Adaptive large model parameter fine-tuning method and system based on end-cloud collaboration

Abstract

The present invention relates to a method and system for adaptive large-scale model parameter fine-tuning based on end-cloud collaboration. The method comprises: setting an edge end and a cloud end to train a large model, forming an end-cloud collaborative architecture to realize distributed processing of model training, utilizing the instant data processing capability of the edge end and the powerful computing resources of the cloud end to improve the efficiency of model fine-tuning; introducing an adaptive parameter optimization mechanism to dynamically adjust the update strategy of the model parameters according to the performance of the model on different ends, thereby ensuring the efficient use of the model parameters; through key exchange protocols, encryption operations, and data obfuscation technologies, ensuring the security and privacy of data during the model fine-tuning process; the dynamic adjustment strategy of the model fine-tuning adjusts the training load and resource allocation of the model in real time according to the performance feedback of each end in the end-cloud collaborative architecture, and can flexibly adapt to different operating environments and task requirements.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for fine-tuning parameters of an adaptive large model based on end-cloud collaboration. Background Art

[0002] With the development of society and the continuous improvement of people's living standards, data processing methods are becoming more diverse. In the field of artificial intelligence, large-scale models (LLMs) have attracted much attention due to their excellent natural language processing capabilities and are widely used in tasks such as text understanding, language translation, and question answering. However, when LLMs are applied to specific tasks, they often require fine-tuning to adapt to the specific data distribution and task requirements. Existing fine-tuning methods rely on large amounts of labeled data and computing resources, which has some limitations in practical applications.

[0003] Specifically, existing technologies face three core issues: First, existing fine-tuning methods typically require large-scale datasets to train models, which poses challenges in terms of data privacy and security. In application scenarios such as healthcare and financial services, data is often sensitive and cannot be used directly for model training. Second, existing fine-tuning methods have high demands on computing resources. Training large models requires a lot of computing power, which usually requires the use of high-performance GPU clusters, but these resources are not widely available among many institutions and individual developers. In addition, each fine-tuning requires a large amount of electricity and time, which is impractical in resource-limited environments. Furthermore, existing end-cloud collaborative solutions have not fully considered the efficient utilization of model parameters and cross-device data privacy protection in the fine-tuning of LLMs. Existing solutions mainly focus on distributed model training and knowledge distillation technology, but ignore the refined management of model parameters and strict protection of data privacy, resulting in inefficiency and the risk of privacy leakage in practical applications.

[0004] In summary, the traditional large model parameter fine-tuning method has low adjustment efficiency and problems of unreliable and insecure data during the adjustment process. Summary of the Invention

[0005] Based on this, in order to solve the above technical problems, a method and system for adaptive large model parameter fine-tuning based on end-cloud collaboration is provided, which can achieve a more efficient, safer and more reliable model fine-tuning process.

[0006] A method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration, the method comprising:

[0007] Collecting large model training data through the edge end, preprocessing the large model training data, performing preliminary large model training based on the preprocessed data to obtain a preliminary large model; identifying key frames through the edge end, and obtaining prediction results based on the key frames and the preliminary large model;

[0008] The encryption key is exchanged between the edge and the cloud through a key exchange protocol; on the edge, a symmetric encryption algorithm is used to encrypt the transmission data to be transmitted to the cloud, and data obfuscation technology is introduced on the basis of data encryption; on the edge, a message authentication code is used to verify the integrity of the transmission data;

[0009] The cloud collects performance feedback from each of the edge terminals, evaluates the training load of each of the edge terminals based on the performance feedback, dynamically adjusts resource allocation for each of the edge terminals based on the training load, and updates the model fine-tuning strategy for each of the edge terminals based on the resource allocation result;

[0010] Receiving, via the cloud, the encrypted transmission data transmitted from the edge, and decrypting the transmission data to obtain the key frame and the prediction result; fine-tuning the parameters of the preliminary large model based on the key frame according to the model fine-tuning strategy, and optimizing the parameters of the fine-tuned preliminary large model based on the prediction result to obtain an optimized large model;

[0011] The optimized large model is evaluated according to performance evaluation indicators, and parameter updates are triggered according to the evaluation results; the performance indicators of the optimized large model in the cloud and the edge are monitored and collected in real time, the model parameter update strategy is dynamically adjusted according to the performance indicators, and the model parameter update frequency is determined; the large model parameters are adjusted based on the model parameter update strategy and the model parameter update frequency.

[0012] In one embodiment, the edge end preprocesses the large model training data, performs preliminary large model training based on the preprocessed data, and obtains a preliminary large model, including:

[0013] At the edge, performing preprocessing operations of denoising, normalization, and data enhancement on the large model training data to obtain preprocessed data;

[0014] Performing a feature extraction operation on the preprocessed data to extract model training features;

[0015] The model training features are used to perform preliminary training of the large model to obtain a preliminary large model.

[0016] In one embodiment, identifying key frames by the edge end and obtaining prediction results based on the key frames and the preliminary large model include:

[0017] A characteristic value threshold is set at the edge end to determine the characteristic value corresponding to the model training feature;

[0018] Based on the eigenvalue threshold, the frame with the largest eigenvalue change is taken as the key frame;

[0019] The edge end obtains model parameters according to the preliminary large model, and generates prediction results based on the model parameters and the key frames.

[0020] In one embodiment, the method further comprises:

[0021] The edge end uses a message authentication code to verify the integrity of the transmitted data, and after the verification is passed, the transmitted data is sent to the cloud;

[0022] The cloud receives the transmitted data and verifies the transmitted data using the same key as that of the edge to obtain an integrity verification result.

[0023] In one embodiment, the cloud collects performance feedback from each of the edge terminals, including:

[0024] The cloud side collects the training loss value, processing time, and model accuracy of the preliminary large model in each of the edge terminals;

[0025] The cloud obtains a performance feedback set of each of the edge terminals based on the training loss value, processing time, and model accuracy.

[0026] In one embodiment, the cloud evaluates the training load of each edge terminal based on the performance feedback, including:

[0027] The cloud determines the number of edge terminals based on the connection relationship with each edge terminal, and obtains the training loss value and processing time of each edge terminal according to the performance feedback;

[0028] The cloud side evaluates the training load of each of the edge terminals based on the training loss value and processing time.

[0029] In one embodiment, the cloud updates the model fine-tuning strategy of each edge terminal based on the resource allocation result, including:

[0030] The cloud end adjusts the model learning rate based on the resource allocation result and the performance feedback;

[0031] The cloud end collects the updated model parameters of each of the edge ends;

[0032] The cloud end updates the model fine-tuning strategy of each of the edge ends according to the model learning rate and the model parameters.

