Cloud mobile phone control system based on large language model

Abstract

The invention is suitable for the technical field of artificial intelligence and cloud computing crossing, and provides a cloud mobile phone control system based on a large language model, comprising an interaction agent used for receiving a cloud mobile phone control instruction input by a user by using a natural language, and sending the cloud mobile phone control instruction to a large language model agent; the large language model agent is used for analyzing and constructing the instruction and sending a tool calling instruction to the MCP client; the MCP client is used for initiating a remote procedure call request to the MCP server; the MCP server side is used for sending a task instruction to the cloud mobile phone control platform; the cloud mobile phone control platform is used for sending the task instruction and the equipment information to the edge server; and the edge server is used for transmitting the task instruction and the equipment information to the cloud mobile phone management service node, so that the cloud mobile phone management service node executes corresponding operation on the target cloud mobile phone. According to the invention, intelligent control of the cloud mobile phone can be realized, and the management efficiency of the cloud mobile phone is improved.

Description

Technical Field

[0001] The present application belongs to the field of intersection of artificial intelligence and cloud computing, and in particular relates to a cloud phone control system based on a large language model. Background Art

[0002] Currently, cloud phones are controlled primarily through the following methods: 1. Application Programming Interface (API) control: This provides APIs to control basic cloud phone operations, such as restarting and resetting. However, these API operations typically rely on users providing explicit instructions or commands and lack natural language interaction capabilities. 2. Script automation: This utilizes scripting languages ​​(such as Python or Shell) to automate operations. These methods typically require users to write and maintain code and are not user-friendly for new users. 3. Device management platforms: Some companies offer cloud phone management platforms that can control devices in batches, but these platforms are mostly based on graphical interfaces or predefined commands and do not support intelligent interaction based on natural language.

[0003] As can be seen from the above, the current control of cloud phones usually relies on manual operations or preset script tools, lacks intelligent control, and results in low efficiency in cloud phone management. Summary of the Invention

[0004] The embodiment of the present application provides a cloud phone control system based on a large language model, which can solve the problem of low efficiency in cloud phone management caused by the lack of intelligent control of cloud phones.

[0005] The present application provides a cloud phone control system based on a large language model, including:

[0006] The interactive agent is used to receive cloud phone control instructions input by the user using natural language and send the cloud phone control instructions to the large language model agent;

[0007] The large language model agent is used to analyze the cloud phone control instructions after receiving them, construct tool call instructions, and send the tool call instructions to the MCP client; the tool call instructions include the tool name and tool parameters;

[0008] The MCP client is used to initiate a remote procedure call request to the MCP server through the MCP protocol after receiving the tool call instruction; the remote procedure call request includes the tool name and tool parameters;

[0009] The MCP server is used to send a task instruction containing the tool name and tool parameters to the cloud phone control platform after receiving the remote procedure call request;

[0010] The cloud phone control platform is used to determine the device information of the target cloud phone to be controlled by the cloud phone control instruction according to the task instruction, and send the task instruction and device information to the edge server to which the target cloud phone belongs;

[0011] The edge server is used to transmit task instructions and device information to the cloud phone management service node to which the target cloud phone belongs according to the device information, so that the cloud phone management service node performs the operation corresponding to the tool name on the target cloud phone.

[0012] Optionally, the MCP client is also used to perform the following steps:

[0013] Establish a connection with the MCP server through the MCP protocol, and obtain the metadata list from the MCP server through the MCP protocol;

[0014] The meta information list is converted into a format recognizable by the large language model, and the meta information list after format conversion is registered with the large language model agent.

[0015] Optionally, the meta-information list includes multiple tool names, a function description corresponding to each tool name, and tool parameters required to execute an operation corresponding to each tool name.

[0016] Optionally, the large language model agent is specifically configured to perform the following steps:

[0017] Use the large language model to analyze the cloud phone control commands and the registered metadata list to obtain the tool name and tool parameters corresponding to the cloud phone control commands;

[0018] The tool calling instructions are constructed using a large language model. The tool calling instructions include the tool name and tool parameters corresponding to the cloud phone control instructions.

