Multi-agent cooperation-based instant information inquiry task processing method and related device

Abstract

The present disclosure provides a kind of instant information inquiry type task processing method based on multi-agent cooperation and related device, it is related to generative large language model, artificial intelligence technology field such as agent.The method comprises: determining the target task to be solved according to the natural language input of user;The target task is decomposed into at least containing instant information inquiry type task multiple sub-target tasks, and each sub-target task is correspondingly issued to each sub-target agent at least containing instant information inquiry agent;Control the associated sub-target agent in multiple sub-target agents generates corresponding associated processing result based on instant feedback output by instant information inquiry agent, and the associated sub-target agent is the sub-target agent that instant feedback is as part of task input information;Determine the target processing result corresponding to target task based on associated processing result.Through application this scheme can bring better comprehensive task processing effect in the case where comprehensive cost is lower.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, specifically to the field of artificial intelligence technology such as generative large language models and intelligent agents, and especially to a method, device, electronic device, computer-readable storage medium and computer program product for processing instant information inquiry tasks based on multi-agent collaboration. Background Art

[0002] With the rapid development and iteration of generative large language models, they have a better understanding of user input requirements and the ability to give corresponding results.

[0003] In order to make the output of the generative large language model more in line with specific needs, an intelligent agent was constructed by using the generative large language model as the base model and combining it with pre-set role parameters.

[0004] How to use intelligent agents to solve complex problems raised by users is still a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the Invention

[0005] The embodiments of the present disclosure provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing instant information inquiry tasks based on multi-agent collaboration.

[0006] In the first aspect, an embodiment of the present disclosure proposes a method for processing instant message inquiry tasks based on multi-agent collaboration, including: determining a target task to be solved based on the user's natural language input; decomposing the target task into multiple sub-target tasks that at least include an instant message inquiry task, and issuing each sub-target task to each sub-target agent that at least includes an instant message inquiry agent; wherein different sub-agents are used to process different types of subtasks; controlling the instant message inquiry agent to ask questions to the inquiry object and obtain instant feedback; wherein the instant message inquiry agent supports question asking in a way that runs in the background; controlling the associated sub-target agent among the multiple sub-target agents to generate corresponding associated processing results based on the instant feedback output by the instant message inquiry agent; wherein the associated sub-target agent is a sub-target agent that relies on instant feedback as part of the task input information; and determining the target processing result corresponding to the target task based on the associated processing result.

[0007] In the second aspect, the embodiment of the present disclosure proposes an instant message inquiry type task processing device based on multi-agent collaboration, including: a target task determination unit, configured to determine the target task to be solved according to the user's natural language input; a task decomposition and corresponding issuance unit, configured to decompose the target task into multiple sub-target tasks including at least an instant message inquiry type task, and issue each sub-target task to each sub-target agent including at least an instant message inquiry agent; wherein different sub-agents are used to process different types of subtasks; an inquiry control unit, configured to control the instant message inquiry agent to ask questions to the inquiry object and obtain instant feedback; wherein the instant message inquiry agent supports question asking in a way that runs in the background; an association processing control unit, configured to control the associated sub-target agent among the multiple sub-target agents to generate corresponding association processing results based on the instant feedback output by the instant message inquiry agent; wherein the associated sub-target agent is a sub-target agent that relies on instant feedback as part of the task input information; a target processing result determination unit, configured to determine the target processing result corresponding to the target task based on the association processing result.

[0008] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the instant information inquiry task processing method based on multi-agent collaboration as described in the first aspect when executing.

[0009] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement the instant information inquiry task processing method based on multi-agent collaboration as described in the first aspect when executed.

[0010] In a fifth aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which, when executed by a processor, can implement the various steps of the instant information inquiry task processing method based on multi-agent collaboration as described in the first aspect.

[0011] The instant information inquiry task processing solution based on multi-agent collaboration provided by the present disclosure is that the main agent determines the target task to be solved according to the user's natural language input, and then decomposes the target task into multiple sub-target tasks including at least the instant information inquiry task, and then sends each sub-target task to each sub-target agent including at least the instant information inquiry agent. Then, the instant information inquiry agent asks questions to the inquiry object under the control of the main agent, thereby obtaining instant feedback, and the associated sub-target agents that rely on the instant feedback will also generate corresponding associated processing results based on the instant feedback under the control of the main agent. Finally, the main agent obtains the target processing result corresponding to the target task based on the associated processing result.

[0012] That is, the present disclosure adopts an agent cluster formed by a pre-built main agent and multiple sub-agents to process the task requirements proposed by users, wherein the main agent is responsible for understanding the user's task requirements and decomposing the overall task requirements into multiple sub-target tasks that can be performed by different sub-agents. Each sub-agent processes the sub-task that matches itself according to the mobilization of the main agent. That is, through the collaboration between the main agent and each sub-agent, different components of a complex task can be handled in their respective roles. Moreover, since different sub-agents are pre-built to be dedicated to handling different types of tasks, the scheme adopted by the present disclosure of the main agent and multiple sub-agents to collaboratively handle task requirements has better processing effects on a single type of task than using a single, all-powerful agent. In addition, the relatively small sub-agents are also convenient for flexible addition and modification of corresponding functions. This scheme can bring better comprehensive task processing effects at a lower overall cost.

[0013] In particular, for instant information inquiry tasks that require combining instant information to verify whether the actual situation meets the task requirements and obtain instant feedback using the verification results, the instant information inquiry agent also supports asking questions in a background manner (i.e., processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, without affecting other user operations.

[0014] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following drawings:

[0016] Figure 1 is an exemplary system architecture in which the present disclosure may be applied;

[0017] Figure 2 A flowchart of a method for processing instant information inquiry tasks based on multi-agent collaboration provided by an embodiment of the present disclosure;

[0018] Figure 3 A flowchart of a method for determining a target task based on natural language input provided by an embodiment of the present disclosure;

[0019] Figure 4 A flowchart of a method for decomposing a target task into multiple sub-target tasks including an instant information inquiry task according to task elements provided by an embodiment of the present disclosure;

[0020] Figure 5 A flowchart of a method for creating a sub-agent provided in an embodiment of the present disclosure;

[0021] Figure 6 A flowchart of a method for determining an associated processing result and a target processing result provided by an embodiment of the present disclosure;

[0022] Figure 7 A flowchart of a method for controlling an associated sub-target agent to generate an associated processing result provided by an embodiment of the present disclosure;

[0023] Figure 8 A flowchart of a method for determining an estimated time and generating a waiting time notification provided in an embodiment of the present disclosure;

[0024] Figure 9 A two-branch schematic diagram of controlling a sub-target agent to output corresponding sub-processing results provided by an embodiment of the present disclosure;

[0025] Figures 10-1 to 10-6 These are all example diagrams of a method for processing instant information inquiry tasks based on multi-agent collaboration in an application scenario provided by an embodiment of the present disclosure;

[0026] Figure 11 A structural block diagram of an instant information inquiry task processing device based on multi-agent collaboration provided by an embodiment of the present disclosure;

[0027] Figure 12 A structural diagram of an electronic device suitable for executing an instant information inquiry task processing method based on multi-agent collaboration provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other unless there is a conflict.

[0029] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0030] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the instant information inquiry task processing method, apparatus, electronic device, and computer-readable storage medium based on multi-agent collaboration disclosed herein can be applied.

[0031] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0032] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications for enabling information communication between the terminal devices 101, 102, and 103 and server 105 can be installed, such as complex task processing applications, browser applications, and instant messaging applications.

[0033] Terminal devices 101, 102, 103 and server 105 can be either hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, laptop computers, and desktop computers. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules, or as a single software or software module, and are not specifically limited here. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, and are not specifically limited here.

[0034] The server 105 can provide various services through various built-in applications. Taking a complex task processing application that can provide a one-click processing service for complex tasks as an example, the server 105 can achieve the following effects when running the complex task processing application: first, the natural language input transmitted by the user through the terminal devices 101, 102, and 103 is received through the network 104, and then the target task to be solved is determined according to the natural language input; then, the target task is decomposed into multiple sub-target tasks including at least an instant information inquiry task, and each sub-target task is sent to a corresponding agent including at least an instant information inquiry agent. Each sub-target agent, different sub-target agents are used to process different types of sub-tasks; next, the instant information inquiry agent is controlled to ask questions to the inquiry object and obtain instant feedback. The instant information inquiry agent supports question asking in a background running manner; and, the associated sub-target agent among the multiple sub-target agents is controlled to generate corresponding associated processing results based on the instant feedback output by the instant information inquiry agent. The associated sub-target agent is a sub-target agent that relies on the instant feedback as part of the task input information; finally, the target processing result corresponding to the target task is determined based on the associated processing result.

[0035] Furthermore, the server 105 may also transmit the target processing result back to the terminal devices 101 , 102 , and 103 via the network 104 , so that the terminal devices 101 , 102 , and 103 display the received target processing result to the user.

[0036] It should be noted that, in addition to being obtained from terminal devices 101, 102, and 103 via network 104, natural language input can also be pre-stored locally on server 105 in various ways. Therefore, when server 105 detects that such data is already stored locally (for example, when starting to process a previously reserved task), it can choose to directly obtain such data locally. In this case, exemplary system architecture 100 may also not include terminal devices 101, 102, 103 and network 104.