[0033] In one embodiment, the real-time monitoring collects performance indicators of the optimized large model on the cloud and the edge, dynamically adjusts the model parameter update strategy based on the performance indicators, and determines the model parameter update frequency, including:

[0034] Using a performance monitoring function, the accuracy and loss values ​​of the optimized large model on the cloud and the edge are monitored and collected respectively, and the accuracy and loss values ​​are used as performance indicators of the large model;

[0035] Constructing a multi-factor trade-off model, inputting the performance indicator into the multi-factor trade-off model, and dynamically adjusting a model parameter update strategy through the multi-factor trade-off model;

[0036] Obtaining a performance change amount and a performance change threshold of the optimized large model based on the performance index; and determining a frequency control coefficient;

[0037] The model parameter update frequency is determined according to the performance change amount, the performance change threshold, and the frequency control coefficient.

[0038] In one embodiment, the cloud fine-tunes parameters of the preliminary large model based on the key frames according to the model fine-tuning strategy, and optimizes parameters of the fine-tuned preliminary large model based on the prediction results to obtain an optimized large model, including:

[0039] The cloud determines the learning rate corresponding to the preliminary large model according to the model fine-tuning strategy, and obtains the gradient data of the loss function with respect to the model parameters in the preliminary large model;

[0040] The cloud uses the key frames to fine-tune the parameters of the preliminary large model according to the learning rate and gradient data, and uses the prediction results as verification conditions to optimize the parameters of the fine-tuned preliminary large model;

[0041] The cloud end globally optimizes the preliminary large model according to the key frames and the prediction results to obtain an optimized large model.

[0042] An adaptive large model parameter fine-tuning system based on end-cloud collaboration, the system comprising:

[0043] The edge end is used to collect large model training data, preprocess the large model training data, perform preliminary large model training based on the preprocessed data, and obtain a preliminary large model; identify key frames through the edge end, and obtain prediction results based on the key frames and the preliminary large model;

[0044] The encryption key is exchanged between the edge and the cloud through a key exchange protocol; the edge is further used to: encrypt the transmission data to be transmitted to the cloud using a symmetric encryption algorithm, and introduce data obfuscation technology based on the data encryption; and verify the integrity of the transmission data using a message authentication code on the edge;

[0045] The cloud is configured to collect performance feedback from each of the edge terminals, evaluate the training load of each of the edge terminals based on the performance feedback, dynamically adjust resource allocation for each of the edge terminals based on the training load, and update the model fine-tuning strategy for each of the edge terminals based on the resource allocation results;

[0046] The cloud is further configured to receive the encrypted transmission data transmitted from the edge, decrypt the transmission data to obtain the key frame and the prediction result; fine-tune the parameters of the preliminary large model based on the key frame according to the model fine-tuning strategy, and optimize the parameters of the fine-tuned preliminary large model based on the prediction result to obtain an optimized large model;

[0047] The control end is used to evaluate the optimized large model according to the performance evaluation indicators and trigger parameter updates according to the evaluation results; monitor and collect the performance indicators of the optimized large model in the cloud and the edge in real time, dynamically adjust the model parameter update strategy according to the performance indicators, and determine the model parameter update frequency; adjust the large model parameters based on the model parameter update strategy and model parameter update frequency.

[0048] The above-mentioned adaptive large model parameter fine-tuning method and system based on end-cloud collaboration, by setting up the edge and cloud to train the large model, forms an end-cloud collaborative architecture to realize distributed processing of model training, and utilizes the real-time data processing capabilities of the edge and the powerful computing resources of the cloud to improve the efficiency of model fine-tuning; introduces an adaptive parameter optimization mechanism, dynamically adjusts the update strategy of model parameters according to the performance of the model on different ends, and ensures the efficient use of model parameters; through key exchange protocols, encryption operations, and data obfuscation technology, ensures the security and privacy of data during the model fine-tuning process; the dynamic adjustment strategy of model fine-tuning adjusts the model training load and resource allocation in real time according to the performance feedback of each end in the end-cloud collaborative architecture, and can flexibly adapt to different operating environments and task requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a diagram illustrating an application environment of an adaptive large model parameter fine-tuning method based on end-cloud collaboration in one embodiment;

[0050] Figure 2 1 is a flow chart of a method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration in one embodiment;

[0051] Figure 3 This is a structural block diagram of an adaptive large model parameter fine-tuning system based on end-cloud collaboration in one embodiment;

[0052] Figure 4 A schematic diagram of the network structure of a device-cloud collaborative architecture in one embodiment;

[0053] Figure 5 A schematic diagram of the structure of an adaptive parameter optimization mechanism in one embodiment;

[0054] Figure 6 A schematic diagram of a privacy-preserving data transmission protocol for ensuring data security and privacy in one embodiment;

[0055] Figure 7 A schematic diagram of the structure of a model fine-tuning dynamic adjustment strategy in one embodiment;

[0056] Figure 8 A schematic diagram of a program flow for fine-tuning large model parameters under a device-cloud collaborative architecture in one embodiment;

[0057] Figure 9 This is a flowchart of an embodiment of an adaptive large model parameter fine-tuning method based on end-cloud collaboration applied to an intelligent customer service system;

[0058] Figure 10 A flowchart of an embodiment of an adaptive large model parameter fine-tuning method based on end-cloud collaboration applied to a smart home control system;

[0059] Figure 11 A flowchart of an embodiment of an adaptive large model parameter fine-tuning method based on end-cloud collaboration applied to an intelligent traffic management system;

[0060] Figure 12 This is a flow chart of an embodiment of an adaptive large model parameter fine-tuning method based on end-cloud collaboration applied to an industrial automation control system. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0062] The adaptive large model parameter fine-tuning method based on end-cloud collaboration provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Figure 1As shown, the application environment includes a cloud 110, an edge 120, and a control end 130, wherein the cloud 110, the edge 120, and the control end 130 are interconnected and communicated. The large model training data is collected through the edge 120, and the large model training data is preprocessed. The large model is preliminarily trained based on the preprocessed data to obtain a preliminary large model; the key frames are identified through the edge 120, and prediction results are obtained based on the key frames and the preliminary large model; the encryption key is exchanged between the edge 120 and the cloud 110 through the key exchange protocol; on the edge 120, a symmetric encryption algorithm is used to encrypt the transmission data to be transmitted to the cloud 110, and data obfuscation technology is introduced on the basis of data encryption; a message authentication code is used on the edge 120 to verify the integrity of the transmission data; the cloud 110 collects performance feedback from each edge 120, evaluates the training load of each edge 120 based on the performance feedback, and dynamically adjusts each edge 120 based on the training load. resource allocation, and updating the model fine-tuning strategy of each edge end 120 based on the resource allocation result; receiving the encrypted transmission data transmitted from the edge end 120 through the cloud end 110, decrypting the transmission data to obtain key frames and prediction results; according to the model fine-tuning strategy, fine-tuning the parameters of the preliminary large model based on the key frames, and optimizing the parameters of the fine-tuned preliminary large model based on the prediction results to obtain the optimized large model; the control end 130 evaluates the optimized large model according to the performance evaluation index, and triggers the parameter update according to the evaluation result; real-time monitoring and collection of the performance indicators of the optimized large model in the cloud end 110 and the edge end 120, dynamically adjusting the model parameter update strategy according to the performance indicators, and determining the model parameter update frequency; adjusting the large model parameters based on the model parameter update strategy and the model parameter update frequency.

