Intelligent computing center multi-agent sharing method and device oriented to popularity

Abstract

The invention provides an intelligent computing center multi-agent sharing method and device oriented to common computing power, and relates to the technical field of computing power infrastructure, and the method comprises the steps: S1, receiving an execution instruction sent by a first terminal; s2, creating an execution task based on the execution instruction, and making an execution plan of the execution task; s3, the execution task is distributed to at least one agent, the execution plan is sent to the at least one agent, and the at least one agent comprises at least one of an agent created based on the computing power of the intelligent computing center and an agent created based on the computing power of a second terminal; and S4, receiving an execution result of the at least one agent, and sending the execution result to the first terminal, the execution result being a result obtained by the at least one agent executing the execution task based on the execution plan. The method can improve the utilization rate of the computing power resource corresponding to the intelligent agent.

Description

Technical Field

[0001] The present invention relates to the technical field of computing power infrastructure, and in particular to a multi-agent sharing method and device for an intelligent computing center for universal computing power. Background Art

[0002] "Intelligent computing center" 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) by using large-scale heterogeneous computing resources, including general computing power and intelligent computing power. 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.

[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] At present, a large number of decentralized agents have been built based on computing power, including agents provided by the platform, agents developed by providers, and even agents developed by some open source organizations or even individuals. On the one hand, on the user side, when tasks need to be performed through agents, many users cannot access these decentralized agents. On the other hand, on the agent provider side, agents cannot be accessed by more users, resulting in idleness and waste of agent capabilities and computing power. In the end, users cannot use agents, and the idleness of agents causes a lot of resource waste, resulting in low utilization of computing power resources corresponding to agents. Summary of the invention

[0005] The embodiments of the present invention provide a multi-agent sharing method and device for an intelligent computing center for universal computing power, so as to solve the problem in the related art that users cannot use the agents and the idle agents cause waste of resources, resulting in low utilization of computing resources corresponding to the agents.

[0006] To solve the above problems, the present invention is achieved as follows: In a first aspect, an embodiment of the present invention provides a multi-agent sharing method of an intelligent computing center for inclusive computing power, comprising: Step S1, receiving an execution instruction sent by a first terminal; Step S2: creating an execution task based on the execution instruction, and formulating an execution plan for the execution task; Step S3, assigning the execution task to at least one agent, and sending the execution plan to the at least one agent, wherein the at least one agent includes at least one of the following: an agent created based on the computing power of the intelligent computing center, and an agent created based on the computing power of the second terminal; Step S4: receiving the execution result of the at least one agent, and sending the execution result to the first terminal, wherein the execution result is the result obtained by the at least one agent executing the execution task based on the execution plan.

[0007] In one embodiment, before step S1, the method further includes: Step S0, receiving registration information of the at least one intelligent agent, wherein the registration information is used for registering the at least one intelligent agent to the intelligent computing center; The registration information includes description information of the tool capabilities of the at least one intelligent agent, computing power billing information, security-related information, interface information, and server environment information that the runtime depends on.

[0008] In one embodiment, after step S3, the method further includes: Step S5, receiving feedback information from the at least one intelligent agent, wherein the feedback information is information sent by the at least one intelligent agent based on the execution plan after receiving the execution plan; Step S6: adjusting the execution plan based on the feedback information; Step S7: Send the adjusted execution plan to the at least one agent.

[0009] In one embodiment, step S3 includes: Step S31, encrypting the execution task, the relevant data of the execution task and the execution plan; Step S32: assign the encrypted execution task to the at least one intelligent agent, and send the encrypted execution plan to the at least one intelligent agent, and the at least one intelligent agent processes the relevant data of the execution task during the processing of the execution task.

[0010] In one embodiment, step S3 includes: Step S33: When the type of the execution task is a preset type, sending a request indication to the first terminal, wherein the request indication is used to request the first terminal to confirm whether to execute the execution task; Step S34: upon receiving a confirmation indication, assigning the execution task to at least one agent and sending the execution plan to the at least one agent, wherein the confirmation indication is an indication that the first terminal confirms the execution of the execution task after receiving the request indication.

