarm information. Users can perform system parameter settings and control strategy selection operations through the interface. The response time of the interface operation does not exceed 0.5 seconds, ensuring the timeliness and fluency of operations. At the same time, it has the functions of historical data query and report generation, facilitating users to review and analyze the communication situation.

[0028] The secure encryption module safeguards the security and confidentiality of communication data. It employs advanced encryption algorithms to encrypt the transmitted data, preventing data from being stolen or tampered with. The security of the encrypted communication data meets the industry standard requirements, and the decryption success rate is not less than 98%.

[0029] In data encryption, the following encryption formula is used:

[0030] E(m,k)=c

[0031] Where E is the encryption function, m is the original data, k is the encryption key, and c is the encrypted data. During decryption, the original data is restored through the corresponding decryption function D(c, k)=m.

[0032] Furthermore, the large model analysis module has the function of self-updating the model. As new communication data continuously pours in, it can automatically perform online updating and optimization of the model. After each update, the prediction accuracy of the model on new data is improved by no less than 3%.

[0033] Furthermore, the adaptive control module supports multi-objective optimization. When adjusting communication parameters, it can take into account the optimization of multiple communication quality indicators simultaneously. By establishing a multi-objective optimization function:

[0034] F=w1×Q1+w2×Q2+…+w n ×Q n

[0035] Where F is the optimization objective function, Q1...Q n are the 1st - nth communication quality indicators, and w1...w n are their corresponding weight coefficients. The weight coefficients are dynamically adjusted according to actual needs to achieve balanced optimization of different quality indicators.

[0036] Furthermore, the fault detection and repair module has the function of intelligent fault classification. It can classify the detected faults according to types and severity levels, such as hardware faults, software faults, minor faults, and severe faults, and adopt corresponding repair strategies according to different classifications to improve the efficiency and accuracy of fault repair.

[0037] Furthermore, the user interface module supports multi-device adaptation. It can run stably on different types of terminal devices (such as computers, tablets, and mobile phones). The display effect adapts to the screen sizes and resolutions of different devices, and the interface layout and operation methods are optimized according to the device characteristics to ensure that users can conveniently use the system for remote communication control on various devices.

[0038] Furthermore, an adaptive remote communication control method based on a large model includes the following steps:

[0039] Communication data acquisition steps: Use specialized communication data acquisition devices and technologies to collect various types of data during remote communication in real time, including signal strength, signal-to-noise ratio, bandwidth utilization rate, data transmission rate, latency, packet loss rate, signal spectrum characteristics, and channel fading characteristics, ensuring that the data acquisition frequency is not less than 10 times per second and the data accuracy reaches within ±0.3%;

[0040] Large model analysis steps: Input the collected communication data into a large model based on deep learning for analysis. Through pre-training on a large amount of historical communication data, this large model can mine potential features and patterns in the data, accurately predict the changing trend of communication quality, and use optimized algorithms such as the stochastic gradient descent algorithm to adjust the model parameters during the prediction process to improve the prediction accuracy, with the prediction accuracy on the validation set not less than 85%;

[0041] Adaptive control decision-making steps: According to the analysis results of the large model, formulate an adaptive control strategy to adjust communication parameters in real time, including modulation mode, coding rate, transmit power, bandwidth allocation, and channel selection, to optimize communication quality. During the adjustment process, continuously feedback and adjust the control strategy by real-time monitoring the changes in communication quality indicators to ensure that the signal strength is stable within the set range, with a fluctuation amplitude not exceeding ±3dB, the signal-to-noise ratio is increased to not less than 20dB, the bandwidth utilization rate is increased to not less than 80%, the latency is controlled within not more than 100ms, and the packet loss rate is reduced to not more than 1%;

[0042] Fault detection and repair steps: Real-time monitor the abnormal conditions of communication data, establish a fault diagnosis model, and use pattern recognition and data analysis technologies to timely identify communication faults such as signal interruption, severe interference, and equipment failures, with the detection accuracy of common faults not less than 95%. When a fault is detected, automatically take corresponding repair measures such as switching to a standby communication link, adjusting communication parameters, and restarting relevant equipment, with the repair success rate not less than 90%, and at the same time issue a fault alarm, with the alarm response time not exceeding 1 second;

[0043] Interference suppression steps: Use adaptive filtering algorithms and spectrum analysis technologies to real-time identify and suppress various interference signals during communication, such as electromagnetic interference and co-channel interference, reduce the impact of interference on communication quality, and improve the clarity and stability of signals. The signal-to-noise ratio after interference suppression is increased by no less than 5dB.

[0044] During the interference suppression process, the formula for calculating the interference suppression effect is: I = S before - S after ,

[0045] where I is the interference suppression amount, S before is the signal-to-noise ratio before interference suppression, Safter The signal-to-noise ratio after interference suppression.

[0046] User interaction operation steps: Provide a visual operation interface for users. Through this interface, users can view the communication status, historical data trends, and fault alarm information in real time, and can perform system parameter settings and control strategy selection operations. The response time of the interface operation does not exceed 0.5 seconds. At the same time, it supports historical data query and report generation functions, facilitating users to analyze and summarize the communication situation.