[0063] In one embodiment, Figure 2 As shown in FIG, a method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration is provided, which includes the following steps:

[0064] In step 202, the large model training data is collected through the edge end, and the large model training data is preprocessed. The large model is initially trained based on the preprocessed data to obtain a preliminary large model; key frames are identified through the edge end, and prediction results are obtained based on the key frames and the preliminary large model.

[0065] In this embodiment, large models are trained on both the edge and the cloud, forming an end-to-end collaborative architecture that enables distributed model training. This architecture allows the edge to leverage its real-time data processing capabilities for preliminary model training and transmit intermediate results to the cloud. The cloud then leverages its powerful computing resources to further process and optimize these results. This architecture not only improves the efficiency of model fine-tuning but also provides a foundation for data privacy protection.

[0066] Specifically, this embodiment uses an end-cloud collaborative architecture to achieve distributed processing of model training, with preliminary model training performed on the edge and further optimization performed on the cloud. This architecture effectively utilizes the real-time data processing capabilities of the edge and the powerful computing resources of the cloud, significantly improving the efficiency of model fine-tuning. In the standard language model fine-tuning task, using the WikiText-103 dataset, the adaptive large model parameter fine-tuning method based on end-cloud collaboration provided in this embodiment saves about 10% of training time compared to the LORA method and improves the average accuracy by about 3%.

[0067] In a cloud-edge collaborative architecture, preliminary model training at the edge is a key step in achieving efficient model fine-tuning. In this embodiment, a lightweight model training module can be deployed at the edge to leverage real-time data processing capabilities to perform preliminary model training, thereby capturing the characteristics and patterns of local data.

[0068] Specifically, in one embodiment, a method for adaptive large model parameter fine-tuning based on end-cloud collaboration is provided, which may also include data processing and preliminary model training processes. The specific processes include: at the edge, performing denoising, normalization, and data enhancement preprocessing operations on the large model training data to obtain preprocessed data; performing feature extraction operations on the preprocessed data to extract model training features; and using the model training features to perform preliminary training of the large model to obtain a preliminary large model.

[0069] Among them, at the edge, the first step is to preprocess the collected data to improve the efficiency and accuracy of model training. The preprocessing steps include denoising, normalization, data enhancement, etc. The preprocessed data is passed through the feature extraction module to extract features useful for model training. Suppose the input data is Where n is the number of samples, d is the feature dimension of each sample, and feature extraction can be expressed as: F = φ(X); where F is the extracted feature and φ is the feature extraction operation.

[0070] Then, at the edge, using the extracted features F, the edge performs preliminary training on the model. The goal of the preliminary training is to minimize the difference between the model prediction and the actual label. Let the model parameters be θ and the loss function be Then the optimization problem of the initial training can be expressed as: Among them, Y is the actual label, θ edge are the parameters of the edge model after training.

[0071] In one embodiment, a method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration is provided, which may also include a process of determining key frames and generating prediction results. The specific process includes: setting a characteristic value threshold at the edge end to determine the characteristic value corresponding to the model training feature; based on the characteristic value threshold, taking the frame with the largest characteristic value change as the key frame; the edge end obtains model parameters based on the preliminary large model, and generates prediction results based on the model parameters and key frames.

[0072] During the initial training process, the edge will identify key frames in the data, which contain the most important information for model prediction; key frames can be determined by setting a threshold to select the frames with the largest feature value changes. The prediction results are based on the key frames and the trained model parameters θ edge To generate. Let the key frame set be K, then the prediction result It can be expressed as: Here, g is the prediction function of the model.

[0073] In step 204, encryption keys are exchanged between the edge and the cloud through a key exchange protocol. On the edge, a symmetric encryption algorithm is used to encrypt the transmission data to be transmitted to the cloud, and data obfuscation technology is introduced based on data encryption. On the edge, a message authentication code is used to verify the integrity of the transmission data.

[0074] Data security and privacy are crucial in the adaptive large-scale model parameter fine-tuning strategy that leverages end-to-end collaboration. To ensure data security and privacy during model fine-tuning, a privacy-preserving data transmission protocol is employed. This protocol combines encryption and data obfuscation techniques to ensure data security during transmission, effectively preventing the risk of data leakage and unauthorized access. This ensures data security and privacy during model fine-tuning.

[0075] First, before encrypted data transmission, encryption keys need to be securely exchanged between the edge and the cloud. In this embodiment, the Diffie-Hellman key exchange protocol is used to implement the encryption key exchange process: suppose the edge and the cloud generate a key pair (d e ,D e ) and (d c ,D c ), then by exchanging public keys and calculating the common key, the encryption key can be obtained: K enc =f agreedkey (D e ,d c )=f agreedkey (D c ,d e ).

[0076] Data encryption is a key technology to ensure that data is not accessed by unauthorized persons during transmission. This paper uses a symmetric encryption algorithm to encrypt data transmitted from the edge to the cloud. Let the original data be D raw , the encryption key is K enc , then the encryption process can be expressed as: D enc =f encrypt (D raw ,K enc ).

[0077] In this embodiment, in order to further enhance the privacy of data, data obfuscation technology is introduced on the basis of data encryption. Obfuscation technology masks the actual content of data by adding random noise. Let the obfuscation operation be f confusion (·), then the obfuscated data is expressed as: D confused =f confusion (D enc ).

[0078] In one embodiment, a method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration is provided, which may also include a process for data integrity verification. The specific process includes: the edge end uses a message authentication code to verify the integrity of the transmitted data, and after the verification is passed, the transmitted data is sent to the cloud; the cloud end receives the transmitted data and uses the same key as the edge end to verify the transmitted data to obtain an integrity verification result.

