Cloud operating system interaction system, method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a cloud operating system interaction system, method and device, electronic equipment and a storage medium, and the system comprises a large language model which is used for recognizing input data of a user, obtaining operation intention information, obtaining operation parameters corresponding to the input data, and storing the operation parameters in a database; the intelligent agent is used for determining a target cloud operating system application programming interface tool according to the operation intention information and the corresponding relation between the operation intention and the cloud operating system application programming interface tool, executing calling of the target cloud operating system application programming interface tool according to the operation parameters, and generating a calling result. The operation intention of the user is recognized through the large language model, multiple rounds of interaction with the user are carried out to obtain the operation parameters, what cloud operation system operation the user wants to do can be grasped, the user can be continuously responded, splicing of the operation parameters is achieved according to input of the user, and the user experience is improved. Therefore, the intelligence and convenience of interaction of the cloud operating system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud operating systems, and particularly relates to a cloud operating system interaction system, method, device, electronic device, and storage medium. Background Art

[0002] A cloud operating system is a new type of operating system that has emerged with the booming development of cloud computing technology. It is responsible for managing and scheduling the computing, storage, and network resources of large-scale clusters, and providing users with efficient and elastic computing services. Different from traditional single-machine operating systems, the core task of a cloud operating system is to expand from single-machine resource management to distributed cluster resource management, and support the concurrent operation of multiple tenants, multiple tasks, and multiple applications. In this process, human-computer interaction, as the bridge between users and cloud operating systems, plays a crucial role.

[0003] The related cloud operating system interaction methods are mainly command-line clients or WebUI (Website User Interface). However, the related cloud operating system interaction methods tend to focus more on the implementation of functions in the trade-off between convenience and functionality, weakening the pursuit of interaction convenience and intelligence. As a result, there will be problems such as inconvenient and unintelligent cloud operating system interaction. Summary of the Invention

[0004] In view of this, the present invention aims to provide a cloud operating system interaction system, method, device, electronic device, and storage medium to solve the problems of inconvenient and unintelligent cloud operating system interaction caused by the weakening of the pursuit of interaction convenience and intelligence in the related cloud operating system interaction methods.

[0005] According to the first aspect of the present invention, a cloud operating system interaction system is provided. The cloud operating system interaction system includes a large language model, an intelligent agent, and a user. Among them, the large language model establishes a communication connection with the intelligent agent, and the intelligent agent establishes a communication connection with the user;

[0006] The large language model is used to identify the input data of the user obtained in advance, obtain operation intention information, and obtain operation parameters corresponding to the input data;

[0007] The intelligent agent is used to determine a target cloud operating system application programming interface tool according to the operation intention information and the corresponding relationship between the preset operation intention and the cloud operating system application programming interface tool, execute the target cloud operating system application programming interface tool call according to the operation parameters, generate a call result, and send the call result to the user.

[0008] Optionally, the cloud operating system interaction system includes a prompt template library, wherein the intelligent agent establishes a communication connection with the prompt template library;

[0009] The intelligent agent is used to receive the input data of the user, determine a first prompt template from the prompt template library, fill the input data into the first prompt template, and generate a first prompt;

[0010] The large language model is used to determine first structured data according to the first prompt, wherein the first structured data includes first missing parameters and first extracted parameters;

[0011] The intelligent agent is used to judge whether the first missing parameter is empty, and in the case where the first missing parameter is empty, use the first extracted parameter as the operation parameter.

[0012] Optionally, the first structured data includes response information;

[0013] The intelligent agent is used to, in the case where the first missing parameter is non-empty, send the response information to the user, receive the user response data in response to the response information from the user, determine a second prompt template from the preset prompt template library, fill the user response data and the first structured data into the second prompt template, and generate a second prompt;

[0014] The large language model is used to determine second structured data according to the second prompt; wherein the second structured data includes the second missing parameters and second extracted parameters;

[0015] The intelligent agent is used to judge whether the second missing parameter is empty, and if the second missing parameter is non-empty, re-send the response information to the user until the second missing parameter is empty, and use the second extracted parameter as the operation parameter.

[0016] Optionally, the cloud operating system interaction system includes a cloud operating system, the cloud operating system establishes a communication connection with the intelligent agent, and the target cloud operating system application programming interface tool includes a target cloud operating system application programming interface;

[0017] The intelligent agent is used to send an application programming interface call request to the cloud operating system, wherein the application programming interface call request includes the operation parameter;

[0018] The cloud operating system is used to receive the application programming interface call request, call the target cloud operating system application programming interface according to the operation parameter, generate a call result, and send the call result to the intelligent agent.

