Multi-agent cooperation system and method realized through computing power of intelligent computing center

Abstract

The invention provides a multi-agent cooperation system and method realized through the computing power of an intelligent computing center, the system comprises a dialogue interface and a plurality of agents, each agent has a specific capability, the plurality of agents can form a team in the dialogue interface in a dialogue communication mode and cooperate to complete a specified task, and the intellectual property of the agent is improved. The dialogue interface is used for displaying a communication process among the plurality of agents and a part of or all decision-making processes of the agents in a process of executing the specified task. According to the method and the device, due to the adoption of cooperation of the multiple agents, the relatively complex task can be processed, and meanwhile, in the process of executing the specified task, the conversation interface is adopted to display the communication process among the multiple agents and part or all decision-making processes of the agents, so that the process of processing the specified task by a user is clearer, and the user experience is improved. And user experience is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the fields of computing power infrastructure and artificial intelligence technology, and in particular, to a multi-agent collaboration system and method implemented through the computing power of an intelligent computing center. Background Art

[0002] With the development of artificial intelligence technology and computing power technology, the concept of intelligent computing center has emerged. "Intelligent computing center" refers to the use of large-scale heterogeneous computing power resources, including general computing power and intelligent computing power, mainly for artificial intelligence applications (such as artificial intelligence deep learning model development, model training and model reasoning and other scenarios) to provide the required computing power, data and algorithms. Intelligent computing center covers facilities, hardware, software, and can provide full-stack capabilities from bottom-level computing power to top-level application enablement.

[0003] An agent is an agent that can perceive the environment and take actions to achieve specific goals. It can be software, hardware or a system with autonomy, adaptability and interaction. Agents perceive changes in the environment (such as through sensors or data input), make judgments and decisions based on their own learned knowledge and algorithms, and then perform actions to affect the environment or achieve predetermined goals. Agents are widely used in the field of artificial intelligence and are commonly seen in automated systems, robots, virtual assistants and game characters. The core of agents is the ability to learn autonomously and continuously evolve to better complete tasks and adapt to complex environments.

[0004] However, the intelligent agents currently realized through the computing power of intelligent computing centers can usually only complete a simple task alone and find it difficult to complete more complex tasks. Summary of the invention

[0005] The embodiments of the present invention provide a multi-agent collaboration system and method realized by the computing power of an intelligent computing center, which is used to solve the problem that the existing intelligent agents realized by the computing power of an intelligent computing center can only complete a simple task alone and have difficulty in completing more complex tasks.

[0006] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0007] In a first aspect, an embodiment of the present invention provides a multi-agent collaboration system, comprising: a dialogue interface and multiple agents, each of the agents having specific capabilities, the multiple agents being able to form a team and collaborate to complete a specified task through dialogue communication in the dialogue interface, and the dialogue interface being used to display the communication process between the multiple agents in the process of executing the specified task, as well as part or all of the decision-making process of the agents.

[0008] Optionally, the multiple agents are organized via a directed acyclic graph, wherein each node in the directed acyclic graph represents one of the agents, and each edge in the directed acyclic graph represents the communication between two of the agents located at both ends of the edge.

[0009] Optionally, in the process of performing the specified task, each of the agents can follow the instructions given by the agent at the previous level, or give feedback suggestions to the agent at the previous level;

[0010] and / or,

[0011] Agents at the same level in the team can perform assigned tasks simultaneously.

[0012] Optionally, the agents in the team used to complete the specified task are all or part of the multiple agents.

[0013] Optionally, the multiple agents include a first agent and at least one second agent;

[0014] The first agent is used to perceive the designated task given by the user, divide the designated task into multiple subtasks, assign the multiple subtasks to the at least one second agent, formulate an execution plan for the designated task and notify the second agent, and generate a report result of the designated task and report it to the user through the dialogue interface or instruct the second agent to generate a report result of the designated task and report it to the user through the dialogue interface;

[0015] The second agent is used to make decisions and take corresponding actions according to the execution plan of the designated task given by the first agent.

[0016] Optionally, the first agent is further used to select at least one second agent from other agents to perform the specified task according to the specified task, and the at least one second agent is all or part of the other agents.

[0017] Optionally, at least some of the agents are able to independently complete tasks given by the user.

[0018] Optionally, each of the intelligent agents can be used to perceive the user's dialogue instructions in real time during the execution of a specified task, and make decisions and take corresponding actions based on the user's dialogue instructions.

[0019] Optionally, the agent is able to obtain report results of historical tasks and perform the designated task based on the report results, where the designated task is the same as or different from the agent members in the team of the historical task.