[0079] Specifically, in the process of data transmission, in addition to confidentiality, the integrity of the data must also be guaranteed, and a message authentication code (MAC) is used to verify the integrity of the data. Suppose the key used by the sender to calculate the MAC is K mac , then the data integrity verification can be expressed as: MAC send =f MAC (D confused ,K mac ). After the cloud receives the data, it will use the same key for verification: ifMAC send ==MAC recv ,then data is intact;MAC recv =f MAC (D confused ,K mac ).

[0080] By adopting a privacy-preserving data transmission protocol, combined with encryption technology and data obfuscation technology, the security of data during transmission is guaranteed; the risks of data leakage and unauthorized access are effectively prevented, and user trust in the system is enhanced.

[0081] In step 206, the cloud collects performance feedback from each edge terminal, evaluates the training load of each edge terminal based on the performance feedback, dynamically adjusts the resource allocation of each edge terminal based on the training load, and updates the model fine-tuning strategy of each edge terminal based on the resource allocation result.

[0082] To further improve the efficiency and performance of model fine-tuning, a dynamic adjustment strategy for model fine-tuning is proposed. It can adjust the model's training load and resource allocation based on the model's performance and resource conditions on different terminals.

[0083] In one embodiment, a method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration is provided, which may also include a process in which the cloud collects performance feedback from each edge end. The specific process includes: the cloud collects the training loss value, processing time, and model accuracy of the preliminary large model in each edge end; the cloud obtains a performance feedback set of each edge end based on the training loss value, processing time, and model accuracy.

[0084] First, the cloud needs to collect performance feedback from the edge, including indicators such as model accuracy, loss value, and processing time. The collection of performance feedback can be expressed as follows: in, represents the performance feedback set, Indicates the accuracy of the edge model, Represents the training loss value of the edge model, T edge Indicates the processing time of the edge model.

[0085] In one embodiment, a method for adaptive large model parameter fine-tuning based on end-cloud collaboration is provided, which may also include a process in which the cloud evaluates the training load of each edge end. The specific process includes: the cloud determines the number of edge ends based on the connection relationship with each edge end, and obtains the training loss value and processing time of each edge end based on performance feedback; the cloud evaluates the training load of each edge end based on the training loss value and processing time.

[0086] Specifically, the cloud evaluates the training load of each edge based on the collected performance feedback. Training load evaluation can help the cloud allocate resources appropriately and avoid overloading or underloading certain edge devices. Training load evaluation can be expressed as: in, represents the average training load, n is the number of edges, and T edge,i They represent the training loss value and processing time of the i-th edge respectively.

[0087] The cloud can dynamically adjust the resource allocation of each edge based on the training load evaluation results. Resource allocation optimization aims to maximize model training efficiency while ensuring that resources on each edge are properly utilized. Resource allocation optimization can be performed using the formula: in, represents the optimized resource allocation plan, is the amount of resources allocated to the i-th edge.

[0088] In one embodiment, a method for adaptive large model parameter fine-tuning based on end-cloud collaboration is provided, which may also include a process in which the cloud updates the model fine-tuning strategy of each edge end. The specific process includes: the cloud adjusts the model learning rate based on resource allocation results and performance feedback; the cloud collects the updated model parameters of each edge end; the cloud updates the model fine-tuning strategy of each edge end according to the model learning rate and model parameters.

[0089] Based on the resource allocation optimization results, the cloud updates the model fine-tuning strategy of each edge terminal, specifically adjusting parameters such as the batch size, learning rate, and number of training rounds for model training. The model fine-tuning strategy update can be expressed as: in, represents the updated model parameters of the i-th edge, α new,i This is the learning rate adjusted based on current resource allocation and performance feedback. Different from initial model training, this is a dynamic adjustment strategy for edge model parameters triggered by the cloud after initial training. Model fine-tuning is an iterative process. The cloud periodically collects performance feedback, evaluates training load, optimizes resource allocation, and updates the model fine-tuning strategy.

[0090] In this embodiment, the dynamic adjustment strategy for model fine-tuning is provided to adjust the model's training load and resource allocation based on the performance feedback of each end in the end-cloud collaborative architecture. This strategy makes the model fine-tuning process more flexible and can adapt to different operating environments and task requirements. If applied in the field of smart home control, it can automatically adjust the working status of home appliances according to the user's living habits and preferences, thereby improving the user experience. In other words, through the dynamic adjustment strategy for model fine-tuning, the efficiency and flexibility of large-scale language model parameter fine-tuning in the end-cloud collaborative architecture can be achieved; this strategy can adapt to different operating environments and task requirements, significantly improving the performance and adaptability of model fine-tuning.

[0091] In step 208, the encrypted transmission data transmitted from the edge is received through the cloud, and the transmission data is decrypted to obtain key frames and prediction results. According to the model fine-tuning strategy, the parameters of the preliminary large model are fine-tuned based on the key frames, and the parameters of the fine-tuned preliminary large model are optimized based on the prediction results to obtain the optimized large model.

[0092] In one embodiment, a method for adaptive large model parameter fine-tuning based on end-cloud collaboration is provided, which may also include a process of further processing and optimizing the model. The specific process includes: the cloud determines the learning rate corresponding to the preliminary large model according to the model fine-tuning strategy, and obtains the gradient data of the loss function in the preliminary large model to the model parameters; the cloud uses key frames to fine-tune the parameters of the preliminary large model according to the learning rate and gradient data, and uses the prediction results as verification conditions to optimize the parameters of the fine-tuned preliminary large model; the cloud globally optimizes the preliminary large model according to the key frames and prediction results to obtain the optimized large model.

[0093] In this embodiment, after receiving the encrypted intermediate results, the cloud first decrypts them to obtain the original key frames and prediction results. The cloud model then further processes and optimizes them based on this information. Specifically, the model is fine-tuned based on the key frames and the prediction results at the edge are used as verification conditions to optimize the model parameters. Let the cloud model parameters be θ cloud , then the fine-tuning process can be expressed as: Where α is the learning rate, is the loss function L cloud θ cloud The cloud also performs global optimization of the model based on key frames and prediction results to ensure the generalization ability of the model on different edge terminals, which involves updating the model parameters to minimize the overall loss function. This loss function takes into account the prediction errors of all edges:

[0094] Combining initial model training at the edge with further processing and optimization in the cloud enables efficient fine-tuning of large language models within an edge-cloud collaborative architecture. This collaborative approach leverages the real-time data processing capabilities of the edge and the powerful computing resources of the cloud, improving the efficiency of model fine-tuning while also providing a foundation for data privacy protection.

[0095] Step 210: Evaluate the optimized large model according to the performance evaluation indicators, and trigger parameter updates based on the evaluation results; monitor and collect the performance indicators of the optimized large model in the cloud and edge in real time, dynamically adjust the model parameter update strategy based on the performance indicators, and determine the model parameter update frequency; adjust the large model parameters based on the model parameter update strategy and model parameter update frequency.