[0011] In one embodiment, when the at least one intelligent agent is an intelligent agent created based on the computing power of the intelligent computing center, the at least one intelligent agent is an intelligent agent created based on a sandbox environment, and the sandbox environment is used to isolate the internal data of the at least one intelligent agent from the outside.

[0012] In a second aspect, an embodiment of the present invention further provides a multi-agent sharing device of an intelligent computing center for universal computing power, comprising: A first receiving module, configured to receive an execution instruction sent by a first terminal; A creation module, used to create an execution task based on the execution instruction and formulate an execution plan for the execution task; an allocation module, configured to allocate the execution task to at least one intelligent agent and send the execution plan to the at least one intelligent agent, wherein the at least one intelligent agent includes at least one of the following: an intelligent agent created based on the computing power of the intelligent computing center, and an intelligent agent created based on the computing power of the second terminal; The first sending module is used to receive the execution result of the at least one intelligent agent and send the execution result to the first terminal. The execution result is the result obtained by the at least one intelligent agent executing the execution task based on the execution plan.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps in the multi-agent sharing method of an intelligent computing center for inclusive computing power as described in the first aspect above are implemented.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the multi-agent sharing method of an intelligent computing center for universal computing power as described in the first aspect above are implemented.

[0015] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps in the multi-agent sharing method of an intelligent computing center for universal computing power as described in the first aspect above.

[0016] In an embodiment of the present invention, a multi-agent sharing method of an intelligent computing center for inclusive computing power includes: step S1, receiving an execution instruction sent by a first terminal; step S2, creating an execution task based on the execution instruction, and formulating an execution plan for the execution task; step S3, assigning the execution task to at least one agent, and sending the execution plan to at least one agent, at least one agent including at least one of the following: an agent created based on the computing power of the intelligent computing center, an agent created based on the computing power of the second terminal; step S4, receiving the execution result of at least one agent, and sending the execution result to the second terminal, the execution result being the result obtained by at least one agent executing the execution task based on the execution plan. In this way, coordinated sharing of agents is achieved through the intelligent computing center, thereby improving the user's accessibility to the agents, and improving the utilization rate of the corresponding computing power resources, and realizing inclusive application of computing power. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0018] Figure 1 It is a flow chart of a multi-agent sharing method of an intelligent computing center for inclusive computing power provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the structure of an intelligent computing center provided by an embodiment of the present invention; Figure 3 This is a structural diagram of a multi-agent sharing device of an intelligent computing center for inclusive computing power provided by an embodiment of the present invention; Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] 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.

[0021] The "computing power" (Computational Power, CP) mentioned 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 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 .

[0022] 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.

[0023] 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.

[0024] 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, safety and reliability, green and low-carbon. It is of great significance to promote industrial transformation and upgrading, enable my country's scientific and technological innovation, meet people's better life and realize high-efficiency social governance.

[0025] The “computing power” mentioned in the present invention includes general computing power, intelligent computing power and super computing power.

[0026] The “general computing power” mentioned in the present invention refers to the computing power provided by servers based on central processing unit (CPU) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0027] The "intelligent computing power" described in the present invention is a computing platform for large-scale deployment of special chips such as graphics processing units (GPUs), field programmable gate arrays (FPGAs), and application-specific integrated circuits (ASICs) for various innovative artificial intelligence applications, such as natural language processing and machine vision.

[0028] 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.

[0029] The "intelligent computing center" mentioned 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) by using large-scale heterogeneous computing resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, 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.

[0030] 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 CPUs and GPUs, 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, and supporting and guarantee resources such as wind, fire, water and electricity.

[0031] The “model” mentioned in the present invention includes but is not limited to a “large language model” and a “multimodal large model”.