[0019] Optionally, the target cloud operating system application programming interface tool includes a number of the target cloud operating system application programming interfaces;

[0020] The intelligent agent is used to send a first application programming interface call request to the cloud operating system, where the first application programming interface call request includes the operation parameters corresponding to the first target cloud operating system application programming interface;

[0021] The cloud operating system is used to receive the first application programming interface call request, call the first target cloud operating system application programming interface according to the operation parameters corresponding to the first target cloud operating system application programming interface, generate a first call result, and send the first call result to the intelligent agent;

[0022] The intelligent agent is used to send a second application programming interface call request to the cloud operating system, where the second application programming interface call request includes the first call result and the operation parameters corresponding to the second target cloud operating system application programming interface;

[0023] The cloud operating system is used to receive the second application programming interface call request, call the second target cloud operating system application programming interface according to the first call result and the operation parameters corresponding to the second target cloud operating system application programming interface, generate a second call result, until a number of the target cloud operating system application programming interfaces are called to generate a call result, and send the call result to the intelligent agent.

[0024] Optionally, the intelligent agent is used to determine a third prompt word template from the prompt word template library, fill the call result into the third prompt word template, and generate a third prompt word;

[0025] The large language model is used to generate a target call result according to the third prompt word and send the target call result to the intelligent agent;

[0026] The intelligent agent is used to send the target call result to the user.

[0027] According to a second aspect of the present invention, there is provided a cloud operating system interaction method, the method including:

[0028] Identifying the input data of the user obtained in advance to obtain operation intention information;

[0029] Obtaining the operation parameters corresponding to the input data;

[0030] When the operation parameters are obtained, a target cloud operating system application programming interface tool is determined according to the operation intention information and the preset correspondence between the operation intention information and the cloud operating system application programming interface tool.

[0031] Execute the call of the target cloud operating system application programming interface tool according to the operation parameters to generate a call result.

[0032] Send the call result to the user.

[0033] According to a third aspect of the present invention, a cloud operating system interaction device is provided. The cloud operating system interaction device includes:

[0034] An operation intention recognition module, configured to recognize the input data of the user obtained in advance to obtain operation intention information.

[0035] An operation parameter acquisition module, configured to acquire operation parameters corresponding to the input data.

[0036] A target application programming interface tool acquisition module, configured to determine a target cloud operating system application programming interface tool according to the operation intention information and the preset correspondence between the operation intention information and the cloud operating system application programming interface tool when the operation parameters are obtained.

[0037] An application programming interface call module, configured to execute the call of the target cloud operating system application programming interface tool according to the operation parameters to generate a call result.

[0038] A call result feedback module, configured to send the call result to the user.

[0039] According to yet another aspect of the present invention, an electronic device is further provided, including:

[0040] A processor;

[0041] A memory for storing executable instructions of the processor;

[0042] Wherein, the processor is configured to execute the instructions to implement the cloud operating system interaction method as described above.

[0043] According to yet another aspect of the present invention, a readable storage medium is further provided. A computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps of the cloud operating system interaction method as described above are implemented.

[0044] The cloud operating system interaction system provided by the embodiments of the present invention includes a large language model, an intelligent agent, and a user. Among them, the large language model establishes a communication connection with the intelligent agent, and the intelligent agent establishes a communication connection with the user. The large language model is used to identify the input data of the user obtained in advance to obtain operation intention information and acquire operation parameters corresponding to the input data. The intelligent agent is used to determine the target cloud operating system application programming interface tool according to the operation intention information and the corresponding relationship between the preset operation intention and the cloud operating system application programming interface tool, execute the target cloud operating system application programming interface tool call according to the operation parameters, generate a call result, and send the call result to the user. By using the large language model to identify the user's operation intention information and conduct multiple rounds of interaction with the user until complete operation parameters are obtained, the present invention can not only more directly grasp what the user wants to do, but also continuously respond to the user and intelligently splice the operation parameters according to the user's input, thereby improving the intelligence and convenience of cloud operating system interaction. In addition, by using the intelligent agent to determine the target cloud operating system application programming interface tool according to the operation intention information and the preset corresponding relationship, the present invention can intelligently call the appropriate cloud operating system application programming interface tool according to the user's operation intention information, avoiding the user from searching for the appropriate cloud operating system application programming interface tool among numerous function options by himself, improving the efficiency of cloud operating system interaction, and solving the problems of inconvenience and lack of intelligence in the related cloud operating system interaction methods.

[0045] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically exemplified below. Brief Description of the Drawings

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art.