[0047] Preferably, before the large model analysis step, there is also a data preprocessing step to clean, denoise, and normalize the collected data, removing outliers and noise interference. The effective rate of the data after data cleaning reaches more than 98%, ensuring the quality and reliability of the data and providing an accurate data basis for the analysis of the large model.

[0048] Furthermore, in the adaptive control decision step, there is also a control strategy optimization step. According to the changes in the communication environment and the needs of users, the adaptive control strategy is optimized through a reinforcement learning algorithm to improve the adaptability and effectiveness of the control strategy. The convergence time of the strategy optimization does not exceed 5 minutes.

[0049] Furthermore, after the fault detection and repair step, there is also a fault record and analysis step to record the occurred faults in detail, including fault types, occurrence times, and repair measure information. By analyzing the fault records, fault patterns are summarized, providing a basis for the improvement and optimization of the system. The accuracy rate of the fault analysis is not less than 85%.

[0050] Furthermore, in the user interaction operation step, it supports users to customize the interface display content and layout. Users can, according to their own preferences and usage habits, choose to display the communication metrics and charts they are interested in, adjust the color and font settings of the interface, and the usage rate of the custom functions is not less than 70%.

[0051] Compared with the existing technologies, the beneficial effects of the present invention are:

[0052] Through a series of innovative designs and technical applications, the present invention has brought significant improvements in many aspects to remote communication.

[0053] By introducing an advanced large model analysis module and applying deep learning technology and an innovative prediction formula, the accurate prediction of the communication quality change trend is achieved, with a prediction accuracy rate of up to more than 85%. It can provide a basis for system adjustment in advance and effectively avoid the decline of communication quality. The multi-objective optimization function ensures the balanced optimization of multiple key quality indicators such as signal strength, signal-to-noise ratio, and bandwidth utilization rate in a complex communication environment, improving the overall performance of the communication system.

[0054] In terms of fault handling, the fault detection and repair module can quickly and accurately identify and handle various communication faults with high detection accuracy (not less than 95%) and a fast repair mechanism (repair success rate not less than 90%, alarm response time not exceeding 1 second), as well as an intelligent fault classification function. This greatly improves the reliability and stability of the system and reduces the impact of faults on communication services.

[0055] The interference suppression module uses an adaptive filtering algorithm and spectrum analysis technology, combined with a filtering coefficient update formula, to effectively suppress various interference signals, increasing the signal-to-noise ratio by no less than 5 dB, ensuring the clarity and stability of communication signals, and ensuring accurate data transmission.

[0056] The security encryption module uses advanced encryption algorithms, such as, to provide reliable security protection for communication data, meet industry standard requirements, have a high decryption success rate, prevent data from being stolen and tampered with, and protect user privacy and data security.

[0057] The user interface module provides an intuitive and convenient operation experience, supports multi-device adaptation, can adapt to the screen sizes and resolutions of different terminal devices, and allows users to customize the interface display content and layout, meeting personalized needs and improving users' control and operation efficiency of the communication system.

[0058] In summary, the present invention comprehensively improves the quality, reliability, security, and user experience of remote communication, promotes the development and application of remote communication technology, and has important practical significance and broad application prospects. Brief Description of the Drawings

[0059] Figure 1 It is a schematic block diagram of an adaptive remote communication control system based on a large model proposed by the present invention. Detailed Embodiments

[0060] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0061] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise" is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0062] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined. In addition, the terms "mounted", "connected" and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below with reference to the drawings.

[0063] Refer to Figure 1 : An adaptive remote communication control system based on a large model, comprising:

[0064] The communication data acquisition module plays a crucial fundamental role in the entire adaptive remote communication control system based on a large model. It is the key data source for the system to achieve precise control and optimization.

[0065] This module is dedicated to comprehensively and accurately collecting various rich data in the remote communication process in real time. Signal strength, as a key indicator to measure the strength of the communication signal, directly reflects the propagation ability and reception quality of the communication signal. Its acquisition not only includes the instant intensity value of the signal, but also covers the fluctuation of the signal strength at different time points, so that the system can promptly detect the change trend of the signal strength and provide a basis for subsequent adjustment decisions.

[0066] The signal-to-noise ratio is one of the important parameters to measure the quality of the communication signal, which reflects the proportional relationship between the signal and the noise. The module accurately obtains the signal-to-noise ratio data through a high-precision detection algorithm, helps the system distinguish the effective signal from the interference noise, thereby evaluating the quality of the communication and providing key information for optimizing the communication environment.

[0067] The bandwidth utilization rate reflects the usage of bandwidth resources in a communication link. The module monitors the occupancy of the bandwidth in real time, including the proportion of bandwidth occupied by different application programs or data transmission tasks, as well as the degree of bandwidth idle. Through the accurate collection of the bandwidth utilization rate, the system can reasonably allocate bandwidth resources, ensure the priority transmission of important data, and improve communication efficiency.

[0068] The data transmission rate directly determines the speed of information transmission. The module accurately measures the amount of data transmitted per second. Whether in peak hours or under low load conditions, it can accurately record the changes in the data transmission rate, so that the system can adjust the transmission strategy according to actual needs to ensure the smooth transmission of data.

[0069] The latency is a key factor affecting communication real-time. The module measures the time delay experienced by data from the sender to the receiver with a high-frequency sampling method, including the network transmission delay, device processing delay, and other delays in each link. For applications with high real-time requirements, such as video calls and online games, accurately grasping the latency can take timely measures to reduce the latency and improve the user experience.