[0019] Optionally, the cloud phone control platform is specifically configured to perform the following steps:

[0020] Determine the device information corresponding to the target cloud phone based on the tool parameters in the task instruction; the device information includes the edge server, cloud phone cluster, cloud phone management service node, instance IP address, and device operating status;

[0021] If the device corresponding to the target cloud phone is in normal operation, the device information and task instructions are packaged and sent to the edge server to which the target cloud phone belongs;

[0022] If the device operating status corresponding to the target cloud phone is abnormal, the abnormal information will be returned to the user through the MCP server, MCP client, large language model agent and interactive agent in sequence; the abnormal information is used to indicate that the operation corresponding to the cloud phone control instruction has failed.

[0023] Optionally, the edge server is specifically configured to perform the following steps:

[0024] According to the cloud phone cluster and cloud phone management service node corresponding to the target cloud phone, the encapsulated device information and task instructions are sent to the cloud phone management service node corresponding to the target cloud phone.

[0025] Optionally, the cloud phone management service node is specifically used to perform the following steps:

[0026] Execute the operation corresponding to the tool name in the task instruction on the target cloud phone based on the instance IP address corresponding to the target cloud phone.

[0027] Optionally, the cloud phone management service node is also used to perform the following steps:

[0028] After executing the operation corresponding to the tool name in the task instruction, the execution result information is returned to the large language model agent through the edge server, cloud phone control platform, MCP server and MCP client in sequence, so that the large language model agent converts the execution result information into natural language form and returns it to the user through the interactive agent; the execution result information is used to indicate the execution status of the operation corresponding to the cloud phone control instruction.

[0029] Optionally, the edge server is also used to collect the operating status of each cloud phone management service node and each cloud phone in the cloud phone control system, and report the collected operating status to the cloud phone control platform in real time.

[0030] Optionally, the cloud phone control instruction is sent to the interactive intelligent body by the human-computer interaction software after receiving the cloud phone control instruction input by the user using natural language.

[0031] The above solution of the present application has the following beneficial effects:

[0032] In an embodiment of the present application, by receiving a cloud phone control instruction input by a user using natural language, and then using a large language model intelligent agent to analyze the cloud phone control instruction, after identifying the user's intention and key parameters, a tool call instruction that conforms to the computer language specification is constructed, and then the MCP client initiates a remote procedure call request to the MCP server based on the tool call instruction through the MCP protocol, and then the MCP server sends a task instruction to the cloud phone control platform based on the remote procedure call request, and finally the cloud phone control platform transmits the task instruction to the cloud phone management service node through the edge server, so that the cloud phone management service node performs the corresponding operation on the target cloud phone and completes the cloud phone control. Among them, since the user does not need to master complex programming skills, only simple natural language instructions are needed to achieve efficient control of the cloud phone and realize intelligent control of the cloud phone. Therefore, the cloud phone control system of the present application greatly simplifies the control process of the cloud phone and greatly improves the efficiency of cloud phone management.

[0033] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0035] Figure 1 A schematic structural diagram of a cloud phone control system based on a large language model provided in one embodiment of the present application. DETAILED DESCRIPTION

[0036] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0037] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0038] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0039] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0040] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0041] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0042] In response to the current problem of lack of intelligent control of cloud phones, which leads to low efficiency in cloud phone management, the embodiment of the present application provides a cloud phone control system based on a large language model. The cloud phone control system receives cloud phone control instructions input by the user using natural language, and then uses the large language model intelligent body to analyze the cloud phone control instructions. After identifying the user's intention and key parameters, it constructs a tool call instruction that conforms to the computer language specification. Then, the MCP client initiates a remote procedure call request to the MCP server based on the tool call instruction through the MCP protocol, and then the MCP server sends a task instruction to the cloud phone control platform based on the remote procedure call request. Finally, the cloud phone control platform transmits the task instruction to the cloud phone management service node through the edge server, so that the cloud phone management service node performs the corresponding operation on the target cloud phone and completes the cloud phone control. Among them, since the user does not need to master complex programming skills, only simple natural language instructions are needed to achieve efficient control of the cloud phone and realize intelligent control of the cloud phone. Therefore, the cloud phone control system of the present application greatly simplifies the control process of the cloud phone and greatly improves the efficiency of cloud phone management.

[0043] The cloud phone control system based on the large language model provided in the embodiment of the present application is exemplarily described below with reference to specific embodiments.

[0044] like Figure 1 As shown, the cloud phone control system based on the large language model provided in the embodiment of the present application includes an interactive intelligent agent, a large language model intelligent agent, an MCP client, an MCP server, a cloud phone control platform, an edge server and a cloud phone management service node.

[0045] The above-mentioned interactive intelligent agent is used to receive cloud phone control instructions input by the user using natural language, and send the cloud phone control instructions to the large language model intelligent agent.

