Automatic implementation method and system for batch operation of networks in virtualization environment

Abstract

The invention discloses an automatic implementation method and system for batch operation of networks in a virtualization environment, and belongs to the technical field of communication service tests.The method comprises the steps that AI generates network parameters, natural language instruction cues containing operation intentions are processed, and a network configuration parameter data set is generated; the AI executes a background network operation script: performing instruction analysis on a natural language instruction cue word of a specific network task, generating a standardized operation instruction sequence, and scheduling and calling a Python network operation execution module for execution; python configuration data is read and integrated, and structured input data is provided for automatic execution; python network operation execution: receiving a scheduling instruction and configuration data, and driving a browser to complete actual webpage operation; the invention relates to a Chrome browser driver. According to the method, the communication service testing efficiency can be remarkably improved, and the operation accuracy is greatly improved by designing network parameters in advance.

Description

Technical Field

[0001] This invention relates to the field of communication service testing technology, and specifically to an automated method and system for batch operation of networks in a virtualized environment. Background Technology

[0002] Traditionally, managing the network via a web interface requires manually clicking on specific locations and entering parameters. This is especially problematic during business testing, where frequent network operations are necessary. When testing multiple environments simultaneously, the workload doubles. Frequent manual network operations are not only time-consuming and labor-intensive but also prone to errors. Summary of the Invention

[0003] The technical objective of this invention is to provide an automated method and system for batch network operations in a virtualized environment, which can significantly improve the efficiency of communication service testing and greatly enhance the accuracy of operations by pre-designing network parameters.

[0004] The technical solution adopted by this invention to solve its technical problem is:

[0005] An automated method for batch network operations in a virtualized environment, the method comprising:

[0006] (1) AI generates network parameters: Process natural language instruction prompts containing operational intentions to generate a dataset of network configuration parameters;

[0007] (2) AI executes background network operation scripts: It parses natural language prompts for specific network tasks (such as creating port groups and configuring distributed switches), generates standardized operation instruction sequences, and schedules and calls the Python network operation execution module to execute them;

[0008] (3) Python configuration for data reading and integration, providing structured input data for automated execution;

[0009] (4) Python network operation execution: Receive scheduling instructions and configuration data, and drive the browser to complete the actual web page operation;

[0010] (5) Chrome browser driver: isolates the underlying browser driver details and provides standardized interfaces for the execution engine to call.

[0011] This method uses Python and the Selenium library to locate web page elements, calls the Chrome browser driver, simulates clicks and input parameters, and implements a series of operations on the web page to control the network on a virtualization platform. It also extends to the management and maintenance of other virtualization platforms, providing a technical solution for testing on other virtualization platforms. For operations requiring frequent network manipulation on the management webpage, AI generates fixed network parameters, understands environmental parameters, and calls scripts to form specific operation processes, thereby automating network operations and improving testing efficiency.

[0012] Furthermore, the AI-generated network parameters are specifically implemented as follows:

[0013] Receive natural language prompts containing the operational intent, as well as the current network topology status and environmental configuration parameters (such as VLAN pools, IP address ranges, available resource constraints, etc.);

[0014] Based on the received information, LLM or other machine learning models are used to understand the requirements and analyze the environmental context.

[0015] Dynamically generate a dataset of precise network configuration parameters that conforms to a predefined template and is adapted to the environment; the dataset includes information such as network interface configuration, VLAN ID, IP address / subnet mask, and gateway.

[0016] Furthermore, the AI ​​executes background network operation scripts, specifically including:

[0017] Receive natural language prompts for specific network tasks (such as creating port groups or configuring distributed switches);

[0018] Analyze the intent of the instructions, determine the required sequence of network actions and their objects, and clarify the execution logic;

[0019] Generates standardized operation instruction sequences and schedules them to be executed by the Python network operation execution module; this module is responsible for understanding "what to do" and "to whom to do it".

[0020] Furthermore, the Python configuration data reading and integration includes:

[0021] Use functions such as xlrd or open_workbook from other data processing libraries to open .xls spreadsheet files containing basic or supplementary network configuration parameters;

[0022] Parse the table structure (such as sheet pages, data ranges) to determine the number of data records to be read or the records marked by specific identifiers;

[0023] Using methods such as cell_value, the data of the target row / column can be accurately read into a predefined data structure (such as a list, dictionary, or array of objects);

[0024] Provide the Python network operation execution module with a formatted data array / object containing the required configuration parameters.

