Task processing method, server, storage medium, and computer program product

Abstract

Provided in the present disclosure is a task processing method, which is executed by a server comprising a plurality of agents. The method comprises: in response to a task processing request of a target agent, acquiring the task type of a target task; on the basis of the task type of the target task, screening a plurality of preset tools, so as to determine at least two target tools; and the target agent calling the at least two target tools to process the target task, so as to obtain a task processing result. Further provided in the present disclosure are a server, a computer-readable storage medium and a computer program product.

Description

Task processing method, server, storage medium and computer program product

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority to Chinese Patent Application No. 202410823516.X, filed on June 24, 2024, the contents of which are incorporated herein by reference in their entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the field of computer technology, and particularly relates to a task processing method, a server, a computer readable storage medium and a computer program product. BACKGROUND

[0004] At present, in a multi-agent task processing system, an agent only adopts one tool to process a task, and when there is a task that needs to be processed by multiple tools, multiple agents need to be used to call a corresponding tool of the agent to process the task, which causes confusion in the arrangement (or scheduling sequence) among the multiple agents, and reduces the processing efficiency of the task.

[0005] DISCLOSURE

[0006] The present disclosure provides a task processing method, a server, a computer readable storage medium and a computer program product.

[0007] In a first aspect, the embodiments of the present disclosure provide a task processing method, executed by a server including multiple agents, the method comprising: in response to a task processing request of a target agent, obtaining a task type of a target task; filtering multiple preset tools according to the task type of the target task to determine at least two target tools; and calling the at least two target tools by the target agent to process the target task to obtain a task processing result.

[0008] In a second aspect, the embodiments of the present disclosure provide a server, comprising: at least one processor; a memory having at least one computer program stored thereon, when the at least one computer program is executed by the at least one processor, the at least one processor implements the task processing method in the embodiments of the present disclosure.

[0009] In a third aspect, the embodiments of the present disclosure provide a computer readable storage medium, the readable storage medium stores a computer program, and the computer program is executed by a processor, so that the processor implements the task processing method in the embodiments of the present disclosure.

[0010] In a fourth aspect, the embodiments of the present disclosure provide a computer program product, comprising a computer program, wherein the computer program is executed by a processor, so that the processor implements the task processing method in the embodiments of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0011] In the drawings of the embodiments of the present disclosure:

[0012] FIG. 1 is a flow diagram of a task processing method according to an embodiment of the present disclosure;

[0013] FIG. 2 is a block diagram of a task processing system according to an embodiment of the present disclosure;

[0014] FIG. 3 is a diagram of a workflow arrangement in a server according to an embodiment of the present disclosure;

[0015] FIG. 4 is a flow diagram of a working method of a task processing system according to an embodiment of the present disclosure;

[0016] FIG. 5 is a block diagram of a server according to an embodiment of the present disclosure;

[0017] FIG. 6 is a block diagram of a server according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0019] The embodiments of the present disclosure will be described more fully with reference to the drawings. The embodiments of the present disclosure can be embodied in many different forms, and the present disclosure should not be construed as being limited to the embodiments set forth below. The purpose of providing these embodiments is to make the present disclosure more thorough and complete, and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0020] The drawings of the embodiments of the present disclosure are used to provide a further understanding of the embodiments of the present disclosure, and form a part of the specification, together with the detailed description, to explain the present disclosure, and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent to those skilled in the art by describing the detailed description with reference to the drawings.

[0021] In the case of no conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0022] The terminology used by the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in the present disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items. As used in the present disclosure, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. As used in the present disclosure, the terms "comprises," "comprising," "consists of, "consisting of," specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0023] Unless otherwise defined, all terms (including technical and scientific terms) used in the present disclosure have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an overly literal or overly formal sense unless expressly so defined herein.

[0024] In some related art, in a task processing system including a plurality of agents, a task is processed by one agent using one tool to obtain a processing result corresponding to the task.

[0025] An agent can be a task execution module capable of processing an obtained task using a tool (e.g., a data parsing tool or a data analysis tool) to obtain a task processing result. The task can be a data parsing task or a data analysis task.

[0026] However, when there is a task that needs to be processed by multiple tools (e.g., the task is an exception positioning task), multiple agents need to be used to call their corresponding tools to process the task (e.g., one agent needs to be called to use its corresponding port analysis tool to analyze the task, and another agent needs to be called to use its corresponding log analysis tool to analyze log data in the task to obtain analysis results of multiple different dimensions, so as to finally determine the cause of the exception), which will cause confusion in the arrangement (or scheduling order) between multiple agents and reduce the processing efficiency of the task.

[0027] The embodiments of the present disclosure provide a task processing method, a server, a computer readable storage medium and a computer program product. In order to facilitate the server including a plurality of agents to screen a plurality of preset tools according to the task type of a target task, determine at least two target tools applicable to processing the target task, and use the target agent to call the at least two target tools to analyze and process the target task, so that the target task can be processed by the at least two target tools, and the processing efficiency of the target task can be improved.

[0028] The embodiments of the present disclosure provide a task processing method.