[0032] The “large language model” mentioned in the present invention refers to a large language model (LLM), which is a language model with a large parameter scale, designed to understand and generate human language, trained with a large amount of text data, and can perform a wide range of tasks including text summarization, translation, sentiment analysis, etc.

[0033] The "Multimodal Large Models" mentioned in the present invention refer to models that combine multimodal information such as text, images, videos, audio, etc. for training, including but not limited to multimodal large language models.

[0034] The "inclusive computing power" mentioned in the present invention refers to providing appropriate and effective computing power services at an affordable cost to all social classes and groups that have computing power service needs based on the requirements of equal opportunity and the principle of commercial sustainability.

[0035] 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 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.

[0036] 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.

[0037] 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.

[0038] See also Figure 1 , Figure 1 is a flowchart of a multi-agent sharing method of an intelligent computing center for inclusive computing power provided by an embodiment of the present invention. Figure 1 As shown, the following steps are included: Step S1: Receive an execution instruction sent by a first terminal.

[0039] The first terminal is a terminal that requires the agent to perform tasks, which can be a mobile phone, a personal computer or an enterprise terminal. When a personal terminal or a server requires the agent to perform tasks, an execution instruction is sent to the intelligent computing center.

[0040] In some embodiments, the above-mentioned execution instructions may be instructions made in natural language. In this case, when the intelligent computing center receives the execution instructions, it can understand the natural language through the NLP module, obtain the intention of the natural language, and confirm the execution of the task based on the intention.

[0041] In some implementations, the execution instruction may directly include the tasks that need to be executed.

[0042] Step S2: Create an execution task based on the execution instruction, and formulate an execution plan for the execution task.

[0043] The above-mentioned execution task is a task created according to the execution instruction after the intelligent computing center receives the execution instruction. Among them, the intelligent computing center is provided with an NLP module. When the execution instruction is an instruction given by the user in natural language, the intelligent computing center can understand the natural language through the NLP module, obtain the intention of the natural language, and confirm the execution task according to the intention.

[0044] The above-mentioned execution task may be one execution task or multiple execution tasks.

[0045] The execution plan is a plan for the agent to execute the task, and may include information such as execution time and / or execution order. For example, when there is one execution task, the execution plan may include the time to execute the task. For another example, when there are multiple execution tasks, the execution plan may include the execution order of each execution task and the execution time of each task.

[0046] Step S3: assign the execution task to at least one intelligent agent, and send the execution plan to the at least one intelligent agent, wherein the at least one intelligent agent includes at least one of the following: an intelligent agent created based on the computing power of the intelligent computing center, and an intelligent agent created based on the computing power of the second terminal.

[0047] It should be noted that the agent can Figure 2 As shown, the intelligent computing center includes computing resources and different models (different models are located in the model layer of the intelligent computing center), such as language models, visual models, and auditory models. In some embodiments, different agents can be created through the computing resources and different models of the intelligent computing center, such as data engineer agents, algorithm engineer agents, operation and maintenance engineer agents, modeling engineer agents, and evaluation engineer agents.

[0048] Furthermore, the intelligent computing execution includes a coordination engine, which receives the execution instruction sent by the first terminal through the coordination engine, creates an execution task based on the execution instruction, and formulates an execution plan for the execution task. Among them, the coordination engine is preset with an NLP module. When the execution instruction is an instruction given by the user in natural language, the intelligent computing center can understand the natural language through the NLP module, obtain the intention of the natural language, and confirm the execution task according to the intention.

[0049] In some implementations, in addition to the above-mentioned method of creating an intelligent entity through the computing power resources of the intelligent computing center, an intelligent entity can also be created through the computing power of a second terminal. The second terminal can be a personal terminal (such as a mobile phone, a personal computer), or an enterprise terminal, or other servers or other intelligent computing centers. By creating an intelligent entity based on the computing power of the second terminal, the intelligent entity of the second terminal is shared to improve the computing power utilization of the second terminal. For example, Figure 2 As shown, a system agent is created for a personal computer and a mobile agent is created for a mobile phone.