[0025] Furthermore, the execution flow of the Python network operation is as follows:

[0026] (4.1) Receive instructions and data: Obtain the standard operation sequence instructions from step (2) and the parameter data passed in step (3);

[0027] (4.1) Initialize the Web driver session: Invoke the Chrome browser driver adapter module to start and configure the browser instance;

[0028] (4.3) Operation sequence execution;

[0029] (4.4) Session Management: After the operation is completed or terminated for any reason, manage the browser session (close the browsing instance and release resources).

[0030] Furthermore, the execution of the operation sequence includes:

[0031] Authentication: Locate the login form element on the webpage (e.g., find_element(By.XPATH,' / / input[@id="username"]')), enter the preset or read username and password, and simulate the Enter key to submit;

[0032] Main process loop: Iterates based on the number of rows or entries in the configuration data array, including:

[0033] Element location: Based on the operation instructions and the current data entries, use the WebDriver API (such as find_element, find_elements) to accurately locate the target HTML element (button, input box, drop-down list, link, etc.). The location method is preferred or supports XPath.

[0034] Interactive simulation:

[0035] Click operation: Call the click() method on various elements, including buttons, links, checkboxes, tabs, etc.

[0036] Data input: Call the `clear()` (optional) and `send_keys(value)` methods on elements such as textboxes and text areas to input the corresponding parameters;

[0037] Selection operation: Use the Select class to select items in dropdown lists;

[0038] Flow control: Handles necessary waiting (explicit or implicit), error capture, and retry logic between operations.

[0039] Furthermore, the Chrome browser driver adapter configuration includes:

[0040] (5.1) Initialization options:

[0041] Use webdriver.ChromeOptions().add_argument() to set startup parameters, including:

[0042] disable-notifications: Disables browser notification pop-ups.

[0043] ignore-certificate-errors: Ignore SSL certificate errors.

[0044] allow-running-insecure-content: Allows loading non-HTTPS resources (if necessary).

[0045] Use webdriver.ChromeOptions().add_experimental_option() to set experimental options:

[0046] Prefs: Configurable preferences, such as {'profile.default_content_setting_values.notifications':2} (disable notifications);

[0047] excludeSwitches: e.g., ['enable-logging'], disables irrelevant logging;

[0048] (5.2) Driver path: Specifies the location of the chromedriver (or ChromeDriver) executable file (executable_path or via the PATH environment variable);

[0049] (5.3) Session creation: Initialize the webdriver.Chrome instance using the above configuration and return a WebDriver object for the execution engine to operate on;

[0050] (5.4) Optional headless mode configuration: Supports enabling headless mode via parameters (--headless=new / --headless) to prevent the UI window from being displayed.

[0051] This invention also claims an automated implementation system for batch operation of networks in a virtualized environment, comprising:

[0052] The AI ​​network parameter intelligent generation module is used to process natural language instruction prompts containing operational intentions and dynamically generate a network configuration parameter dataset.

[0053] The AI ​​operation process parsing and scheduling module is used to parse the natural language instructions for specific network tasks, generate standardized operation instruction sequences, and invoke the operations.

[0054] A Python module for configuring data reading and integration is used to provide structured input data for automated execution.

[0055] This Python network operation execution engine module is used to receive scheduling instructions and configuration data, and drive the browser to complete the actual web page operations.

[0056] The Chrome browser driver adapter module is used to isolate the underlying browser driver details and provide standardized interfaces for the execution engine to call.

[0057] This system can implement the methods described above.

[0058] The present invention also claims an automated implementation apparatus for batch operation networks in a virtualized environment, comprising: at least one memory and at least one processor;

[0059] The at least one memory is used to store a machine-readable program;

[0060] The at least one processor is used to call the machine-readable program to implement the above method.

[0061] The present invention also claims a computer-readable medium, characterized in that the computer-readable medium stores computer instructions that, when executed by a processor, enable the implementation of the above-described method.

[0062] The automated implementation method and system for batch operation of a virtualized environment network of the present invention has the following advantages compared with the prior art:

[0063] This invention uses an AI agent to understand network and environmental parameters. By modifying a fixed template, it generates corresponding information, allowing for the specification of operations on a single network or batch operations on networks. The background uses the Selenium library in Python and calls the Chrome browser driver to automatically operate the network on a webpage, enabling unattended testing and solving the problem of time-consuming and labor-intensive manual network operations.