[0046] In some embodiments of the present application, the cloud phone control instructions are sent to the interactive agent by the human-computer interaction software after receiving the cloud phone control instructions input by the user using natural language. The cloud phone control instructions are used to indicate the need to perform a control operation on the target cloud phone, such as restarting or shutting down the phone.

[0047] Specifically, users can use natural language to input cloud phone control instructions to the human-computer interaction software (such as the integrated platform DingTalk application) (such as restarting cloud phone AC1231, AC1231 is the number of the cloud phone, and cloud phone AC1231 is the aforementioned target cloud phone). After receiving the cloud phone control instruction, the human-computer interaction software triggers the preset network hook (WebHook) interface, and then the WebHook calls the external interface (API) exposed by the interactive intelligent agent in the cloud phone control system to pass the cloud phone control instruction to the interactive intelligent agent.

[0048] The large language model agent is used to analyze the cloud phone control instructions after receiving them, construct tool call instructions, and send the tool call instructions to the MCP client. The tool call instructions include the tool name and tool parameters.

[0049] In some embodiments of the present application, when the large language model agent receives a cloud phone control instruction, it will use the large language model (LLM) to understand and analyze the cloud phone control instruction to identify the user's intention (such as restart, which corresponds to the above-mentioned tool name, that is, the tool corresponding to the above-mentioned tool name is used to achieve the user's intention) and key parameters (that is, the above-mentioned tool parameters, such as the cloud phone number (ID) is AC1231). In other words, the large language model can recognize that the user wants to control the target cloud phone.

[0050] In some embodiments of the present application, after the large language model agent identifies the user intention and key parameters, the large language model agent will determine whether the conditions for executing the user intention are met (such as the existence of the "restart" tool and the parameters (i.e., the above-mentioned key parameters) meet the requirements). If so, a tool call instruction that complies with the computer language specification (such as the function call (FunctionCalling) specification) is constructed to instruct the control operation of the target cloud phone. Exemplarily, the tool call instruction can be: {"name":"restart","arguments":{"device ID":"AC1231"}}. Among them, name represents the tool name, restart represents restart, arguments represents the tool parameters, device ID represents the device number (i.e., the number of the cloud phone), and AC1231 is the number of the cloud phone. It can be understood that if it is not met, a prompt message of operation failure will be returned to the human-computer interaction software through the interactive agent to inform the user that the current operation has failed.

[0051] The Model Context Protocol (MCP) client is used to initiate a remote procedure call request to the MCP server through the MCP protocol after receiving a tool call instruction.

[0052] The above remote procedure call request includes a tool name and tool parameters to instruct a control operation (the operation performed by the tool corresponding to the tool name, such as restart) on the target cloud phone (the cloud phone corresponding to the tool parameters).

[0053] In some embodiments of the present application, the MCP client will initiate a remote procedure call request to the MCP server by specifying the tool name in accordance with the specifications of the MCP protocol to instruct a control operation (the operation performed by the tool corresponding to the tool name, such as restart) on the target cloud phone (the cloud phone corresponding to the tool parameter).

[0054] The MCP server is used to send a task instruction including a tool name and tool parameters to the cloud phone control platform after receiving a remote procedure call request.

[0055] The above task instructions are used to instruct the control operation (the operation performed by the tool corresponding to the tool name, such as restart) on the target cloud phone (the cloud phone corresponding to the tool parameter).

[0056] In some embodiments of the present application, after receiving a remote procedure call request, the MCP server will call the cloud phone platform specified interface and pass the constructed task instructions to the cloud phone control platform.

[0057] It should be noted that, in order to facilitate the large language model agent to determine whether the conditions for executing the user's intention are met, the MCP client is also used to perform the following steps to register a meta-information list for the large language model agent:

[0058] First, a connection is established with the MCP server via the MCP protocol, and a meta-information list is obtained from the MCP server via the MCP protocol. The meta-information list is then converted into a format recognizable by the large language model and registered with the large language model agent. The meta-information list includes multiple tool names, a functional description corresponding to each tool name (i.e., a description of the function of the tool corresponding to that tool name), and the tool parameters required to perform the corresponding operation (e.g., the tool parameter for the restart tool is the device ID).

[0059] After registering the meta-information list, the large language model agent can specifically use the large language model to analyze the cloud phone control instructions and the registered meta-information list to obtain the tool name and tool parameters corresponding to the cloud phone control instructions; and then use the large language model to construct a tool call instruction, which contains the tool name and tool parameters corresponding to the cloud phone control instructions.