[0070] The packet loss rate reflects the loss of data during transmission. The module accurately calculates the packet loss rate by comparing and counting the sent and received data. A high packet loss rate may lead to problems such as incomplete data and communication interruption. Therefore, accurately collecting the packet loss rate is crucial for timely discovering and solving network transmission problems.

[0071] The acquisition of signal spectral characteristics involves a detailed analysis of the distribution of the signal at different frequencies. The module obtains information such as the frequency composition, bandwidth, and power spectral density of the signal through spectral analysis technology, helping the system identify the interfering frequency components in the signal and understand the transmission characteristics of the signal in different frequency bands, providing a basis for frequency selection and interference suppression.

[0072] The channel fading characteristics are important parameters unique to wireless communication. The module collects relevant characteristics such as the amplitude, frequency, and time of channel fading through real-time monitoring and analysis of the wireless channel. Channel fading may cause changes and distortions in signal strength. Understanding the channel fading characteristics helps the system take corresponding compensation measures, such as adaptive modulation coding and power control, to ensure the stability of communication quality.

[0073] To ensure real-time and accurate perception of the communication status, the data acquisition frequency is not less than 10 times per second. Such a high acquisition frequency can capture subtle changes during the communication process and promptly detect potential problems and abnormal situations. At the same time, the accuracy of data acquisition reaches within ±0.3%, which means that the error between the acquired data and the actual value is extremely small, ensuring the reliability and effectiveness of the decisions and control measures made by the system based on these data. Through high-precision and high-frequency data acquisition, the communication data acquisition module provides a solid data foundation for the entire adaptive remote communication control system, enabling the system to more intelligently and precisely optimize the communication quality and ensure the stability and efficiency of remote communication;

[0074] As the core analysis component of the large model-based adaptive remote communication control system, the large model analysis module undertakes the key task of mining deep information from massive communication data and predicting the changing trend of communication quality, which is the key link to achieve intelligent adaptive control of the system.

[0075] This module is closely connected to the communication data acquisition module and obtains rich and diverse communication data in real time. The large model based on deep learning it uses is a complex neural network architecture with powerful computing and learning capabilities. This large model has a multi-layer neural network structure, which contains at least 8 hidden layers, and the number of neurons in each hidden layer is not less than 256. Such a deep and large-scale neural network structure provides sufficient capacity for the model to learn and represent complex patterns and potential laws in communication data.

[0076] During the training process of the model, it makes full use of a large amount of historical communication data for learning. These historical data cover multi-dimensional data such as signal strength, signal-to-noise ratio, bandwidth utilization rate, delay time, etc. under various different communication scenarios, environmental conditions, and network states, as well as their corresponding communication quality results. Through repeated learning and optimization adjustment of these massive historical data, the model gradually masters the internal correlations and changing trends in the data, and thus can accurately predict the future changing trend of communication quality.

[0077] To ensure the prediction accuracy and reliability of the model, a strict verification and evaluation mechanism is adopted. On the validation set, the prediction accuracy of the model is not less than 85%. The achievement of this high accuracy rate benefits from the deep architecture of the model, large-scale data training, and advanced optimization algorithms. During the learning process of the model, the connection weights and biases between neurons are continuously adjusted to minimize the error between the predicted value and the actual value. Through continuous iterative optimization, the model can gradually adapt to different communication data characteristics, accurately capture the subtle signals of communication quality changes, and thus provide accurate decision-making basis for subsequent adaptive control strategies.

[0078] Specifically, when analyzing communication data, the model can automatically extract high-level features from the data. For example, it can identify characteristic patterns such as periodic changes, trend changes, and abnormal fluctuations from the time-series data of signal strength; infer the type and intensity change trend of interference sources from the change in signal-to-noise ratio; understand the rules of network load and potential congestion risks from the dynamic change in bandwidth utilization, etc. The extraction and analysis of these high-level features enable the model to go beyond simple data statistical analysis, deeply understand the internal operation mechanism of the communication system, and thus achieve more accurate communication quality prediction.

[0079] In addition, the large model analysis module also has a certain self-adaptive learning ability. As new communication data continuously floods into the system, the model can update its own parameters and weights online in real time to adapt to the dynamic changes in the communication environment and the emergence of new patterns. This self-adaptive learning ability ensures that the model always maintains the ability to accurately capture the change trend of communication quality. Even in the face of complex and changing actual communication scenarios, it can provide timely and reliable analysis results and prediction information for the system, laying a solid foundation for the realization of efficient adaptive remote communication control.

[0080] In communication quality prediction, the prediction formula is used: Q t+1 = σ(W × X t + b), where Q t+1 is the predicted value of communication quality at time t + 1, σ is the ReLU activation function, W is the weight matrix, X t is the feature vector of communication data at time t, including various collected data and processed features, and b is the bias vector. By continuously training and optimizing W and b, the prediction accuracy can be improved.

[0081] The adaptive control module is the key execution link for realizing precise and dynamic optimization of communication quality in the large model-based adaptive remote communication control system. It closely depends on the analysis results of the large model and ensures that the communication system always maintains an efficient and stable operating state in various complex environments through intelligent decision-making and real-time adjustment.