[0029] FIG. 1 is a flowchart of a task processing method provided by the embodiments of the present disclosure. The task processing method is executed by a server including a plurality of agents. As shown in FIG. 1, the task processing method includes but is not limited to the following steps S101-S103.

[0030] In step S101, the task type of a target task is obtained in response to a task processing request of a target agent.

[0031] The target agent is any one of the plurality of agents in the server. The task processing request is used to request the target agent to process the target task. The task processing request can include at least one of the following: the task type of the target task, the processing time of the target task, the address of the terminal generating the target task, and the address of the receiving end of the target task.

[0032] When the server parses the task processing request, the target agent needs to be used to process the target task according to the address of the receiving end of the target task, and the task type of the target task is obtained, so as to facilitate the target task to be allocated with applicable tools according to the task type, so that the target task can be processed by the applicable tools.

[0033] In step S102, a plurality of preset tools are screened according to the task type of the target task, and at least two target tools are determined.

[0034] The plurality of preset tools are tools respectively used to process different categories of tasks.

[0035] For example, the preset tool is a tool implemented based on a Python program or a Shell script, or a tool providing an Application Programming Interface (API) service, etc. The Python program is a widely used interpreted, high-level and general programming language. The Shell is both a command language and a programming language. As a command language, the Shell interprets and executes commands input by a user interactively; as a programming language, the Shell defines various variables and parameters, and provides many control structures including loops and branches that are only available in high-level languages to implement relevant functions.

[0036] For another example, the plurality of preset tools include at least two of the following: a container detection tool, a port detection tool, a log processing tool, and a configuration parameter detection tool.

[0037] The task type of the target task is matched with the task types that can be processed by the plurality of preset tools of different types respectively, so that at least two target tools capable of processing the target task are obtained. The task types that can be processed by the at least two target tools correspond to the task type of the target task.

[0038] For example, if the task type of the target task is a fault locating type, the task types that can be processed by the selected at least two target tools can be a log analysis type, a port detection type, etc., so as to better process the target task using the at least two target tools and accelerate the processing speed of the target task.

[0039] In step S103, the target Agent calls the at least two target tools to process the target task, and obtains a task processing result.

[0040] One target Agent can call the at least two target tools to process the target task using the at least two target tools. Compared with a conventional task processing system using only one task execution module to process a plurality of tasks, the processing speed of the target task can be accelerated, so that the task processing result of the target task can be obtained more quickly and accurately. The task processing result represents a result of successful processing or failed processing of the target task.

[0041] The task processing method in the embodiments of the present disclosure, when the task type of the target task of the target agent is obtained in the server including a plurality of agents, the server can screen a plurality of preset tools according to the task type of the target task, determine at least two target tools for processing the target task, so that the target agent can call at least two target tools to analyze and execute the target task, so that the target task can be processed by at least two target tools suitable for the target task, without the need to arrange a plurality of agents, thereby improving the processing efficiency of the target task.

[0042] In some example embodiments, the screening of the plurality of preset tools according to the task type of the target task in step S102 to determine at least two target tools includes: selecting a target workflow corresponding to the task type of the target task from a plurality of alternative workflows, and determining the tools in the target workflow as the target tools.

[0043] The alternative workflow refers to a process of automatically managing and executing part or all of a preset task type task in the environment of computer application. It is an abstract and general description of the business rules between the workflow and each operation step. By decomposing the processing process of the preset task type task into a process executed by at least two preset tools and executing these tasks according to the preset execution rules, the processing efficiency of the preset task type task can be improved, and the task processing process can be better controlled.

[0044] Since each alternative workflow corresponds to a preset task type and includes at least two preset tools, selecting a target workflow from a plurality of alternative workflows is equivalent to selecting at least two target tools corresponding to the task type of the target task.

[0045] Then, the target agent calls at least two target tools to process the target task and obtains a task processing result, which can speed up the processing efficiency of the target task.

[0046] In some example embodiments, each alternative workflow further includes an alternative scheduling mode, and the target agent calling at least two target tools to process the target task and obtaining a task processing result in step S103 includes: the target agent calling at least two target tools to process the target task according to the target scheduling mode in the target workflow and obtaining a task processing result.

[0047] The alternative scheduling mode represents the order of calling the preset tools in the alternative workflow. For example, the alternative scheduling mode includes: simultaneously calling at least two preset tools, or calling at least two preset tools in a preset calling order.

[0048] The target agent can call the at least two preset tools in different alternative scheduling manners, and the order of calling the preset tools is different based on different scheduling manners. Therefore, after the target workflow is selected, a target scheduling manner can be selected from the multiple alternative scheduling manners to call the at least two target tools, so as to select an optimal calling order to call the at least two target tools to process the target task, so that the at least two target tools can play their respective roles to process the target task quickly and accurately, and the final task processing result is more accurate.

[0049] In some example embodiments, the target agent calls the at least two target tools to process the target task in step S103, and obtaining the task processing result comprises: determining the target scheduling manner; and the target agent calls the at least two target tools to process the target task according to the target scheduling manner to obtain the task processing result.

