VPN (Virtual Private Network) rapid auto-negotiation connection method and device

Abstract

The invention belongs to the technical field of VPN connection, and provides a VPN rapid auto-negotiation connection method and device, and the technical scheme is that whether a to-be-detected VPN is connected abnormally is judged, if yes, a constructed local knowledge base is called, and the local knowledge base comprises a coding dictionary base and an RAG vector knowledge base; performing multi-thread retrieval in combination with the coding dictionary database to obtain a first solution, obtaining a second solution in combination with the RAG vector knowledge base and the trained LLM large model, and evaluating the first solution and the second solution to obtain a final solution; whether the VPN adjusted according to the final solution is still connected abnormally is judged, if yes, the second solution output last time and the final solution serve as prompt words to be input into the trained LLM large model again till a scheme enabling the VPN to be connected normally is obtained, and a VPN abnormal log and the corresponding solution are updated to a local knowledge base. The configuration difficulty of VPN connection is greatly reduced, and the connection convenience is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of VPN connection, and in particular relates to a VPN fast auto-negotiation connection method and device. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the continuous development of network technology, virtual private networks (VPNs) have been widely used in various fields, providing users with secure and reliable network connection services. However, traditional VPN connection methods have some problems, such as complex configuration, numerous parameters, and difficult debugging, which bring inconvenience to users.

[0004] Currently, various error logs frequently appear during VPN connections, requiring users to manually debug and modify configuration parameters based on these logs. This is not only time-consuming and labor-intensive, but also requires specialized network knowledge. Furthermore, the wide variety of error logs, each requiring unique solutions, presents significant challenges for users.

[0005] Several methods have been published to address the complexities of VPN connection configuration. For example, they employ deep learning neural network models to analyze the textual semantic features of router log data, allowing for remote assessment and judgment of router fault types. However, these methods still rely on remotely transmitting logs to a large server-side model, relying on the network for diagnosis and assessment. They lack data augmentation methods tailored to VPN connection scenarios, making it difficult to effectively increase data complexity and impacting model generalization. Furthermore, they lack effective collection of VPN setup and connection error logs, making it impossible to fully utilize these log data for model training and parameter adjustment, or to automatically adjust VPN parameters based on error logs for connection negotiation. This requires users to manually perform complex configuration and debugging operations. Furthermore, existing technologies are unable to collect and accumulate a knowledge and experience base, hindering further improvement in VPN connection accuracy. In summary, existing technologies suffer from complex VPN connection configuration, numerous parameters, and difficulty in debugging. They also lack the ability to automatically adjust parameters and negotiate connections based on error logs, and lack a proactive knowledge base. Summary of the Invention

[0006] To address at least one of the technical issues presented in the aforementioned background technology, the present invention provides a method and system for fast VPN auto-negotiation. This method simultaneously inputs VPN connection anomaly logs into a multi-threaded search module and a fine-tuned LLM large model module, ultimately outputting evaluation results based on both to achieve a final solution. This allows users to automatically connect to the VPN and automatically adjust these parameters based on error logs, thereby reducing VPN configuration complexity and improving connection convenience and reliability.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: A first aspect of the present invention provides a VPN fast auto-negotiation connection method, comprising the following steps: Determine whether the VPN to be tested has an abnormal connection. If so, call the constructed local knowledge base, which includes a coding dictionary and a RAG vector knowledge base. Combine the coding dictionary with a multi-threaded search to obtain a first solution. Combine the RAG vector knowledge base and the trained LLM large model to obtain a second solution. Evaluate the first and second solutions to obtain a final solution. Determine whether the VPN connection is still abnormal after adjustment based on the final solution. If so, input the second solution and the final solution output last time as prompt words into the trained LLM model again until a solution that makes the VPN connection normal is obtained. Update the VPN abnormality log and the corresponding solution to the local knowledge base.

[0008] Furthermore, the local knowledge base is built based on historical VPN auto-connection error log data and corresponding solutions, including: Arrange the connection error log data and corresponding solutions according to the specified data format to obtain the sorted data; Clean the sorted data, initialize the dictionary, and store the initialized dictionary in the coding dictionary library; The sorted data and the fused data of multiple error logs are vectorized and encoded, and the encoded data is stored in the RAG vector knowledge base.