[0020] In a second aspect, an embodiment of the present invention provides a multi-agent collaboration method, which is applied to the multi-agent collaboration system as described in the first aspect, wherein the multi-agent collaboration system includes a dialogue interface and multiple agents, wherein the multiple agents include a first agent and at least one second agent;

[0021] The multi-agent collaboration method comprises:

[0022] Step S1: the first agent perceives a specified task given by a user;

[0023] Step S2: the first agent divides the designated task into a plurality of subtasks, and assigns the plurality of subtasks to the at least one second agent;

[0024] Step S3: the first agent formulates an execution plan for the designated task and notifies the second agent;

[0025] Step S4: Generate a report result of the designated task and report it to the user through the dialogue interface, or instruct the second agent to generate a report result of the designated task and report it to the user through the dialogue interface.

[0026] In an embodiment of the present invention, a multi-agent collaboration system realized by the computing power of an intelligent computing center is provided with multiple agents, each of which has specific capabilities. Multiple agents can form a team and collaborate to complete a specified task in a dialogue interface in the form of dialogue communication. Since multiple agents are used for collaboration, the computing power of the intelligent computing center can be fully utilized to process more complex tasks. At the same time, in the process of executing the specified task, a dialogue interface is used to display the communication process between multiple agents and part or all of the decision-making process of the agents, so that users can have a clearer understanding of the processing process of the specified task, thereby improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0028] Figure 1 A schematic diagram of a dialogue interface of a multi-agent collaboration system implemented by computing power of an intelligent computing center according to an embodiment of the present invention;

[0029] Figure 2 A schematic diagram of a directed acyclic graph corresponding to multiple agents in a multi-agent collaboration system according to an embodiment of the present invention;

[0030] Figure 3A schematic diagram of a communication method between intelligent agents according to an embodiment of the present invention;

[0031] Figure 4 Schematic diagram of the process of a multi-agent collaboration method implemented by the computing power of an intelligent computing center according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] First, the technical terms involved in the present invention are briefly explained below.

[0034] The "computing power" mentioned in the present invention is the ability of computer equipment or computing / data center to process information. It is the ability of computer hardware and software to work together to execute certain computing requirements. It is the computing power to achieve target result output by processing information data. It is a new type of productivity that integrates information computing power, network carrying capacity, and data storage capacity. It mainly provides services to the society through computing power infrastructure.

[0035] The "computing power" (Computational Power, CP) described in the present invention is the ability of a data center server to process data and output results. It is a comprehensive indicator to measure the computing power of a data center, including general computing power, super computing power and intelligent computing power. The commonly used unit of measurement is the number of floating point operations performed per second (FLOPS: Floating Point Operations Per Second, 1EFLOPS = 10^18FLOPS). The larger the value, the stronger the comprehensive computing power. According to calculations, 1EFLOPS is approximately the computing power output of 5 Tianhe-2A or 500,000 mainstream server CPUs or 2 million mainstream notebooks. The calculation formula is: CP = CP 通用 +CP 智能 +CP 超级 .

[0036] The "Network Power" (NP) described in the present invention is a manifestation of the data transmission capability of computing facilities, including comprehensive capabilities such as network architecture, network bandwidth, transmission latency, intelligent management and scheduling, etc. The carrying capacity involves network transmission within and between data centers, and is a comprehensive indicator for measuring network transmission scheduling capabilities. In the embodiment of the present invention, the carrying capacity uses the memory bandwidth.

[0037] The "Storage Power" (SP) described in the present invention is the comprehensive ability of a data center in terms of data storage capacity, performance, safety and reliability, and green and low-carbon. It is a comprehensive indicator for measuring the data storage capacity of a data center, including external storage devices such as storage arrays and server built-in storage devices. The commonly used unit of measurement for storage capacity is exabyte (EB, 1EB = 2^60bytes), and the commonly used unit of measurement for performance is the number of reads and writes per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB). The disaster recovery ratio is an important manifestation of safety and reliability.

[0038] The "computing power infrastructure" described in the present invention is a new type of information infrastructure that integrates information computing power, network carrying capacity, and data storage capacity. It can realize centralized computing, storage, transmission and application of information, and presents characteristics such as diversity and ubiquity, intelligence and agility, security and reliability, and green and low-carbon.

[0039] The “computing power” mentioned in the present invention includes general computing power, intelligent computing power and super computing power.

[0040] The “general computing power” mentioned in the present invention refers to the computing power provided by servers based on CPU (Central Processing Unit) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0041] The "intelligent computing power" described in the present invention is a computing platform for large-scale deployment of special chips such as GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit) for various innovative applications of artificial intelligence, such as natural language processing and machine vision.