[0064] AI agents can quickly and effectively understand network and environmental parameters through prompts and automatically perform network operations, effectively solving the tedious manual network operations on the page, thereby improving efficiency and reducing error rates. Attached Figure Description

[0065] Figure 1 This is a diagram of the AI ​​operation network provided in an embodiment of the present invention;

[0066] Figure 2 This is a schematic diagram illustrating the principle of the AI ​​understanding operation network provided in this embodiment of the invention;

[0067] Figure 3 This is an example diagram of environmental information generated by AI based on prompt words, provided in an embodiment of the present invention.

[0068] Figure 4 This is an example diagram of network planning data generated by AI based on prompt words, provided in an embodiment of the present invention.

[0069] Figure 5 This is an example diagram of successful network creation provided in an embodiment of the present invention;

[0070] Figure 6 This is an example image of successfully creating a TEST7 network task provided in an embodiment of the present invention;

[0071] Figure 7 This is an example image of successfully creating a TEST8 network task provided in an embodiment of the present invention;

[0072] Figure 8 This is an example image of successfully creating a TEST9 network task provided in an embodiment of the present invention;

[0073] Figure 9 This is an example image showing the successful creation of TEST7 and TEST8 network tasks by the IaaS cloud management platform provided in this embodiment of the invention.

[0074] Figure 10 This is an example image showing the successful deletion of the TEST7 network task on the IaaS cloud management platform provided in this embodiment of the invention.

[0075] Figure 11 This is an example image showing the successful deletion of the TEST8 network task by the IaaS cloud management platform provided in this embodiment of the invention. Detailed Implementation

[0076] The present invention will be further described below with reference to specific embodiments.

[0077] This invention provides an automated method for batch network operations in a virtualized environment. The method includes:

[0078] (1) AI generates network parameters: The natural language instruction prompts containing the operation intention are processed to generate a network configuration parameter dataset.

[0079] (2) AI executes background network operation scripts: It parses natural language prompts for specific network tasks (such as creating port groups or configuring distributed switches), generates standardized operation instruction sequences, and schedules and calls the Python network operation execution module to execute them.

[0080] (3) Python configuration data reading and integration to provide structured input data for automated execution.

[0081] (4) Python network operation execution: Receive scheduling instructions and configuration data, and drive the browser to complete the actual web page operation.

[0082] (5) Chrome browser driver: isolates the underlying browser driver details and provides standardized interfaces for the execution engine to call.

[0083] AI generates network parameters, and the specific implementation includes:

[0084] Receive natural language prompts containing the operational intent, as well as the current network topology status and environmental configuration parameters (such as VLAN pools, IP address ranges, available resource constraints, etc.);

[0085] Based on the received information, LLM or other machine learning models are used to understand the requirements and analyze the environmental context.

[0086] Dynamically generate a dataset of precise network configuration parameters that conforms to a predefined template and is adapted to the environment; the dataset includes information such as network interface configuration, VLAN ID, IP address / subnet mask, and gateway.

[0087] The AI ​​executes background network operation scripts, specifically including:

[0088] Receive natural language prompts for specific network tasks (such as creating port groups or configuring distributed switches);

[0089] Analyze the intent of the instructions, determine the required sequence of network actions and their objects, and clarify the execution logic;

[0090] Generates standardized operation instruction sequences and schedules them to be executed by the Python network operation execution module; this module is responsible for understanding "what to do" and "to whom to do it".

[0091] Python configuration data reading and integration, including:

[0092] Use functions such as xlrd or open_workbook from other data processing libraries to open .xls spreadsheet files containing basic or supplementary network configuration parameters;

[0093] Parse the table structure (such as sheet pages, data ranges) to determine the number of data records to be read or the records marked by specific identifiers;

[0094] Using methods such as cell_value, the data of the target row / column can be accurately read into a predefined data structure (such as a list, dictionary, or array of objects);

[0095] Provide the Python network operation execution module with a formatted data array / object containing the required configuration parameters.

[0096] Python network operations are executed, and the execution flow is as follows:

[0097] (4.1) Receive instructions and data: Obtain the standard operation sequence instructions from step (2) and the parameter data passed from step (3).

[0098] (4.1) Initialize Web driver session: Call the Chrome browser driver adapter module to start and configure the browser instance.