[0047] Figure 1 It is a schematic diagram of a cloud operating system interaction system provided by an embodiment of the present invention;

[0048] Figure 2 It is a step flow chart of a cloud operating system interaction method provided by an embodiment of the present invention;

[0049] Figure 3 It is a block diagram of a cloud operating system interaction device provided by an embodiment of the present invention;

[0050] Figure 4 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. Specific Embodiments

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will elaborate on each embodiment of the present invention in detail with reference to the accompanying drawings. However, those of ordinary skill in the art can understand that in each embodiment of the present invention, many technical details are provided to help readers better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can still be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation to the specific implementation of the present invention. The various embodiments can be combined and cross-referenced with each other on the premise of not being contradictory.

[0052] For ease of understanding, first, a brief introduction to the terms involved in the embodiments of the present application will be given.

[0053] 1. Cloud OS (Cloud Operating System)

[0054] The cloud operating system, also known as the cloud computing environment operating system or the cloud computing center operating system, is the overall infrastructure software environment for building a cloud computing center and is also the system platform for operation, management, and maintenance. It is an adaptive extension of traditional single-machine operating systems for Internet applications and the cloud computing model. The cloud operating system not only manages the software and hardware resources of a single computer but also provides a complete set of network- and software / hardware-based services by managing the software and hardware devices of the entire cloud computing data center, in order to better quickly build various application services in the cloud computing environment.

[0055] 2. LLMs (Large Language Models)

[0056] Large language models are a type of deep neural network learning model with a large number of parameters. By processing a large amount of text data, large language models learn language patterns, grammar, and semantics, enabling them to understand and generate human language and playing an important role in the field of natural language processing (NLP). Currently, artificial intelligence technology is developing rapidly, and representative large language models such as GPT4, LLaMA, Wenxin Yiyan, and Doubao are showing increasingly strong intelligent interaction capabilities.

[0057] Please refer to Figure 1 , Figure 1 which is a schematic diagram of a cloud operating system interaction system provided by the embodiments of the present application.

[0058] As shown in Figure 1As shown in the figure, the cloud operating system interaction system includes a user 101, an intelligent agent 102, a preset prompt word template library 103, a large language model 104, a cloud operating system API (Application Programming Interface) tool library 105, a memory 106, and a cloud operating system 107. It should be noted that the intelligent agent includes a preset behavior template library.

[0059] Among them, the behavior template library includes several behavior templates. One behavior template corresponds to the operation intention information of a user. At least an operation name, an operation API, and operation parameters are included in one behavior template. The behavior templates correspond to various operations of the cloud operating system, such as: creating an application, creating a pod, creating a storage pool storage volume, deleting and modifying the above-created resources, viewing logs, viewing monitoring information, etc.

[0060] The prompt word template library includes several prompt word templates. The prompt word templates are mainly used to generate prompt words when determining the operation intention of the user before sending a request to the large language model and when judging the call result and translating and explaining after API call.

[0061] The large language model can take the prompt word as input and output a set of structured data. This set of structured data can include the operation intention of the user, the extracted parameters, the missing parameters, and the response information (the response information to the user).

[0062] The memory mainly stores the context key information in the multi-round conversation process of the user, such as: user information, relevant resource information, relevant task information, the structured data output by the large language model, etc. These information can be filled into the prompt word template to form the final prompt word when having a conversation with the large language model.

[0063] The cloud operating system API tool library is an encapsulation of the underlying API of the cloud operating system and is a collection of atomic operations of the cloud operating system. The API tool library can generally be encapsulated into other language libraries according to needs. The cloud operating system API tool library includes several cloud operating system API tools. One cloud operating system API tool corresponds to the operation intention information of a user. Among them, one cloud operating system API tool can include one cloud operating system API or multiple cloud operating system APIs. If one cloud operating system API tool includes one cloud operating system API, it means to execute one cloud operating system API call. If one cloud operating system API tool includes multiple cloud operating system APIs, it means to execute multiple cloud operating system API calls. It should be noted that the call process can be a serial call or a parallel call.

[0064] In an alternative embodiment of the present invention, a large language model is used to identify the input data of a user obtained in advance, obtain operation intention information, and obtain operation parameters corresponding to the input data.

[0065] The intelligent agent is used to determine the target cloud operating system application programming interface tool according to the operation intention information and the preset correspondence between the operation intention and the cloud operating system application programming interface tool, execute the target cloud operating system application programming interface tool call according to the operation parameters, generate a call result, and send the call result to the user.

[0066] It should be noted that in the embodiment of the present invention, the large language model can perform intention recognition on the input data of the user obtained in advance to obtain the operation intention information of the user. For example: if the input data of the user is "I want to create an application named 'demo', the startup command is ' / mywork / start-demo.exe', and the external port number is 80", then the operation intention information of the user is "create a demo application pod".