[0042] The "super computing power" mentioned in the present invention is mainly the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of multiple computer systems working in parallel and uses a dedicated operating system to handle extremely complex or data-intensive problems. It is mainly used for calculations in cutting-edge scientific fields, such as planetary simulation, drug molecule design, and gene analysis.

[0043] The "intelligent computing center" described in the present invention refers to a facility that provides the required computing power, data and algorithms for artificial intelligence applications (such as artificial intelligence deep learning model development, model training and model reasoning scenarios) by using large-scale heterogeneous computing power resources, including general computing power (CPU: Central Processing Unit) and intelligent computing power (GPU: Graphics Processing Unit, FPGA: Field Programmable Gate Array, ASIC: Application Specific Integrated Circuit, etc.). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from bottom-level computing power to top-level application enablement.

[0044] The "computing resources" mentioned in the present invention refer to the technologies and facilities with information calculation, transmission, storage and application capabilities required for the development of the digital society, including but not limited to computing resources such as CPU (Central Processing Unit), GPU (Graphics Processing Unit), network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, as well as supporting and guarantee resources such as wind, fire, water and electricity.

[0045] The agent described in the embodiments of the present invention refers to an agent that can perceive the environment and take actions to achieve specific goals. It can be software, hardware or a system with autonomy, adaptability and interaction capabilities. The agent perceives changes in the environment (such as through sensors or data input), makes judgments and decisions based on the knowledge and algorithms it has learned, and then performs actions to affect the environment or achieve predetermined goals. Agents are widely used in the field of artificial intelligence and are commonly found in automated systems, robots, virtual assistants, and game characters. The core of agents is the ability to learn autonomously and continuously evolve to better complete tasks and adapt to complex environments.

[0046] The natural language processing (NLP) described in the embodiments of the present invention is a core technology that enables intelligent agents to understand, generate and interact with human natural language. Through NLP, intelligent agents can parse the semantics, grammar and context of human language, so as to perform tasks such as text understanding, language translation, dialogue system, sentiment analysis, etc. This enables intelligent agents to communicate with humans in natural language, understand the user's intentions, and provide corresponding responses and services.

[0047] The “large language model (also referred to as a large language model)” described in the embodiments of the present invention refers to a large language model (LLM), which is a language model with a large parameter scale that is designed to understand and generate human language. It is trained with a large amount of text data and can perform a wide range of tasks including text summarization, translation, sentiment analysis, etc.

[0048] The directed acyclic graph described in the embodiment of the present invention means that in graph theory, if a directed graph cannot start from a vertex and return to the vertex through several edges, then the graph is a directed acyclic graph (DAG graph).

[0049] In order to solve the problem that a single existing intelligent agent can only complete a simple task alone and has difficulty in completing more complex tasks, an embodiment of the present invention provides a multi-agent collaboration system, including: a dialogue interface and multiple intelligent agents, each of which has specific capabilities, and the multiple intelligent agents can form a team and collaborate to complete a specified task through dialogue communication in the dialogue interface. The dialogue interface is used to display the communication process between the multiple intelligent agents in the process of executing the specified task, as well as part or all of the decision-making process of the agents.

[0050] Please refer to Figure 1 , Figure 1 A schematic diagram of a dialogue interface of a multi-agent collaboration system according to an embodiment of the present invention. Figure 1 It can be seen that the multi-agent collaboration system in this embodiment includes multiple agents, including: NANA (project manager), Hu (PM assistant), Wang (operation and maintenance engineer), Doudou (data engineer), Li (large language model training engineer), Guo (large language model evaluation engineer), where each agent is built on the basis of a large language model, and each agent has specific capabilities. For example, "Hu (PM assistant)" can be responsible for confirming necessary parameters and recording parameters for reference by other users. Each agent can communicate with other agents and users (i.e. humans, such as Figure 1 In the dialogue interface, the communication process between multiple agents in the process of executing a specified task, as well as part or all of the decision-making process of the agents can be displayed.

[0051] In an embodiment of the present invention, a multi-agent collaboration system realized by the computing power of an intelligent computing center is provided with multiple agents, each of which has specific capabilities. Multiple agents can form a team and collaborate to complete a specified task in a dialogue interface in the form of dialogue communication. Since multiple agents are used for collaboration, the computing power of the intelligent computing center can be fully utilized to process more complex tasks. At the same time, in the process of executing the specified task, a dialogue interface is used to display the communication process between multiple agents and part or all of the decision-making process of the agents, so that users can have a clearer understanding of the processing process of the specified task, thereby improving user experience.