[0050] Step S4: receiving the execution result of the at least one agent, and sending the execution result to the first terminal, wherein the execution result is the result obtained by the at least one agent executing the execution task based on the execution plan.

[0051] After at least one intelligent agent is assigned an execution task and receives an execution plan, the assigned execution task can be executed based on the execution plan to obtain an execution result. After obtaining the execution result, the execution result is sent to the first terminal through the intelligent computing center, so that the first terminal completes the task with the help of the computing power of the intelligent computing center or the second terminal, thereby improving the computing power utilization rate of the intelligent computing center or the second terminal.

[0052] In some implementations, when only one agent is required to execute, the execution result is directly sent to the first terminal.

[0053] In some implementations, when multiple agents are required to execute, the execution results of the multiple agents are combined and sent to the first terminal.

[0054] In an embodiment of the present invention, a multi-agent sharing method of an intelligent computing center for inclusive computing power includes: step S1, receiving an execution instruction sent by a first terminal; step S2, creating an execution task based on the execution instruction, and formulating an execution plan for the execution task; step S3, assigning the execution task to at least one agent, and sending the execution plan to at least one agent, at least one agent including at least one of the following: an agent created based on the computing power of the intelligent computing center, an agent created based on the computing power of the second terminal; step S4, receiving the execution result of at least one agent, and sending the execution result to the second terminal, the execution result being the result obtained by at least one agent executing the execution task based on the execution plan. In this way, coordinated sharing of agents is achieved through the intelligent computing center, thereby improving the user's accessibility to the agents, and improving the utilization rate of the corresponding computing power resources, and realizing inclusive application of computing power.

[0055] For example, the first terminal sends an execution instruction through natural language, specifically: Help me analyze the data of new customers in different industries last month, and save it to a suitable document on the D drive. Figure 2 Step 1 in the above example sends an execution instruction to the coordination engine. After receiving the execution instruction, the coordination engine creates an execution task based on the execution instruction and formulates an execution plan for the execution task ( Figure 2 Step 2 in ), and by Figure 2 Step 3 in assigns execution tasks to different agents and sends the execution plan.

[0056] In one embodiment, before step S1, the method further includes: Step S0, receiving registration information of the at least one intelligent agent, wherein the registration information is used for registering the at least one intelligent agent to the intelligent computing center; The registration information includes description information of the tool capabilities of the at least one intelligent agent, computing power billing information, security-related information, interface information, and server environment information that the runtime depends on.

[0057] For example, Figure 2 As shown, the intelligent computing center includes a registration engine, and different intelligent agents send registration information to the registration engine ( Figure 2 to register with the Intelligent Computing Center.

[0058] It should be noted that since the intelligent agent can be created based on the computing power of the second terminal, the computing power of the second terminal can be more fully utilized, thereby improving the computing power utilization rate. However, there is a difference between the second terminal and the intelligent computing center, and it is necessary to confirm whether the second terminal has the conditions for sharing the intelligent agent before determining whether to use the intelligent agent of the second terminal.

[0059] In an embodiment of the present invention, by receiving the registration information of the at least one intelligent agent, the registration information is used for the at least one intelligent agent to register with the intelligent computing center, wherein the registration information includes description information of the tool capability of the at least one intelligent agent, computing power billing information, security-related information, and at least one of a plurality of running server environment information. In this way, the registration of the intelligent agent of the second terminal is completed through the registration information of the second terminal, so that the intelligent computing center can subsequently call the intelligent agent of the second terminal to perform tasks, thereby improving the computing power utilization rate of the second terminal.

[0060] The above description information can be used to describe the function of the agent, for example, the agent of the second terminal is an engineer agent, which can perform specific engineering tasks, etc.