[0096] In one embodiment, a method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration is provided, which may also include a process of introducing an adaptive parameter optimization mechanism. The specific process includes: through a performance monitoring function, respectively monitoring and collecting the accuracy and loss value of the optimized large model on the cloud and edge, and using the accuracy and loss value as performance indicators of the large model; constructing a multi-factor trade-off model, inputting the performance indicator into the multi-factor trade-off model, and dynamically adjusting the model parameter update strategy through the multi-factor trade-off model; obtaining the performance change amount and performance change threshold of the optimized large model based on the performance indicator; determining the frequency control coefficient; and determining the model parameter update frequency based on the performance change amount, performance change threshold, and frequency control coefficient.

[0097] The introduction of an adaptive parameter optimization mechanism aims to achieve efficient utilization and dynamic adjustment of model parameters. This mechanism intelligently adjusts the update strategy of model parameters based on the model's performance on the edge and in the cloud to adapt to different data characteristics and task requirements.

[0098] In this embodiment, the introduced adaptive parameter optimization mechanism mainly includes triggering conditions for parameter updates, real-time performance monitoring, multi-factor trade-off updates, and frequency control of parameter updates.

[0099] Specifically, parameter updates are not performed periodically, but are determined based on the actual performance of the edge model. (usually recall rate), when the model performance does not meet the preset standard, the parameter update is triggered. The trigger condition can be expressed as: Where τ is the preset performance threshold.

[0100] Real-time performance monitoring is the basis of the adaptive parameter optimization mechanism. By monitoring key indicators such as the accuracy and loss value of the model at the edge and in the cloud, we can understand the performance of the model in real time. and They represent the performance indicators of edge and cloud models respectively. The real-time performance monitoring process can be expressed as: in, Represents a performance monitoring function, used to collect and analyze model performance data.

[0101] In addition to performance evaluation, the update of model parameters can also take into account multiple factors, including data characteristics, task requirements, and resource constraints. The adaptive parameter optimization mechanism can dynamically adjust the parameter update strategy by establishing a multi-factor trade-off model.

[0102] The frequency of parameter updates is determined by the rate of change of model performance and the degree of change of data characteristics. By controlling the update frequency, we can balance the stability of model training and adaptability to new data. The update frequency control can be expressed as: Among them, fupdate is the update frequency, γ is the control coefficient, is the performance change, τ change is the threshold for performance change.

[0103] In this embodiment, based on the end-cloud collaborative architecture, an adaptive parameter optimization mechanism is designed to dynamically adjust the update strategy of the model parameters according to the performance of the model on the edge and the cloud. Through this dynamic adjustment, the model can more accurately adapt to different data characteristics and task requirements, thereby optimizing the utilization efficiency of the model parameters. In other words, the introduced adaptive parameter optimization mechanism dynamically adjusts the update strategy of the model parameters according to the performance of the model on different ends. This dynamic adjustment ensures the efficient utilization of the model parameters and avoids waste of resources. In addition, through the adaptive parameter optimization mechanism and the privacy-preserving data transmission protocol, unnecessary data transmission is reduced and communication overhead is lowered. Through the end-cloud collaborative architecture and adaptive parameter optimization, the model can more accurately adapt to different data characteristics and task requirements.

[0104] It should be understood that, although the various steps in the above flow chart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above flow chart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0105] In one embodiment, Figure 1 、 Figure 3 As shown, an adaptive large model parameter fine-tuning system based on end-cloud collaboration is provided, including a cloud end 110, an edge end 120, and a control end 130, wherein:

[0106] The edge end 120 is used to collect and preprocess the large model training data, perform preliminary training on the large model based on the preprocessed data, and obtain a preliminary large model; the edge end 120 identifies key frames and obtains prediction results based on the key frames and the preliminary large model;

[0107] The encryption key is exchanged between the edge 120 and the cloud 110 via a key exchange protocol. The edge 120 is also used to: encrypt the data to be transmitted to the cloud 110 using a symmetric encryption algorithm, and introduce data obfuscation technology based on the data encryption; and verify the integrity of the transmitted data using a message authentication code on the edge 120;

[0108] The cloud 110 is configured to collect performance feedback from each edge terminal 120, evaluate the training load of each edge terminal 120 based on the performance feedback, dynamically adjust resource allocation of each edge terminal 120 based on the training load, and update the model fine-tuning strategy of each edge terminal 120 based on the resource allocation result;

[0109] The cloud 110 is further configured to receive encrypted transmission data transmitted from the edge 120, decrypt the transmission data to obtain key frames and prediction results; fine-tune the parameters of the preliminary large model based on the key frames according to the model fine-tuning strategy, and optimize the parameters of the fine-tuned preliminary large model based on the prediction results to obtain an optimized large model;

[0110] The control end 130 is used to evaluate the optimized large model according to the performance evaluation indicators and trigger parameter updates according to the evaluation results; monitor and collect the performance indicators of the optimized large model in the cloud 110 and the edge end 120 in real time, dynamically adjust the model parameter update strategy according to the performance indicators, and determine the model parameter update frequency; adjust the large model parameters based on the model parameter update strategy and model parameter update frequency.

[0111] In one embodiment, the edge end 120 is also used to perform preprocessing operations such as denoising, normalization, and data enhancement on the large model training data to obtain preprocessed data; perform feature extraction operations on the preprocessed data to extract model training features; and use the model training features to perform preliminary training on the large model to obtain a preliminary large model.

[0112] In one embodiment, the edge end 120 is also used to set a eigenvalue threshold to determine the eigenvalue corresponding to the model training feature; based on the eigenvalue threshold, the frame with the largest eigenvalue change is used as the key frame; the model parameters are obtained according to the preliminary large model, and the prediction results are generated based on the model parameters and the key frames.

[0113] In one embodiment, the edge terminal 120 is also used to use a message authentication code to verify the integrity of the transmitted data. After the verification is passed, the transmitted data is sent to the cloud 110; the cloud 110 is also used to receive the transmitted data and use the same key as the edge terminal 120 to verify the transmitted data to obtain an integrity verification result.

[0114] In one embodiment, the cloud 110 is also used to collect the training loss value, processing time, and model accuracy of the preliminary large model in each edge terminal 120; and obtain a performance feedback set of each edge terminal 120 based on the training loss value, processing time, and model accuracy.

[0115] In one embodiment, the cloud 110 is further used to determine the number of edge terminals 120 based on the connection relationship with each edge terminal 120, and obtain the training loss value and processing time of each edge terminal 120 according to performance feedback; based on the training loss value and processing time, the training load of each edge terminal 120 is evaluated.