[0052] In an embodiment of the present invention, optionally, the multiple agents are organized via a directed acyclic graph, wherein each node in the directed acyclic graph represents one of the agents, and each edge in the directed acyclic graph represents the communication between two of the agents located at both ends of the edge.

[0053] Please refer to Figure 2 , Figure 2 A directed acyclic graph corresponding to multiple agents of a multi-agent collaboration system according to an embodiment of the present invention, wherein the directed acyclic graph represents an organization with an overall goal, includes five nodes (A1, A2, A3, A4 and A5), each node represents an agent with a specific capability, and each edge in the directed acyclic graph represents the communication between two agents at both ends of the edge, wherein communication refers to sending information, such as Figure 2 As shown, A1 can communicate with A2, A3, A4, and A5, A2 can communicate with A1 and A4, and so on.

[0054] In the embodiment of the present invention, optionally, in the process of executing the specified task, each of the agents can follow the instructions given by the agent at the previous level, or give feedback suggestions to the agent at the previous level. Figure 2 , Figure 2 Among them, A1 is the parent agent of A2, A3, A4 and A5, and A2 is the parent agent of A4.

[0055] In the embodiment of the present invention, optionally, agents at the same level can simultaneously execute the assigned tasks, thereby improving the execution efficiency of the tasks. Figure 2 , A2 and A3 are agents of the same level. A1 can assign tasks to A2 and A3, and A2 and A3 can perform the assigned tasks at the same time.

[0056] In the embodiment of the present invention, the agents in the team used to complete the specified task are optionally all or part of the multiple agents. That is, when performing a specified task, not all agents in the system may be used, and the agents required to perform the specified task may be determined as needed and formed into a team. For example, Figure 2 The agents A1, A2, and A4 in the system form a team to complete the specified task. It should be noted that the selected agents also need to be organized according to the predetermined directed acyclic graph.

[0057] In the embodiment of the present invention, optionally, the multiple agents include a first agent and at least one second agent;

[0058] The first agent is used to perceive the designated task given by the user, divide the designated task into multiple subtasks, assign the multiple subtasks to the at least one second agent, formulate an execution plan for the designated task and notify the second agent, and generate a report result of the designated task and report it to the user through the dialogue interface or instruct the second agent to generate a report result of the designated task and report it to the user through the dialogue interface;

[0059] The second agent is used to make decisions and take corresponding actions according to the execution plan of the designated task given by the first agent.

[0060] For example, Figure 2 A1 is the first agent, A2, A3, A4 and A5 are the second agents, A1 perceives the specified task given by the user, divides the specified task into multiple subtasks, and assigns the multiple subtasks to A2, A3, A4 and A5, formulates the execution plan of the specified task and notifies A2, A3, A4 and A5.

[0061] It should be noted that if Figure 3 As shown in the figure, when A1 sends an execution plan (Instruction and input) to other agents (such as A2), other agents (such as A2) can also give feedback (Feedback) on the execution plan given by A1. A1 can re-formulate the execution plan (Action) based on the feedback given by other agents (such as A2) and notify other agents (such as A2). The interaction between the two can be multiple times until other agents (such as A2) accept the execution plan given by A1. In addition, if A2 accepts the execution plan given by A1, it can not give feedback.

[0062] In the embodiment of the present invention, optionally, the first agent is further used to select at least one second agent from other agents to perform the specified task according to the specified task, and the at least one second agent is all or part of the other agents. In other words, the first agent is used as the agent for selecting team members. It should be noted that the first agent needs to understand the capabilities of other agents.

[0063] In the embodiment of the present invention, optionally, at least some of the agents can complete the tasks given by the user independently. That is, some of the agents in the embodiment of the present invention can complete the collaborative tasks in the team as well as complete the tasks given by the user independently, which is highly flexible.

[0064] In the embodiment of the present invention, optionally, each of the intelligent agents can be used to perceive the user's dialogue instructions in real time during the execution of the specified task, and make decisions and take corresponding actions based on the user's dialogue instructions. That is to say, in the embodiment of the present invention, in the process of multiple intelligent agents collaborating to complete the specified task, humans can join in at any time, give suggestions on the execution of the specified task, or terminate the operation of the specified task, etc., which is highly flexible. Of course, the user's dialogue instructions may also be unrelated to the specified task. For example, the specified task is to train a large language model. During the training of the large language model, the user can ask a certain intelligent agent in the team (such as Hu (PM Assistant)), such as "Can you sing?", and "Hu (PM Assistant)" can make corresponding replies based on the user's question without affecting the normal process of training the large language model.