[0061] The above computing power billing information is used to describe the information about the resources consumed by the intelligent body of the second terminal. The selection indicates that the user can share the intelligent body of the second terminal to exchange more computing power indicators, so that the user can subsequently rent other computing power services of the intelligent computing center through computing power indicators, thereby reducing the cost of users enjoying computing power services and realizing the universal application of computing power.

[0062] The above security-related information is used to describe the security situation of the second terminal, for example, whether the second terminal is a personal terminal or an enterprise terminal, whether the use environment of the second terminal is a secure environment, etc.

[0063] The above interface information is used to describe the interface-related information for accessing the agent of the second terminal. The interface information enables the interface to be configured when calling the agent of the second terminal, thereby achieving access to the agent of the second terminal.

[0064] The above server environment information is used to describe the intelligent agent operating environment of the second terminal. It should be noted that different second terminals have different default program operating environments, and the operating environments of second terminals created based on the computing power of the second terminal are different. When executing tasks, a special operating environment may be required. Therefore, when registering the intelligent agent of the second terminal, it is necessary to determine the operating environment of the intelligent agent, so that the subsequent intelligent computing center can call the intelligent agent of the second terminal according to the operating environment.

[0065] In some implementations, when the at least one agent is an agent of the second terminal, before receiving the registration information of the at least one agent, a registration protocol is sent to the second terminal so that the second terminal sends the registration information according to the registration protocol.

[0066] The above registration protocol includes the content of the registration information that the agent needs to send. In some embodiments, the registration protocol also includes preset conditions that the agent needs to meet. When the agent of the second terminal meets the preset conditions, the second terminal sends the registration information according to the registration protocol.

[0067] Among them, the preset conditions include that data is not allowed to escape from the secure area, data must be transmitted encrypted, sensitive tasks must be confirmed by the user or automatically interrupted, etc.

[0068] In one embodiment, after step S3, the method further includes: Step S6, receiving feedback information from the at least one intelligent agent, wherein the feedback information is information sent by the at least one intelligent agent based on the execution plan after receiving the execution plan; Step S7: adjusting the execution plan based on the feedback information; Step S8: Send the adjusted execution plan to the at least one agent.

[0069] It should be noted that after the execution plan is formulated, there may be a situation where the agent assigned to the execution task cannot perform the task as planned. At this time, the execution evolution needs to be adjusted so that the agent can execute according to the adjusted execution plan.

[0070] In the embodiment of the present invention, feedback information from at least one intelligent agent is received, and the feedback information is information sent by at least one intelligent agent based on the execution plan after receiving the execution plan; the execution plan is adjusted based on the feedback information; and the adjusted execution plan is sent to at least one intelligent agent. In this way, when the intelligent agent receives the execution plan and determines that it cannot be carried out according to the execution plan, the execution plan is adjusted through the feedback information, so that each intelligent agent can execute the execution task according to the execution plan.

[0071] In one embodiment, step S3 includes: Step S31, encrypting the execution task, the relevant data of the execution task and the execution plan; Step S32: assign the encrypted execution task to the at least one intelligent agent, and send the encrypted execution plan to the at least one intelligent agent, and the at least one intelligent agent processes the relevant data of the execution task during the processing of the execution task.

[0072] It should be noted that in the process of executing tasks, different data have different confidentiality requirements. In order to avoid data leakage, the data in the process of executing tasks needs to be encrypted to improve data security.

[0073] In the embodiment of the present invention, the execution task, the relevant data of the execution task and the execution plan are encrypted; the encrypted execution task is assigned to the at least one intelligent agent, and the encrypted execution plan is sent to the at least one intelligent agent. In this way, by encrypting the execution task and the execution plan, the data leakage of the execution task and the execution plan is avoided, and the security of the data is improved. At the same time, the relevant data of the execution task has been encrypted, and the leakage of the relevant data can be reduced when the intelligent agent processes the relevant data of the execution task, further improving the security of the data.

[0074] In some embodiments, the encrypted execution task is assigned to at least one intelligent agent, and the encrypted execution plan is sent to at least one intelligent agent. After receiving the encrypted execution task and execution plan, the intelligent agent decrypts the execution task and execution plan to obtain the data content of the execution task and execution plan.