[0050] The target scheduling manner represents the calling order of the at least two target tools.

[0051] For example, the target scheduling manner comprises: simultaneously calling the at least two target tools, or calling the at least two target tools in a preset calling sequence.

[0052] When the at least two target tools are simultaneously called to process the target task, the target task can be analyzed and processed by the at least two target tools at the same time, thereby speeding up the processing speed of the target task.

[0053] When the at least two target tools are called in a preset calling sequence to process the target task, one target tool can be used to analyze or decompose the target task first, and then other target tools are called to further process the decomposed target task, thereby making the target task obtain more accurate processing and improving the accuracy of the task processing result.

[0054] In some example embodiments, the target task comprises multiple subtasks, and each subtask is processed by a corresponding tool.

[0055] Each subtask can be processed by one or more tools, and each tool can also process multiple subtasks. The correspondence can be set according to actual needs, and the present disclosure does not limit this.

[0056] Determining the target scheduling manner comprises: the target agent determines the target scheduling manner according to the subtask state transition information; or the target agent determines the target scheduling manner according to the scheduling priority information of each subtask.

[0057] The subtask state transition information includes the processing status of each subtask and the execution steps corresponding to each processing status.

[0058] For example, if the processing status of a subtask includes successful processing and failed processing, the target tool will only continue to process the next subtask if the current subtask is successfully processed, and so on, until all subtasks of the target task are processed and the final task processing result is obtained.

[0059] For example, if a subtask has multiple processing states (e.g., first state, second state, and third state), then the execution steps corresponding to each subtask need to be determined based on the state transition information between each subtask, and then the target scheduling method needs to be determined so that at least two target tools can be invoked according to the target scheduling method, and multiple subtasks can be processed to obtain the final task processing result.

[0060] The scheduling priority information of a subtask indicates the level at which the subtask can be processed by the target agent. For example, if multiple subtasks include: hardware detection subtask, logging subtask, and configuration parameter detection subtask, then among these three subtasks, the hardware detection subtask has the highest priority, followed by the logging subtask, and the configuration parameter detection subtask has the lowest priority.

[0061] By prioritizing high-priority subtasks, urgent and important subtasks are processed by their corresponding target tools. Then, other low-priority subtasks are called, allowing less important and less urgent subtasks to be processed later. This ensures that the most needed subtasks are processed, clarifying the direction of the target task. Finally, by combining the processing results of each subtask, the final task processing result is more accurate.

[0062] In some exemplary embodiments, the task type of the target task includes at least one of the following: fault location type, business processing type, and business management type.

[0063] Fault location type refers to the type of task that locates the cause of a fault that may occur in different node devices in a data link or network structure. For example, a task to locate a link break fault in a base station is classified as a link break fault location type; a task to locate a network delay fault in a communication network is classified as a network delay fault location type.

[0064] The business processing type is a type of processing a business based on different business requirements and business processing logic. For example, for a processing task of a session service in a base station, the task type of the task is a session service processing type; for a processing task of a data transmission service, the task type of the task is a data transmission processing type.

[0065] The business management type is a type of classified management of a plurality of different types of services. For example, for a task of operation and maintenance of a plurality of different types of communication services, the task type of the task is a communication service operation and maintenance management type.

[0066] The above is only an example of different task types, and corresponding settings can be made according to actual needs. Other unexplained task types are also within the protection scope of the present disclosure, and will not be described here.

[0067] For different target tasks of different task types in different use scenarios, the target Agent can process the target task based on at least two target tools selected to match the task type of the target task, which can speed up the processing speed of the target task.

[0068] In some example embodiments, the plurality of preset tools includes at least two of the following: a container detection tool, a port detection tool, a log processing tool, and a configuration parameter detection tool.

[0069] The container detection tool is a tool for detecting an abnormality of a container.

[0070] In the field of communication, a container is a lightweight, executable software package that contains an application program and all its dependencies, configuration files, library files, runtime environment information, etc. The container can be regarded as a basic unit of resource isolation and scheduling, used to realize virtualization at the operating system level.

[0071] By using the container detection tool to detect the abnormality of the container, it can be determined whether the container as a basic unit of resource isolation and scheduling has an abnormality, thereby facilitating faster fault location.

[0072] The port detection tool is a tool for detecting an abnormality of interfaces between various modules in a communication device and interfaces between various communication devices. By using the port detection tool to detect various interfaces, it can quickly identify which interfaces between devices (or internal interfaces of devices) have an abnormality, so as to facilitate interface-level positioning of faults.

[0073] The log processing tool is a tool for collecting and processing log information recorded in the process of executing a business processing of a communication device. For example, the log processing tool includes a log collection tool and / or a log analysis tool.

[0074] The configuration parameter detection tool is a tool for detecting relevant preset configuration parameters of a task. For example, for interface configuration parameters (such as network addresses, network port numbers, etc.) pre-configured for a data transmission service, the configuration parameter detection tool can be used to detect the interface configuration parameters to determine whether the interface configuration parameters match the current network environment, thereby determining whether a fault is caused by an error in the configuration parameters, and thereby quickly locating the fault.