[0099] (4.3) Operation sequence execution; including:

[0100] Authentication: Locate the login form element on the webpage (e.g., find_element(By.XPATH,' / / input[@id="username"]')), enter the preset or read username and password, and simulate the Enter key to submit;

[0101] Main process loop: Iterates based on the number of rows or entries in the configuration data array, including:

[0102] Element location: Based on the operation instructions and the current data entries, use the WebDriver API (such as find_element, find_elements) to accurately locate the target HTML element (button, input box, drop-down list, link, etc.). The location method is preferred or supports XPath.

[0103] Interactive simulation:

[0104] Click operation: Call the click() method on various elements, including buttons, links, checkboxes, tabs, etc.

[0105] Data input: Call the `clear()` (optional) and `send_keys(value)` methods on elements such as textboxes and text areas to input the corresponding parameters;

[0106] Selection operation: Use the Select class to select items in dropdown lists;

[0107] Flow control: Handles necessary waiting (explicit or implicit), error capture, and retry logic between operations.

[0108] (4.4) Session Management: After the operation is completed or terminated for any reason, manage the browser session (close the browsing instance and release resources).

[0109] Chrome browser driver adapter configuration includes:

[0110] (5.1) Initialization options:

[0111] Use webdriver.ChromeOptions().add_argument() to set startup parameters, including:

[0112] disable-notifications: Disables browser notification pop-ups.

[0113] ignore-certificate-errors: Ignore SSL certificate errors.

[0114] allow-running-insecure-content: Allows loading non-HTTPS resources (if necessary).

[0115] Use webdriver.ChromeOptions().add_experimental_option() to set experimental options:

[0116] Prefs: Configurable preferences, such as {'profile.default_content_setting_values.notifications':2} (disable notifications);

[0117] excludeSwitches: e.g., ['enable-logging'], disables irrelevant logging.

[0118] (5.2) Driver path: Specifies the location of the chromedriver (or ChromeDriver) executable file (executable_path or via the PATH environment variable).

[0119] (5.3) Session creation: Initialize the webdriver.Chrome instance using the above configuration and return a WebDriver object for the execution engine to operate on.

[0120] (5.4) Optional headless mode configuration: Supports enabling headless mode via parameters (--headless=new / --headless) to prevent the UI window from being displayed.

[0121] This method solves the problem of frequent network operations during the creation or deletion of services in the test environment, which previously required manual creation and was tedious and time-consuming. This method uses an AI agent to understand network parameters and operation commands, calls a Python script combined with the Selenium library, and invokes the Chrome browser driver. By parsing and finding corresponding HTML elements, it simulates basic computer operations such as clicks or input, enabling web-based network operations. The AI ​​agent understands virtualization environment parameters and network parameters, providing corresponding batch network operation functions. It also provides a graphical interface for pre-setting environment and network design parameters to automate network operations on the virtualization environment management webpage. Based on testing needs, it can be extended to the management and maintenance of other virtualization environments, such as OpenStack and other mainstream virtualization environments.

[0122] This technology significantly improves the efficiency of communication service testing. The AI ​​agent directly understands network and environmental parameters, automatically executes operations that shorten the time required to access the network via web pages, and greatly improves the accuracy of operations by pre-designing network parameters.

[0123] The following example, using a virtual platform test scenario, further illustrates the application of this method in detail. AI generates an xls file with specified parameters based on prompt words, automatically operating the network.

[0124] 1. Examples of AI input prompts and precise network and environmental information are as follows:

[0125] Example prompts: In the first environment, create the following 3 networks and enter the following information into the table:

[0126] VLAN ID, gateway mask, name, port group name, external network

[0127] 3140 10.20.140.254 24TEST7 TEST-DVS yes

[0128] 3141 10.20.141.254 24TEST8 TEST-DVS yes

[0129] 3142 10.20.142.254 24TEST9 TEST-DVS no

[0130] 2. AI generates environment and network parameters, settings, and descriptions in an XLS table file based on the prompt words. A designated tab is set to "Environment Information," and column B contains the URL, username, and password required for the login page. Figure 3 As shown.

[0131] Specify the business network segment planning for the specified tab, with a fixed position, and generate the necessary planning parameters based on the template. For example... Figure 4 As shown in the example, the VLAN ID, default gateway, subnet mask, network name, port name, and whether to enable external networks are specified: yes, the corresponding external network will be automatically created on the IaaS cloud management platform; no, it will not be created automatically.