[0116] In one embodiment, the cloud 110 is also used to adjust the model learning rate based on resource allocation results and performance feedback; collect updated model parameters of each edge end 120; and update the model fine-tuning strategy of each edge end 120 according to the model learning rate and model parameters.

[0117] In one embodiment, the control end 130 is also used to monitor and collect the accuracy and loss value of the optimized large model on the cloud 110 and the edge end 120 through a performance monitoring function, and use the accuracy and loss value as performance indicators of the large model; construct a multi-factor trade-off model, input the performance indicators into the multi-factor trade-off model, and dynamically adjust the model parameter update strategy through the multi-factor trade-off model; obtain the performance change amount and performance change threshold of the optimized large model based on the performance indicators; determine the frequency control coefficient; determine the model parameter update frequency according to the performance change amount, performance change threshold, and frequency control coefficient.

[0118] In one embodiment, the cloud 110 is also used to determine the learning rate corresponding to the preliminary large model according to the model fine-tuning strategy, and obtain the gradient data of the loss function in the preliminary large model to the model parameters; according to the learning rate and gradient data, the key frames are used to fine-tune the parameters of the preliminary large model, and the prediction results are used as verification conditions to optimize the parameters of the fine-tuned preliminary large model; according to the key frames and prediction results, the preliminary large model is globally optimized to obtain the optimized large model.

[0119] In one embodiment, a network structure of edge-cloud collaborative architecture is provided to achieve real-time data processing at the edge and deep model optimization at the cloud to improve the fine-tuning efficiency and accuracy of large language models. Figure 4 As shown, it can specifically include: data preprocessing and feature extraction, preliminary model training, key frame determination and prediction result generation, and further processing and optimization on the cloud, among which: data preprocessing and feature extraction are responsible for preprocessing and feature extraction of the original data collected on the edge to enhance the model's ability to understand the data; preliminary model training mainly uses the extracted features to perform preliminary model training on the edge to minimize prediction errors; key frame determination and prediction result generation are responsible for identifying key frames from the preliminary training process and generating prediction results based on these key frames; further processing and optimization on the cloud specifically receives the intermediate results of the edge on the cloud, and performs further processing and optimization to improve the global performance of the model.

[0120] like Figure 4As shown in the figure, arrows represent data flow and information transfer in each part. The output of data preprocessing and feature extraction is subjected to preliminary model training to produce keyframes and prediction results. These results are sent to the cloud via a secure data transmission protocol for further processing and optimization. There, the cloud-based model is fine-tuned and globally optimized based on this information. The optimization results of further processing and optimization in the cloud are fed back to the data preprocessing and feature extraction and preliminary model training to guide further training and feature extraction on the client side.

[0121] like Figure 5 As shown in FIG, in one embodiment, a structure of an adaptive parameter optimization mechanism is provided to achieve efficient utilization and dynamic adjustment of model parameters. Figure 5 As shown, it can specifically include: performance evaluation triggering, real-time performance monitoring, multi-factor trade-off updating, and parameter update frequency control, among which: performance evaluation triggering is responsible for evaluating the performance of the edge model and deciding whether to trigger parameter updates based on preset standards. It is the entry point of the entire adaptive parameter optimization mechanism; real-time performance monitoring continuously monitors the performance indicators of edge and cloud models, and provides real-time data support for parameter updates; multi-factor trade-off updating comprehensively considers performance evaluation results and other factors (such as data characteristics, task requirements, and resource constraints) to dynamically adjust the model parameter update strategy; parameter update frequency control specifically controls the frequency of parameter updates based on the rate of change of model performance and the degree of change of data characteristics, so as to balance the stability and adaptability of model training.

[0122] like Figure 5 As shown in the figure, arrows represent data flow and information transfer in each part. The performance evaluation triggers the multi-factor trade-off update strategy and influences the parameter update frequency control. Real-time performance monitoring data supports the decision-making process of the multi-factor trade-off update and provides feedback to the parameter update frequency control to adjust the update frequency. The update strategy of the multi-factor trade-off update guides the parameter update frequency control to achieve dynamic adjustment of parameter updates. Finally, the outputs of all modules are summarized to achieve efficient and accurate optimization of model parameters.

[0123] In one embodiment, a privacy protection data transmission protocol diagram for ensuring data security and privacy is provided, such as Figure 6As shown in Figure 1, this protocol combines encryption and data obfuscation technologies to ensure data security during transmission. Specifically, it includes a data encryption module, a data obfuscation unit, a secure key exchange mechanism, and a data integrity verification unit. The data encryption module encrypts data on edge devices to ensure data security before transmission; the data obfuscation unit further obfuscates encrypted data to increase data privacy and prevent potential data leaks; the secure key exchange mechanism is responsible for securely exchanging encryption keys between edge devices and cloud servers; and the data integrity verification unit verifies data integrity after receiving it in the cloud to ensure that the data has not been tampered with during transmission.

[0124] like Figure 6 As shown, the output of the edge device points to the data encryption module through an arrow, indicating the encryption process of the original data; the output of the data encryption module points to the data obfuscation unit, indicating the data obfuscation process; the secure key exchange mechanism is connected to the data encryption module and the data obfuscation unit through dotted arrows, indicating that the key exchange provides support for the encryption and obfuscation processes; the output of the data obfuscation unit points to the cloud server through an arrow, indicating the transmission of encrypted and obfuscated data; after the cloud server receives the data, the data integrity is verified by the data integrity verification unit.

[0125] In one embodiment, a structure of a dynamic adjustment strategy for model fine-tuning is provided, aiming to achieve high efficiency and adaptability of model fine-tuning under a cloud-end collaborative architecture. Figure 7 As shown in the figure, the structure includes: performance feedback collection, training load evaluation, resource allocation optimization, and model fine-tuning strategy update, among which: performance feedback collection is responsible for collecting performance feedback from the edge, including indicators such as model accuracy, loss value and processing time, to provide data support for dynamic adjustment strategies; training load evaluation evaluates the training load of each edge based on performance feedback to ensure the rationality of resource allocation; resource allocation optimization dynamically adjusts the resource allocation of each edge to maximize model training efficiency and ensure the rational use of resources; model fine-tuning strategy update updates the model fine-tuning strategy of each edge based on the resource allocation optimization results, including parameters such as batch size, learning rate and number of training rounds.

[0126] like Figure 7 As shown in the figure, the arrows in each part represent data flow and information transmission; the output of performance feedback collection drives training load evaluation, guides resource allocation optimization, and triggers model fine-tuning strategy updates; the results of training load evaluation affect the decision of resource allocation optimization and are fed back to the model fine-tuning strategy update to adjust the fine-tuning strategy; the resource allocation optimization plan guides the model fine-tuning strategy update; finally, the output of all modules is summarized to achieve dynamic adjustment of model fine-tuning.