[0075] Through the different types of preset tools described above, different types of modules or parameters can be detected, and the target task can be processed from different angles. This not only enables more comprehensive analysis and processing of the target task and improves the processing speed of the target task, but also improves the processing accuracy of the target task.

[0076] In some example embodiments, the types of the plurality of Agents in the server include at least one of the following: an interface Agent, a transmission Agent, and a configuration Agent.

[0077] The interface Agent is an interface-level proxy module configured to process interface tasks. The transmission Agent is a module configured to process tasks in the transmission field. The configuration Agent is a module configured to process tasks in the configuration field.

[0078] In some embodiments, the priority level of the interface Agent is higher than the priority levels of the transmission Agent and the configuration Agent, and the priority level of the transmission Agent is higher than the priority level of the configuration Agent.

[0079] The inclusion of multiple different types of Agents in one server enables hierarchical processing of target tasks, and clearly defines the processing requirements of the target tasks in different fields, thereby enabling better analysis and processing of the target tasks and improving the processing accuracy of the target tasks. Moreover, for Agents in one field, the target tasks in the field can be processed in a targeted manner, thereby accelerating the processing speed of the tasks.

[0080] Embodiments of the present disclosure provide a task processing system.

[0081] FIG. 2 is a block diagram of a task processing system according to an embodiment of the present disclosure. The task processing system can process multiple different types of tasks, such as processing tasks of communication service data and management tasks of operation and maintenance.

[0082] As shown in FIG. 2, the task processing system includes a terminal 210 and a server 220.

[0083] The server 220 comprises a plurality of agents (such as an interface agent 221, a transmission agent 222, and a configuration agent 223) and a tool pool 224.

[0084] Different workflows are respectively executed by the respective agents, so that the respective agents call different tools in the tool pool 224 to process the tasks performed thereby, thereby efficiently completing the processing of the tasks and reducing the risk of task backlog in the task processing system.

[0085] When the server 220 receives the task processing request sent by the terminal 210, the server 220 parses the task processing request to obtain the description information of the target task (such as including the task type of the target task, the time information of the target task, the sending end address of the target task, and the like). Then, for the description information of the target task, the server 220 calls the interface agent 221 to process the target task.

[0086] The interface agent 221 is configured to select a target workflow corresponding to the task type of the target task from a plurality of alternative workflows, and determine the tools in the target workflow as target tools.

[0087] In some embodiments, if a workflow corresponding to the task type of the target task cannot be selected from the plurality of alternative workflows, the server 220 dynamically arranges a new workflow to ensure that the target task can obtain corresponding processing.

[0088] The transmission agent 222 and the configuration agent 223 are agents in different fields. The transmission agent 222 is configured to process tasks in the transmission field, and the configuration agent 223 is configured to process tasks in the configuration management field.

[0089] The tool pool 224 comprises a plurality of preset tools. The preset tools can be tools capable of processing different categories of tasks based on Python programs or Shell scripts, or tools capable of providing API services, and the like.

[0090] In some embodiments, the preset tools can be stored in the tool pool 224 in the form of a compressed package to reduce the storage capacity of the tool pool 224 occupied by the preset tools.

[0091] The preset tool implementation source code (and / or, an executable file, and / or a preset tool description file (e.g., a file recording selection criteria information of the preset tool, and / or information for using the preset tool, etc.)) is stored in the preset tool compressed package. The preset tool description file can be in a file format such as JS object notation (JSON), YAML language (a language for expressing data serialization format), or extensible markup language (XML).

[0092] The selection criteria information of the preset tool includes at least two of the following: a Chinese name of the preset tool, an English name of the preset tool, function description information of the preset tool, path information of the preset tool in the tool pool 224, and a development language of the preset tool.

[0093] The information for using the preset tool includes at least two of the following: an English name of the preset tool, input parameter description information of the preset tool, output parameter description information of the preset tool, and a case prompt word (e.g., task description information, etc.) for using the preset tool.

[0094] It should be noted that each preset tool in the tool pool can be updated, such as version iteration, upgrade, optimization, and custom addition, to meet the processing needs of different tasks.

[0095] In some embodiments, each preset tool in the tool pool 224 meets a standardized input specification, and the tool pool 224 can provide a uniform access interface (e.g., a representational state transfer (RESTful) interface) for other modules or agents, so as to facilitate the calling of each preset tool.

[0096] In some embodiments, each alternative workflow corresponds to a preset task type and includes at least two preset tools. When the preset task type corresponding to a certain alternative workflow is the same as the task type of a target task that needs to be processed by a certain agent (e.g., the transmission agent 222 or the configuration agent 223), the agent can select the alternative workflow as a target workflow for processing the target task, which is essentially selecting at least two target tools included in the target workflow as tools for processing the target task.

[0097] In some embodiments, the alternative workflow and the at least two preset tools included therein can be bound to implement processing of a preset task type by using the corresponding alternative workflow, so as to improve the use efficiency of the preset tools and the processing speed of the tasks of the preset task type.

