Instant message inquiry type task processing method based on multi-agent cooperation and related device

Abstract

The invention provides an instant message inquiry type task processing method based on multi-agent cooperation and a related device, and relates to the technical field of artificial intelligence such as generative large language models and agents. The method comprises the steps of determining a to-be-solved target task according to natural language input of a user; the target task is decomposed into a plurality of sub-target tasks at least including instant information inquiry tasks, each sub-target task is correspondingly issued to each sub-target agent at least including an instant information inquiry agent, and different sub-agents are used for processing different types of sub-tasks; the instant information inquiry agent is controlled to inquire questions from the inquiry object to obtain instant feedback, and the instant information inquiry agent supports question inquiry in a background operation mode; an associated sub-target agent in the multiple sub-target agents is controlled to generate a corresponding associated processing result based on instant feedback output by the instant information inquiry agent, and the associated sub-target agent is a sub-target agent which depends on the instant feedback and serves as part of task input information; and determining a target processing result corresponding to the target task based on the association processing result. By applying the scheme, a better comprehensive task processing effect can be achieved under the condition that the comprehensive cost is lower, and in particular, an instant information inquiry task which needs to be combined with the instant information to verify whether the actual situation meets the task requirement or not and takes the verification result as instant feedback is obtained; in addition, the instant information inquiry agent also supports question inquiry (namely asynchronous task processing) in a background operation mode, so that the user does not need to stay in a session interface all the time, and other operations of the user are not influenced.

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 propose 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, the disclosed embodiment proposes a method for processing instant message inquiry tasks based on multi-agent collaboration, including: determining a target task to be solved based on a 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 issuing 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 sub-tasks; 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 manner of running in the background; controlling associated sub-target agents among the plurality of 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 the instant feedback as part of the task input information; and determining a 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 information inquiry 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 distribution unit, configured to decompose the target task into a plurality of sub-target tasks including at least an instant information inquiry task, and distribute each sub-target task to each sub-target agent including at least an instant information inquiry agent; wherein different sub-agents are used to process different types of sub-tasks; an inquiry control unit, configured to control the instant information inquiry agent to ask questions to the inquiry object and obtain instant feedback; wherein the instant information inquiry agent supports question asking in a way of running in the background; an association processing control unit, configured to control the associated sub-target agent among the plurality of sub-target agents to generate corresponding association processing results based on the instant feedback output by the instant information inquiry agent; 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 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 when the at least one processor executes, it is able to implement the instant information inquiry task processing method based on multi-agent collaboration as described in the first aspect.

[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 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 handle 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 executed by different sub-agents, and 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 complex tasks can be handled in their respective roles, and because 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 used in the present disclosure to collaboratively handle task requirements has better processing effects on a single type of task than using a single, all-powerful agent, and the relatively small-scale 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 with the verification results, the instant information inquiry agent also supports asking questions in the background (that is, processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, and do not affect 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 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 according to 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 in 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 consumption and generating a waiting time notification provided by an embodiment of the present disclosure;

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

[0025] Figure 10-1 to Figure 10-6 All of them are example diagrams of an instant information inquiry task processing method based on multi-agent collaboration in an application scenario provided by an embodiment of the present disclosure;

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

[0027] Fig.12 A schematic diagram of the structure 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 is a description of exemplary embodiments of the present disclosure 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 of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for 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 may be combined with each other without conflict.

[0029] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance 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 of the present disclosure can be applied.

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

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

[0033] Terminal devices 101, 102, 103 and server 105 can be 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 smart phones, tablet computers, laptop computers, desktop computers, etc.; when terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above, which can be implemented as multiple software or software modules, or as a single software or software module, and no specific limitation is made here. When server 105 is hardware, it can be implemented as a distributed server cluster composed 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 no specific limitation is made 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 a plurality of sub-target tasks including at least an instant information inquiry task, and each sub-target task is sent to a corresponding one of at least an instant information inquiry intelligent 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 , 103 via the network 104 , so that the terminal devices 101 , 102 , 103 display the received target processing result to the user.

[0036] It should be noted that, in addition to being obtained from the terminal devices 101, 102, 103 through the network 104, the natural language input can also be pre-stored in the server 105 in various ways. Therefore, when the server 105 detects that the data has been stored locally (for example, starting to process the tasks to be processed before), it can choose to directly obtain the data locally. In this case, the exemplary system architecture 100 may also not include the terminal devices 101, 102, 103 and the network 104.