[0009] Furthermore, the multi-threaded search in combination with the coding dictionary library to obtain the first solution includes: starting n Each thread searches the contents of the coding dictionary library, and determines the first thread according to the character length L of the dictionary description in the coding dictionary library and the number of threads. i The starting and ending positions of the thread retrieval, for the i threads, whose starting position for retrieval is , the end position of the search is .

[0010] Furthermore, the trained LLM large model is obtained by loading the tokenizer on the server, fine-tuning the lora parameters and training epochs and losses, loading the weights for LLM model inference training, and adjusting the hyperparameters on the test set.

[0011] Furthermore, the evaluating the first solution and the second solution to obtain a final solution includes: If the first and second solutions are completely consistent, the same solution is taken as the final solution; If the first solution and the second solution are inconsistent, the first solution is taken as the final solution; If the first solution has no content, the second solution is used as the final solution.

[0012] Furthermore, updating the VPN exception log and the corresponding solution to the local knowledge base includes embedding the VPN exception log and the solution into a model through embedding, storing the new knowledge in the local RAG vector knowledge base, and cleaning the VPN exception log and the solution and updating them to the local encoding dictionary library.

[0013] A second aspect of the present invention provides a VPN fast auto-negotiation connection system, comprising: An anomaly detection module, which is used to determine whether the VPN to be detected has an abnormal connection. If so, it calls the constructed local knowledge base, which includes a coding dictionary library and a RAG vector knowledge base; A solution generation module is used to perform multi-threaded retrieval in combination with the coding dictionary library to obtain a first solution, combine the RAG vector knowledge base and the trained LLM large model to obtain a second solution, and evaluate the first and second solutions to obtain a final solution; The solution update module is used to determine whether the VPN connection is still abnormal after adjustment based on the final solution. If so, the second solution and the final solution output last time are input into the trained LLM model again as prompt words until a solution that makes the VPN connection normal is obtained. The VPN abnormality log and the corresponding solution are updated to the local knowledge base.

[0014] A third aspect of the present invention provides a computer-readable storage medium.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the VPN fast auto-negotiation connection method as described above.

[0016] A fourth aspect of the present invention provides a computer device.

[0017] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the above-mentioned VPN fast auto-negotiation connection method are implemented.

[0018] A fourth aspect of the present invention provides a program product.

[0019] A program product is a computer program product, comprising a computer program. When the computer program is executed by a processor, the computer program implements the steps in the above-mentioned VPN fast auto-negotiation connection method.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention effectively collects VPN establishment logs and connection error logs, enhances data for VPN connection scenarios, and downloads trained knowledge bases and models to the device. Users only need to enter a few basic parameters, and the VPN can automatically connect without complex manual configuration, greatly reducing the difficulty of VPN connection configuration and improving connection convenience.

[0021] 2. The present invention simultaneously inputs the log of VPN connection abnormality into the multi-threaded retrieval program block and the fine-tuned LLM large model module, and finally outputs the corresponding solution based on the two. It automatically adjusts the VPN parameters according to the error log to automatically negotiate the connection; it independently and continuously accumulates the knowledge base and continuously improves the accuracy of VPN connection.

[0022] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 This is an overall flow chart of a VPN fast auto-negotiation connection method provided by an embodiment of the present invention; Figure 2 This is a data flow diagram of a VPN fast auto-negotiation connection method provided by an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a VPN fast auto-negotiation connection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0027] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0028] Existing technologies still rely on remote transmission of logs to large server-side models, relying on the network for diagnosis and evaluation. This lacks data augmentation methods tailored to VPN connection scenarios, preventing effective data complexity and impacting model generalization. Existing technologies also lack effective collection of VPN setup and connection error logs, preventing them from fully utilizing this log data for model training and parameter adjustment. Existing technologies are unable to automatically adjust VPN parameters based on error logs for auto-negotiating connections, requiring users to manually perform complex configuration and debugging operations. Existing technologies also lack the ability to collect and accumulate a knowledge and experience base, preventing them from further improving VPN connection accuracy. In summary, existing technologies suffer from complex VPN connection configuration, numerous parameters, and difficulty debugging. They also lack the ability to automatically adjust parameters and auto-negotiate connections based on error logs, and they lack the ability to proactively accumulate a knowledge base.

[0029] This paper proposes a method for fast VPN auto-negotiation based on multi-threaded retrieval and large-scale model inference. This method simultaneously feeds VPN connection anomaly logs into a multi-threaded retrieval program block and a fine-tuned LLM large-scale model module. Finally, based on the output of both, evaluation code is generated, resulting in the final option parameter output. This method allows users to automatically connect to the VPN and adjust parameters based on error logs, reducing VPN configuration complexity and improving connection convenience and reliability.