[0098] In addition, the alternative workflow can further include an alternative scheduling manner, which is a manner of calling preset tools in the alternative workflow. For example, a manner of simultaneously calling at least two preset tools, or a manner of calling at least two preset tools in a preset calling sequence, and the like.

[0099] In some embodiments, the different Agents described above can each be implemented by a large language model (LLM).

[0100] Based on the framework idea of synergizing reasoning and acting in language models (ReAct), the LLM can be trained using the collected sample data to obtain the corresponding Agent.

[0101] The sample business data used by each Agent is different. For example, the transmission Agent 222 is obtained by training the LLM using transmission business data as sample data, and the configuration Agent 223 is obtained by training the LLM using configuration management data as sample data.

[0102] The LLM can be prompted by a prompt to generate operation steps matching the task type of the target task. The prompt is a guiding text when interacting with the LLM model.

[0103] In some embodiments, the prompt can be a description text determined based on at least two preset tools included in each alternative workflow. By adding the prompt to different Agents, the Agents can be assisted to select each alternative workflow to obtain a target workflow most suitable for implementing the target task.

[0104] For example, the prompt can be recorded in a configuration file, so that the Agents can select and use each alternative workflow based on the information in the configuration file.

[0105] In some embodiments, the configuration file can include at least one of the following: an English name of the Agent, a Chinese name of the Agent, processing capability description information of the Agent, a number of preset tools supported by the Agent and functions of the preset tools, and a prompt of each preset tool in each alternative workflow.

[0106] In some embodiments, the transition information of the processing state of each preset tool to the preset task can be defined by means of a configuration file, and the transition information includes the processing state of each preset task, and the execution step corresponding to each processing state, etc.

[0107] For example, the configuration file can further include at least one of the following information: processing state description information of the preset task, processing state transition information, target state, and triggered action.

[0108] The processing state description information of the preset task is state information describing the processing of the preset task by the preset tool, such as including a to-be-processed state, a being-processed state, and a completed state, etc.

[0109] When it is determined by the processing state transition information that state transition is needed, the next preset tool can be called to process the preset task according to different trigger conditions, or other steps can be performed, so that at least two preset tools of one preset workflow can work in coordination, and the task processing can be quickly performed, thereby realizing flexible processing of different preset tools for different preset tasks, and improving the processing efficiency of the task.

[0110] In some embodiments, the server 220 can also use the implementation manner of the LLM model to autonomously arrange a workflow matching the task type of the target task for the target task.

[0111] FIG. 3 is a schematic diagram of the arrangement of a workflow in a server according to an embodiment of the present disclosure. As shown in FIG. 3, the server inputs the description information of the target task to the interface Agent 221; the interface Agent 221 selects a workflow matching the task type of the target task from a plurality of alternative workflows (such as a first alternative workflow, a second alternative workflow, …, a kth alternative workflow, etc., k represents the number of alternative workflows, and k is an integer greater than or equal to 1) as a target workflow according to the task type of the target task, and binds the target task to the target workflow.

[0112] The description information of the target task can completely describe the relevant parameter information of the target task, so as to provide data support for subsequent task analysis and processing of the target task.

[0113] In the case where the server cannot find an alternative workflow matching the task type of the target task, the interface Agent 221 will automatically generate a workflow (i.e., an automatically generated workflow) for processing the target task based on the LLM model. For example, the interface Agent 221 can arrange a suitable workflow for processing the target task according to the ReAct architecture and the prompt description of each alternative Agent in the domain Agent.

[0114] Each of the alternative workflows can select any number of alternative agents from the domain agents (e.g., including the 1st alternative agent, the 2nd alternative agent, the 3rd alternative agent, the 4th alternative agent, …, the mth alternative agent, m represents the number of alternative agents, and m is an integer greater than or equal to 1) so as to integrate the individual alternative agents.

[0115] Further, when the target agent (e.g., the 1st alternative agent is selected as the target agent) is selected, the target agent also selects a target workflow from a plurality of alternative tool workflows (e.g., the 1st alternative tool workflow, the 2nd alternative tool workflow, …, the nth alternative tool workflow, n represents the number of alternative tool workflows, and n is an integer greater than or equal to 1) according to the task type of the subtask in the target task, and binds the target workflow to the task type of the subtask in the target task.

[0116] It should be noted that when the target agent cannot select a tool workflow from the plurality of alternative tool workflows that matches the task type of the subtask in the target task, the target agent automatically generates a tool workflow (i.e., an automatically generated tool workflow) for processing the subtask in the target task based on the LLM model. For example, the target agent arranges a suitable tool workflow for processing the subtask in the target task based on the ReAct architecture and the prompt description of each preset tool in the tool pool 224.

[0117] Each of the alternative tool workflows can select any number of preset tools from the tool pool 224 so as to integrate the individual preset tools. The tool pool 224 includes a plurality of preset tools (e.g., the 1st preset tool, the 2nd preset tool, …, the pth preset tool, p represents the number of preset tools, and p is an integer greater than or equal to 1).