[0082] Based on the in-depth analysis results provided by the large model, this module formulates highly intelligent adaptive control strategies. These strategies cover the fine-tuning of multiple key communication parameters, aiming to comprehensively optimize communication quality to cope with the changing communication environment and business requirements.

[0083] In terms of communication parameter adjustment, the choice of modulation method directly affects the anti-interference ability and transmission efficiency of signals during transmission. The module intelligently switches between different modulation methods according to the real-time communication status. For example, it switches from a relatively simple modulation method (such as BPSK) to ensure basic communication in a low signal-to-noise ratio environment, to a complex modulation method (such as QAM) to increase the data transmission rate when the channel conditions are good. The adjustment of the coding rate focuses on finding a balance between data reliability and transmission efficiency. When the channel quality deteriorates, the coding rate is reduced to increase redundant information and improve the data error correction ability to ensure the accurate transmission of information; while when the channel quality is good, the coding rate is increased to reduce redundancy and improve the transmission efficiency.

[0084] The control of the transmission power is of great significance for optimizing communication quality and reducing energy consumption. The adaptive control module adjusts the transmission power in real time dynamically according to factors such as signal strength, distance, and interference. While ensuring that the signal strength is stable within the set range (the fluctuation amplitude does not exceed ±3dB), it avoids excessive transmission power causing energy waste and interference to other devices, and also prevents insufficient transmission power from leading to a decline or interruption in communication quality. Bandwidth allocation is another important control dimension. The module reasonably allocates bandwidth resources according to the priorities of different applications and the real-time data traffic requirements. Applications with high real-time requirements (such as video conferencing, online games) are preferentially allocated sufficient bandwidth to ensure their smooth operation; at the same time, reasonable flow limiting is performed on other non-critical applications to improve the overall bandwidth utilization rate, which is increased to no less than 80%.

[0085] Channel selection is one of the key decisions in adaptive control. The module comprehensively considers various factors such as the signal quality, interference level, and historical stability of the channel, and selects the optimal channel for communication from multiple available channels. By real-time monitoring and evaluating the status of each channel, it timely switches to a channel with better quality to avoid communication problems caused by the deterioration of the channel quality and ensure the stability and reliability of data transmission.

[0086] In setting the goal of optimizing communication quality, the module has clear and strict requirements. By precisely adjusting communication parameters, it is committed to ensuring that the signal strength is stably within the set ideal range, with its fluctuation amplitude strictly controlled within no more than ±3dB. This enables the receiving end to always receive signals with a stable strength, reducing data loss and increased error rate caused by signal fluctuations. The signal-to-noise ratio is increased to no less than 20dB, effectively improving the signal clarity and anti-interference ability, and ensuring the accuracy of data transmission. The bandwidth utilization rate is increased to no less than 80%, giving full play to the efficiency of network bandwidth resources and meeting the data transmission rate requirements of various applications. The latency time is controlled within no more than 100ms, which is crucial for real-time interactive applications, ensuring that users can hardly feel obvious latency during communication and enhancing the user experience. The packet loss rate is reduced to no more than 1%, greatly reducing the situation of data loss and ensuring the integrity and reliability of data transmission.

[0087] To achieve these goals, the adaptive control module adopts advanced algorithms and a real-time feedback mechanism. It continuously receives real-time data from the communication data acquisition module, evaluates the gap between the current communication quality and the goal based on this data in real time, and quickly adjusts the control strategy. At the same time, the module maintains close interaction with the large model analysis module, makes corresponding adjustment preparations in advance according to the prediction of the large model on the changing trend of the communication environment, and realizes forward-looking optimization control, so as to ensure that the communication system can always operate in the best state and provide users with high-quality, stable and reliable remote communication services.

[0088] In channel selection, the following selection formula based on channel quality assessment is adopted:

[0089] C i =α×S i +β×N i +γ×B i

[0090] where C i is the comprehensive evaluation value of the i-th channel, S i is the signal strength index of this channel, N i is the signal-to-noise ratio index, B i is the available bandwidth index, and α, β, γ are weight coefficients determined according to actual needs and experience. By calculating the C i value of each channel, select the channel with the largest C i for communication.

[0091] The fault detection and repair module is an important part of the adaptive remote communication control system based on the large model to ensure communication reliability and stability. It is like the "health guard" of the system, always guarding the normal operation of the communication link and ensuring that it can quickly respond and effectively solve problems when faults occur.

[0092] This module always maintains real-time monitoring of communication data without missing any abnormal situations. By establishing an advanced fault diagnosis model and applying a variety of intelligent data analysis techniques and algorithms, it deeply analyzes and compares all dimensions of communication data. These data include, but are not limited to, sudden changes in signal strength, sharp drops in signal-to-noise ratio, abnormal fluctuations in bandwidth utilization, sudden decreases in data transmission rate, significant increases in latency time, and increases in packet loss rate, etc. Through real-time monitoring and analysis of these data characteristics, the module can accurately identify various communication faults in a timely manner, such as common signal interruptions, severe interference, and equipment failures.