[0037] Since processing complex tasks requires more computing resources and stronger computing power, the instant message inquiry task processing methods based on multi-agent collaboration provided in the subsequent embodiments of the present disclosure are generally executed by the server 105 with stronger computing power and more computing resources. Correspondingly, the instant message inquiry task processing device based on multi-agent collaboration is generally also set in the server 105. However, it should also be pointed out that when the terminal devices 101, 102, and 103 also have computing power and computing resources that meet the requirements, the terminal devices 101, 102, and 103 can also complete the various calculations assigned to the server 105 through the complex task processing applications installed thereon, and then output the same results as the server 105. In particular, when there are multiple terminal devices with different computing capabilities, if a complex task processing application determines that the terminal device where it is located has stronger computing capabilities and more remaining computing resources, the terminal device can be allowed to perform the aforementioned operations, thereby appropriately reducing the computing pressure on the server 105. Accordingly, the instant information query task processing device based on multi-agent collaboration can also be set in the terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104.

[0038] It should be noted that the main agent and each sub-target agent can be installed on the server 105 at the same time, and each sub-target agent called and controlled by the main agent can also be installed on other servers or terminal devices different from the server 105. No specific limitation is made here.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0040] Please refer to Figure 2 , Figure 2 This is a flowchart of a method for processing instant information inquiry tasks based on multi-agent collaboration provided by an embodiment of the present disclosure, wherein process 200 includes the following steps:

[0041] Step 201: Determine the target task to be solved based on the user's natural language input;

[0042] This step is intended to be performed by the execution subject (e.g. Figure 1 The server 105 carrying the main agent as shown) fully understands and analyzes the natural language input received from the user (for example, through Figure 1The network 104 shown receives the natural language input by the user through the terminal devices 101, 102, and 103 used, and then determines the target task that the user wants to solve, that is, the target task corresponds to a task requirement.

[0043] Specifically, this step is usually a comprehensive multi-step process involving complex intelligent reasoning steps such as language understanding, context analysis, and task modeling. For example, it involves receiving input, preprocessing and normalization, semantic understanding and intent recognition, and task modeling and reasoning.

[0044] Among them, the main intelligent agent as the execution subject first receives the user's natural language input, then preprocesses and normalizes the received natural language input to ensure that it can be effectively understood and processed, and then understands the user intention reflected by the input information obtained after preprocessing and normalization based on the context, thereby determining the target task.

[0045] Among them, the input form of natural language may be voice, text, image, video or other forms of language data. For the convenience of processing, conversion technology can be used to convert non-text natural language input into natural language text that is easy to identify and process; considering that natural language input has multiple forms of request information (such as direct requests, indirect requests and multi-step requests), in order to effectively understand the user's actual task requirements, preprocessing and normalization processing including word segmentation and annotation, noise removal, spelling correction and synonym processing can also be used; in the intent recognition stage, keyword extraction, entity recognition and contextual information can be used to accurately identify the intention that the user wants to express through natural language input; in order to convert the identified intention into a specific task, task modeling operations including task abstraction (mapping the user's needs to a task framework that the system can recognize) and target task definition can also be used to finally obtain the target task corresponding to the natural language input.

[0046] Step 202: Decompose the target task into multiple sub-target tasks including at least an instant message inquiry task, and assign each sub-target task to each sub-target agent including at least an instant message inquiry agent;

[0047] Based on step 201, this step aims to have the execution entity decompose the target task into multiple sub-tasks and assign each sub-task to each sub-target agent. The multiple sub-tasks decomposed in this step should include at least one IM query task. Accordingly, each sub-target agent should include at least one IM query agent dedicated to handling IM query tasks.

[0048] Among them, different sub-agents are used to process different types of sub-tasks, that is, sub-agents dedicated to a single type of task are created in advance according to different task types. There are various ways to divide task types, such as according to the task processing steps, task processing methods, task complexity, data types involved in the task, etc., which are not specifically limited here, that is, different sub-agents are used to process different atomic tasks (that is, the smallest unit of task, the "smallest" here is a relative concept, not an absolute concept, and is the smallest task unit that can be decomposed at present).

[0049] Instant message inquiry tasks involve tasks where the expected results are not fixed but require temporary confirmation based on instant messaging. This means that the actual situation must be verified using instant messaging to determine if the task requirements are met, and the verification results serve as immediate feedback. Examples include manual customer service consultation tasks and telephone consultation tasks. For example, the task of "booking a private room that seats 10 at 8 PM" requires that no one knows whether a hotel has any unreserved private rooms that can seat 10 at 8 PM. This information cannot be obtained without first inquiring with the hotel staff. Therefore, the key to executing these tasks is to conduct temporary inquiries with relevant parties who have accurate and current information.

[0050] It should be noted that this embodiment requires that in this step, the multiple sub-target tasks decomposed from the target task should include at least instant information inquiry tasks. In addition, there is no limitation on the task types of other decomposed sub-target tasks. They can be any type of tasks. Correspondingly, it is also necessary to use a matching sub-target intelligent agent with the corresponding type of task processing capabilities.

[0051] Step 203: Control the instant message inquiry agent to ask questions to the inquiry object and obtain instant feedback;

[0052] On the basis of step 202, this step aims to control the instant information inquiry agent by the above-mentioned execution subject so that the instant information inquiry agent asks the inquiry object the question and obtains instant feedback in the form of inquiry results.

[0053] An implementation including but not limited to:

[0054] First, the above-mentioned execution subject controls the instant message inquiry agent to determine the inquiry object and question based on the received task input information. The received task input information is determined based on the task description information related to the instant message inquiry task decomposed from the target task. Furthermore, the received task input information can also be determined based on the task description information related to the instant message inquiry task decomposed from the target task and the user's personalized preferences, so as to improve the matching degree between the determined task input information and the actual task requirements through the additional introduction of personalized preferences.

[0055] Then, the execution subject controls the instant information inquiry agent to ask questions to the inquiry object using a preset inquiry method. The inquiry method may include at least one of the following:

[0056] Voice telephone inquiries, text inquiries, image inquiries containing specified image elements, and video inquiries containing specified video elements.

[0057] Specifically, when the number of inquiry objects exceeds a preset number (for example, greater than 1, that is, there are multiple different inquiry objects), the above-mentioned execution subject can also control the instant information inquiry agent to ask questions to different inquiry objects using corresponding inquiry methods.

[0058] One method may be: the execution subject controls the instant information inquiry agent to ask questions to different inquiry objects in turn using a single inquiry instance and corresponding inquiry methods;

[0059] Another method may be: the execution subject controls the instant information inquiry agent to construct multiple inquiry instances and simultaneously ask questions to different inquiry objects using corresponding inquiry methods.

[0060] When multiple query instances can be constructed to ask questions to multiple different query objects simultaneously in a parallel manner, the time required to obtain all immediate feedback returned by all query objects can be significantly shortened.

[0061] Furthermore, if there are multiple inquiries, the execution entity can control the instant message inquiry agent to present real-time inquiry progress, so that the user can be informed of the current inquiry status and partial feedback through the presented inquiry progress. The inquiry progress can include the first inquiring party currently being asked a question and the second inquiring party who has completed the inquiry, as well as the instant feedback returned by the second inquiring party.

[0062] Step 204: controlling the associated sub-goal agents among the multiple sub-goal agents to generate corresponding associated processing results based on the instant feedback output by the instant information query agent;

[0063] Based on step 203, this step aims to control the associated sub-target agent among the multiple sub-target agents by the above-mentioned execution subject to generate corresponding associated processing results based on the instant feedback output by the instant information inquiry agent. The associated sub-target agent is a sub-target agent that relies on the instant feedback as part of the task input information. Therefore, the execution of the corresponding sub-target task by the associated sub-target agent is actually arranged after the instant information inquiry agent outputs the instant feedback.

[0064] It should be understood that each sub-goal agent, including the instant information inquiry agent and the associated sub-goal agent, should actually output the sub-processing results corresponding to the issued sub-goal task in combination with the user's personalized preferences under the call or arrangement of the main agent. Specifically, the main agent can simultaneously inform the execution order or execution trigger signal when issuing each sub-goal task to each sub-goal agent, so that each sub-goal agent executes the corresponding sub-goal task according to the informed execution order or executes the corresponding sub-goal task when it determines that the current state meets the requirements of the execution trigger signal, that is, each sub-goal agent actively executes the corresponding sub-goal task at the appropriate time; the main agent can also actively call each sub-goal agent to execute the corresponding sub-goal task as required when it determines that different sub-goal agents meet the execution time, that is, each sub-goal agent only passively executes the corresponding sub-goal task according to the call instruction.

[0065] Both the active execution mechanism and the passive execution mechanism mentioned above belong to different forms of collaboration between the main intelligent agent and multiple sub-intelligent agents to jointly process tasks. The specific choice can be based on the actual needs of the actual application scenario, and no specific limitation is made here.

[0066] Furthermore, as each sub-goal agent executes its corresponding sub-goal task and obtains its corresponding sub-processing result, the user's personalized preferences can also be incorporated. The multiple sub-processing results include at least the instant feedback corresponding to the corresponding instant message query task output by the instant message query agent and the associated processing result output by the associated sub-goal agent. The remaining sub-processing results can also be the results obtained by other agents when processing tasks of the corresponding type. These sub-processing results can be dependent on other sub-processing results or determined independently based on the task description information of the sub-goal task without relying on other sub-processing results.

[0067] Step 205: Determine a target processing result corresponding to the target task based on the associated processing result.

[0068] On the basis of step 203 , this step aims to determine the target processing result corresponding to the target task based on the associated processing result.

[0069] Specifically, in the process of processing the associated processing results to obtain the target processing results, we can fully refer to the decomposition method of decomposing multiple sub-target tasks from the target task, and adopt a variety of processing methods including deduplication, expression adjustment, sentence adjustment and rich expression methods, so that the final target processing results can not only meet the user's task requirements, but also highlight the key requirement result information as much as possible and improve information recognition.