[0127] In one embodiment, Figure 8 As shown in the figure, a program flow for fine-tuning large model parameters under the end-cloud collaborative architecture is provided. The flowchart shows the complete process from data preprocessing to model training, performance evaluation, parameter optimization, and finally model fusion and update. Specifically, it mainly includes: data preprocessing step, local model training step, performance evaluation step, cloud model optimization step, parameter optimization strategy decision step, model fusion and update step, among which, data preprocessing step: executed on the edge device, responsible for data cleaning, standardization and feature engineering; local model training step: performed on the edge device, using local data to perform preliminary training on the model; performance evaluation step: real-time monitoring and evaluation of model performance to provide a basis for subsequent optimization; cloud model optimization step: performed on the cloud server, further optimizing the model based on the performance feedback of the edge; parameter optimization strategy decision step: dynamically determining the parameter update strategy based on the performance evaluation results and resource status; model fusion and update step: executed on the cloud server, responsible for fusing and updating the optimized model parameters to the edge device.

[0128] like Figure 8 As shown, the data preprocessing step points to the local model training step, indicating that local model training is performed after data preprocessing; the local model training step points to the performance evaluation step, indicating that performance evaluation is performed after training; the outputs of the performance evaluation step point to the cloud model optimization step and the parameter optimization strategy decision step respectively, indicating that the performance evaluation results are used for both cloud model optimization and parameter optimization strategy decision; the outputs of the cloud model optimization step and the parameter optimization strategy decision step point to the model fusion and update step, indicating that the optimized model parameters are fused and updated; the output of the model fusion and update step points to the edge device, indicating that the updated model parameters are transmitted back to the edge device.

[0129] In one embodiment, for example, this embodiment applies the adaptive large model parameter fine-tuning method based on end-cloud collaboration to the intelligent customer service system to improve the response speed and service quality of the customer service system. Figure 9 The specific implementation process is as follows:

[0130] User request reception: The intelligent customer service system receives user service requests in various forms, including text, voice, or images;

[0131] Request preprocessing: The system preprocesses user requests, including language recognition and semantic parsing, to extract key information;

[0132] End-cloud collaborative processing: The edge performs preliminary request processing, such as simple question-answer matching, and transmits complex requests to the cloud.

[0133] Adaptive parameter fine-tuning: The cloud dynamically adjusts model parameters based on the type of user request and historical data to optimize the response strategy;

[0134] Privacy-preserving data transmission: During data transmission, privacy-preserving protocols are used to ensure the security of user data.

[0135] Intelligent response generation: The cloud generates intelligent responses based on the fine-tuned model and sends them back to the edge.

[0136] Response feedback and optimization: The intelligent customer service system adjusts its response strategy based on user feedback and performs iterative optimization of the model.

[0137] In one embodiment, this embodiment applies the adaptive large model parameter fine-tuning method based on end-cloud collaboration to the smart home control system to achieve intelligent management of the home environment. Figure 10 The specific implementation process is as follows:

[0138] Environmental monitoring data collection: Smart home systems use sensors to collect various data about the home environment, such as temperature, humidity, and light intensity;

[0139] Data preprocessing: The system preprocesses the collected environmental data, including data cleaning and standardization, to ensure data quality;

[0140] End-cloud collaborative decision-making: The edge makes preliminary environmental control decisions based on real-time data and transmits complex decisions to the cloud;

[0141] Adaptive parameter optimization: The cloud dynamically adjusts control parameters based on historical data and user preferences to optimize the home environment;

[0142] Privacy-preserving data transmission: During data transmission, privacy-preserving protocols are used to ensure the security of family data.

[0143] Intelligent control execution: The cloud generates intelligent control commands and sends them to the edge for execution, such as adjusting air conditioning temperature and lighting brightness;

[0144] System performance evaluation and optimization: The smart home system conducts performance evaluation based on execution results and user feedback, and continuously optimizes control strategies.

[0145] In one embodiment, this embodiment applies the adaptive large model parameter fine-tuning method based on end-cloud collaboration to the intelligent traffic management system to improve the efficiency and safety of traffic management. Figure 11 The specific implementation process is as follows:

[0146] Traffic data collection: Real-time collection of traffic flow and vehicle information data through sensors and cameras deployed at major traffic arteries;

[0147] Data preprocessing: Preprocess the collected raw traffic data, including data cleaning and format conversion, to ensure data quality;

[0148] End-to-end collaborative analysis: The edge performs preliminary analysis of real-time traffic data, identifies events such as traffic congestion and accidents, and transmits key information to the cloud.

[0149] Adaptive parameter fine-tuning: The cloud dynamically adjusts the parameters of the traffic management model based on the traffic event information received to optimize the traffic flow control strategy;

[0150] Privacy-preserving data transmission: During data transmission, privacy-preserving protocols are used to ensure the privacy of traffic participants.

[0151] Traffic control command generation: Traffic control commands, such as traffic light adjustment and vehicle diversion, are generated in the cloud and sent to the edge for execution.

[0152] System performance evaluation and optimization: Evaluate system performance based on traffic conditions and control effects, and continuously optimize models and control strategies.

[0153] In one embodiment, this embodiment applies the adaptive large model parameter fine-tuning method based on end-cloud collaboration to industrial automation control systems to improve production efficiency and product quality. Figure 12 The specific implementation process is as follows:

[0154] Production data collection: Real-time collection of production process data through sensors and monitoring equipment deployed on the production line;

[0155] Data preprocessing: preprocess the collected production data, including data cleaning and standardization, to ensure data quality;

[0156] End-cloud collaborative decision-making: The edge performs preliminary analysis of real-time production data, identifies production anomalies, and exchanges information with the cloud.

[0157] Adaptive parameter fine-tuning: The cloud dynamically adjusts the parameters of the production control model based on the analysis results of the edge end to optimize the production process;

[0158] Privacy-preserving data transmission: During the data transmission process, privacy-preserving protocols are used to ensure the security of enterprise production data;

[0159] Production control command generation: The cloud generates production control commands, such as machine start / stop and speed adjustment, and sends them to the edge for execution.

[0160] System performance evaluation and optimization: Evaluate system performance based on production efficiency and product quality, and continuously optimize models and control strategies.