[0118] Each of the alternative tool workflows includes at least two preset tools, and each preset tool can serve as an execution node of the alternative tool workflow, and the processing state of the subtask can be determined according to the processing result of the preset tool on the subtask.

[0119] It should be noted that the target workflow selected by the interface agent 221 is used to determine the domain to which the target task belongs and which domain agent to call as the target agent, and the target workflow selected by the target agent is used to select which preset tools to use to process the subtasks in the target task, so as to quickly process the subtasks in the target task using multiple tools and improve the processing speed of the target task.

[0120] FIG. 4 is a flow diagram of a working method of a task processing system according to an embodiment of the present disclosure. As shown in FIG. 4, the working method of the task processing system includes, but is not limited to, the following steps S411-S418.

[0121] In step S411, the terminal 210 sends a task processing request to the interface Agent 221 in the server, so that the interface Agent 221 processes a target task included in the task processing request.

[0122] The server parses the task processing request received by it to obtain description information of the target task (for example, including the task type of the target task (for example, a positioning task of a link failure occurring in a base station), time information of the target task, a sending end address of the target task, etc.).

[0123] In step S412, the interface Agent 221 selects a target workflow corresponding to the task type of the target task from a plurality of alternative workflows according to the task type of the target task.

[0124] The target workflow is a domain workflow including processing by the transmission Agent 222 and the configuration Agent 223. The transmission Agent 222 and the configuration Agent 223 each correspond to a different tool workflow as the target workflow.

[0125] The target task includes a plurality of subtasks (for example, a first subtask (for example, a container detection subtask) processed by the transmission Agent 222, a second subtask (for example, a port detection subtask), a third subtask (for example, a log collection subtask), and a fourth subtask (for example, a log analysis subtask), and a fifth subtask (for example, a configuration parameter detection subtask) processed by the configuration Agent 223).

[0126] In step S4131, the transmission Agent 222 requests to invoke a container diagnosis tool in the tool pool 224.

[0127] The transmission Agent 222 can send a tool invocation request message including an identifier of the container diagnosis tool to the tool pool 224; and obtain a use right of the container diagnosis tool in response to a tool invocation response message fed back by the tool pool 224.

[0128] In step S4132, the transmission Agent 222 processes the first subtask according to the obtained container diagnosis tool to obtain a processing result of the first subtask.

[0129] The processing result of the first subtask includes container detection success or container detection failure. The container detection success represents that the container is normal when the chain break fault occurs. The container detection failure represents that the container is abnormal when the chain break fault occurs.

[0130] In the case where it is determined that the container is abnormal, the detection result can be directly fed back to the interface Agent 221, so that the interface Agent 221 can obtain the abnormality of the container in time and quickly determine the cause of the chain break fault.

[0131] In the case where it is determined that the container is normal, step S4133 is executed.

[0132] In step S4133, the transmission Agent 222 requests to call a port diagnosis tool in the tool pool 224.

[0133] The transmission Agent 222 can send a tool calling request message to the tool pool 224, the tool calling request message including the identification of the port diagnosis tool; and obtain the use right of the port diagnosis tool in response to a tool calling response message fed back by the tool pool 224.

[0134] In step S4134, the transmission Agent 222 processes the second subtask according to the obtained port diagnosis tool, and obtains the processing result of the second subtask.

[0135] The processing result of the second subtask includes port detection success or port detection failure. The port detection success represents that the port is normal when the chain break fault occurs. The port detection failure represents that the port is abnormal when the chain break fault occurs.

[0136] In the case where it is determined that the port is abnormal, the detection result can be directly fed back to the interface Agent 221, so that the interface Agent 221 can obtain the abnormality of the port in time and quickly determine the cause of the chain break fault.

[0137] In the case where it is determined that the port is normal, step S4135 is executed.

[0138] The port can include ports between various modules inside the base station, or ports between the base station and other network element devices, which are not limited in the present disclosure and will not be described herein.

[0139] In step S4135, the transmission Agent 222 requests to call a log collection tool in the tool pool 224.

[0140] The transmission agent 222 can send a tool call request message to the tool pool 224, the tool call request message comprising an identifier of the log collection tool; in response to a tool call response message fed back by the tool pool 224, obtain a use right of the log collection tool.

[0141] In step S4136, the transmission agent 222 processes the third subtask according to the obtained log collection tool, and obtains a processing result of the third subtask.

[0142] The processing result of the third subtask comprises log collection success or log collection failure. The log collection success indicates that relevant log information when the disconnection fault occurs is collected; and the log collection failure indicates that the log information when the disconnection fault occurs is not collected, or the collected log information is incomplete, etc.

[0143] In the case of determining the log collection failure, the detection result is directly fed back to the interface agent 221.

[0144] In the case of determining the port log collection success, step S4137 is continued to be executed.

[0145] In step S4137, the transmission agent 222 requests to call the log analysis tool in the tool pool 224.