[0037] Since the processing of complex tasks requires more computing resources and stronger computing power, the instant information inquiry task processing method based on multi-agent collaboration provided in the subsequent embodiments of the present disclosure is generally executed by the server 105 with stronger computing power and more computing resources, and accordingly, the instant information 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 operations assigned to the server 105 by the complex task processing application installed thereon, and then output the same results as the server 105. Especially when there are multiple terminal devices with different computing capabilities at the same time, but when the terminal device where the complex task processing application is located has strong computing capabilities and more remaining computing resources, the terminal device can be allowed to perform the above-mentioned operations, thereby appropriately reducing the computing pressure of the server 105. Correspondingly, the instant information inquiry 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, which is not specifically limited here.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0040] Please refer to Figure 2 , 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, wherein process 200 includes the following steps:

[0041] Step 201: Determine a target task to be solved according to a natural language input of a user;

[0042] This step is intended to be performed by the execution subject (e.g. Figure 1 The server 105 carrying the main agent shown in the figure fully understands and analyzes the received natural language input of the user (for example, through Figure 1The network 104 shown receives the natural language input by the user through the terminal devices 101, 102, 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 process involving multiple steps, involving complex intelligent reasoning links such as language understanding, context analysis, and task modeling. For example, receiving input, preprocessing and normalization, semantic understanding and intent recognition, 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's 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 also 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, pre-processing 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: decomposing the target task into a plurality of sub-target tasks including at least an instant information inquiry task, and issuing each sub-target task to each sub-target agent including at least an instant information inquiry agent;

[0047] Based on step 201, this step aims to decompose the target task into multiple sub-target tasks by the execution subject, and issue each sub-target task to each sub-target agent. Among them, the multiple sub-target tasks decomposed in this step at least include instant information inquiry tasks, and correspondingly, each sub-target agent should at least include an instant information inquiry agent dedicated to processing instant information inquiry 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 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 it is the smallest task unit that can be decomposed at present).

[0049] Among them, instant information inquiry tasks refer to tasks in which the expected results are not fixed but need to be temporarily confirmed in combination with instant information, that is, it is necessary to verify whether the actual situation meets the task requirements in combination with instant information, and obtain instant feedback from the verification results, such as manual customer service consultation tasks, telephone consultation tasks, etc. Taking the task of "booking a private room that can seat 10 people at 8 pm" as an example, it can be known that: whether a hotel still has unreserved private rooms that can seat 10 people at 8 pm, no one can know the result before making an instant inquiry with the hotel staff, so the execution focus of this type of task is to conduct temporary inquiry operations on relevant objects that need to know accurate 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, which 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 capability.

[0051] Step 203: Control the instant information 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 method including but not limited to may be:

[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 in 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 in parallel, the time required to obtain all immediate feedback returned by all query objects can be significantly shortened.

[0061] Furthermore, in the case of multiple inquiry objects, the execution subject can also control the instant information inquiry agent to present the real-time inquiry progress, so that the user can know the current inquiry status and part of the feedback status through the presented inquiry progress. The inquiry progress can include the first inquiry object currently being asked questions and the second inquiry object who has completed the inquiry, as well as the instant feedback returned by the second inquiry object.

[0062] Step 204: controlling 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;

[0063] On the basis of 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 tasks in combination with the personalized preferences of the user 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 judging 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 determining 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 collaborative forms of 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] In addition, in the process of each sub-goal agent executing the corresponding sub-goal task to obtain the corresponding sub-processing result, the user's personalized preferences can also be combined. Among them, the multiple sub-processing results at least include the instant feedback corresponding to the instant information inquiry type task output by the instant information inquiry 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 the corresponding type of tasks. The sub-processing result can be obtained by relying on other sub-processing results, or it can be determined by itself according to 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 associated processing results to obtain 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, adjustment of expressions, adjustment of sentence patterns and enrichment of expressions, 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 executed by different sub-agents, and each sub-agent processes the sub-tasks that match 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 the complex task can be processed in their respective roles, and since different sub-agents are pre-built to be dedicated to processing different types of tasks, the scheme 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-powerful agent, and the relatively small-scale sub-agents are also convenient for flexibly adding and changing corresponding functions. This scheme can bring better comprehensive task processing effects at a lower comprehensive 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 with the verification results, the instant information inquiry agent also supports asking questions in the background (that is, processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, and do not affect other user operations.