[0132] 3. Begin creating network software:

[0133] The Chrome driver is invoked to open the Chrome browser, automatically execute the script, and begin automatically creating the three sample networks.

[0134] 4. The results of automated network creation, such as Figure 5 , Figure 6 , Figure 7 and Figure 8 As shown.

[0135] 5. Create a network on the IaaS cloud management platform, such as... Figure 9 As shown, according to Figure 4 In the network element planning, only TEST7 and TEST8 are created for the external network.

[0136] 6. Automatic network deletion begins.

[0137] Example prompt: In the first environment, delete the network created earlier.

[0138] 7. Automated network deletion process.

[0139] The script is invoked to open the Chrome browser and automatically execute the script to begin automatically deleting the three example networks.

[0140] 8. Automated deletion of network results. For example... Figure 10 and Figure 11 As shown.

[0141] This invention also provides an automated system for batch network operations in a virtualized environment. It uses an AI agent to understand network and environmental parameters, and generates corresponding information by modifying fixed templates. It can specify operations for a single network or perform batch network operations. The system uses the Selenium library from Python in the background and calls the Chrome browser driver to automatically operate the network on a webpage, enabling unattended testing and solving the problem of time-consuming and labor-intensive manual network operations.

[0142] The system includes:

[0143] The AI ​​network parameter intelligent generation module is used to process natural language instruction prompts containing operational intentions and dynamically generate a network configuration parameter dataset.

[0144] The AI ​​operation process parsing and scheduling module is used to parse the natural language instructions for specific network tasks, generate standardized operation instruction sequences, and invoke the operations.

[0145] A Python module for configuring data reading and integration is used to provide structured input data for automated execution.

[0146] This Python network operation execution engine module is used to receive scheduling instructions and configuration data, and drive the browser to complete the actual web page operations.

[0147] The Chrome browser driver adapter module is used to isolate the underlying browser driver details and provide standardized interfaces for the execution engine to call.

[0148] This system can automate the batch operation network method in the virtualized environment described in the above embodiments.

[0149] 1. AI Network Parameter Intelligent Generation Module:

[0150] Function: Receives natural language prompts containing the operation intent, as well as the current network topology status and environmental configuration parameters (such as VLAN pools, IP address ranges, available resource constraints, etc.).

[0151] Processing: Based on the received information, use LLM or other machine learning models to understand the requirements and analyze the environmental context.

[0152] Output: Dynamically generated dataset of precise network configuration parameters that conforms to a predefined template and is adapted to the environment. This dataset typically includes, but is not limited to, information such as network interface configurations, VLAN IDs, IP addresses / subnet masks, and gateways.

[0153] 2. AI Operation Process Analysis and Scheduling Module:

[0154] Function: Receives natural language prompts for specific network tasks (such as creating port groups or configuring distributed switches).

[0155] Processing: Parse the instruction intent, determine the required sequence of network operations (Actions) and their objects, and clarify the execution step logic.

[0156] Output: Generates a standardized sequence of operation instructions and schedules them to be executed by the Python network operation execution module. This module is responsible for understanding "what to do" and "to whom to do it".

[0157] 3. Configure the Python data reading and integration module:

[0158] Function: Provides structured input data for automated execution.

[0159] deal with:

[0160] Use functions such as xlrd or open_workbook from other data processing libraries to open .xls spreadsheet files containing basic or supplementary network configuration parameters.

[0161] Parse the table structure (such as sheet pages, data ranges) to determine the number of data records to be read (or records marked with specific identifiers).

[0162] Methods such as cell_value can be used to accurately read data from the target row / column into a predefined data structure (such as a list, dictionary, or array of objects).

[0163] Output: Provides a formatted array / object of data containing the required configuration parameters to the Python network operations execution module.

[0164] 4. Python network operation execution engine module:

[0165] Function: As the core of browser interaction and operation execution, it receives scheduling instructions and configuration data, and drives the browser to complete actual web page operations.

[0166] Execution process:

[0167] (1) Receiving instructions and data: Obtain standard operation sequence instructions from the AI ​​operation process parsing and scheduling module and parameter data passed by the Python configuration data reading and integration module.

[0168] (2) Initialize Web driver session: Call the Chrome browser driver adapter module to start and configure the browser instance.