[0146] The transmission agent 222 can send a tool call request message to the tool pool 224, the tool call request message comprising an identifier of the log analysis tool; in response to a tool call response message fed back by the tool pool 224, obtain a use right of the log analysis tool.

[0147] In step S4138, the transmission agent 222 processes the fourth subtask according to the obtained log analysis tool, and obtains a processing result of the fourth subtask.

[0148] The processing result of the fourth subtask comprises determining that the log information is normal, or determining that there is disconnection-related abnormality in the log information.

[0149] In the case of determining that there is disconnection-related abnormality in the log information, disconnection-related abnormality information existing in the log information is directly fed back to the interface agent 221.

[0150] In the case of determining that the log information is normal, step S414 is executed according to a preset processing flow of the domain workflow.

[0151] In step S414, the transmission agent 222 determines that the transmission domain is normal, and sends a configuration parameter diagnosis request to the configuration agent 223.

[0152] The configuration parameter diagnosis request comprises description information of the target task and diagnosis result of the target task by the transmission agent 222.

[0153] In step S415, the configuration agent 223 requests to invoke the configuration parameter detection tool in the tool pool 224.

[0154] In step S416, the configuration agent 223 detects the related configuration parameter in the disconnection fault according to the obtained configuration parameter detection tool, and obtains a configuration parameter detection result.

[0155] The configuration parameter detection result comprises a correct configuration parameter or an abnormal configuration parameter (for example, a configuration parameter error of a network port).

[0156] In a case where it is determined that the configuration parameter detection result is an abnormal configuration parameter, step S417 is performed.

[0157] In step S417, the configuration agent 223 feeds back the abnormal configuration parameter to the interface agent 221.

[0158] In step S418, the interface agent 221 sends the disconnection fault reason to the terminal 210.

[0159] The disconnection fault reason is that the configuration parameter of the network port is incorrect, and the terminal 210 needs to be prompted to update the related configuration parameter of the network port, such as a network connection parameter.

[0160] In the above processing process, the interface agent 221 in the server analyzes the fault based on the processing flow of the domain workflow, respectively invokes the transmission agent 222 and the configuration agent 223, the transmission agent 222 respectively invokes different tools from the tool pool 224 for fault positioning and detection according to the processing flow of the tool workflow, in a case where it is detected that there is no abnormality in the transmission domain, the configuration agent 223 continues to invoke the configuration parameter detection tool in the tool pool 224 to detect the related configuration parameter in the disconnection fault, so as to determine the reason for the disconnection fault.

[0161] Based on multiple different workflows, different agents and multiple tools are used cooperatively to locate the disconnection fault, which not only can improve the processing efficiency of the target task (i.e., the positioning task of the disconnection fault) and reduce the fault positioning time, but also can flexibly invoke multiple tools in the tool pool by the agent, and improve the use flexibility of the tools.

[0162] The embodiment of the present disclosure provides a server.

[0163] FIG. 5 is a block diagram of a server according to an embodiment of the present disclosure. The server includes a plurality of agents, and the plurality of agents include a target agent.

[0164] As shown in FIG. 5, the server 500 includes, but is not limited to, the following modules: an obtaining module 501, a screening module 502, and a target agent 503.

[0165] The obtaining module 501 is configured to obtain a task type of a target task in response to a task processing request of the target agent.

[0166] The screening module 502 is configured to screen a plurality of preset tools according to the task type of the target task, and determine at least two target tools.

[0167] The target agent 503 is configured to call the at least two target tools to process the target task, and obtain a task processing result.

[0168] It should be noted that the server in this embodiment can implement the task processing method in the present disclosure.

[0169] According to the server in the present disclosure, the obtaining module obtains a task type of a target task of a target agent, the screening module screens a plurality of preset tools according to the task type of the target task, and determines at least two target tools for processing the target task, so that the target agent can call the at least two target tools to analyze and execute the target task, so that the target task can be processed by the at least two target tools most suitable for it, without the need to arrange a plurality of agents, and the processing efficiency of the target task is improved.

[0170] It should be noted that the present disclosure is not limited to the specific configurations and processes described in the above embodiments and shown in the drawings. For the convenience and brevity of description, detailed descriptions of known methods are omitted, and the specific working processes of the above-described systems, modules, and units can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0171] The present disclosure provides a server, a computer readable storage medium, and a computer program product.

[0172] FIG. 6 is a block diagram of a server according to an embodiment of the present disclosure.

[0173] As shown in FIG. 6, the server includes at least one processor 601, at least one memory 602, and one or more I / O interfaces 603. The processor 601, the memory 602, and the I / O interface 603 are connected to each other through a bus 604. The memory 602 stores at least one computer program, and the at least one computer program is executed by the at least one processor 601, so that the at least one processor 601 can implement the task processing method described in the above embodiments.

[0174] Each module in the above server can be implemented by software, hardware, and a combination thereof, in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0175] The embodiments of the present disclosure further provide a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to enable the processor to implement the task processing method described in the above embodiments. The computer readable storage medium can be a volatile or non-volatile computer readable storage medium.