[0030] Example 1 like Figure 1 and Figure 2 As shown, this embodiment provides a VPN fast auto-negotiation connection method, including the following steps: Step 1: Obtain connection error log data and corresponding solutions when VPN automatically connects; In this embodiment, after obtaining the historical VPN automatic connection error log data and the corresponding solutions, the data is sorted. The data format is as follows: { "instruction": "Error connection log A, "input": "", "output": "Change option to optionA" }, { "instruction": "packet from 27.154.56.18:500: initial Main Modemessage received on 58.23.17.102:500 but no connection has been authorizedwith policy=PSK", "input": "", "output": "Change option to optionB; change optionX to optionY" }, { "instruction":"vpn erro c", "input": "", "output": "Change option to optionC" } Through step 1 of the present invention, connection error log data and corresponding solutions during automatic VPN connection can be obtained to build a local knowledge base.

[0031] Step 2: Build a coding dictionary library and RAG vector knowledge base based on the acquired connection error log data and corresponding solutions; The specific steps include: Step 201: Build a coding dictionary library based on the acquired connection error log data and corresponding solutions; Simplify and clean the instruction data, initialize the instruction-output dictionary, download the dictionary to the device, and store it in the local knowledge base - "Encoding Dictionary Library".

[0032] For example, for instruction: "packet from 27.154.56.18:500: initial Main Mode message received on 58.23.17.102:500 but no connection has been authorized with policy=PSK", remove the IP and punctuation, and only extract "packet from initial Main Mode message received on but no connection has been authorized with policy=PSK".

[0033] Step 202: vectorize the instruction data and the data obtained by fusing multiple error logs to construct a RAG vector knowledge base. In this embodiment, instruction data and data obtained by merging multiple error logs are vectorized and encoded, and each JSON-encoded input text encoding and output text encoding is returned to an encoded dictionary.

[0034] In this embodiment, fusing multiple error logs specifically refers to fusing data in JSON format, such as adding multiple data together, which can increase the amount of data and enhance the complexity. This step is mainly to generate large model fine-tuning data.

[0035] In this embodiment, vectorizing the instruction data and the data obtained by fusing multiple error logs is specifically used to format the data. Because the LoRa training data needs to be formatted and encoded before being input into the model for training, the input text needs to be encoded as input_ids and the output text needs to be encoded as labels. The results of the encoding are all multi-dimensional vectors.

[0036] You can use tokenizer to encode the input text and output text separately, and store the input_ids and labels in a dictionary.

[0037] Step 3: Determine whether the VPN connection is abnormal. If so, perform a multi-threaded search based on the coding dictionary to obtain the first solution. Combine the RAG vector knowledge base and the LLM large model to obtain the second solution. Evaluate the first and second solutions to obtain the final solution. The multi-threaded search module uses a complete information comparison method, which is highly reliable, but may sometimes fail to match, resulting in an inability to output results. The LLM large model module has a certain ability to learn unknown knowledge and its generalization ability is much higher than that of the multi-threaded search module. Therefore, this embodiment sets dynamic evaluation rules to output effective solutions; The VPN connection is determined to be abnormal. If so, the cleaned abnormality information is fed to the multi-threaded retrieval module. The uncleaned data and the output from searching the local RAG vector knowledge base are fed to the LLM model. The evaluation module then evaluates the outputs of the two modules and outputs the final option.

[0038] The specific steps include: Step 301: Obtain a real-time VPN automatic connection error log, and perform a multi-threaded search in conjunction with a coding dictionary library to obtain a first solution; In this embodiment, start n Each thread searches the dictionary description content in the coding dictionary library, and determines the first thread according to the character length of the dictionary description and the number of threads. i The starting and ending positions of each thread; Specifically, a multi-threaded search module is established and started through the multi-threaded search module. n Each thread searches the contents of the dictionary instruction respectively, and outputs the output content that matches the instruction content, that is, outputs the correct option.

[0039] For example, the length of instruction characters is L = 16 , the number of threads is n = 4 .

[0040] The length of characters processed by each thread is L / n = 16 = 4 .

[0041] For the i threads (of which i Starting from 0), the starting position of the search is , the end position of the search is .