[0072] To deepen your understanding of how to determine the target tasks, please refer to Figure 3 , Figure 3 A flowchart of a method for determining a target task according to a 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: performing intent recognition on the natural language text to obtain an intent recognition result including the intent of demand verification combined with the instant information;

[0076] On the basis of step 301, this step aims to perform intent recognition on the natural language text by the above-mentioned execution subject, and obtain an intent recognition result including the intent of verifying the demand in combination with the instant information. That is, the intent recognition result at least includes the intent of verifying the demand in combination with the instant information, and may also include other intents, which are not specifically limited here.

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

[0078] First, the execution subject performs semantic understanding on the natural language text to obtain a semantic understanding result; then, the execution subject determines a preliminary intention (or suspected intention) based on the semantic understanding result. In order to improve the accuracy of intention determination, the execution subject may also use the personalized preferences of the user to perform personalized corrections on the preliminary intention to obtain an intention recognition result including the intention to verify the needs combined with 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 screening, 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, which will not be listed here one by one.

[0081] Step 303: Determine the target task to be solved according to 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 also 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 plan with high feasibility and more accurate determination of the target task as much as possible.

[0085] To deepen your understanding of 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, wherein the process 400 includes the following steps:

[0086] Step 401: determining a plurality of task elements constituting a target task;

[0087] This step aims to enable the above-mentioned execution subject to determine multiple task elements that constitute the target task, and different task elements correspond to different types of tasks.

[0088] Among them, task elements refer to the basic units or components that constitute the target task. Each target task may be composed of several independent elements, which are the key steps, subtasks or resources necessary 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] Assuming the target task is "develop a new software product", the target task can be decomposed into multiple task elements, each of which corresponds to a different type of task:

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

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

[0092] 3) Coding development (technical tasks): programmers write codes 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: according to the specific needs, the instant information is combined to verify whether the actual situation meets the task requirements, and a single task element with the verification result as instant feedback is obtained, and the instant information inquiry task is decomposed 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 from 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 aims to decompose the target task into multiple sub-target tasks containing only a single task element, by referring to the method of decomposing the target task by task elements in step 402 by the above-mentioned execution subject to obtain clear result acquisition tasks, that is, the sub-target tasks at least include instant information inquiry tasks.

[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-agents), the task decomposition can be flexibly completed according to actual conditions.

[0100] Furthermore, considering that even the same task element may be attached with 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 existence of additional conditions corresponding to the task elements, decompose the target task into multiple sub-target tasks containing only a single task element and the corresponding additional conditions, and the additional conditions may include: a specified task processing method and / or a specified result presentation form. Among them, different task processing methods are abstracted from different processing logics for the same type of tasks (for example, the same type of tasks may have multiple different processing logics, but they can all get the correct answer in the end); the result presentation form may include: at least one of text, table, image, video, and interactive card.

[0102] For a deeper understanding of how to pre-create different sub-agents, see Figure 5 , Figure 5 A flowchart of a method for creating a sub-agent provided by an embodiment of the present disclosure, wherein the 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 having the task processing capability of the corresponding type of task is constructed.

[0105] This embodiment provides a solution for building a sub-agent with task processing capabilities of the corresponding type of task for each type of task determined through steps 501 and 502. Further, the number of sub-agents corresponding to each type of task may be only one or multiple, and the multiple sub-agents may be different or completely the same. Whether the distinction is needed depends on whether the type of task usually contains further 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 deepen the understanding of how the associated sub-goal agent processes immediate feedback and how to obtain the target processing result based on the associated processing result, please also refer to Figure 6 , 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 is provided. The embodiment is based on the 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-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;

[0109] The above-mentioned execution subject controls the associated sub-goal agent to make feedback decisions based on the instant feedbacks corresponding to the inquiry objects output by the instant information inquiry agent, and obtains feedback decision results, which include candidate execution objects that meet the task requirements of the target task selected according to the instant feedbacks. That is, the current associated sub-goal agent is used to screen the instant feedbacks returned by the instant information inquiry agent for those that meet the task requirements.