[0060] The cloud phone control platform is used to determine the device information of the target cloud phone to be controlled by the cloud phone control instruction according to the task instruction, and send the task instruction and device information to the edge server to which the target cloud phone belongs.

[0061] In some embodiments of the present application, the cloud phone control platform is specifically configured to perform the following steps:

[0062] Determine the device information corresponding to the target cloud phone based on the tool parameters in the task instruction; the device information includes the edge server, cloud phone cluster, cloud phone management service node, instance IP address, and device operating status;

[0063] If the device corresponding to the target cloud phone is in a normal operating state (including but not limited to online, idle, etc.), the device information and task instructions are packaged and sent to the edge server to which the target cloud phone belongs (i.e., the edge server corresponding to the target cloud phone. It is understood that the edge server has the ability to decapsulate the packaged device information and task instructions according to a pre-agreed packaging method);

[0064] If the device corresponding to the target cloud phone is in an abnormal state (including but not limited to offline, faulty, etc.), no instructions will be issued. Instead, an exception message will be returned to the user through the MCP server, MCP client, large language model agent, and interactive agent in sequence. This exception message is used to indicate that the operation corresponding to the cloud phone control instruction failed (or the device is unavailable). In other words, the cloud phone control platform returns the exception information to the interactive agent through layer-by-layer feedback, and the interactive agent then returns the exception information to the human-computer interaction software to inform the user that the current operation has failed. This mechanism ensures status pre-check before task distribution, improving system stability and the success rate of task execution.

[0065] The above-mentioned edge server is used to transmit the task instructions and device information to the cloud phone management service node to which the target cloud phone belongs according to the device information, so that the cloud phone management service node performs the operation corresponding to the tool name on the target cloud phone.

[0066] In some embodiments of the present application, the edge server is specifically used to perform the following steps: according to the cloud phone cluster and cloud phone management service node corresponding to the target cloud phone, the encapsulated device information and task instructions are sent to the cloud phone management service node corresponding to the target cloud phone. It can be understood that generally, there are multiple cloud phones under the cloud phone management service node, which can realize the management of multiple cloud phones. Therefore, it is necessary to first find the cloud phone management service node to which the target cloud phone belongs based on the device information, and then send the device information and task instructions to the cloud phone management service node. It should be noted that the cloud phone management service node has the ability to unpack the encapsulated device information and task instructions according to the pre-agreed encapsulation method.

[0067] The above-mentioned cloud phone management service node is deployed on an ARM server (ARM server refers to a server that uses an ARM architecture processor. The ARM architecture is an architecture based on the reduced instruction set (RISC)). When the edge server sends a message to the cloud phone management service node to which the target cloud phone belongs, it will first find the cloud phone cluster corresponding to the target cloud phone, and then send task instructions and device information to the cloud phone management service node in the cloud phone cluster, so that the cloud phone management service node can accurately determine the target cloud phone based on the instance IP address corresponding to the target cloud phone, and then execute the operation corresponding to the tool name on the target cloud phone, that is, execute the tool corresponding to the tool name on the target cloud phone (such as restart).

[0068] The above-mentioned edge server is a long-connection edge server, which maintains a continuous two-way connection with the cloud phone control platform and the cloud phone management service node in the cloud phone cluster, and assumes the dual responsibilities of task relay and status synchronization. In addition to quickly and accurately routing to the corresponding cloud phone management service node according to the target cloud phone cluster and instance location information provided by the cloud phone control platform during the task issuance process, and relaying the task instructions to the cloud phone management service node, the edge server is also used to collect the operating status of each cloud phone management service node and each cloud phone in the cloud phone control system (including but not limited to online, offline, abnormal operation, etc.), and report the collected operating status to the cloud phone control platform in real time, so that the cloud phone control platform can understand the operating status of each cloud phone management service node and each cloud phone. This mechanism not only ensures the reliable relay of control tasks, but also provides basic support for the upper-level platform's equipment scheduling, task fault tolerance, status monitoring and other functions.