[0070] The instant information inquiry task processing method based on multi-agent collaboration provided by the embodiment of the present disclosure adopts an agent cluster formed by a pre-built main agent and multiple sub-agents to process the task requirements proposed by the user, wherein the main agent is responsible for understanding the user's task requirements and decomposing the overall task requirements into multiple sub-target tasks that can be performed by different sub-agents. Each sub-agent processes the sub-task that matches itself according to the mobilization of the main agent. That is, through the collaboration between the main agent and each sub-agent, each can perform its own duties to process different components of the complex task. Moreover, since different sub-agents are pre-built to handle different types of tasks, the scheme of the main agent and multiple sub-agents cooperating to process task requirements adopted by the present disclosure has better processing effects on a single type of task than using a single, all-round agent. In addition, the relatively small sub-agents also facilitate the flexible addition and modification of corresponding functions. This scheme can bring better comprehensive task processing effects at a lower overall cost.

[0071] In particular, for instant information inquiry tasks that require combining instant information to verify whether the actual situation meets the task requirements and obtain instant feedback using the verification results, the instant information inquiry agent also supports asking questions in a background manner (i.e., processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, without affecting other user operations.

[0072] To deepen your understanding of how to determine the target tasks, please refer to Figure 3 , Figure 3 This is a flowchart of a method for determining a target task based on natural language input provided by an embodiment of the present disclosure, wherein process 300 includes the following steps:

[0073] Step 301: Convert the user's natural language input into natural language text;

[0074] This step aims to convert the natural language input in various forms into natural language text that is easy to recognize and output by the above-mentioned execution subject, that is, to uniformly convert various forms into text form. For example, speech-to-text technology can be used to convert natural speech signals in speech form into natural language text.

[0075] Step 302: Perform intent recognition on the natural language text to obtain an intent recognition result including the demand verification intent combined with the instant information;

[0076] Based on step 301, this step aims to perform intent recognition on the natural language text by the aforementioned execution entity, obtaining an intent recognition result that includes the intent to verify the demand in conjunction with the instant message. This intent recognition result at least includes the intent to verify the demand in conjunction with the instant message, but may also include other intents, which are not specifically limited here.

[0077] An implementation method including but not limited to the following specific steps may include:

[0078] First, the above-mentioned execution subject performs semantic understanding on the natural language text to obtain a semantic understanding result; then, the above-mentioned execution subject determines the preliminary intention (or suspected intention) based on the semantic understanding result. In order to improve the accuracy of intention determination, the above-mentioned execution subject can also use the user's personalized preferences to personalize the preliminary intention and obtain an intention recognition result that includes the intention to verify the needs of the instant information.

[0079] That is, this implementation method first determines the preliminary intention that directly corresponds to the natural language text by using semantic understanding, and then uses the user's personalized preferences to personalize the preliminary intention, such as filtering, excluding, and supplementing implicit or missing information, so that the final intention recognition result is more in line with the user's actual expectations.

[0080] In addition to this implementation method, you can also use the various technologies involved in the multiple processing links mentioned in step 201 to combine them with actual application scenarios to construct other implementation methods to obtain a determined intent recognition result. They will not be listed one by one here.

[0081] Step 303: Determine the target task to be solved based on the intention recognition result.

[0082] Based on step 302, this step aims to determine the target task to be solved by the execution subject according to the intention recognition result. The target task includes a task for obtaining a clear existing result.

[0083] Specifically, in order to convert the identified intent into a specific task, task modeling operations including task abstraction (mapping the user's needs into a task framework recognizable by the system) and target task definition can be used to ultimately obtain the target task corresponding to the natural language input.

[0084] This embodiment provides a more specific implementation method for determining the target task based on natural language input through steps 301 to 303, which includes the key processing steps of conversion of expression form, intent recognition and determination of the target task based on the intent recognition result, so as to provide an implementation solution with high feasibility and more accurate determination of the target task as much as possible.

[0085] To further understand how to decompose the target task into multiple sub-target tasks, see Figure 4 , Figure 4 A flowchart of a method for decomposing a target task into multiple sub-target tasks including a clear result acquisition task according to task elements is provided in an embodiment of the present disclosure. The process 400 includes the following steps:

[0086] Step 401: Determine multiple task elements that constitute the target task;

[0087] This step aims to enable the execution subject to determine the multiple task elements that constitute the target task, with different task elements corresponding to different types of tasks.

[0088] Task elements are the basic units or components that make up the target task. Each target task may be composed of several independent elements, which are the key steps, subtasks, or resources required to achieve the target task. Each task element may correspond to an independent task, and they work together to promote the completion of the target task.

[0089] Assume that the target task is to "develop a new software product". This target task can be decomposed into multiple task elements, each of which corresponds to a different type of task:

[0090] 1) Demand analysis (management task): determine user needs and market demand;

[0091] 2) System design (technical tasks): architecture design, database design, and interface design;

[0092] 3) Coding and development (technical tasks): programmers write code and implement functions;

[0093] 4) Testing and quality control (technical and management tasks): unit testing, integration testing, quality assurance;

[0094] 5) Marketing and promotion (management and communication tasks): formulate marketing plans and promote products.

[0095] Step 402: Verify whether the actual situation meets the task requirements based on the instant information and obtain a single task element with the verification result serving as instant feedback, and decompose the instant information inquiry task from the target task;

[0096] This step aims to decompose instant information inquiry tasks from the target tasks by the above-mentioned execution entity. Specifically, it relies on a single task element that needs to verify whether the actual situation meets the task requirements in combination with instant information, and obtains instant feedback with the verification results.

[0097] Step 403: Decompose the target task into multiple sub-target tasks each containing only a single task element.

[0098] This step is intended to decompose the target task into multiple sub-target tasks containing only a single task element, wherein the sub-target task at least includes an instant information inquiry task, by referring to the method of decomposing the target task by task elements in step 402 to obtain a clear result acquisition task.

[0099] This embodiment provides a task decomposition method through steps 401 to 403, which is based on the task elements that constitute the target task and decomposes each task element into sub-target tasks. Combined with the pre-definition of the task elements (for example, according to the method of constructing different sub-intelligent agents), the task decomposition can be flexibly completed according to actual conditions.

[0100] Furthermore, considering that even the same task element may be subject to additional conditions, it is necessary to decompose it into sub-target tasks carrying the additional conditions when decomposing the task, so that when the sub-target tasks are subsequently issued to the sub-target agents, the appropriate sub-agent can be selected as the sub-target agent based on the additional conditions.

[0101] One implementation method, including but not limited to, may be: in response to the presence of additional conditions corresponding to task elements, decomposing the target task into multiple sub-target tasks each consisting of a single task element and the corresponding additional conditions. The additional conditions may include a specified task processing method and / or a specified result presentation format. Different task processing methods are abstracted from different processing logics for the same type of task (e.g., the same type of task can have multiple different processing logics, but ultimately produce a correct answer). The result presentation format may include at least one of text, table, image, video, and interactive card formats.

[0102] To further understand how to pre-create different sub-agents, see Figure 5 , Figure 5 A flowchart of a method for creating a sub-agent provided in an embodiment of the present disclosure, wherein process 500 includes the following steps:

[0103] Step 501: Determine a set of task types for creating a sub-agent;

[0104] Step 502: For each type of task in the task type set, a sub-agent with the task processing capability of the corresponding type of task is constructed.

[0105] This embodiment, through steps 501 and 502, provides a solution for constructing a sub-agent with the task processing capabilities for each of the multiple identified task types. Furthermore, each task type can have only one or multiple sub-agents, each of which may be distinct or identical. Whether these sub-agents are required depends on whether the task type typically includes additional conditions.

[0106] Specifically, for a first target type task with at least two task processing methods, a sub-agent corresponding to each task processing method can be constructed; for a second target type task with at least two result presentation forms, a sub-agent corresponding to each result presentation form can be constructed.

[0107] To further understand how the agent processes immediate feedback and how it obtains the target processing result based on the associated processing result, please refer to Figure 6 , Figure 6 A flowchart of a method for determining an associated processing result and a target processing result provided in an embodiment of the present disclosure is provided. This embodiment is based on a situation where there are multiple inquiry objects and multiple instant feedbacks are obtained. The process 600 includes the following steps:

[0108] Step 601: Control the associated sub-goal agent to make a feedback decision based on the instant feedback corresponding to each inquiry object output by the instant information inquiry agent, and obtain a feedback decision result;

[0109] The aforementioned execution agent controls the associated sub-goal agent to make feedback decisions based on the instant feedback corresponding to each query object output by the instant message query agent, generating a feedback decision result. This feedback decision result includes candidate execution objects that meet the task requirements of the target task, selected based on the instant feedback. In other words, the current associated sub-goal agent is used to filter the instant feedback returned by the instant message query agent to determine which ones meet the task requirements.

[0110] Step 602: Presenting alternative execution objects to the user;

[0111] Based on step 601, this step is intended to present alternative execution objects to the user by the above-mentioned execution subject. When there is only one alternative execution object, this step will only exist to enable the user to clearly determine the only execution object that is finally determined; when there are multiple alternative execution objects, this step will exist as a step for the user to select the target execution object that he or she thinks is more suitable.

[0112] Step 603: In response to the number of candidate execution objects being greater than 1, receiving user selection information on multiple candidate execution objects, and determining the candidate execution object corresponding to the selection information as the target execution object;

[0113] This step is established when the number of candidate execution objects is greater than 1, and is intended for the above-mentioned execution subject to receive the user's selection information on multiple candidate execution objects, and determine the candidate execution object corresponding to the selection information as the target execution object.