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

[0111] Based on step 601, this step aims 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 as an effect 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 a plurality of 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 by the above-mentioned execution subject to initiate an execution operation to the target execution object for realizing the task requirements of the target task, and obtain a demand fulfillment notification returned by the target execution object.

[0116] Still 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 initiated telephone voice inquiries to 5 hotels respectively, and the screening agent screened out 3 hotels that meet the task requirements, and the user selected Hotel C as the target execution object, the execution agent of this step can initiate a telephone reservation operation to Hotel C, and then obtain 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 are obtained, including screening whether the multiple instant feedbacks provided by the screening agent meet the task requirements and the execution operation initiated by the execution agent to the target execution object, thereby ultimately ensuring the completion of the target task.

[0118] For a deeper understanding of how the associative subgoal agent generates associative processing results based on immediate feedback, see Figure 7 , 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, wherein 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 stage of issuing sub-goal tasks, the above-mentioned execution subject first sends the task information of the sub-goal task corresponding to the associated sub-goal intelligent agent as the 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 subject may control the associated sub-goal agent that has not received the supplementary task information to be in a standby state, and the execution subject may control the associated sub-goal agent that has received the supplementary task information to switch to a working state. That is, by making the associated sub-goal agent that has not received the supplementary task information in a standby state, the consumption of resources can be reduced as much as possible.

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

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

[0126] Specifically, the instant information query agent can predict the estimated time required to obtain instant feedback based on at least one of the following query 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 information inquiry agent to output a waiting time notification generated based on the estimated time consumption when executing the inquiry action of asking a question to the inquiry object.

[0129] On the basis of step 801, this step aims 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, when the estimated time exceeds the preset time, the execution subject can also control the associated sub-goal agent to be in an idle frozen state for a first time without receiving immediate feedback, the first time being determined based on the estimated time and shorter than the estimated time; and the execution subject can control the associated sub-goal agent that maintains the idle frozen state for more than the first time to switch from the idle frozen state to the standby ready state; finally, the execution subject can control the associated sub-goal agent that receives immediate feedback to switch from the standby ready state to the working state. Compared with the standby ready state, the idle frozen state can further reduce the consumption of resources.

[0131] Based on any of the above embodiments, considering that the user may modify the content of part of the output sub-processing results 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 Fig. 9 , Fig. 9 A two-branch schematic diagram of controlling a sub-target agent to output a corresponding sub-processing result provided by an embodiment of the present disclosure, wherein 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 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-target agent outputting the corresponding sub-processing result. That is, in the schemes of the embodiments provided in the disclosure, once the instruction input box is in a selected state, it may represent that the user needs to input some new instructions and needs to interrupt the original sub-processing result output process.

[0134] Step 902: In response to no new instruction being generated in 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, so the sub-processing result output result originally interrupted by 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 a selected state to an 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, and the correction information 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] Steps 904 and 905 are that the execution subject first determines the sub-target agent affected by the correction information, and then controls the affected sub-target agent to re-output the corresponding sub-processing result in combination with the correction information. Specifically, if all sub-target agents are affected, the execution can also be restarted from the process of outputting the sub-processing result of the first executed sub-target agent based on the correction information.

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

[0142] The existing way to meet needs is mainly through search engines, using multi-layer system funnels to recall, sort, and mix heterogeneous results of relevant web pages. Each strategy funnel sorts web pages based on basic relevance, user feedback behavior, authority and other information and truncates the output to the next layer. The disadvantage of this system is that it can only match relevance from the content level through relevance, and cannot understand and solve problems for users from the task level. In addition, web pages can only use fixed content to meet user needs. When users express personalized needs and need to be further satisfied through multiple rounds, high-quality and coherent satisfaction effects cannot be achieved. Again, the entire matching process is not explainable to users, and users can only perform the final information screening.

[0143] Related assistant products based on big models usually try to solve this problem through an all-round assistant based on big models. However, it is difficult for a single big model to achieve high-quality satisfaction in different open fields and tasks. In professional fields and special scenarios, it is difficult for a single assistant to establish trust among users and achieve the expected satisfaction.