[0093] In terms of fault detection ability, the detection accuracy rate for common faults is not less than 95%. This high accuracy rate benefits from its precise fault diagnosis model and efficient algorithms. The module can not only accurately judge a single fault symptom but also identify some complex and potential fault hazards through comprehensive analysis of multiple related data indicators. For example, when the signal strength suddenly drops and is accompanied by an increase in latency time and an increase in packet loss rate at the same time, the module can quickly determine that it may be due to a failure of a key device or severe interference in the communication link, rather than simply attributing it to a signal problem.

[0094] Once a fault is detected, the module will immediately automatically start a repair mechanism and adopt a variety of effective repair strategies. Among them, switching to an alternative communication link is a common and efficient method. The module is pre-configured with multiple alternative links and monitors their status in real time. When the primary link fails, it can automatically switch to the alternative link within an extremely short time (usually in milliseconds) to ensure the continuity of communication. At the same time, the module will also try to adjust communication parameters, such as adjusting the modulation method, coding rate, transmit power, etc. according to the current channel conditions, to adapt to the changing environment and restore normal communication. For problems that may be caused by a short-term device failure or software anomaly, the module will automatically restart the relevant device to eliminate the fault through re-initializing the device. Through these comprehensive repair measures, the repair success rate is not less than 90%, greatly improving the reliability and availability of the system.

[0095] At the same time as a fault occurs, the module will promptly issue a fault alarm to notify relevant management and maintenance personnel of the fault situation. The alarm response time does not exceed 1 second to ensure that the problem can be promptly attended to and addressed. The alarm information includes key information such as the detailed fault type, occurrence time, and possible impact scope, helping maintenance personnel quickly locate the problem and take corresponding measures for repair. In addition, the module will also record the entire process of the fault occurrence in detail, including the communication data status before the fault, the repair measures taken, and the effects after repair, providing valuable data support for subsequent fault analysis and system optimization. By continuously accumulating and analyzing these fault data, the module can continuously optimize its fault diagnosis model and repair strategy, further improving the efficiency and accuracy of fault detection and repair, and providing a strong guarantee for the stable operation of the remote communication system.

[0096] In fault diagnosis, the following fault judgment formula based on probability statistics is adopted:

[0097]

[0098] Where P(F) is the probability of fault F occurring, n(F) is the number of times fault F is detected within a certain period of time, and n(T) is the total number of detections. When P(F) exceeds the set threshold, it is judged that fault F has occurred.

[0099] The interference suppression module is used to identify and suppress various interference signals in the communication process in real time, such as electromagnetic interference and co-frequency interference. By adopting an adaptive filtering algorithm and spectrum analysis technology, it can effectively reduce the impact of interference on communication quality and improve the clarity and stability of the signal. The improvement amplitude of the signal-to-noise ratio after interference suppression is not less than 5 dB.

[0100] In adaptive filtering, the following filtering coefficient update formula is adopted:

[0101] w n+1 = w n + μ × e n × x n

[0102] Where w n+1 is the filtering coefficient vector for the (n + 1)-th iteration, w n is the filtering coefficient vector for the n-th iteration, μ is the step size factor, e n is the error signal, and x n is the input signal vector. By continuously updating the filtering coefficient, effective suppression of interference signals is achieved.

[0103] The user interface module provides an intuitive communication status monitoring interface for users, displaying real-time communication data, quality index trend charts, and fault alarm information. Users can perform system parameter settings and control strategy selection operations through the interface, and the response time of the interface operation does not exceed 0.5 seconds, ensuring the timeliness and fluency of operations. It also has the functions of historical data query and report generation, facilitating users to review and analyze communication situations.

[0104] The security encryption module ensures the security and confidentiality of communication data. It uses advanced encryption algorithms to encrypt the transmitted data, preventing data from being stolen and tampered with. The security of the encrypted communication data meets the industry standard requirements, and the decryption success rate is not less than 98%.

[0105] In data encryption, the following encryption formula is used:

[0106] E(m,k)=c

[0107] Where E is the encryption function, m is the original data, k is the encryption key, and c is the encrypted data. When decrypting, the original data is restored through the corresponding decryption function D(c, k)=m.

[0108] In the present invention, the large model analysis module has the function of model self-update. As new communication data continuously pours in, it can automatically perform online update and optimization of the model, and the prediction accuracy of the model on new data increases by no less than 3% after each update.

[0109] In the present invention, the adaptive control module supports multi-objective optimization. When adjusting communication parameters, it can take into account the optimization of multiple communication quality indicators simultaneously. By establishing a multi-objective optimization function:

[0110] F=w1×Q1+w2×Q2+…+w n ×Q n

[0111] Where F is the optimization objective function, Q1...Q n is the 1-nth communication quality indicator, and w1...w n is its corresponding weight coefficient. The weight coefficient is dynamically adjusted according to actual needs to achieve balanced optimization of different quality indicators.

[0112] In the adaptive remote communication control system based on the large model of the present invention, the intelligent fault classification function of the fault detection and repair module is a highly innovative and practical design, which greatly improves the efficiency and accuracy of fault repair and plays a key role in ensuring the stable operation of the communication system.