[0069] In some embodiments of the present application, the cloud phone management service node is specifically used to perform the following steps: according to the instance IP address corresponding to the target cloud phone, the operation corresponding to the tool name in the task instruction is executed on the target cloud phone, that is, the tool corresponding to the tool name is executed on the target cloud phone. It is understandable that after the cloud phone management service node executes the operation corresponding to the tool name in the task instruction, it will return the execution result information to the large language model agent through the edge server, the cloud phone control platform, the MCP server and the MCP client in sequence, so that the large language model agent converts the execution result information into natural language form and returns it to the user through the interactive agent; the execution result information is used to indicate the execution status of the operation corresponding to the cloud phone control instruction.

[0070] After receiving the execution result information returned by the MCP client (which includes a structured status code / message or a lower-level log fragment), the large language model agent uses the large language model to analyze the received execution result information, determine whether the operation on the cloud phone was successfully executed (if unsuccessful, it will also understand the reason for the failure), and generate a natural language execution summary that is easy for users to understand (for example, "Cloud phone AC1231 has successfully restarted" or "Restarting cloud phone AC1231 failed. The reason for failure is: the device is currently unavailable"). It is understandable that the execution result information received by the large language model agent is in a computer language format, while the execution result information sent to the interactive agent (i.e., the execution summary) is in a natural language format.

[0071] It is understandable that after receiving the execution result information, the interactive intelligent agent will return the execution result information in natural language format to the human-computer interaction software to inform the user of the execution status of the current operation, and realize the original path (or the notification channel set by the system) to feedback the execution status of the current operation to the user (for example, reply to the user who sent the instruction through DingTalk message).

[0072] It should be noted that in order to ensure that the large language model accurately converts information in computer language format and information in natural language format, a large number of training samples (including information in computer language format and information in natural language format corresponding to the information) can be used to train the large language model before use.

[0073] The cloud phone control system based on the large language model of the present application is illustrated below with reference to specific examples.

[0074] In this example, the test environment is as follows:

[0075] The large language model uses qwen-plus, the cloud phone control platform uses the cloud phone PAAS platform, the communication protocol uses the MCP protocol, and the tool set includes cloud phone restart and reset.

[0076] Typical implementation cases are as follows:

[0077] User command (i.e. cloud phone control command): Send "Restart cloud phone AC1231" via DingTalk.

[0078] Instruction analysis:

[0079] The MCP client obtains tool metadata (including tool parameter rules: the device ID cannot be empty) from the MCP server.

[0080] After LLM parses the command, it generates a structured call: {"name":"restart","arguments":{"device ID":"AC1231"}. Command execution: The MCP protocol encapsulates the parameters and calls the API of the cloud phone PAAS platform.

[0081] The cloud phone PAAS platform execution result is: {"code":"200","msg":"Operation successful"}; "code":"200" is the code indicating successful execution, and "msg" is the Chinese description. Closed-loop feedback: LLM converts the result into a natural language response: "Cloud phone AC1231 restart operation successfully executed."

[0082] In addition, this application tested 200 commands containing ambiguous expressions to control cloud phones and found that the command parsing accuracy was 98.5%, the end-to-end delay was an average of 3 to 10 seconds (from command input to user feedback), and the exception handling capability was as follows: when the device is empty, it returns "Device ID cannot be empty" (such as AC1231), and the illegal command interception rate is 100% (such as "Delete system files" returns "No operation permission"). These test data show that: the MCP protocol effectively bridges the LLM intelligent layer and the cloud phone execution layer (100% correct command routing), the LLM dual parsing mechanism (command understanding + result translation) significantly reduces the usage threshold, and dynamic tool set management supports seamless business expansion (new tools take effect in real time).

[0083] In summary, the cloud phone control system based on the large language model provided by this application has the following advantages:

[0084] 1. Natural Language Control: Compared to existing API-based control or script automation methods, this application leverages the natural language understanding capabilities of the Large Language Model (LLM) to parse user-entered natural language commands into executable cloud phone control operations. This interface interacts with the cloud phone control backend via the standardized MCP protocol, enabling intelligent closed-loop control. Operations and maintenance personnel no longer need to master complex programming skills; they can efficiently operate the cloud phone using simple natural language commands, greatly simplifying the operational process.

[0085] 2. Intelligent Parsing and Efficient Automation: Existing technologies often rely on predefined commands or codes and lack flexible intelligent parsing capabilities. This application leverages the Function Calling capabilities of a large language model to accurately parse user natural language input into structured control instructions. The system intelligently interprets the context and avoids errors that can occur when manually writing scripts, improving operational accuracy and automation.