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

[0145] 1) How to efficiently understand and decompose the needs expressed by users 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 solve the above difficulties, this embodiment proposes a solution to end-to-end task completion of user requirements based on multi-agent asynchronous collaboration. The characteristics of this solution are as follows:

[0149] Before, searches were all single-point, with one query (query word, query statement, search word, search statement) completing one requirement. Each requirement required the user to think and define it by themselves, which was too costly for the user. For a complex task, the user often did not know how to break down the task and conceive multiple queries for searching. The paradigm proposed in this embodiment is intended to help users complete tasks thoroughly. The task completion paradigm can help users complete the problems that need to be solved or the tasks to be completed in one step. Compared with the single query satisfaction of the search, the task satisfaction paradigm deeply understands the user's complete task and breaks it down to complete it, which is more in line with the user's needs.

[0150] This embodiment is based on the collaboration between multiple agents to achieve the decomposition and multi-step satisfaction of user needs, and finally automatically integrates 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 sub-task agents;

[0152] 2) Subtask agent generation: Based on the 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 collaboration according to the requirements of the task and key steps, as well as user preference information input, and generate step-by-step results of task completion;

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

[0155] That is, this embodiment constructs a main agent to schedule multiple subtask agents to collaborate, and completes the entire task through collaboration between the main agent and multiple subtask agents, and collaboration between multiple subtask agents. Compared with search or intelligent assistant products, it can be completed using agents with better effects in subdivided fields, and the effect of satisfaction is better;

[0156] By providing a scheduling and distribution mechanism based on an end-to-end generative large model, the large model has stronger expressive power, can overcome the problems of insufficient effect consistency and global optimality of the traditional multi-layer sorting mechanism, and can achieve task-oriented global optimal combination scheduling optimization. From the perspective of model capability, it can achieve end-to-end alignment training of the model from the perspective 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 sub-task completion is generated based on user input and user preferences. Different solution decompositions, sub-task 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 the requirements and the distributable set of agents (including the basic settings of these agents, mounted plug-ins, workflows, etc.), and the output is the multi-level generated content to complete the task. The entire system is built based on multi-agent collaboration, and mainly includes two types of agents: 1) Main Agent: It performs overall understanding, decomposition and concatenation of tasks and gives the final result. 2) Task Agent: The main agent schedules the subtask agent to perform asynchronous scheduling and collaborate to complete the tasks issued by the main agent.

[0159] The solution provided in this embodiment can be widely applied to various information-satisfying applications or independent products. The following takes the scenario where the BaiX application is used 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, need a private room, help me book a restaurant with convenient parking" (corresponding to Figure 10-2 ), display the results of web search and intelligent answer, switch to the "Restaurant Reservation Tonight" page through the AI ​​button, and display the results generated for user personalization, as follows Figure 10-3 The task completion page displayed includes personalized requirements such as "close distance", "private room available", 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 whole process needs to be completed asynchronously. The "Smart Phone Reservation" subagent 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 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 the same independent entrance (not shown separately).

[0163] It can be more specifically seen from the above examples that this embodiment has the following improvements and technical effects compared to the prior art:

[0164] 1) Task satisfaction paradigm: the user's request is no longer regarded as an information retrieval, but upgraded to a complete multi-agent task completion satisfaction model

[0165] The current search engines can retrieve information by matching requests with relevance, and the intelligent assistants can decompose a task into multiple steps and search for them step by step. However, decomposing tasks and satisfying users' complete needs through multi-agent collaboration is a new user needs satisfaction model. The decomposition and multi-agent capability alignment training is proposed, which can achieve high consistency between task decomposition and task completion, greatly improving the task completion effect.

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

[0167] Based on the results of task decomposition, the target collaborative agent set is generated end-to-end through the large model. This is a brand-new approach that is different from the traditional method of sorting agents through a retrieval recall sorting system. The task of multi-agent collaboration meets the need to combine multiple agents when the task is not completed. The large model is required to have a deep understanding of the task decomposition and the ability of each agent to carefully depict the boundary of the problem, and finally obtain the optimal agent set under the current goal through combinatorial optimization. The difficulties here include:

[0168] Difficulty 1: In-depth 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 agents and the subtle differences in capabilities in photo editing.