[0113] This module can conduct a comprehensive and detailed classification of the detected faults. First, it is divided according to the type of faults, clearly distinguished as hardware faults and software faults. Hardware faults cover problems that occur in various physical components of communication devices, such as sensor faults, antenna damage, chip faults, power module abnormalities, etc. For sensor faults, it may be manifested as inaccurate or completely uncollectible data; antenna damage may lead to a significant decrease in signal reception or transmission intensity; chip faults may affect the overall operation stability of the device, resulting in data processing errors or device crashes; power module abnormalities may cause unstable power supply to the device, affecting its normal operation. Software faults involve problems in the programs, algorithms, and related configuration files running in the communication system, such as operating system crashes, application errors, driver incompatibilities, communication protocol errors, etc. An operating system crash will cause the entire device to fail to start or operate normally; application errors may lead to the inability to use specific functions normally or data processing errors; driver incompatibilities may cause hardware devices to fail to work properly or have degraded performance; communication protocol errors may result in incorrect data transmission formats or the inability to communicate normally.

[0114] In addition to classification by type, the module will further subdivide according to the severity of the faults. The faults are divided into different levels such as minor faults and severe faults. Minor faults usually have a relatively small impact on communication quality, but if not dealt with in a timely manner, they may gradually deteriorate. For example, a minor data packet loss at a certain communication node may not have an obvious impact on the overall communication temporarily, but if it persists, it may lead to damaged data integrity or affect applications with high real-time requirements. For such minor faults, the module can adopt relatively mild repair strategies, such as temporarily adjusting the data transmission path, adding some redundancy check mechanisms, or performing background software repair and parameter optimization without affecting normal communication. Severe faults will have a greater impact on the communication system and may even cause communication interruption. For example, a complete interruption of the main communication link, hardware damage to key devices, large-scale severe interference, etc. For such severe faults, the module will immediately activate the emergency repair mechanism to prioritize the restoration of communication. This may include quickly switching to the backup communication link, notifying relevant maintenance personnel to conduct on-site hardware repairs, and backing up and restoring the affected data to minimize the impact of the fault on the business.

[0115] Through this intelligent fault classification function, the fault detection and repair module can more accurately adopt corresponding repair strategies for different types and severities of faults. For hardware faults, according to the specific hardware components and fault manifestations, the module can automatically generate a detailed fault report and notify the relevant hardware maintenance personnel to carry the corresponding tools and spare parts for on-site repair. Meanwhile, during the waiting period for repair, the module will try to alleviate the impact of the fault through some emergency measures, such as adjusting communication parameters to bypass some functions of the faulty hardware, or enabling standby hardware modules (if any). For software faults, the module can automatically attempt operations such as reinstalling, upgrading, and rolling back the software, or repairing and resetting the incorrect configuration files. For severe software faults, the module will promptly back up important data and notify the software R & D personnel for remote assistance or on-site debugging.

[0116] In the present invention, the user interface module supports multi-device adaptation, can stably operate on different types of terminal devices (such as computers, tablets, mobile phones), the display effect adapts to the screen sizes and resolutions of different devices, and the interface layout and operation methods are optimized according to the device characteristics to ensure that users can conveniently use the system for remote communication control on various devices.

[0117] In the present invention, an adaptive remote communication control method based on a large model includes the following steps:

[0118] Communication data collection step: Using specialized communication data collection devices and technologies, various data in the remote communication process are collected in real time, including signal strength, signal-to-noise ratio, bandwidth utilization rate, data transmission rate, delay time, packet loss rate, signal spectrum characteristics, and channel fading characteristics, ensuring that the data collection frequency is not less than 10 times per second, and the data accuracy reaches within ±0.3%;

[0119] Large model analysis step: The collected communication data is input into a large model based on deep learning for analysis. This large model, through pre-training on a large amount of historical communication data, can mine the potential features and rules in the data, accurately predict the change trend of communication quality, and adopt optimized algorithms such as the stochastic gradient descent algorithm to adjust the model parameters during the prediction process to improve the prediction accuracy, and the prediction accuracy on the validation set is not less than 85%;

[0120] Adaptive control decision-making steps: Based on the analysis results of the large model, formulate an adaptive control strategy to adjust communication parameters in real time, including modulation mode, coding rate, transmit power, bandwidth allocation, and channel selection, to optimize communication quality. During the adjustment process, continuously feedback and adjust the control strategy by monitoring the changes in communication quality indicators in real time to ensure that the signal strength is stable within the set range, the fluctuation amplitude does not exceed ±3 dB, the signal-to-noise ratio is increased to not less than 20 dB, the bandwidth utilization rate is increased to not less than 80%, the delay time is controlled within not more than 100 ms, and the packet loss rate is reduced to not more than 1%.

[0121] Fault detection and repair steps: Monitor the abnormal conditions of communication data in real time. By establishing a fault diagnosis model and using pattern recognition and data analysis techniques, identify communication faults in a timely manner, such as signal interruption, severe interference, and equipment failure. The detection accuracy rate of common faults is not less than 95%. When a fault is detected, automatically take corresponding repair measures, such as switching to a standby communication link, adjusting communication parameters, and restarting relevant equipment. The repair success rate is not less than 90%. At the same time, send a fault alarm, and the alarm response time does not exceed 1 second.

[0122] Interference suppression steps: Adopt adaptive filtering algorithms and spectrum analysis techniques to identify and suppress various interference signals in the communication process in real time, such as electromagnetic interference and co-channel interference, reduce the impact of interference on communication quality, and improve the clarity and stability of the signal. The signal-to-noise ratio improvement amplitude after interference suppression is not less than 5 dB.