[0067] Moreover, the large language model can also obtain all operation parameters related to the input data of the user, and send all the obtained operation parameters to the intelligent agent. When the intelligent agent obtains all the operation parameters, it determines the target cloud operating system application programming interface tool according to the obtained operation intention information and the preset correspondence between the operation intention information and the cloud operating system application programming interface tool, executes the target cloud operating system application programming interface tool call according to the operation parameters, generates a call result, and sends the call result to the user.

[0068] The present invention identifies the operation intention information of the user through the large language model, conducts multiple rounds of interaction with the user until all operation parameters are obtained, which can not only more directly grasp what the user wants to do, but also continuously respond to the user, and intelligently splice the operation parameters according to the user's input, thereby improving the intelligence and convenience of the cloud operating system interaction. In addition, the present invention determines the target cloud operating system application programming interface tool according to the operation intention information and the preset correspondence through the intelligent agent, can intelligently call the appropriate cloud operating system application programming interface tool according to the operation intention information of the user, avoids the user from searching for the appropriate cloud operating system application programming interface tool among numerous function options by himself, improves the efficiency of the cloud operating system interaction, and solves the problems of inconvenience and non-intelligence existing in the related cloud operating system interaction methods.

[0069] Furthermore, in an alternative embodiment of the present invention, the cloud operating system interaction system includes a prompt word template library, wherein the intelligent agent establishes a communication connection with the prompt word template library.

[0070] The intelligent agent is used to receive the input data of the user, determine the first prompt word template from the prompt word template library, fill the input data into the first prompt word template, and generate the first prompt word.

[0071] The large language model is used to determine the first structured data according to the first prompt word, wherein the first structured data includes the first missing parameter and the first extracted parameter.

[0072] The intelligent agent is used to judge whether the first missing parameter is empty. In the case where the first missing parameter is empty, the first extracted parameter is used as the operation parameter.

[0073] It should be noted that in the embodiment of the present invention, the user inputs data, and the input data of the user can be "I want to create an application named 'demo', the startup command is ' / mywork / start-demo.exe', and the external port number is 80".

[0074] The user sends the input data to the intelligent agent. When the intelligent agent receives the input data of the user, the intelligent agent selects a prompt word template from the preset prompt word template library, and the selected prompt word template is the first prompt word template.

[0075] After determining the first prompt word template, the intelligent agent fills the input data of the user into the first prompt word template to generate the first prompt word. The first prompt word can be "You are an expert in cloud operating system operation and maintenance, good at solving problems of cloud operating system users. Your approach is to identify the operation intention information of the user and be able to map the operation intention information to the behavior template. The available behavior templates are as follows: $behavior template library. Note that you can only select the appropriate behavior template from the above behavior template library and judge the missing parameters. When the parameters are incomplete, please output the parameters that need to be supplemented by the user. When the parameters are sufficient, output the call operation that you will complete on behalf of the user. Here is an example: $example. Next is the user's question: $user input. Additional context information: $context information of this session in memory". It should be noted that the fields starting with "$" in the first prompt word are pre-set content or variable filling input by the user.

[0076] After generating the first prompt, the intelligent agent sends the first prompt to the large language model. Using the first prompt as the input to the large language model, the large language model outputs a set of structured data, which is the first structured data. Specifically, 1) The large language model identifies the user's operation intention information based on the input data of the user in the first prompt. For example, if the user's first input data is "I want to create an application named 'demo', the start command is ' / mywork / start-demo.exe', and the external port number is 80", then the user's operation intention information is "create a demo application pod". 2) Then, the large language model selects the behavior template corresponding to the user's operation intention information from the behavior template library of the intelligent agent and obtains the operation parameters included in the behavior template. The operation parameters included in the behavior template are all the operation parameters required to implement the user's operation intention information. 3) The large language model extracts parameters based on the user's first input data in the first prompt to obtain the extracted parameters. 4) The large language model compares the operation parameters included in the behavior template with the extracted parameters to determine whether there are missing parameters. Specifically, it determines whether the missing parameters are empty. If the missing parameters are non-empty, it means there are missing parameters. If the missing parameters are empty, it means there are no missing parameters. In the case of missing parameters, the large language model will output the response information to the user, that is, the response information. Therefore, the large language model can finally output the user's operation intention information, extracted parameters, missing parameters, and response information.

[0077] Among them, the first structured data output by the large language model may include the first operation intention information, the first extracted parameters, the first missing parameters, and the first response information. For example: The first structured data may be "[{\"toolname\":\"createpod\",\"params\":{\"user\":\"xxx\",\"command\":\" / mywork / start-demo.exe\",\"port\":80,\"image\":\"\"},\"missing_params\":[\"image\"],\"response_to_user\":\"What image do you want to use to run the demo application\"}]".