[0169] Difficulty 2: Understanding the matching relationship between tasks and intelligent agent capabilities is not a semantic similarity match, but a deep match in task completion capabilities. It requires a deep characterization and understanding of the tasks, task types and task boundaries. Matching the open set of intelligent agent capabilities and task requirements is a great 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) Task completion experience brought by asynchronous collaboration: Multiple subtask agents complete tasks through asynchronous collaboration, which is a necessary condition for tasks that require asynchronous actions in actual needs. The asynchronous actions of multiple agents collaborate and can communicate with each other to transfer tasks and results.

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

[0175] Further references Fig.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, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0176] like Fig.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 according to the natural language input of the user; the task decomposition and corresponding distribution unit 1102 is configured to decompose the target task into multiple sub-target tasks including at least instant information inquiry tasks, and distribute each sub-target task to each sub-target agent including at least an instant information inquiry agent; wherein different sub-agents are used to process different types of sub-tasks; the inquiry control unit 1103 is configured to control the instant information inquiry agent to ask questions to the inquiry object and obtain instant feedback; wherein the instant information inquiry agent supports question asking in a way of running in the background; 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 information 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 distribution 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] The intention recognition subunit is configured to perform intention recognition on the natural language text and obtain an intention recognition result including the 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 instant 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 and 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 issuing unit 1102 may include 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 may include:

[0186] A task element determination module is 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 information inquiry task decomposition module is configured to verify whether the actual situation meets the task requirements in combination with the instant information according to specific needs, and obtain a single task element with the verification result serving as instant feedback, thereby decomposing the instant information 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 as follows:

[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 information inquiry task processing device 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 determination 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 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 as follows:

[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 as follows:

[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, table, image, video, and interactive card.

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

[0199] The first control subunit is configured to control the instant message inquiry agent to determine the inquiry object and question based on the received task input information; wherein 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;

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

[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 respectively 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 respective 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 respective 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 also include:

[0208] 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 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 feedbacks corresponding to each inquiry object output by the instant information inquiry agent, and obtains feedback decision results; wherein the feedback decision results include alternative execution objects that meet the task requirements of the target task selected according to each instant feedback.

[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 a 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 information 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 issuing unit 1102 may include a corresponding issuing subunit configured to issue each sub-goal task to each sub-goal agent including at least the instant information inquiry agent, and the corresponding issuing subunit includes an issuing module configured to issue the sub-goal task corresponding to the associated sub-goal agent to the associated sub-goal agent, and the issuing 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 also include:

[0224] A first standby ready state control unit is configured to control the associated sub-target 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-target 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 also 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] Control the instant information query agent to predict the estimated time required to obtain 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 also include:

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

[0234] A second standby ready state control unit is configured to control the associated sub-target 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-target agent that receives the immediate feedback to switch from the standby 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 also include:

[0237] The pause output control unit is 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;

[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 determination 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 a device 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 executed by different sub-agents, and 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 complex tasks can be processed in their respective roles, and because different sub-agents are pre-built to be dedicated to processing different types of tasks, the scheme 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-powerful agent, and the relatively small-scale 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 with the verification results, the instant information inquiry agent also supports asking questions in the background (that is, processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, and do not affect 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 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 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] Fig.12A schematic block diagram of an example electronic device 1200 that can be used to implement an embodiment 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 processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0248] like Fig.12 As shown, the 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. In the RAM 1203, various programs and data required for the operation of the device 1200 can also be stored. The computing unit 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

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

[0250] The computing unit 1201 may be a variety of general and / or special processing components 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 dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1201 performs the various methods and processes described above, such as an instant information inquiry task processing method based on multi-agent collaboration. For example, in some embodiments, the instant information inquiry task processing method based on multi-agent collaboration may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1208. In some embodiments, part or all of the computer program may be loaded and / or installed on 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 instant information inquiry task processing method based on multi-agent collaboration described above may be executed. 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 type task processing method based on multi-agent collaboration.

[0251] Various implementations of the systems and techniques described above herein 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), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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 may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, 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, device, or equipment. 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, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, 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 may 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 may 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 the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0257] The technical solution of the disclosed embodiment 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 executed by different sub-agents, and each sub-agent processes the sub-tasks that match 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 complex tasks can be processed in their respective roles, and because different sub-agents are pre-built to be dedicated to processing different types of tasks, the scheme 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-powerful agent, and the relatively small-scale 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.

[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 with the verification results, the instant information inquiry agent also supports asking questions in the background (that is, processing tasks asynchronously), so that users do not need to stay in the conversation interface all the time, and do not affect other user operations.