[0123] During the interference suppression process, the formula for calculating the interference suppression effect is: I = S before - S after ,

[0124] where I is the interference suppression amount, S before is the signal-to-noise ratio before interference suppression, and S after is the signal-to-noise ratio after interference suppression.

[0125] User interaction operation steps: Provide a visual operation interface for users. Users can view the communication status, historical data trends, and fault alarm information in real time through this interface, and can also perform system parameter settings and control strategy selection operations. The response time of the interface operation does not exceed 0.5 seconds. At the same time, it supports historical data query and report generation functions to facilitate users to analyze and summarize the communication situation.

[0126] Preferably, before the large model analysis step, a data preprocessing step is further included to clean, denoise, and normalize the collected data, remove outliers and noise interference. The data efficiency after data cleaning reaches more than 98% to ensure the quality and reliability of the data and provide an accurate data basis for the analysis of the large model.

[0127] In the present invention, in the adaptive control decision-making step, a control strategy optimization step is further included. According to the changes in the communication environment and the user's requirements, the adaptive control strategy is optimized through a reinforcement learning algorithm to improve the adaptability and effectiveness of the control strategy, and the convergence time of the strategy optimization does not exceed 5 minutes.

[0128] In the present invention, after the fault detection and repair step, a fault recording and analysis step is further included. The occurring faults are recorded in detail, including the fault type, occurrence time, and repair measure information. By analyzing the fault records, the fault patterns are summarized to provide a basis for the improvement and optimization of the system, and the accuracy rate of the fault analysis is not less than 85%.

[0129] In the present invention, in the user interaction operation step, the user is supported to customize the interface display content and layout. The user can, according to their own preferences and usage habits, select to display the communication metrics and charts of interest, adjust the interface color and font settings, and the usage rate of the custom functions is not less than 70%.

[0130] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, with the same substitution or change, should be covered by the protection scope of the present invention.

Claims

1. An adaptive remote communication control system based on a large model, characterized in that: include: Communication data acquisition module, used to collect various data in the remote communication process in real time, including signal strength, signal-to-noise ratio, bandwidth utilization, data transmission rate, delay time, packet loss rate, signal spectrum characteristics, and channel fading characteristics; The large model analysis module is connected to the communication data acquisition module and uses a large model based on deep learning to analyze the collected communication data. The large model has a multi-layer neural network structure, including at least 8 hidden layers, and the number of neurons in each hidden layer is not less than 256; In the communication quality prediction, the prediction formula is used: Q t+1 =σ(W×X t +b), where Q t+1 is the predicted value of communication quality at time t+1, σ is the ReLU activation function, W is the weight matrix, X t is the communication data feature vector at time t, including various collected data and processed features, and b is the bias vector; The adaptive control module formulates adaptive control strategies based on the analysis results of the large model and makes real-time adjustments to communication parameters, including modulation mode, coding rate, transmission power, bandwidth allocation, and channel selection; In channel selection, the following selection formula based on channel quality assessment is adopted: C i =α×S i +β×N i +γ×B i Among them C i is the comprehensive evaluation value of the ith channel, S i is the signal strength index of the channel, N i is the signal-to-noise ratio indicator, B i is the bandwidth availability index, α, β, and γ are weight coefficients, which are determined according to actual needs and experience. i Value, select C i The largest channel for communication; Fault detection and repair module, which monitors abnormal conditions of communication data in real time and establishes fault diagnosis models, including signal interruption, severe interference, and equipment failure; In fault diagnosis, the following fault judgment formula based on probability statistics is used: Where P(F) is the probability of fault F occurring, n(F) is the number of times fault F is detected within a certain period of time, and n(T) is the total number of detections. When P(F) exceeds the set threshold, it is determined that fault F has occurred. Interference suppression module is used to identify and suppress various interference signals in the communication process in real time, including electromagnetic interference and co-frequency interference. By adopting adaptive filtering algorithm and spectrum analysis technology, the signal-to-noise ratio after interference suppression is improved by no less than 5dB; In adaptive filtering, the following filter coefficient update formula is used: In n+1 =in n +μ×e n ×x n where w n+1 is the filter coefficient vector of the n+1th iteration, w n is the nth filter coefficient vector, μ is the step size factor, e n is the error signal, x n The input signal vector is used to effectively suppress interference signals by continuously updating the filter coefficients. The user interface module provides users with an intuitive communication status monitoring interface that displays real-time communication data, quality indicator trend charts, and fault alarm information; The security encryption module ensures the security and confidentiality of communication data. It uses advanced encryption algorithms to encrypt the transmitted data to prevent data from being stolen and tampered with. In data encryption, the following encryption formula is used: E(m, k) = c Wherein E is the encryption function, m is the original data, k is the encryption key, and c is the encrypted data. During decryption, the original data is restored through the corresponding decryption function D(c, k)=m.

2. According to the large model-based adaptive remote communication control system described in claim 1, the large model analysis module has a model self-update function. With the continuous influx of new communication data, the model can be automatically updated and optimized online. After each update, the prediction accuracy of the model on the new data is improved by no less than 3%.