[0086] 3. Operation Feedback and Intelligent Adjustment Mechanism: Compared to existing technologies that simply record or ignore operation feedback, this application uses a feedback mechanism to achieve real-time feedback and intelligent adjustment of cloud phone operation results. After the operation, the system will determine whether the operation is successful based on the feedback and automatically perform subsequent operations or provide prompts when necessary. This automated feedback process greatly improves the system's reliability and self-correction capabilities.

[0087] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A cloud phone control system based on a large language model, characterized in that: include: An interactive agent, configured to receive a cloud phone control instruction input by a user using natural language, and send the cloud phone control instruction to a large language model agent; The large language model agent is used to analyze the cloud phone control instruction after receiving it, construct a tool call instruction, and send the tool call instruction to the MCP client; the tool call instruction includes a tool name and tool parameters; The MCP client is configured to initiate a remote procedure call request to the MCP server via the MCP protocol after receiving the tool call instruction; The remote procedure call request includes the tool name and the tool parameters; The MCP server is configured to send a task instruction including the tool name and the tool parameters to the cloud phone control platform after receiving the remote procedure call request; The cloud phone control platform is used to determine the device information of the target cloud phone to be controlled by the cloud phone control instruction according to the task instruction, and send the task instruction and the device information to the edge server to which the target cloud phone belongs; The edge server is used to transmit the task instruction and the device information to the cloud phone management service node to which the target cloud phone belongs according to the device information, so that the cloud phone management service node performs the operation corresponding to the tool name on the target cloud phone.

2. The cloud phone control system according to claim 1, characterized in that: The MCP client is further configured to perform the following steps: Establishing a connection with the MCP server through the MCP protocol, and obtaining a meta-information list from the MCP server through the MCP protocol; The meta information list is converted into a format recognizable by the large language model, and the meta information list after the format conversion is registered with the large language model agent.

3. The cloud phone control system according to claim 2, characterized in that: The meta-information list includes multiple tool names, a function description corresponding to each tool name, and tool parameters required to execute an operation corresponding to each tool name.

4. The cloud phone control system according to claim 3, characterized in that: The large language model agent is specifically configured to perform the following steps: Analyze the cloud phone control command and the registered meta-information list using a large language model to obtain a tool name and tool parameters corresponding to the cloud phone control command; The large language model is used to construct a tool calling instruction, wherein the tool calling instruction includes a tool name and tool parameters corresponding to the cloud phone control instruction.

5. The cloud phone control system according to claim 1, characterized in that: The cloud phone control platform is specifically used to perform the following steps: Determine the device information corresponding to the target cloud phone according to the tool parameters in the task instruction; the device information includes the edge server, cloud phone cluster, cloud phone management service node, instance IP address and device operation status; If the device operating status corresponding to the target cloud phone is normal, the device information and the task instruction are packaged and sent to the edge server to which the target cloud phone belongs; If the device operating status corresponding to the target cloud phone is abnormal, abnormal information is returned to the user through the MCP server, the MCP client, the large language model agent, and the interactive agent in sequence; the abnormal information is used to indicate that the operation corresponding to the cloud phone control instruction has failed.

6. The cloud phone control system according to claim 5, characterized in that: The edge server is specifically configured to perform the following steps: According to the cloud phone cluster and cloud phone management service node corresponding to the target cloud phone, the packaged device information and task instructions are sent to the cloud phone management service node corresponding to the target cloud phone.

7. The cloud phone control system according to claim 6, characterized in that: The cloud phone management service node is specifically used to perform the following steps: According to the instance IP address corresponding to the target cloud phone, the operation corresponding to the tool name in the task instruction is executed on the target cloud phone.

8. The cloud phone control system according to claim 7, characterized in that: The cloud phone management service node is further configured to perform the following steps: After executing the operation corresponding to the tool name in the task instruction, the execution result information is returned to the large language model agent through the edge server, the cloud phone control platform, the MCP server and the MCP client in sequence, so that the large language model agent converts the execution result information into natural language form and returns it to the user through the interactive agent; the execution result information is used to indicate the execution status of the operation corresponding to the cloud phone control instruction.

9. The cloud phone control system according to claim 1, characterized in that: The edge server is also used to collect the operating status of each cloud phone management service node and each cloud phone in the cloud phone control system, and report the collected operating status to the cloud phone control platform in real time.

10. The cloud phone control system according to claim 1, characterized in that: The cloud phone control instruction is sent to the interactive intelligent body by the human-computer interaction software after receiving the cloud phone control instruction input by the user using natural language.

Images