[0259] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0260] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for processing instant information inquiry tasks based on multi-agent collaboration, applied to a 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 information inquiry task, and issuing each of the sub-target tasks to each sub-target agent including at least an instant information inquiry agent; wherein 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 and obtain instant feedback; wherein the instant information inquiry agent supports asking questions in a manner of running in the background; Controlling an associated sub-goal agent among the plurality of sub-goal agents to generate a corresponding associated processing result based on the instant feedback output by the instant information inquiry agent; wherein the associated sub-goal agent is a sub-goal agent that relies on the instant feedback as part of the task input information; A target processing result corresponding to the target task is determined based on the associated processing result.

2. The method according to claim 1, wherein: The step of determining the target task to be solved according to 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 instant 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 according to the semantic understanding result, and the preliminary intention is personalized modified using the personalized preference of the user to obtain the intention recognition result.

4. The method according to claim 2, wherein: Decomposing the target task into a plurality of sub-target tasks including at least an instant information inquiry task comprises: Determine 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 specific need to verify whether the actual situation meets the task requirements in combination with the instant information and obtain a single task element with the verification result serving as the instant feedback; The target task is decomposed into a plurality of 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: Decomposing the target task into a plurality of sub-target tasks each containing only a single task element comprises: In response to the existence of additional conditions corresponding to the task elements, the target task is decomposed into multiple sub-target tasks each including 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: Determining a set of task types for creating sub-agents; For each type of task in the task type set, a sub-agent having the 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 having 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 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 having 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 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.

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 the 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 in a preset inquiry manner.

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 inquire the question to different inquiry objects respectively using corresponding inquiry methods includes: The instant information inquiry agent is controlled to ask the question to different inquiry objects in turn 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 inquire the question to different inquiry objects respectively 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 a first inquiry object who is currently being asked the question and a second inquiry object who has completed the inquiry.

14. The method according to any one of claims 10 to 12, wherein: The controlling 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 comprises: Control the associated sub-target agent to make feedback decisions based on the instant feedbacks corresponding to each inquiry object output by the instant information inquiry agent, and obtain feedback decision results; wherein the feedback decision results include alternative execution objects that meet the task requirements of the target task selected according to each of the instant feedbacks.

15. The method according to claim 14, wherein: The determining the target processing result corresponding to the target task based on the association processing result includes: presenting the candidate execution objects to the user; In response to the number of the candidate execution objects being greater than 1, receiving selection information of the user on the plurality of candidate execution objects, and determining the candidate execution object corresponding to the selection information as the target execution object; 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.

16. 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.

17. 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.

18. 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; Control the associated sub-goal agent to generate corresponding associated processing results based on the basic task information and the supplementary task information.

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

20. The method of claim 1, further comprising: Controlling the instant information query 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 executing the inquiry action of asking the inquiry object the question, so that the user temporarily leaves the task conversation generated based on the natural language input for a period of time corresponding to the estimated time.

21. The method according to claim 20, wherein: The controlling the instant information query 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 subjects to be questioned, the inquiry method adopted, and the number and complexity of the key points to be verified contained in the questions.

22. The method according to claim 20, 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-target 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.

23. The method of claim 1, further comprising: In response to the instruction input box being in a selected state, controlling the currently executed sub-agent to pause outputting the corresponding sub-processing result; 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; 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; Determining the sub-target agent affected by the correction information; Control the affected sub-target agent to re-output the corresponding sub-processing result in combination with the correction information.

24. An instant information inquiry task processing device based on multi-agent collaboration, applied to a main 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 distribution unit is configured to decompose the target task into a plurality of sub-target tasks including at least an instant information inquiry task, and distribute each of the sub-target tasks to each sub-target agent including at least an instant information inquiry agent; wherein different sub-agents are used to process different types of sub-tasks; An inquiry control unit configured to control the instant information inquiry agent to ask questions to the inquiry object and obtain instant feedback; wherein the instant information inquiry agent supports question asking in a background running manner; An association processing control unit is configured to control an associated sub-goal agent among the plurality of sub-goal agents to generate a corresponding association processing result based on the instant feedback output by the instant information inquiry agent; wherein the associated sub-goal agent is a sub-goal agent that relies on the instant feedback as part of the task input information; The target processing result determining unit is configured to determine the target processing result corresponding to the target task based on the associated processing result.