3. According to the large model-based adaptive remote communication control system of claim 1, the adaptive control module supports multi-objective optimization. When adjusting communication parameters, it can simultaneously take into account the optimization of multiple communication quality indicators, by establishing a multi-objective optimization function: F=w1×Q1+w2×Q2+···+w n ×Q n Where F is the optimization objective function, Q1...Q n are the 1st to nth communication quality indicators, w1...w n The corresponding weight coefficient is dynamically adjusted according to actual needs to achieve balanced optimization of different quality indicators.

4. According to the large model-based adaptive remote communication control system described in claim 1, the fault detection and repair module has an intelligent fault classification function, which classifies the detected faults according to type and severity, and divides them into hardware faults, software faults, minor faults, and major faults, and adopts corresponding repair strategies according to different classifications to improve the efficiency and accuracy of fault repair.

5. According to the large model-based adaptive remote communication control system described in claim 1, the user interface module supports multi-device adaptation, runs stably on different types of terminal devices, the display effect adapts to the screen size and resolution of different devices, and the interface layout and operation method are optimized according to the characteristics of the device, ensuring that users can conveniently use the system for remote communication control on various devices.

6. A method for applying the large model-based adaptive remote communication control system according to any one of claims 1 to 5, characterized in that: The following steps are involved: Communication data collection steps: Use specialized communication data collection equipment and technology to collect various data in the remote communication process in real time, including signal strength, signal-to-noise ratio, bandwidth utilization, data transmission rate, delay time, packet loss rate, signal spectrum characteristics, channel fading characteristics, and ensure that the frequency of data collection is not less than 10 times / second and the accuracy of the data is within ±0.3%; Big model analysis steps: input the collected communication data into a big model based on deep learning for analysis. The big model can mine the potential features and rules in the data and accurately predict the changing trend of communication quality by pre-training a large amount of historical communication data. In the prediction process, the optimization algorithm and stochastic gradient descent algorithm are used to adjust the model parameters to improve the prediction accuracy. The prediction accuracy on the validation set is not less than 85%; Adaptive control decision-making steps: According to the analysis results of the large model, formulate an adaptive control strategy to adjust the communication parameters in real time, including modulation mode, coding rate, transmission power, bandwidth allocation, and channel selection to optimize communication quality. During the adjustment process, by real-time monitoring of changes in communication quality indicators, continuous feedback adjustment of the control strategy is carried out to ensure that the signal strength is stable within the set range, the fluctuation range does not exceed ±3dB, the signal-to-noise ratio is increased to no less than 20dB, the bandwidth utilization rate is increased to no less than 80%, the delay time is controlled to no more than 100ms, and the packet loss rate is reduced to no more than 1%; Fault detection and repair steps: Real-time monitoring of abnormal communication data, timely identification of communication faults by establishing fault diagnosis models, and applying pattern recognition and data analysis technologies. The detection accuracy of common faults is not less than 95%. When a fault is detected, corresponding repair measures are automatically taken, with a repair success rate of not less than 90%. At the same time, a fault alarm is issued, and the alarm response time does not exceed 1 second; Interference suppression steps: Adopt adaptive filtering algorithm and spectrum analysis technology to identify and suppress various interference signals in the communication process in real time, including electromagnetic interference and co-frequency interference, reduce the impact of interference on communication quality, improve signal clarity and stability, and the signal-to-noise ratio after interference suppression is improved by no less than 5dB; In the interference suppression process, the formula for calculating the interference suppression effect is: I = S before -S after , Where I is the interference suppression amount, S before is the signal-to-noise ratio before interference suppression, S after is the signal-to-noise ratio after interference suppression; User interactive operation steps: Provide users with a visual operation interface, through which users can view communication status, historical data trends, fault alarm information in real time, and can set system parameters and select control strategies. The response time of interface operations does not exceed 0.5 seconds. It also supports historical data query and report generation functions, which is convenient for users to analyze and summarize communication conditions.

7. According to the method of adaptive remote communication control system based on large model described in claim 6, before the large model analysis step, it also includes a data preprocessing step, which cleans, denoises and normalizes the collected data to remove outliers and noise interference. The data efficiency after data cleaning reaches more than 98%, ensuring the quality and reliability of the data and providing an accurate data basis for the analysis of the large model.

8. According to the method of adaptive remote communication control system based on large model described in claim 6, in the adaptive control decision step, it also includes a control strategy optimization step, according to the changes in the communication environment and the needs of users, the adaptive control strategy is optimized through the reinforcement learning algorithm to improve the adaptability and effectiveness of the control strategy, and the convergence time of the strategy optimization does not exceed 5 minutes.

9. According to the method of adaptive remote communication control system based on large model described in claim 6, after the fault detection and repair step, it also includes a fault recording and analysis step, which records the occurred faults in detail, including the fault type, occurrence time, and repair measures information. By analyzing the fault records, the fault laws are summarized to provide a basis for the improvement and optimization of the system. The accuracy of fault analysis is not less than 85%.

10. According to the method of the large model-based adaptive remote communication control system described in claim 6, in the user interaction operation step, it supports users to customize the interface display content and layout. Users can choose to display communication indicators and charts of interest according to their preferences and usage habits, and adjust the color and font settings of the interface. The usage rate of custom functions is not less than 70%.

Images