[0169] (3) Operation sequence execution:

[0170] Authentication: Locate the login form element on the webpage (e.g., find_element(By.XPATH,' / / input[@id="username"]')), enter the preset or read username and password, and simulate the Enter key to submit.

[0171] Main process loop: Iterates based on the number of rows (or entries) in the configuration data array:

[0172] Element location: Based on the operation instructions and the current data entries, use the WebDriver API (such as find_element, find_elements) to accurately locate the target HTML element (button, input box, drop-down list, link, etc.). The location method is preferred or supports XPath.

[0173] Interactive simulation:

[0174] Click operation: Call the click() method on elements such as buttons, links, checkboxes, and tabs.

[0175] Data input: Call the clear() (optional) and send_keys(value) methods on elements such as textboxes and text areas to input the corresponding parameters.

[0176] Selection operation: Use the Select class to select items in dropdown lists.

[0177] Flow control: Handles necessary waiting (explicit or implicit), error capture, and retry logic between operations.

[0178] (4) Session Management: After the operation is completed or terminated for any reason, manage the browser session (close the browsing instance and release resources).

[0179] 5. Chrome browser driver adapter module:

[0180] Function: Isolates the underlying browser driver details and provides standardized interfaces for the execution engine to call.

[0181] Core configuration:

[0182] (1) Initialization options:

[0183] Use webdriver.ChromeOptions().add_argument() to set startup parameters:

[0184] --disable-notifications: Disables browser notification pop-ups.

[0185] --ignore-certificate-errors: Ignore SSL certificate errors.

[0186] --allow-running-insecure-content: Allows loading non-HTTPS resources (if necessary).

[0187] Use webdriver.ChromeOptions().add_experimental_option() to set experimental options:

[0188] prefs: Configurable preferences, such as {'profile.default_content_setting_values.notifications':2} (disable notifications).

[0189] excludeSwitches: e.g., ['enable-logging'], disables irrelevant logging.

[0190] (2) Driver path: Specifies the location of the chromedriver (or ChromeDriver) executable file (executable_path or via the PATH environment variable).

[0191] (3) Session creation: Initialize the webdriver.Chrome instance using the above configuration and return a WebDriver object for the execution engine to operate on.

[0192] (4) Headless mode (optional): Enables headless mode via parameters (--headless=new / --headless) to prevent the UI window from being displayed.

[0193] This invention also provides an automated implementation device for batch operation of a virtualized environment network, comprising: at least one memory and at least one processor;

[0194] The at least one memory is used to store a machine-readable program;

[0195] The at least one processor is used to call the machine-readable program to implement the automated implementation method for batch operation of the network in the virtualized environment described in the above embodiments.

[0196] This invention also provides a computer-readable medium storing computer instructions. When executed by a processor, the computer instructions cause the processor to perform the automated implementation method for batch operation networks in a virtualized environment as described in the above embodiments. Specifically, a system or apparatus equipped with a storage medium storing software program code that implements the functions of any of the above embodiments can be provided, and the computer (or CPU or MPU) of the system or apparatus can read and execute the program code stored in the storage medium.

[0197] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0198] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0199] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0200] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0201] The present invention has been shown and described in detail above with reference to the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above embodiments, those skilled in the art will know that more embodiments of the present invention can be obtained by combining the code review methods in the different embodiments. These embodiments are also within the protection scope of the present invention.

Claims

1. An automated implementation method for batch operation of a network in a virtualized environment, characterized in that, The implementation of this method includes: (1) AI generates network parameters: Process natural language instruction prompts containing operational intentions to generate a dataset of network configuration parameters; (2) AI executes background network operation scripts: it parses natural language instruction prompts for specific network tasks, generates standardized operation instruction sequences, and schedules and calls the Python network operation execution module to execute them; (3) Python configuration for data reading and integration, providing structured input data for automated execution; (4) Python network operation execution: Receive scheduling instructions and configuration data, and drive the browser to complete the actual web page operation; (5) Chrome browser driver: isolates the underlying browser driver details and provides standardized interfaces for the execution engine to call.