25. The device according to claim 24, wherein: The target task determination unit comprises: a conversion subunit, configured to convert the user's natural language input into a natural language text; an intention recognition subunit, configured to perform intention recognition on the natural language text to obtain an intention recognition result including a demand verification intention combined with 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.

26. The device according to claim 25, 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 according to the semantic understanding result, and the preliminary intention is personalized modified using the personalized preference of the user to obtain the intention recognition result.

27. The device according to claim 25, wherein: The task decomposition and corresponding issuing 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 is configured to determine a plurality of task elements constituting the target task; wherein different task elements correspond to different types of tasks; The instant information inquiry task decomposition module is configured to verify whether the actual situation meets the task requirements in combination with the instant information according to specific needs, and obtain a single task element with the verification result serving as the instant feedback, and decompose the instant information inquiry task from the target task; 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 contain the instant information inquiry type task.

28. The device according to claim 27, wherein The sub-goal task decomposition module is further configured as follows: In response to the existence of additional conditions corresponding to the task elements, the target task is decomposed into multiple sub-target tasks each including 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.

29. The apparatus of claim 24, further comprising: A sub-agent construction unit configured to construct different sub-agents, the sub-agent construction unit comprising: A task type set determination subunit configured to determine a task type set for creating a sub-agent; The construction subunit 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.

30. The device according to claim 29, 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 different task processing methods are abstracted from different processing logics for the same type of tasks.

31. The device according to claim 29, 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 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.

32. The apparatus of claim 24, wherein: The inquiry control unit comprises: A first control subunit is configured to control 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 the 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.

33. The device according to claim 32, 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 respectively using corresponding inquiry methods in response to the number of inquiry objects exceeding a preset number.

34. The device according to claim 33, 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 turn using a single inquiry instance and a corresponding inquiry method.

35. The device according to claim 33, 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.

36. The apparatus according to any one of claims 33 to 35, 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 currently being asked the question and the second inquiry object that has completed the inquiry.

37. The device according to any one of claims 33 to 35, wherein: The association processing control unit is further configured to: Control the associated sub-target agent to make feedback decisions based on the instant feedbacks corresponding to each inquiry object output by the instant information inquiry agent, and obtain feedback decision results; wherein the feedback decision results include alternative execution objects that meet the task requirements of the target task selected according to each of the instant feedbacks.

38. The device according to claim 37, wherein The target processing result determination unit is further configured to: presenting the candidate execution objects to the user; In response to the number of the candidate execution objects being greater than 1, receiving selection information of the user on the plurality of candidate execution objects, and determining the candidate execution object corresponding to the selection information as the target execution object; 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.

39. The device according to claim 32, 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.

40. The apparatus of claim 32, 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.

41. The apparatus of claim 24, wherein: The task decomposition and corresponding issuing unit includes a corresponding issuing subunit configured to issue each of the sub-goal tasks to each of the sub-goal agents including at least the instant information inquiry agent, and the corresponding issuing subunit includes an issuing module configured to issue the sub-goal tasks corresponding to the associated sub-goal agent to the associated sub-goal agent, and the issuing 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; Control the associated sub-goal agent to generate corresponding associated processing results based on the basic task information and the supplementary task information.

42. The apparatus of claim 41, 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-target agent that receives the supplementary task information to switch to a working state.

43. The apparatus of claim 24, 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; A 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 executing 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 period of time corresponding to the estimated time.

44. The device according to claim 43, wherein The estimated time-consuming 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 subjects to be questioned, the inquiry method adopted, and the number and complexity of the key points to be verified contained in the questions.

45. The apparatus of claim 43, further comprising: An idle frozen state control unit is configured to control the associated sub-goal agent to be in an idle frozen state for a first time period without receiving the immediate feedback in response to the estimated time period exceeding a preset time period; wherein the first time period is determined based on the estimated time period and is shorter than the estimated time period; A second standby ready state control unit is configured to control the associated sub-target 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-target agent that receives the instant feedback to switch from the standby ready state to the working state.

46. ​​The apparatus of claim 24, further comprising: A pause output control unit is 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 generating a new instruction in the process of restoring from the selected state to the unselected state; 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.

47. 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 1-23.

48. 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 1-23.

49. 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 1-23.

Images