[0114] Step 604: The control execution agent initiates an execution operation to the target execution object for realizing the task requirement of the target task, and obtains a requirement fulfillment notification returned by the target execution object.

[0115] On the basis of step 603, this step aims to control the execution agent to initiate an execution operation to the target execution object to realize the task requirements of the target task, and obtain a demand fulfillment notification returned by the target execution object.

[0116] Taking the task of "booking a private room that can accommodate 10 people at 8 pm" as an example, assuming that the instant message inquiry agent initiates telephone voice inquiries to 5 hotels respectively, the screening agent selects 3 hotels that meet the task requirements, and the user selects Hotel C as the target execution object, the execution agent of this step can initiate a telephone reservation operation to Hotel C, and then receive the demand fulfillment notification returned by Hotel C that "the private room for 10 people at 8 pm has been successfully booked."

[0117] This step provides a specific implementation method through steps 601-604 for the situation where there are multiple inquiry objects and multiple instant feedbacks will be obtained, including screening whether the multiple instant feedbacks provided by the screening agent meet the task requirements and executing the execution operation initiated by the execution agent to the target execution object, thereby ultimately ensuring the completion of the target task.

[0118] To further understand how the agent generates relevant processing results based on immediate feedback, see Figure 7 , Figure 7 This is a flowchart of a method for controlling an associated sub-goal agent to generate an associated processing result provided by an embodiment of the present disclosure. The process 700 includes the following steps:

[0119] Step 701: Sending the task information of the sub-goal task corresponding to the associated sub-goal agent as basic task information to the associated sub-goal agent;

[0120] Step 702: Control the instant information inquiry agent to send the output instant feedback as supplementary task information to the associated sub-goal agent;

[0121] Step 703: Control the associated sub-goal agent to generate corresponding associated processing results based on the basic task information and the supplementary task information.

[0122] According to the above three steps, in the sub-goal task issuance stage, the above-mentioned execution subject first sends the task information of the sub-goal task corresponding to the associated sub-goal intelligent agent as basic task information to the associated sub-goal intelligent agent, and then the execution subject controls the instant information inquiry intelligent agent to send the output instant feedback as supplementary task information to the associated sub-goal intelligent agent, and finally enables the associated sub-goal intelligent agent to perform the operation of generating associated processing results based on complete task information.

[0123] Furthermore, the execution entity can control the associated sub-goal agents that have not received supplementary task information to be in a standby state, and control the associated sub-goal agents that have received supplementary task information to switch to an active state. In other words, by keeping the associated sub-goal agents that have not received supplementary task information in a standby state, resource consumption can be minimized.

[0124] On the basis of any of the above embodiments, especially when there are multiple inquiry objects, the present disclosure further Figure 8 A flowchart of a method for determining an estimated waiting time and generating a waiting time notification is provided. The flowchart 800 includes the following steps:

[0125] Step 801: Control the instant message inquiry agent to predict the estimated time required to obtain instant feedback;

[0126] Specifically, the instant information inquiry agent can predict the estimated time required to obtain instant feedback based on at least one of the following inquiry parameters:

[0127] The number of people being questioned, the questioning methods used, and the number and complexity of the points to be verified in the questions.

[0128] Step 802: Control the instant message inquiry agent to output a waiting time notification generated based on the estimated time consumption when performing the inquiry action of asking a question to the inquiry object.

[0129] Based on step 801, this step is intended to control the instant information inquiry agent to output a waiting time notification generated based on the estimated time when executing the inquiry action of asking questions to the inquiry object, so that the user can temporarily leave the task conversation generated based on the natural language input for a period of time corresponding to the estimated time according to the waiting time notification, without having to stay in the task conversation interface for a long time and without affecting other operations.

[0130] Furthermore, if the estimated time exceeds a preset duration, the execution entity may control the associated sub-goal agent to remain in an idle frozen state for a first duration before receiving immediate feedback, where the first duration is determined based on the estimated time and is shorter than the estimated time. Furthermore, the execution entity may control the associated sub-goal agent that has remained in the idle frozen state for longer than the first duration to switch from the idle frozen state to a standby ready state. Finally, the execution entity may control the associated sub-goal agent that has received immediate feedback to switch from the standby ready state to a working state. Compared to the standby ready state, the idle frozen state can further reduce resource consumption.

[0131] Based on any of the above embodiments, considering that the user may modify the content of some of the sub-processing results that have been output or issue new restriction information at any time during the entire process of each sub-target agent performing the corresponding sub-target task and outputting the sub-processing results, please refer to Figure 9 , Figure 9 A two-branch schematic diagram of controlling a sub-goal agent to output corresponding sub-processing results is provided in an embodiment of the present disclosure. The process 900 includes the following steps:

[0132] Step 901: In response to the instruction input box being in the selected state, controlling the currently executed sub-goal agent to pause outputting the corresponding sub-processing result;

[0133] The command input box is used for user input of commands. It remains unselected while the sub-goal agent is outputting the corresponding sub-processing result. In other words, in the disclosed embodiments, once the command input box is selected, it indicates that the user needs to input new commands, interrupting the original sub-processing result output process.

[0134] Step 902: In response to no new instruction being generated during the process of the instruction input box being restored from the selected state to the unselected state, controlling the currently executed sub-goal agent to continue outputting the corresponding sub-processing result;

[0135] This step corresponds to a branch situation in which no new instruction is generated during the process of the instruction input box being restored from the selected state to the unselected state, that is, the user does not enter a new instruction, then the sub-processing result output that was originally interrupted due to the selection of the instruction input box will continue.

[0136] Step 903: In response to a new instruction being generated in the process of the instruction input box being restored from the selected state to the unselected state, extracting correction information from the new instruction;

[0137] This step corresponds to another branch situation in which a new instruction is generated during the process of the instruction input box being restored from a selected state to an unselected state. In this case, the above-mentioned execution subject is required to extract correction information from the new instruction, which includes corrections to the original information and additions of new information.

[0138] Step 904: Determine the sub-target agent affected by the correction information;

[0139] Step 905: Control the affected sub-target agent to re-output the corresponding sub-processing result in combination with the correction information.

[0140] In steps 904 and 905, the execution agent first determines the sub-target agents affected by the correction information. It then controls the affected sub-target agents to re-output the corresponding sub-processing results based on the correction information. Specifically, if all sub-target agents are affected, execution can be restarted from the first sub-target agent to output the sub-processing results based on the correction information.

[0141] To deepen understanding, the present disclosure also provides a specific implementation solution that attempts to eliminate the existing technical defects and overcome the existing technical problems in combination with the actual existing technical defects in specific application scenarios:

[0142] The current method of satisfying demand is primarily through search engines, which employ a multi-layered system funnel to retrieve, rank, and mix heterogeneous results from relevant web pages. Each strategic funnel ranks web pages based on basic relevance, user feedback behavior, authority, and other information, and then truncates the output to the next layer. The disadvantage of this system is that it can only match relevance at the content level, rather than understanding and solving problems for users at the task level. Furthermore, web pages can only meet user needs with fixed content, and when users express personalized needs and require multiple rounds of further satisfaction, high-quality, consistent satisfaction cannot be achieved. Furthermore, the entire matching process is inexplicable to users, who can only perform a final information screening.

[0143] Related assistant products based on large models typically attempt to address this problem through a single, all-purpose assistant. However, a single large model struggles to achieve high-quality satisfaction across diverse, open domains and tasks. In specialized fields and specialized scenarios, a single assistant struggles to build user trust and achieve the desired satisfaction.

[0144] That is, the relevant technologies have the following difficulties in completing tasks in open fields:

[0145] 1) How to effectively understand and decompose user needs into key steps;

[0146] 2) How to find the best way to meet each key step;

[0147] 3) How to output the execution process and integration results in a user-friendly and complete manner.

[0148] To address the above difficulties, this embodiment proposes a solution for user-demand end-to-end task completion based on multi-agent asynchronous collaboration. The features of this solution are as follows:

[0149] Previously, search was a single-point approach, with one query (query term, query statement, search term, and search statement) fulfilling a single requirement. Each requirement required users to define it on their own, which was prohibitively expensive. For complex tasks, users often didn't know how to break down the task and formulate multiple queries for search. However, the paradigm proposed in this embodiment aims to thoroughly help users complete tasks. The task completion paradigm allows users to directly complete the problem or task in one step. Compared to single-query search, the task completion paradigm deeply understands the user's complete task and breaks it down to complete it, better meeting user needs.

[0150] This embodiment is based on the collaboration between multiple intelligent agents to achieve the decomposition and multi-step satisfaction of user needs, and finally automatically integrate them into a complete solution that can meet the entire task. This solution can complete the following functions:

[0151] 1) Understand the key steps of the requirements, build a main agent, understand the intention of the user's expressed requirements and break them down into key steps that can be completed by multiple subtask agents;

[0152] 2) Subtask agent generation: Based on its understanding of key steps and agent capabilities, the main agent is responsible for generating multiple subtask agent candidates required to complete the current task;

[0153] 3) Multi-agent collaborative task completion: multiple subtask agents complete the entire task through multi-agent scheduling and collaboration based on the requirements of the task and key steps, as well as user preference information input, and generate step-by-step results for task completion;

[0154] 4) Complete the integrated output of the plan. The main agent integrates the task decomposition process and the results of asynchronous collaboration among multiple subtask agents to present the final complete process and results.