[0176] The embodiments of the present disclosure further provide a computer program product including computer readable code, or a non-volatile computer readable storage medium carrying the computer readable code, and when the computer readable code is run in the processor of the server, the processor in the server executes the above task processing method.

[0177] Those skilled in the art can understand that all or some steps in the above disclosed method, the functions of the modules / units in the system and the device can be implemented as software, firmware, hardware, and appropriate combinations thereof. In the hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components in cooperation.

[0178] Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application- specific integrated circuit. Such software can be distributed on computer readable storage media, which can comprise any medium or device readable by a computer or other machine and encoding or storing instructions for execution by the computer or other machine. Such computer readable storage media can include, without limitation, volatile memory, non-volatile memory, and transmission media (or other storage devices). Examples of volatile memory include random access memory (RAM), dynamic RAM (DRAM), static RAM (SRAM), and other forms of volatile memory. Examples of non-volatile memory include read only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, compact disc read only memory (CD-ROM), digital versatile disc read only memory (DVD-ROM), magnetic disks, other magnetic media, and other forms of non-volatile memory. Examples of transmission media include coaxial cables, copper wires, optical fibers, and other forms of transmission media. The computer readable storage media can be used to store data, computer readable instructions, or both, for use by the computer or other machine. The computer readable storage media can be embodied in the computer readable program instructions described herein, in the computer readable program instructions executed by the computer or other machine, or in a combination of the two.

[0179] The computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0180] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, or any combination of one or more of the above in any combination, written in any combination of one or more programming languages, including object oriented programming languages such as Smalltalk, C++ or the like, and conventional procedural programming languages such as "C" or the like. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0181] The computer program product described herein can be embodied in a specific manner by hardware, software, or a combination thereof. In one embodiment, the computer program product is embodied as a computer storage medium. In another embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), and the like.

[0182] Various aspects of the disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer readable program instructions.

[0183] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data, programs, program modules, e.g., instructions for operation, or digital content stored thereon or therein for a short time or not at all. The computer readable storage medium can also have instructions stored thereon or therein which may

[0184] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0185] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0186] Example embodiments and implementations have been disclosed herein and, although specific terms are employed, they are used in a generic and descriptive sense only and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that features, characteristics or / and elements described in connection with a particular embodiment and / or implementation can be used in conjunction with other embodiments and / or implementations unless otherwise explicitly stated. Accordingly, it will be understood that various changes in form and details can be made without departing from the scope of the disclosure.

Claims

1. A task processing method, executed by a server comprising multiple agents, comprising: In response to the task processing request from the target Agent, obtain the task type of the target task; Based on the task type of the target task, multiple preset tools are filtered to determine at least two target tools; The target Agent invokes at least two target tools to process the target task and obtain the task processing result.

2. The method according to claim 1, wherein, The step of filtering multiple preset tools based on the task type of the target task to determine at least two target tools includes: Select a target workflow from multiple alternative workflows that corresponds to the task type of the target task, and determine the tool in the target workflow as the target tool. Each alternative workflow corresponds to a preset task type and includes at least two preset tools.

3. The method according to claim 2, wherein, Each of the alternative workflows further includes: an alternative scheduling mode, wherein the alternative scheduling mode represents the order in which preset tools in the alternative workflow are invoked; The target agent invokes the at least two target tools to process the target task, and the task processing results include: The target Agent invokes at least two target tools to process the target task according to the target scheduling method in the target workflow, and obtains the task processing result.

4. The method according to claim 1, wherein, The target agent invokes the at least two target tools to process the target task, and the task processing results include: Determine the target scheduling method, wherein the target scheduling method characterizes the invocation order of the at least two target tools; The target Agent invokes at least two target tools to process the target task according to the target scheduling method, and obtains the task processing result.

5. The method according to claim 4, wherein, The target scheduling method includes: simultaneously calling the at least two target tools, or calling the at least two target tools according to a preset calling order.

6. The method according to claim 4, wherein, The target task includes multiple sub-tasks, and each sub-task is processed by its corresponding tool. The method for determining the target scheduling includes: The target Agent determines the target scheduling method based on the subtask state transition information, wherein the subtask state transition information includes the processing status of each subtask and the execution steps corresponding to each processing status. or, The target Agent determines the target scheduling method based on the scheduling priority information of each subtask.

7. The method according to any one of claims 1 to 6, wherein, The target task's task type includes at least one of the following: fault location type, business processing type, and business management type.

8. The method according to any one of claims 1 to 6, wherein, The plurality of preset tools include at least two of the following: container detection tool, port detection tool, log processing tool, and configuration parameter detection tool.

9. The method according to any one of claims 1 to 6, wherein, The types of agents in the server include at least one of the following: interface agent, transport agent, and configuration agent.

10. A server, comprising a memory and a processor; the memory storing a computer program executable by the processor, the computer program being executed by the processor to cause the processor to perform the task processing method according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor such that the processor performs the task processing method according to any one of claims 1 to 9.

12. A computer program product comprising a computer program that is executed by a processor, causing the processor to perform the task processing method according to any one of claims 1 to 9.

Images