2. The automated implementation method for batch operation of a network in a virtualized environment according to claim 1, characterized in that, The AI-generated network parameters are specifically implemented as follows: Receive natural language prompts containing the operational intent, as well as the current network topology status and environmental configuration parameters; Based on the received information, LLM or other machine learning models are used to understand the requirements and analyze the environmental context. Dynamically generate a dataset of precise network configuration parameters that conforms to a predefined template and is adapted to the environment; the dataset includes: network interface configuration, VLAN ID, IP address / subnet mask, and gateway information.

3. The automated implementation method for batch operation of a network in a virtualized environment according to claim 1, characterized in that, The AI ​​executes the background network operation script, specifically including: Receive natural language instruction prompts for specific network tasks; Analyze the intent of the instructions, determine the required sequence of network operations and their targets, and clarify the execution logic. Generate a standardized sequence of operation instructions and schedule the Python network operation execution module to execute them.

4. The automated implementation method for batch operation of a virtualized environment network according to claim 1, characterized in that, The Python configuration data reading and integration includes: Use the open_workbook function of xlrd or other data processing libraries to open the .xls table file containing basic or supplementary network configuration parameters; Parse the table structure to determine the number of rows of data records to be read or the records marked by specific identifiers; Precisely read the data of the target row / column into a predefined data structure; Provide the Python network operation execution module with a formatted data array / object containing the required configuration parameters.

5. The automated implementation method for batch operation networks in a virtualized environment according to claim 1 or 4, characterized in that, The execution flow of the Python network operation is as follows: (4.1) Receive instructions and data: Obtain the standard operation sequence instructions from step (2) and the parameter data passed in step (3); (4.1) Initialize the Web driver session: Invoke the Chrome browser driver adapter module to start and configure the browser instance; (4.3) Operation sequence execution; (4.4) Session Management: Manage browser sessions after an operation is completed or terminated for any reason.

6. The automated implementation method for batch operation of a network in a virtualized environment according to claim 5, characterized in that, The execution of the operation sequence includes: Identity authentication: Locate the login form element on the webpage, input the preset or read username and password, and simulate the Enter key to submit; Main process loop: Iterates based on the number of rows or entries in the configuration data array, including: Element location: Based on the operation instructions and the current data entry, use the WebDriver API to accurately locate the target HTML element, with XPath as the preferred or supported location method; Interactive simulation: Click operation: Call the click() method on each element, including buttons, links, checkboxes, and tabs; Data input: For text boxes and text fields, you can selectively call the clear() and send_keys(value) methods to input the corresponding parameters; Selection operation: Use the Select class to select items in the drop-down list; Process control: Handles necessary waiting, error capture, and retry logic between operations.

7. The automated implementation method for batch operation of a network in a virtualized environment according to claim 1, characterized in that, Chrome browser driver adapter configuration includes: (5.1) Initialization options: Use webdriver.ChromeOptions().add_argument() to set startup parameters, including: disable-notifications: Disables browser notification pop-ups. ignore-certificate-errors: Ignore SSL certificate errors. allow-running-insecure-content: Allows loading non-HTTPS resources. Use webdriver.ChromeOptions().add_experimental_option() to set experimental options: Prefs: Configurable preferences; excludeSwitches: Disables irrelevant logging; (5.2) Driver path: Specifies the location of the chromedriver executable file; (5.3) Session creation: Initialize the webdriver.Chrome instance using the above configuration and return a WebDriver object for the execution engine to operate on; (5.4) Optional headless mode configuration: Supports enabling headless mode via parameters to prevent the UI window from being displayed.

8. An automated implementation system for batch operation of a network in a virtualized environment, characterized in that, include: The AI ​​network parameter intelligent generation module is used to process natural language instruction prompts containing operational intentions and dynamically generate a network configuration parameter dataset. The AI ​​operation process parsing and scheduling module is used to parse the natural language instructions for specific network tasks, generate standardized operation instruction sequences, and invoke the operations. A Python module for configuring data reading and integration is used to provide structured input data for automated execution. This Python network operation execution engine module is used to receive scheduling instructions and configuration data, and drive the browser to complete the actual web page operations. The Chrome browser driver adapter module is used to isolate the underlying browser driver details and provide standardized interfaces for the execution engine to call. The system is capable of implementing the method described in any one of claims 1 to 7.

9. An automated implementation device for batch operation of a network in a virtualized environment, characterized in that, include: At least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is configured to invoke the machine-readable program to implement the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that, The computer-readable medium stores computer instructions that, when executed by a processor, enable the implementation of the method described in any one of claims 1 to 7.

Images