[0078] After obtaining the first structured data, the large language model sends the first structured data to the intelligent agent. When the intelligent agent receives the first structured data sent by the large language model, it will determine whether the first missing parameters in the first structured data are empty.

[0079] If the first missing parameters are empty, it means there are no missing parameters, then the first extracted parameters in the first structured data are used as the operation parameters.

[0080] Through the interaction between the large language model and the user, the present invention automatically extracts the filled parameters and determines the missing parameters, reducing manual intervention and improving the acquisition efficiency of operation parameters.

[0081] Further, in an optional embodiment of the present invention, the intelligent agent is used to send a response message to the user when the first missing parameter is non-empty, receive the user response data in response to the response message, determine a second prompt template from a preset prompt template library, fill the user response data and the first structured data into the second prompt template, and generate a second prompt.

[0082] The large language model is used to determine the second structured data according to the second prompt; wherein, the second structured data includes the second missing parameter and the second extracted parameter.

[0083] The intelligent agent is used to determine whether the second missing parameter is empty. If the second missing parameter is non-empty, it will send a response message to the user again until the second missing parameter is empty, and use the second extracted parameter as the operation parameter.

[0084] It should be noted that in the embodiment of the present invention, when the first missing parameter is non-empty, the intelligent agent sends the response message in the first structured data to the user, and at the same time stores the first structured data in the memory.

[0085] When the user receives the response message, the user will continue to input data according to the response message. The input data is the user response data, and the user response data is sent to the intelligent agent. For example: if the response message is "What image do you want to use to run the demo application", the user response data can be "Use the image my-demo:v1".

[0086] When the intelligent agent receives the user response data, it obtains the first structured data from the memory and selects a prompt template from the preset prompt template library. The selected prompt template is the second prompt template. After determining the second prompt template, the intelligent agent fills the user response data and the first structured data into the second prompt template to generate a second prompt.

[0087] After generating the second prompt, the intelligent agent sends the second prompt to the large language model. Using the second prompt as the input of the large language model, the large language model outputs a set of structured data, and this set of structured data is the second structured data. The second structured data can include the second operation intention information, the second extracted parameter, the second missing parameter and the second response information. The large language model sends the second structured data to the intelligent agent.

[0088] When the intelligent agent receives the second structured data sent by the large language model, it determines whether the second missing parameter is empty. If the second missing parameter is not empty, it sends a response message to the user again until the second missing parameter is empty, and uses the second extracted parameter as the operation parameter.

[0089] By continuously receiving user input data and determining structured data according to the prompt words until the missing parameter is empty, the present invention can effectively ensure that the finally obtained operation parameter is complete, avoiding errors or inability to perform subsequent operations caused by missing parameters, and improving the accuracy of the entire operation process based on complete data.

[0090] Further, in an optional embodiment of the present invention, the cloud operating system interaction system includes a cloud operating system, the cloud operating system establishes a communication connection with the intelligent agent, and the target cloud operating system application programming interface tool includes a target cloud operating system application programming interface.

[0091] The intelligent agent is used to send an application programming interface call request to the cloud operating system, where the application programming interface call request includes operation parameters.

[0092] The cloud operating system is used to receive the application programming interface call request, call the target cloud operating system application programming interface according to the operation parameters, generate a call result, and send the call result to the intelligent agent.

[0093] It should be noted that in the embodiment of the present invention, when the target cloud operating system API tool includes a target cloud operating system API, it means that the call process of the target cloud operating system API only needs to be executed once. Specifically, the intelligent agent sends an API call request to the cloud operating system, where the API call request includes operation parameters. When the cloud operating system receives the API call request sent by the intelligent agent, it calls the target cloud operating system API according to the operation parameters and generates a call result.

[0094] By receiving different API call requests respectively, the present invention can flexibly call the target cloud operating system API according to actual needs. Whether it is a single cloud operating system API or multiple cloud operating system APIs, they can be called orderly to adapt to different business logic requirements.

[0095] Further, in an optional embodiment of the present invention, the target cloud operating system application programming interface tool includes several target cloud operating system application programming interfaces:

[0096] The intelligent agent is used to send a first application programming interface (API) call request to the cloud operating system, where the first API call request includes operation parameters corresponding to the first target cloud operating system API.

[0097] The cloud operating system is used to receive the first API call request, call the first target cloud operating system API according to the operation parameters corresponding to the first target cloud operating system API, generate a first call result, and send the first call result to the intelligent agent.

[0098] The intelligent agent is used to send a second API call request to the cloud operating system, where the second API call request includes the first call result and operation parameters corresponding to the second target cloud operating system API.