[0155] This embodiment builds a master agent to schedule multiple subtask agents to collaborate. The master agent collaborates with multiple subtask agents, and the subtask agents collaborate with each other to complete the entire task. Compared with search or intelligent assistant products, it can use agents with better performance in specific areas to complete the task, achieving better results.

[0156] By providing a scheduling and distribution mechanism based on end-to-end generative large models, large models have stronger expressive capabilities, overcoming the lack of consistency and global optimality in traditional multi-layer sorting mechanisms, and enabling task-oriented, globally optimal combined scheduling optimization. From a modeling perspective, it enables end-to-end aligned training of models from the perspectives of agent understanding and task understanding.

[0157] At the same time, since the generative completion of the entire task is personalized, everything from task decomposition to subtask completion is generated based on user input and user preferences. Different solution decompositions, subtask agent completion solutions and presentation effects are generated for different users to improve user satisfaction.

[0158] The implementation block diagram of this solution is as follows Figure 10-1 As shown in the figure, the user inputs requirements and a set of distributable agents (including their basic settings, installed plugins, workflows, etc.), which output multi-level generated content to complete the task. The entire system is built based on multi-agent collaboration and primarily comprises two types of agents: 1) Main Agent: This agent comprehensively understands, decomposes, and connects tasks, producing the final result. 2) Task Agent: This agent dispatches subtask agents through asynchronous scheduling to collaboratively complete tasks assigned by the main agent.

[0159] The solution provided by this embodiment can be widely applied to various information-satisfying applications or independent products. The following uses the scenario of the BaiX application as an example to illustrate the specific application form of this embodiment:

[0160] While performing traditional searches, users can switch to the functional usage mode provided by this embodiment with one click (such as the "AI button" on the bottom bar in the figure below). The user enters "8 people are having dinner tonight and need a private room. Please help me book a restaurant with convenient parking" (corresponding to Figure 10-2 ), displaying the results of web search and intelligent answers, and switching to the "Restaurant Reservations Tonight" page through the AI ​​button to display the results generated for user personalization, as shown below Figure 10-3 The task completion page displayed includes personalized requirements such as "close distance", "private room", and "easy parking".

[0161] On the task completion page, the work results of multiple task completion agents are displayed, including the host agent Food Planner, and the subtask agents "Smart Phone Reservation" and "Restaurant Selection Guide". The entire process needs to be completed asynchronously. The "Smart Phone Reservation" sub-agent reminds the user that it is calling the "Changan Ji" restaurant and needs to return the result later. The results of each task completion agent are executed through asynchronous actions, and the results are displayed in a structured, personalized, and user-friendly generated UI. Users can download and share the results, such as Figure 10-4 shown.

[0162] In the revisit form, when the user returns to the BaiX application, even if he does not enter a new query in the search bar, he can still return to the task list that can display the history by clicking the entry button. At this time, he can still click to enter the corresponding result page, such as Figure 10-5 and Figure 10-6 Other applications may also have similar independent entrances (not shown separately).

[0163] The above examples show that this embodiment has the following improvements and technical effects compared to the prior art:

[0164] 1) Task satisfaction paradigm: user requests are no longer considered as information retrieval, but upgraded to a complete multi-agent task completion satisfaction model

[0165] Current search engines can retrieve information by matching requests to relevant information, while intelligent assistants can break down a task into multiple steps and search for solutions in stages. However, multi-agent collaboration, which breaks down tasks and meets the user's complete needs, presents a completely new model for satisfying user needs. Furthermore, we propose training for aligning task breakdown with multi-agent capabilities, which can achieve a high degree of consistency between task breakdown and completion, significantly improving task completion effectiveness.

[0166] 2) Multi-agent candidate generation based on multi-agent collaboration

[0167] Based on the results of task decomposition, the large model generates a target collaborative agent set end-to-end. This is a completely new approach that differs from the traditional search-recall ranking system for agent sorting. Multi-agent collaborative tasks meet the need to combine multiple agents when tasks are not completed. This requires the large model to deeply understand the task decomposition and the capabilities of each agent, meticulously delineating the difficulty boundaries of the problem, and ultimately obtaining the optimal agent set for the current goal through combinatorial optimization. The difficulties here include:

[0168] Difficulty 1: Deep understanding of the capabilities of intelligent agents, understanding the boundaries of the capabilities of intelligent agents and the tasks that intelligent agents are good at, and carefully depicting the subtle differences between capabilities, such as the different creative styles of painting intelligent agents and the subtle differences in capabilities in photo editing.

[0169] Difficulty 2: Understanding the matching relationship between tasks and agent capabilities is not a semantic similarity match, but a deep match in task completion capabilities. This requires a deep characterization and understanding of the tasks, task types and task boundaries. Matching the open set of agent capabilities and task requirements is a huge challenge.

[0170] Difficulty 3: Given a multi-agent collaborative task, obtaining the optimal combination is a combinatorial optimization problem that requires combinatorial optimization.

[0171] 3) The task completion process and results are completed through end-to-end asynchronous collaboration of intelligent agents.

[0172] The end-to-end experience mainly includes:

[0173] 1) Asynchronous collaboration improves task completion experience: Multiple subtask agents collaborate asynchronously to complete tasks. This approach is essential for tasks requiring asynchronous execution. Asynchronous actions by multiple agents collaborate, enabling communication and sharing of tasks and results.

[0174] 2) End-to-end experience of result presentation: Currently, search engines struggle to present the search process to users, while intelligent assistants present the results of thinking and single-step execution, and the UI presentation is essentially a pre-set style. Thanks to the multi-agent collaborative task decomposition, combination, and multi-subtask completion mode, the solution provided in this embodiment can present the results in an end-to-end generated manner, including the steps, style, and results of each step. Furthermore, the results of each step and the subtask results completed by each subtask agent can be further interacted with. This experience is a comprehensive innovation.

[0175] Further references Figure 11 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an instant information inquiry task processing device based on multi-agent collaboration. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0176] like Figure 11As shown, the instant information inquiry task processing device 1100 based on multi-agent collaboration of this embodiment may include: a target task determination unit 1101, a task decomposition and corresponding issuance unit 1102, an inquiry control unit 1103, an association processing control unit 1104, and a target processing result determination unit 1105. Among them, the target task determination unit 1101 is configured to determine the target task to be solved based on the user's natural language input; the task decomposition and corresponding issuance unit 1102 is configured to decompose the target task into multiple sub-target tasks including at least instant message inquiry tasks, and issue each sub-target task to each sub-target agent including at least an instant message inquiry agent; wherein different sub-agents are used to process different types of subtasks; the inquiry control unit 1103 is configured to control the instant message inquiry agent to ask questions to the inquiry object and obtain instant feedback; wherein the instant message inquiry agent supports question asking in a background running manner; the association processing control unit 1104 is configured to control the associated sub-target agent among the multiple sub-target agents to generate corresponding associated processing results based on the instant feedback output by the instant message inquiry agent; wherein the associated sub-target agent is a sub-target agent that relies on instant feedback as part of the task input information; the target processing result determination unit 1105 is configured to determine the target processing result corresponding to the target task based on the associated processing result.

[0177] In this embodiment, in the instant information inquiry task processing device 1100 based on multi-agent collaboration: the specific processing of the target task determination unit 1101, the task decomposition and corresponding issuance unit 1102, the inquiry control unit 1103, the association processing control unit 1104, and the target processing result determination unit 1105 and the technical effects thereof can be referred to respectively. Figure 2 The relevant descriptions of steps 201-205 in the corresponding embodiment are not repeated here.

[0178] In some optional implementations of this embodiment, the target task determination unit 1101 may include:

[0179] a conversion subunit configured to convert a user's natural language input into a natural language text;

[0180] an intention recognition subunit configured to perform intention recognition on the natural language text and obtain an intention recognition result including a demand verification intention combined with the instant information;

[0181] The target task determination subunit is configured to determine the target task to be solved based on the intention recognition result; wherein the target task includes a task that is verified in combination with real-time information to see whether it meets the requirements.

[0182] In some optional implementations of this embodiment, the intention identification subunit may be further configured to:

[0183] Perform semantic understanding on natural language text to obtain semantic understanding results;

[0184] The preliminary intention is determined based on the semantic understanding results, and the preliminary intention is personalized modified using the user's personalized preferences to obtain the intention recognition result.

[0185] In some optional implementations of this embodiment, the task decomposition and corresponding dispatching unit 1102 may include a task decomposition sub-unit configured to decompose the target task into a plurality of sub-target tasks including at least an instant information inquiry task. The task decomposition sub-unit may include:

[0186] a task element determination module configured to determine a plurality of task elements constituting a target task; wherein different task elements correspond to different types of tasks;

[0187] The instant message inquiry task decomposition module is configured to verify whether the actual situation meets the task requirements based on specific needs and obtain individual task elements with the verification results serving as immediate feedback, thereby decomposing the instant message inquiry task from the target task;

[0188] The sub-goal task decomposition module is configured to decompose the target task into multiple sub-goal tasks each containing only a single task element; wherein the sub-goal tasks at least include instant information inquiry tasks.

[0189] In some optional implementations of this embodiment, the sub-goal task decomposition module may be further configured to:

[0190] In response to the existence of additional conditions corresponding to the task elements, the target task is decomposed into multiple sub-target tasks containing only a single task element and the corresponding additional conditions; wherein the additional conditions include: a specified task processing method and / or a specified result presentation form.