[0042] Specifically: The first thread ( i = 0 ) The starting position of the search is , the end position of the search is .

[0043] The second thread ( i = 1) The starting position of the search is , the end position of the search is .

[0044] The third thread ( i = 2) The starting position of the search is , the end position of the search is .

[0045] The fourth thread ( i = 3) The starting position of the search is , the end position of the search is .

[0046] Step 302: Combining the RAG vector knowledge base and the LLM large model to obtain a second solution; Specifically, we load the tokenizer on the server, fine-tune the Lora parameters and training epochs and losses, load the weights for LLM model inference training, adjust the hyperparameters on the test set, download the trained model to the device, and combine the RAG vector knowledge base and the LLM large model to obtain the second solution.

[0047] Step 303: Evaluate the first solution and the second solution according to the set evaluation rules to obtain a final solution; Specifically, the multi-threaded search module is called and its output result is recorded as multi_threaded_search_output; Call the LLM model and obtain its output result llm_output; In this embodiment, the evaluation rules are set as follows: If the output of the multi-threaded retrieval module and the LLM large model are exactly the same, the result will be output directly; If the multi-threaded retrieval module has output results, but they are inconsistent with the output of the LLM model, the results of the multi-threaded retrieval module will be output first; If the multi-threaded retrieval module does not output any results, the results of the LLM large model are output.

[0048] The process is expressed as: if (multi-threaded retrieval module output == LLM model output) { Directly output option } else if (multi-threaded retrieval module output result && (multi-threaded retrieval module output != LLM model output)) { Output multi-threaded search module option } else { Output LLM large model option } By effectively collecting VPN setup logs and connection error logs, we enhance data for VPN connection scenarios. By downloading the trained knowledge base and model to the device, users only need to enter a few basic parameters for the VPN to automatically connect, eliminating the need for complex manual configuration. This significantly reduces the difficulty of VPN connection configuration and improves connection convenience.

[0049] Step 4: Determine whether the VPN connection is still abnormal after adjustment based on the final solution. If so, input the results and evaluation results output by the last LLM large model as prompts into the LLM large model again until a solution to make the VPN connection normal is obtained. Update the local knowledge base with the VPN abnormality log and the corresponding solution.

[0050] After adjusting the options based on the evaluation module's output, if the VPN connection is still abnormal, simply input the last LLM model's output options and the evaluation module's output options as prompts to the LLM model again and repeat this step. If the VPN connection is normal, update the VPN abnormality log and solution to the local knowledge base. Specifically, VPN exception logs and solutions are embedded into the model through embedding, and the new knowledge is saved in the local RAG vector knowledge base.

[0051] Clean the VPN exception logs and solutions according to the method in step 2. Then update the local encoding dictionary with the exception logs and output solutions. Step 5: Synchronize the local knowledge base to the cloud to obtain the cloud knowledge base.

[0052] The local knowledge base will synchronize and pull the cloud knowledge base when the device network is unobstructed. Continuously collecting and accumulating knowledge and experience will further improve the effectiveness and accuracy of resolving VPN connection anomalies.

[0053] Using this method, when users open a VPN connection, they only need to enter the server IP, port, and key. Other complex parameters are no longer necessary. If the initial VPN connection fails, VPN parameters are automatically adjusted to achieve auto-negotiation. This solution reduces VPN configuration complexity and allows for faster auto-negotiation and connection.

[0054] The method of the present invention reduces the complexity of VPN configuration, has self-learning properties, and can quickly perform automatic negotiation and automatic connection.

[0055] Example 2 like Figure 3 As shown, this embodiment provides a VPN fast auto-negotiation connection device, including: An anomaly detection module, which is used to determine whether the VPN to be detected has an abnormal connection. If so, it calls the constructed local knowledge base, which includes a coding dictionary library and a RAG vector knowledge base; A solution generation module is used to perform multi-threaded retrieval in combination with the coding dictionary library to obtain a first solution, combine the RAG vector knowledge base and the trained LLM large model to obtain a second solution, and evaluate the first and second solutions to obtain a final solution; The solution update module is used to determine whether the VPN connection is still abnormal after adjustment based on the final solution. If so, the second solution and the final solution output last time are input into the trained LLM model again as prompt words until a solution that makes the VPN connection normal is obtained. The VPN abnormality log and the corresponding solution are updated to the local knowledge base.