[0099] The cloud operating system is used to receive the second API call request, call the second target cloud operating system API according to the first call result and the operation parameters corresponding to the second target cloud operating system API, generate a second call result, and continue this process until several target cloud operating system APIs are called to generate a call result, and then send the call result to the intelligent agent.

[0100] It should be noted that in the embodiments of the present invention, when the target cloud operating system API tool includes several target cloud operating system APIs (the first target cloud operating system API, the second target cloud operating system API, the third target cloud operating system API...), the operation parameters include the operation parameters of all target cloud operating system APIs (the first target cloud operating system API, the second target cloud operating system API, the third target cloud operating system API...), which means that the call process of the target cloud operating system APIs needs to be executed multiple times until all the target cloud operating system APIs included in the target cloud operating system API tool are called to generate a call result.

[0101] Specifically, the intelligent agent sends a first API call request to the cloud operating system, where the first API call request includes the operation parameters corresponding to the first target cloud operating system API.

[0102] When the cloud operating system receives the first API call request sent by the intelligent agent, it calls the first target cloud operating system API according to the operation parameters corresponding to the first target cloud operating system API, generates a first call result, and sends the first call result to the intelligent agent.

[0103] In the case that the intelligent agent receives the first call result, a second API call request is sent to the cloud operating system, where the second API call request includes the first call result and the operation parameters corresponding to the second target cloud operating system API.

[0104] In the case that the cloud operating system receives the second API call request, the second target cloud operating system API is called according to the first call result and the operation parameters corresponding to the second target cloud operating system API to generate a second call result, until several target cloud operating system APIs are called to generate a call result.

[0105] In the present invention, when multiple cloud operating system API calls are involved, the result of the previous call can be combined with the operation parameters corresponding to the next target cloud operating system API to gradually construct and integrate the call result, which helps to implement complex business processes and complete higher-level functions through the collaborative work of multiple cloud operating system APIs.

[0106] Further, in an optional embodiment of the present invention, the intelligent agent is used to determine a third prompt word template from the prompt word template library, fill the call result into the third prompt word template to generate a third prompt word.

[0107] The large language model is used to generate a target call result according to the third prompt word and send the target call result to the intelligent agent.

[0108] The intelligent agent is used to send the target call result to the user.

[0109] It should be noted that in the embodiment of the present invention, in the case that the cloud operating system obtains the call result, the cloud operating system sends the call result to the intelligent agent.

[0110] In the case that the intelligent agent receives the call result sent by the cloud operating system, the intelligent agent selects a template for explaining the call result, that is, the third prompt word template, from the preset prompt word template library, fills the call result into the third prompt word template to generate a third prompt word, and sends the third prompt word to the large language model.

[0111] The large language model takes the third prompt word as input, polishes, interprets and processes the call result in the third prompt word, finally outputs the target call result, and sends the target call result to the intelligent agent.

[0112] In the case that the intelligent agent receives the target call result, the intelligent agent sends the target call result to the user.

[0113] In the present invention, the third prompt word template is determined from a preset prompt word template library, and then the call result is filled in to generate the third prompt word. Finally, the large language model polishes, interprets, and processes the call result to obtain the target call result. This process can transform the originally possibly rather rigid and difficult-to-understand call result into a form more in line with the user's understanding habits, enabling the user to more easily understand the call result of the cloud operating system.

[0114] Further, in an alternative embodiment of the present invention, the intelligent agent is used to send the user's operation intention information to the user.

[0115] When the user receives the operation intention information, the user determines whether the operation intention information is correct. If the operation intention information is correct, the user sends a confirmation result to the intelligent agent.

[0116] The intelligent agent is used to, when receiving the confirmation result, execute the step of determining the target cloud operating system application programming interface tool according to the operation intention information and the corresponding relationship between the preset operation intention information and the cloud operating system application programming interface tool.

[0117] It should be noted that in the embodiment of the present invention, when the intelligent agent determines that there are no missing parameters, the intelligent agent sends the operation intention information of the user output by the large language model to the user. When the user receives the operation intention information sent by the intelligent agent, the user determines whether the operation intention information is correct. If the operation intention information is correct, the user feeds back a confirmation result to the intelligent agent. When the intelligent agent receives the confirmation result, the intelligent agent continues to execute the step of determining the target cloud operating system application programming interface tool according to the operation intention information and the corresponding relationship between the preset operation intention information and the cloud operating system application programming interface tool.

[0118] In this application, by sending the operation intention information output by the large language model to the user and allowing the user to judge the correctness, an additional accuracy review level is added. As the ultimate executor or relevant stakeholder of the operation, the user can judge whether the operation intention information meets the expectations based on their own knowledge and needs, avoiding the situation where subsequent operation mistakes are directly caused by the incorrect output of the large language model.