[0191] In some optional implementations of this embodiment, the instant message inquiry task processing apparatus 1100 based on multi-agent collaboration may further include: a sub-agent construction unit configured to construct different sub-agents, and the sub-agent construction unit may include:

[0192] a task type set determining subunit configured to determine a task type set for creating a sub-agent;

[0193] The construction sub-unit is configured to construct a sub-agent with the task processing capability of the corresponding type of task for each type of task in the task type set.

[0194] In some optional implementations of this embodiment, the construction subunit may be further configured to:

[0195] In response to the first target type task having at least two task processing methods, a sub-agent corresponding to each task processing method is constructed for the first target type task; wherein the different task processing methods are abstracted from different processing logics for the same type of tasks.

[0196] In some optional implementations of this embodiment, the construction subunit may be further configured to:

[0197] In response to the second target type task having at least two result presentation forms, a sub-agent corresponding to each result presentation form is constructed for the second target type task; wherein the result presentation form includes: at least one of: text type, table type, image type, video type, and interactive card type.

[0198] In some optional implementations of this embodiment, the query control unit 1103 may include:

[0199] The first control subunit is configured to control the instant message inquiry agent to determine an inquiry object and a question based on received task input information; wherein the received task input information is determined based on task description information related to the instant message inquiry task decomposed from the target task;

[0200] The second control subunit is configured to control the instant information inquiry agent to ask questions to the inquiry object using a preset inquiry method.

[0201] In some optional implementations of this embodiment, the second control subunit may be further configured to:

[0202] The separate inquiry control module is configured to control the instant information inquiry agent to ask questions to different inquiry objects using corresponding inquiry methods in response to the number of inquiry objects exceeding a preset number.

[0203] In some optional implementations of this embodiment, the separate query control module may be further configured to:

[0204] The instant information inquiry agent is controlled to ask questions to different inquiry objects in turn using corresponding inquiry methods through a single inquiry instance.

[0205] In some optional implementations of this embodiment, the separate query control module may be further configured to:

[0206] The instant information inquiry agent is controlled to construct multiple inquiry instances and simultaneously ask questions to different inquiry objects using corresponding inquiry methods.

[0207] In some optional implementations of this embodiment, the instant information inquiry task processing device 1100 based on multi-agent collaboration may further include:

[0208] The inquiry progress presentation control unit is configured to control the instant information inquiry agent to present the real-time inquiry progress; wherein the inquiry progress includes the first inquiry object currently being asked questions and the second inquiry object who has completed the inquiry.

[0209] In some optional implementations of this embodiment, the association processing control unit 1104 may be further configured to:

[0210] The control-associated sub-goal agent makes feedback decisions based on the instant feedback corresponding to each inquiry object output by the instant information inquiry agent, and obtains a feedback decision result; wherein the feedback decision result includes alternative execution objects selected according to each instant feedback that meet the task requirements of the target task.

[0211] In some optional implementations of this embodiment, the target processing result determining unit 1105 may be further configured to:

[0212] Presenting alternative execution objects to the user;

[0213] In response to the number of candidate execution objects being greater than 1, receiving user selection information on the plurality of candidate execution objects, and determining the candidate execution object corresponding to the selection information as the target execution object;

[0214] The control execution agent initiates the execution operation of the task requirement for realizing the target task to the target execution object, and obtains the demand fulfillment notification returned by the target execution object.

[0215] In some optional implementations of this embodiment, the inquiry method includes at least one of the following:

[0216] Voice telephone inquiries, text inquiries, image inquiries containing specified image elements, and video inquiries containing specified video elements.

[0217] In some optional implementations of this embodiment, the received task input information is determined based on task description information related to the instant message inquiry task decomposed from the target task and the user's personalized preference.

[0218] In some optional implementations of this embodiment, the task decomposition and corresponding dispatching unit 1102 may include a corresponding dispatching sub-unit configured to dispatch each sub-goal task to each sub-goal agent including at least the instant message inquiry agent. The corresponding dispatching sub-unit includes a dispatching module configured to dispatch the sub-goal task corresponding to the associated sub-goal agent to the associated sub-goal agent. The dispatching module may be further configured to:

[0219] Sending the task information of the sub-goal task corresponding to the associated sub-goal agent as basic task information to the associated sub-goal agent;

[0220] Correspondingly, the association processing control unit 1104 may be further configured to:

[0221] Control the instant information inquiry agent to send the output instant feedback as supplementary task information to the associated sub-goal agent;

[0222] The control-associated sub-goal agent generates corresponding associated processing results based on the basic task information and supplementary task information.

[0223] In some optional implementations of this embodiment, the instant information inquiry task processing device 1100 based on multi-agent collaboration may further include:

[0224] A first standby ready state control unit is configured to control the associated sub-goal agent that has not received the supplementary task information to be in a standby ready state;

[0225] The first working state control unit is configured to control the associated sub-goal agent that receives the supplementary task information to switch to a working state.

[0226] In some optional implementations of this embodiment, the instant information inquiry task processing device 1100 based on multi-agent collaboration may further include:

[0227] An estimated time consumption prediction control unit is configured to control the instant information inquiry agent to predict the estimated time consumption for obtaining instant feedback;

[0228] The waiting time notification output control unit is configured to control the instant message inquiry agent to output a waiting time notification generated based on the estimated time when performing an inquiry action of asking a question to the inquiry object, so that the user can temporarily leave the task conversation generated based on the natural language input for a period of time corresponding to the estimated time.

[0229] In some optional implementations of this embodiment, the estimated time consumption prediction control unit may be further configured to:

[0230] Controls the instant message query agent to predict the estimated time it takes to get instant feedback based on at least one of the following query parameters:

[0231] The number of people being questioned, the questioning methods used, and the number and complexity of the points to be verified in the questions.

[0232] In some optional implementations of this embodiment, the instant information inquiry task processing device 1100 based on multi-agent collaboration may further include:

[0233] an idle frozen state control unit configured to, in response to the estimated time exceeding a preset time, control the associated sub-goal agent to be in an idle frozen state for a first time without receiving immediate feedback; wherein the first time is determined based on the estimated time and is shorter than the estimated time;

[0234] a second standby ready state control unit configured to control the associated sub-goal agent that maintains the idle frozen state for more than a first time period to switch from the idle frozen state to the standby ready state;

[0235] The second working state control unit is configured to control the associated sub-goal agent that receives the immediate feedback to switch from the standby ready state to the working state.

[0236] In some optional implementations of this embodiment, the instant information inquiry task processing device 1100 based on multi-agent collaboration may further include:

[0237] a pause output control unit configured to control the currently executing sub-agent to pause outputting the corresponding sub-processing result in response to the instruction input box being in a selected state; wherein the instruction input box is used for user input of instructions, and the instruction input box is in an unselected state during the process of the sub-agent outputting the corresponding sub-processing result;

[0238] a correction information extraction unit configured to extract correction information from a new instruction in response to a new instruction being generated in the process of the instruction input box being restored from a selected state to an unselected state;

[0239] an affected sub-goal agent determining unit, configured to determine the sub-goal agent affected by the correction information;

[0240] The re-output result control unit is configured to control the affected sub-target agent to re-output the corresponding sub-processing result in combination with the correction information.

[0241] This embodiment exists as an apparatus embodiment corresponding to the above method embodiment. This embodiment provides an instant information inquiry task processing device based on multi-agent collaboration.

[0242] An agent cluster formed by a pre-built main agent and multiple sub-agents is used to process the task requirements proposed by users, wherein the main agent is responsible for understanding the user's task requirements and decomposing the overall task requirements into multiple sub-target tasks that can be performed by different sub-agents. Each sub-agent processes the sub-task that matches itself according to the mobilization of the main agent. That is, through the collaboration between the main agent and each sub-agent, different components of a complex task can be handled in their respective roles. Moreover, since different sub-agents are pre-built to be dedicated to handling different types of tasks, the scheme of the main agent and multiple sub-agents collaboratively handling task requirements adopted in the present disclosure has better processing effects on a single type of task than using a single, all-powerful agent. In addition, the relatively small sub-agents are also convenient for flexibly adding and changing corresponding functions. This scheme can bring better comprehensive task processing effects at a lower overall cost.

[0243] In particular, for instant information inquiry tasks that require combining instant information to verify whether the actual situation meets the task requirements and obtain instant feedback using the verification results, the instant information inquiry agent also supports asking questions in a background manner (i.e., processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, without affecting other user operations.

[0244] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the instant information inquiry task processing method based on multi-agent collaboration described in any of the above embodiments when executing.

[0245] According to an embodiment of the present disclosure, the present disclosure also provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the instant information inquiry task processing method based on multi-agent collaboration described in any of the above embodiments when executed.

[0246] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which, when executed by a processor, can implement the instant information inquiry task processing method based on multi-agent collaboration described in any of the above embodiments.

[0247] Figure 12A schematic block diagram of an example electronic device 1200 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0248] like Figure 12 As shown, device 1200 includes a computing unit 1201, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1202 or a computer program loaded from a storage unit 1208 into a random access memory (RAM) 1203. RAM 1203 may also store various programs and data required for the operation of device 1200. Computing unit 1201, ROM 1202, and RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to bus 1204.

[0249] Various components in device 1200 are connected to I / O interface 1205, including an input unit 1206, such as a keyboard and mouse; an output unit 1207, such as various types of displays and speakers; a storage unit 1208, such as a magnetic disk and optical disk; and a communication unit 1209, such as a network card, a modem, a wireless communication transceiver, etc. Communication unit 1209 allows device 1200 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0250] The computing unit 1201 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 1201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1201 performs the various methods and processes described above, such as the method for processing instant messaging query tasks based on multi-agent collaboration. For example, in some embodiments, the method for processing instant messaging query tasks based on multi-agent collaboration can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1208. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1200 via the ROM 1202 and / or the communication unit 1209. When the computer program is loaded into the RAM 1203 and executed by the computing unit 1201, one or more steps of the method for processing instant messaging query tasks based on multi-agent collaboration described above can be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured in any other appropriate manner (eg, by means of firmware) to execute an instant information inquiry task processing method based on multi-agent collaboration.