[0161] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. An adaptive large model parameter fine-tuning method based on end-cloud collaboration, characterized in that: The method comprises: Collecting large model training data through the edge end, preprocessing the large model training data, performing preliminary large model training based on the preprocessed data to obtain a preliminary large model; identifying key frames through the edge end, and obtaining prediction results based on the key frames and the preliminary large model; The encryption key is exchanged between the edge and the cloud through a key exchange protocol; on the edge, a symmetric encryption algorithm is used to encrypt the transmission data to be transmitted to the cloud, and data obfuscation technology is introduced on the basis of data encryption; on the edge, a message authentication code is used to verify the integrity of the transmission data; The cloud collects performance feedback from each of the edge terminals, evaluates the training load of each of the edge terminals based on the performance feedback, dynamically adjusts resource allocation for each of the edge terminals based on the training load, and updates the model fine-tuning strategy for each of the edge terminals based on the resource allocation result; Receiving, via the cloud, the encrypted transmission data transmitted from the edge, and decrypting the transmission data to obtain the key frame and the prediction result; fine-tuning the parameters of the preliminary large model based on the key frame according to the model fine-tuning strategy, and optimizing the parameters of the fine-tuned preliminary large model based on the prediction result to obtain an optimized large model; The optimized large model is evaluated according to performance evaluation indicators, and parameter updates are triggered according to the evaluation results; the performance indicators of the optimized large model in the cloud and the edge are monitored and collected in real time, the model parameter update strategy is dynamically adjusted according to the performance indicators, and the model parameter update frequency is determined; the large model parameters are adjusted based on the model parameter update strategy and the model parameter update frequency.

2. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 1 is characterized in that: The edge end preprocesses the large model training data, performs preliminary training of the large model based on the preprocessed data, and obtains a preliminary large model, including: At the edge, performing preprocessing operations of denoising, normalization, and data enhancement on the large model training data to obtain preprocessed data; Performing a feature extraction operation on the preprocessed data to extract model training features; The model training features are used to perform preliminary training of the large model to obtain a preliminary large model.

3. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 2 is characterized in that: Identifying key frames through the edge end, and obtaining prediction results based on the key frames and the preliminary large model, including: A characteristic value threshold is set at the edge end to determine the characteristic value corresponding to the model training feature; Based on the eigenvalue threshold, the frame with the largest eigenvalue change is taken as the key frame; The edge end obtains model parameters according to the preliminary large model, and generates prediction results based on the model parameters and the key frames.

4. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 1 is characterized in that: The method further comprises: The edge end uses a message authentication code to verify the integrity of the transmitted data, and after the verification is passed, the transmitted data is sent to the cloud; The cloud receives the transmitted data and verifies the transmitted data using the same key as that of the edge to obtain an integrity verification result.

5. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 1 is characterized in that: The cloud collects performance feedback from each of the edge terminals, including: The cloud side collects the training loss value, processing time, and model accuracy of the preliminary large model in each of the edge terminals; The cloud obtains a performance feedback set of each of the edge terminals based on the training loss value, processing time, and model accuracy.

6. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 5 is characterized in that: The cloud evaluates the training load of each edge terminal according to the performance feedback, including: The cloud determines the number of edge terminals based on the connection relationship with each edge terminal, and obtains the training loss value and processing time of each edge terminal according to the performance feedback; The cloud side evaluates the training load of each of the edge terminals based on the training loss value and processing time.

7. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 6 is characterized in that: The cloud updates the model fine-tuning strategy of each edge terminal based on the resource allocation results, including: The cloud end adjusts the model learning rate based on the resource allocation result and the performance feedback; The cloud end collects the updated model parameters of each of the edge ends; The cloud end updates the model fine-tuning strategy of each of the edge ends according to the model learning rate and the model parameters.

8. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 1 is characterized in that: The real-time monitoring collects performance indicators of the optimized large model on the cloud and the edge, dynamically adjusts the model parameter update strategy according to the performance indicators, and determines the model parameter update frequency, including: Using a performance monitoring function, the accuracy and loss values ​​of the optimized large model on the cloud and the edge are monitored and collected respectively, and the accuracy and loss values ​​are used as performance indicators of the large model; Constructing a multi-factor trade-off model, inputting the performance indicator into the multi-factor trade-off model, and dynamically adjusting a model parameter update strategy through the multi-factor trade-off model; Obtaining a performance change amount and a performance change threshold of the optimized large model based on the performance index; and determining a frequency control coefficient; The model parameter update frequency is determined according to the performance change amount, the performance change threshold, and the frequency control coefficient.

9. The method for fine-tuning parameters of an adaptive large model based on end-cloud collaboration according to claim 1 is characterized in that: The cloud fine-tunes the parameters of the preliminary large model based on the key frames according to the model fine-tuning strategy, and optimizes the parameters of the fine-tuned preliminary large model based on the prediction results to obtain an optimized large model, including: The cloud determines the learning rate corresponding to the preliminary large model according to the model fine-tuning strategy, and obtains the gradient data of the loss function with respect to the model parameters in the preliminary large model; The cloud uses the key frames to fine-tune the parameters of the preliminary large model according to the learning rate and gradient data, and uses the prediction results as verification conditions to optimize the parameters of the fine-tuned preliminary large model; The cloud end globally optimizes the preliminary large model according to the key frames and the prediction results to obtain an optimized large model.

10. An adaptive large model parameter fine-tuning system based on end-cloud collaboration, characterized in that: The system comprises: The edge end is used to collect large model training data, preprocess the large model training data, perform preliminary large model training based on the preprocessed data, and obtain a preliminary large model; identify key frames through the edge end, and obtain prediction results based on the key frames and the preliminary large model; The encryption key is exchanged between the edge and the cloud through a key exchange protocol; the edge is further used to: encrypt the transmission data to be transmitted to the cloud using a symmetric encryption algorithm, and introduce data obfuscation technology based on the data encryption; and verify the integrity of the transmission data using a message authentication code on the edge; The cloud is configured to collect performance feedback from each of the edge terminals, evaluate the training load of each of the edge terminals based on the performance feedback, dynamically adjust resource allocation for each of the edge terminals based on the training load, and update the model fine-tuning strategy for each of the edge terminals based on the resource allocation results; The cloud is further configured to receive the encrypted transmission data transmitted from the edge, decrypt the transmission data to obtain the key frame and the prediction result; fine-tune the parameters of the preliminary large model based on the key frame according to the model fine-tuning strategy, and optimize the parameters of the fine-tuned preliminary large model based on the prediction result to obtain an optimized large model; The control end is used to evaluate the optimized large model according to the performance evaluation indicators and trigger parameter updates according to the evaluation results; monitor and collect the performance indicators of the optimized large model in the cloud and the edge in real time, dynamically adjust the model parameter update strategy according to the performance indicators, and determine the model parameter update frequency; adjust the large model parameters based on the model parameter update strategy and model parameter update frequency.

Images