[0119] According to the embodiment of the present invention, a cloud operating system interaction method is also provided. As Figure 2 shown, the step flowchart of the cloud operating system interaction method provided by the embodiment of the present invention is shown. The method may include:

[0120] Step 201, identify the input data of the user obtained in advance to obtain the operation intention information.

[0121] Step 202, obtain the operation parameters corresponding to the input data.

[0122] Step 203: When the operation parameters are obtained, determine the target cloud operating system application programming interface tool according to the operation intention information and the preset correspondence between the operation intention information and the cloud operating system application programming interface tool.

[0123] Step 204: Execute the target cloud operating system application programming interface tool call according to the operation parameters to generate a call result.

[0124] Step 205: Send the call result to the user.

[0125] It should be noted that in the embodiments of the present invention, the input data of the user is obtained. The intention of the input data of the user is recognized to obtain the operation intention information of the user. For example, if the input data of the user is "I want to create an application named 'demo', the start command is ' / mywork / start - demo.exe', and the external port number is 80", then the operation intention information of the user is "create a demo application pod".

[0126] Obtain all operation parameters related to the input data of the user. When the operation parameters are obtained, determine the target cloud operating system application programming interface tool according to the obtained operation intention information and the preset correspondence between the operation intention information and the cloud operating system application programming interface tool.

[0127] Execute the target cloud operating system application programming interface tool call according to the operation parameters to generate a call result, and send the call result to the user.

[0128] By recognizing the operation intention information of the user, the present invention can more directly grasp what cloud operating system interaction operations the user wants to perform, thereby simplifying the operation process and improving the intelligence and convenience of cloud operating system interaction. In addition, by determining the target application cloud operating system program programming interface tool according to the operation intention information and the preset correspondence, the present invention can intelligently call the appropriate cloud operating system application programming interface tool according to the operation intention information of the user, avoiding the user from searching for the appropriate cloud operating system application programming interface tool among numerous function options by himself, improving the efficiency of cloud operating system interaction, and solving the problems of inconvenience and non - intelligence existing in the related cloud operating system interaction methods.

[0129] According to the embodiments of the present invention, a cloud operating system interaction device is further provided. Refer to Figure 3 , Figure 3 is the block diagram of a cloud operating system interaction device provided by the embodiments of the present invention. The cloud operating system interaction device includes:

[0130] The operation intention recognition module 301 is used to recognize the input data of the user obtained in advance to obtain operation intention information;

[0131] The operation parameter acquisition module 302 is used to acquire the operation parameters corresponding to the input data;

[0132] The target cloud operating system application programming interface tool acquisition module 303 is used to determine the target cloud operating system application programming interface tool according to the operation intention information and the preset corresponding relationship between the operation intention information and the cloud operating system application programming interface tool when the operation parameters are acquired;

[0133] The application programming interface call module 304 is used to execute the call of the target cloud operating system application programming interface tool according to the operation parameters to generate a call result;

[0134] The call result feedback module 305 is used to send the call result to the user.

[0135] An embodiment of the present invention further provides an electronic device, as Figure 4 shown, including a processor 401, a communication interface 402, a memory 403, and a communication bus 404. Among them, the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404,

[0136] The memory 403 is used to store computer programs;

[0137] When the processor 401 is used to execute the program stored on the memory 403, the following steps are implemented:

[0138] Recognize the input data of the user obtained in advance to obtain operation intention information;

[0139] Acquire the operation parameters corresponding to the input data;

[0140] When the operation parameters are acquired, determine the target cloud operating system application programming interface tool according to the operation intention information and the preset corresponding relationship between the operation intention information and the cloud operating system application programming interface tool;

[0141] Execute the call of the target cloud operating system application programming interface tool according to the operation parameters to generate a call result;

[0142] Send the call result to the user.

[0143] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0144] The communication interface is used for communication between the above terminal and other devices.

[0145] The memory may include a Random Access Memory (RAM), or may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0146] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0147] In another embodiment provided by the present invention, a computer-readable storage medium is also provided. Instructions are stored in this computer-readable storage medium, and when it runs on a computer, it causes the computer to execute the cloud operating system interaction method described in any one of the above embodiments.

[0148] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0149] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device that includes the element.

[0150] Each embodiment in this specification is described in a related manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0151] The above are only the preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are all included in the protection scope of the present invention.

Claims

1. A cloud operating system interactive system, characterized in that: The cloud operating system interaction system includes a large language model, an intelligent agent and a user, wherein the large language model establishes a communication connection with the intelligent agent, and the intelligent agent establishes a communication connection with the user; The large language model is used to identify the input data of the user obtained in advance, obtain operation intention information, and obtain operation parameters corresponding to the input data; The intelligent agent is used to determine the target cloud operating system application programming interface tool based on the operation intention information and the preset correspondence between the operation intention and the cloud operating system application programming interface tool, execute the target cloud operating system application programming interface tool call according to the operation parameters, generate a call result, and send the call result to the user.