[0251] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0252] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0253] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0254] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0255] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0256] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host. This is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and virtual private server (VPS) services.

[0257] The technical solution of the embodiment of the present disclosure adopts an agent cluster formed by a pre-built main agent and multiple sub-agents to process the task requirements proposed by the user, wherein the main agent is responsible for understanding the user's task requirements and decomposing the overall task requirements into multiple sub-target tasks that can be performed by different sub-agents. Each sub-agent processes the sub-task that matches itself according to the mobilization of the main agent. That is, through the collaboration between the main agent and each sub-agent, each can perform its own duties to process different components of a complex task. Since different sub-agents are pre-built to be dedicated to processing different types of tasks, the solution of the main agent and multiple sub-agents used in the present disclosure to collaboratively process task requirements has better processing effects on a single type of task than using a single, all-round agent. The relatively small sub-agents are also convenient for flexible addition and modification of corresponding functions. This solution can bring better comprehensive task processing effects at a lower overall cost.

[0258] In particular, for instant information inquiry tasks that require combining instant information to verify whether the actual situation meets the task requirements and obtain instant feedback using the verification results, the instant information inquiry agent also supports asking questions in a background manner (i.e., processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, without affecting other user operations.

[0259] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0260] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for processing instant information inquiry tasks based on multi-agent collaboration, applied to the main agent, comprising: Determine the target task to be solved based on the user's natural language input; Decomposing the target task into a plurality of sub-target tasks including at least an instant message inquiry task, and assigning each of the sub-target tasks to a corresponding sub-target agent including at least an instant message inquiry agent; different sub-agents are used to process different types of sub-tasks; Controlling the instant information inquiry agent to ask questions to the inquiry object based on the received task input information to obtain instant feedback; The instant information inquiry agent supports asking questions in a manner running in the background; Controlling an associated sub-target agent among a plurality of sub-target agents to generate a corresponding associated processing result based on the instant feedback output by the instant information inquiry agent, including: controlling the associated sub-target agent to make a feedback decision based on each instant feedback corresponding to each inquiry object output by the instant information inquiry agent, to obtain a feedback decision result; the feedback decision result includes an alternative execution object that meets the task requirements of the target task selected according to each instant feedback; the associated sub-target agent is a sub-target agent that relies on the instant feedback as part of the task input information; Determine a target processing result corresponding to the target task based on the association processing result; In response to the instruction input box being in a selected state, the currently executed sub-agent is controlled to pause outputting the corresponding sub-processing result; the instruction input box is used for the user to input instructions, and the instruction input box is in an unselected state during the process of the sub-agent outputting the corresponding sub-processing result; in response to the instruction input box generating a new instruction during the process of restoring from the selected state to the unselected state, correction information is extracted from the new instruction; the sub-target agent affected by the correction information is determined; and the affected sub-target agent is controlled to re-output the corresponding sub-processing result in combination with the correction information.

2. The method according to claim 1, wherein Determining the target task to be solved based on the user's natural language input includes: Converting the user's natural language input into natural language text; Performing intent recognition on the natural language text to obtain an intent recognition result including the intent of verifying the demand in combination with the instant information; Determine the target task to be solved based on the intention recognition result; wherein, the target task includes a task that is verified in combination with real-time information to see whether the requirements are met.

3. The method according to claim 2, wherein: The performing intent recognition on the natural language text to obtain an intent recognition result includes: Performing semantic understanding on the natural language text to obtain a semantic understanding result; A preliminary intention is determined based on the semantic understanding result, and the preliminary intention is personalized modified using the user's personalized preferences to obtain the intention recognition result.

4. The method according to claim 2, wherein: The step of decomposing the target task into a plurality of sub-target tasks including at least an instant information inquiry task includes: Determining a plurality of task elements constituting the target task, wherein different task elements correspond to different types of tasks; Decomposing the instant information inquiry task from the target task according to the need to verify whether the actual situation meets the task requirements in combination with the instant information and obtaining a single task element with the verification result serving as the instant feedback; The target task is decomposed into multiple sub-target tasks each including only a single task element; wherein the sub-target tasks at least include the instant information inquiry task.

5. The method according to claim 4, wherein The decomposition of the target task into multiple sub-target tasks each containing only a single task element includes: In response to the existence of additional conditions corresponding to the task elements, the target task is decomposed into multiple sub-target tasks each containing only a single task element and the corresponding additional conditions; wherein the additional conditions include: a specified task processing method and / or a specified result presentation form.

6. The method according to claim 1, wherein The process of constructing different sub-agents includes: Determine the set of task types used to create sub-agents; For each type of task in the task type set, a sub-agent with task processing capability of the corresponding type of task is constructed.

7. The method according to claim 6, wherein: For each type of task in the task type set, a sub-agent with the task processing capability of the corresponding type of task is constructed, including: In response to the first target type task having at least two task processing methods, a sub-agent corresponding to each task processing method is constructed for the first target type task; wherein the different task processing methods are abstracted from different processing logics for the same type of tasks.

8. The method according to claim 6, wherein: For each type of task in the task type set, a sub-agent with the task processing capability of the corresponding type of task is constructed, including: In response to the second target type task having at least two result presentation forms, a sub-agent corresponding to each of the result presentation forms is constructed for the second target type task; wherein the result presentation forms include: at least one of: text type, table type, image type, video type, and interactive card type.

9. The method according to claim 1, wherein The controlling the instant information inquiry agent to ask questions to the inquiry object and obtain instant feedback includes: Controlling the instant message inquiry agent to determine the inquiry object and the question based on the received task input information; wherein the received task input information is determined based on task description information related to the instant message inquiry task decomposed from the target task; The instant information inquiry agent is controlled to ask the inquiry object the question using a preset inquiry method.

10. The method according to claim 9, wherein: The controlling the instant information inquiry agent to ask the inquiry object the question in a preset inquiry manner includes: In response to the number of inquiry objects exceeding a preset number, the instant information inquiry agent is controlled to respectively inquire the question to different inquiry objects using corresponding inquiry methods.

11. The method according to claim 10, wherein: The controlling the instant information inquiry agent to ask the question to different inquiry objects using corresponding inquiry methods includes: The instant information inquiry agent is controlled to ask the question to different inquiry objects in sequence using a single inquiry instance and a corresponding inquiry method.

12. The method according to claim 10, wherein: The controlling the instant information inquiry agent to ask the question to different inquiry objects using corresponding inquiry methods includes: The instant information inquiry agent is controlled to construct multiple inquiry instances and simultaneously inquire the question to different inquiry objects using corresponding inquiry methods.

13. The method according to any one of claims 10 to 12, further comprising: The instant information inquiry agent is controlled to present a real-time inquiry progress; wherein, the inquiry progress includes the first inquiry object who is currently being asked the question and the second inquiry object who has completed the inquiry.

14. The method according to claim 1, wherein The determining the target processing result corresponding to the target task based on the association processing result includes: presenting the alternative execution objects to the user; In response to the number of the candidate execution objects being greater than 1, receiving selection information of the plurality of the candidate execution objects by the user, and determining the candidate execution object corresponding to the selection information as the target execution object; The control execution agent initiates an execution operation for realizing the task requirement of the target task to the target execution object, and obtains a requirement fulfillment notification returned by the target execution object.

15. The method according to claim 9, wherein The inquiry method includes at least one of the following: Voice telephone inquiries, text inquiries, image inquiries containing specified image elements, and video inquiries containing specified video elements.

16. The method according to claim 9, wherein The received task input information is determined based on task description information related to the instant information inquiry task decomposed from the target task and the personalized preference of the user.

17. The method according to claim 1, wherein Sending the sub-goal task corresponding to the associated sub-goal agent to the associated sub-goal agent includes: Sending the task information of the sub-goal task corresponding to the associated sub-goal agent as basic task information to the associated sub-goal agent; Correspondingly, the controlling of the associated sub-target agent among the plurality of sub-target agents to generate corresponding associated processing results based on the instant feedback output by the instant information inquiry agent includes: Controlling the instant information inquiry agent to send the output instant feedback as supplementary task information to the associated sub-goal agent; The associated sub-goal agent is controlled to generate corresponding associated processing results based on the basic task information and the supplementary task information.

18. The method according to claim 17, further comprising: Controlling the associated sub-goal agent that has not received the supplementary task information to be in a standby state; The associated sub-goal agent that receives the supplementary task information is controlled to switch to a working state.

19. The method of claim 1, further comprising: Controlling the instant information inquiry agent to predict the estimated time required to obtain the instant feedback; The instant message inquiry agent is controlled to output a waiting time notification generated based on the estimated time when performing the inquiry action of asking the question to the inquiry object, so that the user temporarily leaves the task conversation generated based on the natural language input for a time corresponding to the estimated time.

20. The method according to claim 19, wherein The controlling the instant information inquiry agent to predict the estimated time required to obtain the instant feedback includes: Control the instant information query agent to predict the estimated time required to obtain the instant feedback based on at least one of the following query parameters: The number of inquiry subjects, the inquiry method adopted, and the number and complexity of the key points to be verified contained in the questions.