[0056] It should be noted that the specific implementation method of a VPN fast auto-negotiation connection system in an embodiment of the present invention is similar to the specific implementation method of a VPN fast auto-negotiation connection method in an embodiment of the present invention. Please refer to the description of the method part for details. In order to reduce redundancy, it will not be repeated here.

[0057] Example 3 This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps in the VPN fast auto-negotiation connection method described above are implemented.

[0058] Example 4 This embodiment provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the VPN fast auto-negotiation connection method described above are implemented.

[0059] Example 5 This embodiment provides a program product, which is a computer program product and includes a computer program. When the computer program is executed by a processor, the steps in the VPN fast auto-negotiation connection method described above are implemented.

[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0064] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0065] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A VPN fast auto-negotiation connection method, characterized in that: The steps include: Determine whether the VPN to be tested has an abnormal connection. If so, call the constructed local knowledge base, which includes a coding dictionary and a RAG vector knowledge base. Combine the coding dictionary with a multi-threaded search to obtain a first solution. Combine the RAG vector knowledge base and the trained LLM large model to obtain a second solution. Evaluate the first and second solutions to obtain a final solution. Determine whether the VPN connection is still abnormal after adjustment based on the final solution. If so, input the second solution and the final solution output last time as prompt words into the trained LLM model again until a solution that makes the VPN connection normal is obtained. Update the VPN abnormality log and the corresponding solution to the local knowledge base.

2. A VPN fast auto-negotiation connection method according to claim 1, characterized in that: The local knowledge base is built based on historical VPN auto-connection error log data and corresponding solutions, including: Arrange the connection error log data and corresponding solutions according to the specified data format to obtain the sorted data; Clean the sorted data, initialize the dictionary, and store the initialized dictionary in the coding dictionary library; The sorted data and the fused data of multiple error logs are vectorized and encoded, and the encoded data is stored in the RAG vector knowledge base.

3. A VPN fast auto-negotiation connection method according to claim 1, characterized in that: The multi-threaded search in combination with the coding dictionary library to obtain the first solution includes: starting n Each thread searches the contents of the coding dictionary library, and determines the first thread according to the character length L of the dictionary description in the coding dictionary library and the number of threads. i The starting and ending positions of the thread retrieval, for the i threads, whose starting position for retrieval is , the end position of the search is .

4. A VPN fast auto-negotiation connection method according to claim 1, characterized in that: The trained LLM large model is obtained by loading the tokenizer on the server, fine-tuning the lora parameters and training epochs and losses, loading the weights for LLM model inference training, and adjusting the hyperparameters on the test set.

5. A VPN fast auto-negotiation connection method according to claim 1, characterized in that: The evaluation of the first solution and the second solution to obtain a final solution includes: If the first and second solutions are completely consistent, the same solution is taken as the final solution; If the first solution and the second solution are inconsistent, the first solution is taken as the final solution; If the first solution has no content, the second solution is used as the final solution.

6. A VPN fast auto-negotiation connection method according to claim 1, characterized in that: The updating of VPN anomaly logs and corresponding solutions to the local knowledge base includes embedding the VPN anomaly logs and solutions into a model through embedding, storing the new knowledge in the local RAG vector knowledge base, and cleaning the VPN anomaly logs and solutions and updating them to the local encoding dictionary library.

7. A VPN fast auto-negotiation connection device, characterized in that: include: An anomaly detection module, which is used to determine whether the VPN to be detected has an abnormal connection. If so, it calls the constructed local knowledge base, which includes a coding dictionary library and a RAG vector knowledge base; A solution generation module is used to perform multi-threaded retrieval in combination with the coding dictionary library to obtain a first solution, combine the RAG vector knowledge base and the trained LLM large model to obtain a second solution, and evaluate the first and second solutions to obtain a final solution; The solution update module is used to determine whether the VPN connection is still abnormal after adjustment based on the final solution. If so, the second solution and the final solution output last time are input into the trained LLM model again as prompt words until a solution that makes the VPN connection normal is obtained. The VPN abnormality log and the corresponding solution are updated to the local knowledge base.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the VPN fast auto-negotiation connection method according to any one of claims 1 to 6 are implemented.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the VPN fast auto-negotiation connection method according to any one of claims 1 to 6 are implemented.

10. A program product, wherein the program product is a computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the VPN fast auto-negotiation connection method according to any one of claims 1 to 6 are implemented.

Images