2. The cloud operating system interactive system according to claim 1, characterized in that: The cloud operating system interaction system includes a prompt word template library, wherein the intelligent agent establishes a communication connection with the prompt word template library; The intelligent agent is used to receive the input data of the user, determine a first prompt word template from the prompt word template library, fill the input data into the first prompt word template, and generate a first prompt word; The large language model is used to determine first structured data according to the first prompt word, wherein the first structured data includes a first missing parameter and a first extracted parameter; The intelligent agent is used to determine whether the first missing parameter is empty, and if the first missing parameter is empty, use the first extracted parameter as an operation parameter.

3. The cloud operating system interactive system according to claim 2, characterized in that: The first structured data includes response information; The intelligent agent is used to send the response information to the user, receive user response data of the user in response to the response information, determine a second prompt word template from the preset prompt word template library, fill the user response data and the first structured data into the second prompt word template, and generate a second prompt word; The large language model is used to determine second structured data according to the second prompt word; wherein the second structured data includes the second missing parameter and the second extracted parameter; The intelligent agent is used to determine whether the second missing parameter is empty. If the second missing parameter is not empty, the response information is resent to the user until the second missing parameter is empty, and the second extracted parameter is used as the operation parameter.

4. The cloud operating system interactive system according to claim 1, characterized in that: The cloud operating system interaction system includes a cloud operating system, the cloud operating system establishes a communication connection with the intelligent agent, and the target cloud operating system application programming interface tool includes a target cloud operating system application programming interface; The intelligent agent is used to send an application programming interface call request to the cloud operating system, wherein the application programming interface call request includes the operation parameter; The cloud operating system is used to receive the application programming interface call request, call the target cloud operating system application programming interface according to the operation parameters, generate a call result, and send the call result to the intelligent agent.

5. The cloud operating system interactive system according to claim 4, characterized in that: The target cloud operating system application programming interface tool includes a plurality of target cloud operating system application programming interfaces; The intelligent agent is used to send a first application programming interface call request to the cloud operating system, wherein the first application programming interface call request includes the operation parameters corresponding to the first target cloud operating system application programming interface; The cloud operating system is used to receive the first application programming interface call request, call the first target cloud operating system application programming interface according to the operation parameters corresponding to the first target cloud operating system application programming interface, generate a first call result, and send the first call result to the intelligent agent; The intelligent agent is used to send a second application programming interface call request to the cloud operating system, wherein the second application programming interface call request includes the first call result and the operation parameters corresponding to the second target cloud operating system application programming interface; The cloud operating system is used to receive the second application programming interface call request, call the second target cloud operating system application programming interface according to the first call result and the operation parameters corresponding to the second target cloud operating system application programming interface, generate a second call result, until several calls to the target cloud operating system application programming interface are completed, generate a call result, and send the call result to the intelligent agent.

6. The cloud operating system interactive system according to claim 2, characterized in that: The intelligent agent is used to determine a third prompt word template from the prompt word template library, fill the calling result into the third prompt word template, and generate a third prompt word; The large language model is used to generate a target call result according to the third prompt word, and send the target call result to the intelligent agent; The intelligent agent is used to send the target call result to the user.

7. A cloud operating system interaction method, characterized in that: The method comprises: Identify the user's input data acquired in advance to obtain operation intention information; Obtaining operation parameters corresponding to the input data; In the case where the operation parameters are obtained, determining a target cloud operating system application programming interface tool according to the operation intention information and a preset correspondence between the operation intention information and the cloud operating system application programming interface tool; Execute the target cloud operating system application programming interface tool call according to the operation parameters to generate a call result; The calling result is sent to the user.

8. A cloud operating system interaction device, characterized in that: The cloud operating system interaction device comprises: An operation intention recognition module is used to recognize the user's input data acquired in advance to obtain operation intention information; An operation parameter acquisition module, used to acquire the operation parameters corresponding to the input data; a target application programming interface tool acquisition module, configured to determine a target cloud operating system application programming interface tool according to the operation intention information and a preset correspondence between the operation intention information and the cloud operating system application programming interface tool when the operation parameters are acquired; An application programming interface calling module, used to execute the target cloud operating system application programming interface tool call according to the operation parameters and generate a call result; The calling result feedback module is used to send the calling result to the user.

9. An electronic device, characterized in that: include: a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the instructions to implement the cloud operating system interaction method as described in claim 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by the processor, the cloud operating system interaction method as described in claim 7 is implemented.

Images