[0065] In the embodiment of the present invention, optionally, the agent can obtain the report results of the historical task and perform the specified task based on the report results, and the specified task is the same as or different from the agent members in the team of the historical task. That is to say, in the embodiment of the present invention, when performing the specified task, the team performing the specified task can obtain the report results of other tasks performed in the past by other teams, and perform the specified task based on the report results, and the members of the other teams can be the same as or different from the members of the team performing the task this time.

[0066] Please refer to Figure 4 , an embodiment of the present invention further provides a multi-agent collaboration method, which is applied to a multi-agent collaboration system in any of the above embodiments, wherein the multi-agent collaboration system includes a dialogue interface and a plurality of agents, wherein the plurality of agents include a first agent and at least one second agent;

[0067] The multi-agent collaboration method comprises:

[0068] Step S1: the first agent perceives a specified task given by a user;

[0069] Step S2: the first agent divides the designated task into a plurality of subtasks, and assigns the plurality of subtasks to the at least one second agent;

[0070] Step S3: the first agent formulates an execution plan for the specified task and notifies the second agent;

[0071] Step S4: Generate a report result of the designated task and report it to the user through the dialogue interface, or instruct the second agent to generate a report result of the designated task and report it to the user through the dialogue interface.

[0072] In some embodiments, optionally, the method further includes:

[0073] Step S0: selecting at least one second agent from other agents to perform the specified task according to the specified task, wherein the at least one second agent is all or part of the other agents.

[0074] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0076] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A multi-agent collaboration system realized by the computing power of an intelligent computing center, characterized in that: include: A dialogue interface and multiple intelligent agents, each of which has specific capabilities, and the multiple intelligent agents can form a team and collaborate to complete a specified task through dialogue communication in the dialogue interface. The dialogue interface is used to display the communication process between the multiple intelligent agents in the process of executing the specified task, as well as part or all of the decision-making process of the intelligent agents.

2. The system according to claim 1, characterized in that The multiple agents are organized via a directed acyclic graph, wherein each node in the directed acyclic graph represents one of the agents, and each edge in the directed acyclic graph represents the communication between two of the agents located at both ends of the edge.

3. The system according to claim 2, characterized in that In the process of performing the designated task, each of the agents can follow the instructions given by the agent at the previous level, or give feedback suggestions to the agent at the previous level.

4. The system according to claim 2, characterized in that Agents at the same level can perform their assigned tasks simultaneously.

5. The system according to claim 1, characterized in that The agents in the team used to complete the specified task are all or part of the multiple agents.

6. The system according to any one of claims 1 to 5, characterized in that: The plurality of agents include a first agent and at least one second agent; The first agent is used to perceive the designated task given by the user, divide the designated task into multiple subtasks, assign the multiple subtasks to the at least one second agent, formulate an execution plan for the designated task and notify the second agent, and generate a report result of the designated task and report it to the user through the dialogue interface or instruct the second agent to generate a report result of the designated task and report it to the user through the dialogue interface; The second agent is used to make decisions and take corresponding actions according to the execution plan of the designated task given by the first agent.

7. The system according to claim 6, characterized in that The first agent is further used to select at least one second agent from other agents to perform the specified task according to the specified task, and the at least one second agent is all or part of the other agents.

8. The system according to claim 1, characterized in that Each of the intelligent agents can be used to perceive the user's dialogue instructions in real time during the execution of a specified task, and make decisions and take corresponding actions based on the user's dialogue instructions.

9. The system according to claim 1, characterized in that The agent is capable of obtaining the report results of the historical tasks and executing the designated task based on the report results, wherein the designated task is the same as or different from the agent members in the team of the historical tasks.

10. A multi-agent collaboration method realized by the computing power of an intelligent computing center, characterized in that: Applied to a multi-agent collaboration system as claimed in any one of claims 1 to 9, the multi-agent collaboration system comprising a dialogue interface and a plurality of agents, the plurality of agents comprising a first agent and at least one second agent; The multi-agent collaboration method comprises: Step S1: the first agent perceives a specified task given by a user; Step S2: the first agent divides the designated task into a plurality of subtasks, and assigns the plurality of subtasks to the at least one second agent; Step S3: the first agent formulates an execution plan for the specified task and notifies the second agent; Step S4: Generate a report result of the designated task and report it to the user through the dialogue interface, or instruct the second agent to generate a report result of the designated task and report it to the user through the dialogue interface.

Images