21. The method of claim 19, further comprising: In response to the estimated time exceeding a preset time, controlling the associated sub-goal agent to be in an idle frozen state for a first time without receiving the immediate feedback; wherein the first time is determined based on the estimated time and is shorter than the estimated time; Controlling the associated sub-goal agent that maintains the idle frozen state for more than the first time period to switch from the idle frozen state to a standby ready state; The associated sub-target agent that receives the instant feedback is controlled to switch from the standby state to the working state.

22. A multi-agent collaborative instant information inquiry task processing device, applied to a master agent, comprising: a target task determination unit, configured to determine a target task to be solved according to a natural language input of a user; The task decomposition and corresponding dispatching unit is configured to decompose the target task into a plurality of sub-target tasks including at least an instant message inquiry task, and dispatch each of the sub-target tasks to each sub-target agent including at least an instant message inquiry agent; wherein different sub-agents are used to process different types of subtasks; An inquiry control unit is configured to control the instant message inquiry agent to ask questions to the inquiry object based on the received task input information and obtain immediate feedback; wherein the instant message inquiry agent supports question asking in a background manner; An association processing control unit is configured to control an associated sub-target agent among a plurality of sub-target agents to generate a corresponding association processing result based on the instant feedback output by the instant information inquiry agent; the association processing control unit is further configured to: control the associated sub-target agent to make a feedback decision based on each instant feedback corresponding to each inquiry object output by the instant information inquiry agent, and obtain a feedback decision result; wherein the feedback decision result includes an alternative execution object that meets the task requirements of the target task selected according to each instant feedback; wherein the associated sub-target agent is a sub-target agent that relies on the instant feedback as part of the task input information; a target processing result determining unit, configured to determine a target processing result corresponding to the target task based on the association processing result; a pause output control unit, configured to control the currently executed sub-agent to pause outputting the corresponding sub-processing result in response to the instruction input box being in a selected state; wherein the instruction input box is used for the user to input instructions, and the instruction input box is in an unselected state during the process of the sub-agent outputting the corresponding sub-processing result; a correction information extraction unit configured to extract correction information from a new instruction in response to the instruction input box being restored from the selected state to the unselected state and generating the new instruction; an affected sub-target agent determining unit, configured to determine the sub-target agent affected by the correction information; The re-output result control unit is configured to control the affected sub-target agent to re-output the corresponding sub-processing result in combination with the correction information.

23. The device according to claim 22, wherein The target task determination unit includes: a conversion subunit, configured to convert the user's natural language input into natural language text; an intention recognition subunit configured to perform intention recognition on the natural language text and obtain an intention recognition result including a demand verification intention combined with the instant information; The target task determination subunit is configured to determine the target task to be solved based on the intention recognition result; wherein, the target task includes a task that is verified in combination with instant information to see whether it meets the requirements.

24. The device according to claim 23, wherein The intention recognition subunit is further configured to: Performing semantic understanding on the natural language text to obtain a semantic understanding result; A preliminary intention is determined based on the semantic understanding result, and the preliminary intention is personalized modified using the user's personalized preferences to obtain the intention recognition result.

25. The apparatus according to claim 23, wherein The task decomposition and corresponding dispatching unit includes a task decomposition subunit configured to decompose the target task into a plurality of sub-target tasks including at least an instant information inquiry task, and the task decomposition subunit includes: a task element determination module, configured to determine a plurality of task elements constituting the target task; wherein different task elements correspond to different types of tasks; An instant message inquiry task decomposition module is configured to verify whether the actual situation meets the task requirements based on specific needs and instant information, and obtain a single task element with the verification result serving as the instant feedback, thereby decomposing the instant message inquiry task from the target task; The sub-target task decomposition module is configured to decompose the target task into multiple sub-target tasks each containing only a single task element; wherein the sub-target tasks at least include the instant information inquiry task.

26. The device according to claim 25, wherein The sub-goal task decomposition module is further configured to: In response to the existence of additional conditions corresponding to the task elements, the target task is decomposed into multiple sub-target tasks each containing only a single task element and the corresponding additional conditions; wherein the additional conditions include: a specified task processing method and / or a specified result presentation form.

27. The apparatus of claim 22, further comprising: A sub-agent construction unit configured to construct different sub-agents, the sub-agent construction unit comprising: a task type set determining subunit configured to determine a task type set for creating a sub-agent; The construction sub-unit is configured to construct a sub-agent with task processing capability of the corresponding type of task for each type of task in the task type set.

28. The apparatus according to claim 27, wherein The construction subunit is further configured to: In response to the first target type task having at least two task processing methods, a sub-agent corresponding to each task processing method is constructed for the first target type task; wherein the different task processing methods are abstracted from different processing logics for the same type of tasks.

29. The apparatus according to claim 27, wherein The construction subunit is further configured to: In response to the second target type task having at least two result presentation forms, a sub-agent corresponding to each of the result presentation forms is constructed for the second target type task; wherein the result presentation forms include: at least one of: text type, table type, image type, video type, and interactive card type.

30. The apparatus of claim 22, wherein: The query control unit includes: A first control subunit is configured to control the instant message inquiry agent to determine the inquiry object and the question based on received task input information; wherein the received task input information is determined based on task description information related to the instant message inquiry task decomposed from the target task; The second control subunit is configured to control the instant information inquiry agent to ask the inquiry object the question in a preset inquiry manner.

31. The device according to claim 30, wherein The second control subunit is further configured to: The separate inquiry control module is configured to control the instant information inquiry agent to ask the question to different inquiry objects using corresponding inquiry methods in response to the number of the inquiry objects exceeding a preset number.

32. The apparatus according to claim 31, wherein The respective inquiry control module is further configured to: The instant information inquiry agent is controlled to ask the question to different inquiry objects in sequence using a single inquiry instance and a corresponding inquiry method.

33. The apparatus according to claim 31, wherein The respective inquiry control module is further configured to: The instant information inquiry agent is controlled to construct multiple inquiry instances and simultaneously inquire the question to different inquiry objects using corresponding inquiry methods.

34. The apparatus according to any one of claims 31 to 33, further comprising: The inquiry progress presentation control unit is configured to control the instant information inquiry agent to present real-time inquiry progress; wherein, the inquiry progress includes the first inquiry object who is currently being asked the question and the second inquiry object who has completed the inquiry.

35. The apparatus of claim 22, wherein: The target processing result determination unit is further configured to: presenting the alternative execution objects to the user; In response to the number of the candidate execution objects being greater than 1, receiving selection information of the plurality of the candidate execution objects by the user, and determining the candidate execution object corresponding to the selection information as the target execution object; The control execution agent initiates an execution operation for realizing the task requirement of the target task to the target execution object, and obtains a requirement fulfillment notification returned by the target execution object.

36. The apparatus of claim 30, wherein: The inquiry method includes at least one of the following: Voice telephone inquiries, text inquiries, image inquiries containing specified image elements, and video inquiries containing specified video elements.

37. The apparatus according to claim 30, wherein The received task input information is determined based on task description information related to the instant information inquiry task decomposed from the target task and the personalized preference of the user.

38. The apparatus of claim 22, wherein: The task decomposition and corresponding dispatching unit includes a dispatching sub-unit configured to dispatch each of the sub-goal tasks to each of the sub-goal agents including at least the instant information inquiry agent. The dispatching sub-unit includes a dispatching module configured to dispatch the sub-goal tasks corresponding to the associated sub-goal agents to the associated sub-goal agents. The dispatching module is further configured to: Sending the task information of the sub-goal task corresponding to the associated sub-goal agent as basic task information to the associated sub-goal agent; Correspondingly, the association processing control unit is further configured to: Controlling the instant information inquiry agent to send the output instant feedback as supplementary task information to the associated sub-goal agent; The associated sub-goal agent is controlled to generate corresponding associated processing results based on the basic task information and the supplementary task information.

39. The apparatus of claim 38, further comprising: A first standby ready state control unit is configured to control the associated sub-goal agent that has not received the supplementary task information to be in a standby ready state; The first working state control unit is configured to control the associated sub-goal agent that receives the supplementary task information to switch to a working state.

40. The apparatus of claim 22, further comprising: An estimated time consumption prediction control unit is configured to control the instant information inquiry agent to predict the estimated time consumption for obtaining the instant feedback; The waiting time notification output control unit is configured to control the instant message inquiry agent to output a waiting time notification generated based on the estimated time when performing the inquiry action of asking the question to the inquiry object, so that the user can temporarily leave the task conversation generated based on the natural language input for a period of time corresponding to the estimated time.

41. The apparatus according to claim 40, wherein The estimated time consumption prediction control unit is further configured to: Control the instant information query agent to predict the estimated time required to obtain the instant feedback based on at least one of the following query parameters: The number of inquiry subjects, the inquiry method adopted, and the number and complexity of the key points to be verified contained in the questions.

42. The apparatus of claim 40, further comprising: an idle frozen state control unit, configured to, in response to the estimated time exceeding a preset time, control the associated sub-goal agent to be in an idle frozen state for a first time period in which the immediate feedback is not received; wherein the first time period is determined based on the estimated time and is shorter than the estimated time; a second standby ready state control unit configured to control the associated sub-goal agent that maintains the idle frozen state for more than the first time period to switch from the idle frozen state to the standby ready state; The second working state control unit is configured to control the associated sub-goal agent that receives the instant feedback to switch from the standby ready state to the working state.

43. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the instant information inquiry task processing method based on multi-agent collaboration as described in any one of claims 1-21.

44. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the instant information inquiry task processing method based on multi-agent collaboration as described in any one of claims 1-21.

45. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the instant information inquiry task processing method based on multi-agent collaboration according to any one of claims 1 to 21.

Images