[0075] In one embodiment, step S3 includes: Step S33: When the type of the execution task is a preset type, sending a request indication to the first terminal, wherein the request indication is used to request the first terminal to confirm whether to execute the execution task; Step S34: upon receiving a confirmation indication, assigning the execution task to at least one agent and sending the execution plan to the at least one agent, wherein the confirmation indication is an indication that the first terminal confirms the execution of the execution task after receiving the request indication.

[0076] The above-mentioned preset types are types of pre-division of different tasks. Different tasks can be divided into different types, such as ordinary tasks, sensitive tasks or confidential tasks, etc., and sensitive tasks and confidential tasks are used as preset types. When the execution task belongs to the preset type, the first terminal is required to confirm whether to execute the task of this type to avoid the occurrence of less secure intelligent agents executing preset types of execution tasks, thereby improving security.

[0077] In an embodiment of the present invention, when the type of the execution task is a preset type, a request indication is sent to the first terminal, and the request indication is used to request the first terminal to confirm whether to execute the execution task; when the confirmation indication is received, the execution task is assigned to at least one intelligent agent, and the execution plan is sent to the at least one intelligent agent, and the confirmation indication is an indication of the first terminal confirming the execution of the execution task after receiving the request indication, so as to avoid the occurrence of intelligent agents with lower security executing execution tasks of preset types, thereby improving security.

[0078] In one embodiment, when the at least one intelligent agent is an intelligent agent created based on the computing power of the intelligent computing center, the at least one intelligent agent is an intelligent agent created based on a sandbox environment, and the sandbox environment is used to isolate the internal data of the at least one intelligent agent from the outside.

[0079] In the embodiment of the present invention, an intelligent agent is created based on a sandbox environment to isolate the internal data of the intelligent agent from the outside, thereby further improving the security of the data.

[0080] See also Figure 3 , Figure 3 is a structural diagram of a multi-agent sharing device of an intelligent computing center for universal computing power provided by an embodiment of the present invention, such as Figure 3 As shown, the intelligent computing center multi-agent sharing device 300 for universal computing power includes: A first receiving module 301, configured to receive an execution instruction sent by a first terminal; A creation module 302, used to create an execution task based on the execution instruction and formulate an execution plan for the execution task; An allocation module 303 is used to allocate the execution task to at least one intelligent agent and send the execution plan to the at least one intelligent agent, wherein the at least one intelligent agent includes at least one of the following: an intelligent agent created based on the computing power of the intelligent computing center, and an intelligent agent created based on the computing power of the second terminal; The first sending module 304 is used to receive the execution result of the at least one agent and send the execution result to the first terminal. The execution result is the result obtained by the at least one agent executing the execution task based on the execution plan.

[0081] In one embodiment, before the first receiving module 301, the intelligent computing center multi-agent sharing device 300 for inclusive computing power further includes: A second receiving module, used to receive registration information of the at least one intelligent agent, wherein the registration information is used for the at least one intelligent agent to register with the intelligent computing center; The registration information includes description information of the tool capabilities of the at least one intelligent agent, computing power billing information, security-related information, interface information, and server environment information that the runtime depends on.

[0082] In one embodiment, after the allocation module 303, the intelligent computing center multi-agent sharing device 300 for universal computing power further includes: A third receiving module is used to receive feedback information of the at least one agent, wherein the feedback information is information sent by the at least one agent based on the execution plan after receiving the execution plan; An adjustment module, used for adjusting the execution plan based on the feedback information; The second sending module is used to send the adjusted execution plan to the at least one intelligent agent.

[0083] In one embodiment, the allocation module 303 includes: An encryption unit, used for encrypting the execution task, data related to the execution task and the execution plan; The first sending unit is used to assign the encrypted execution task to the at least one intelligent agent, and send the encrypted execution plan to the at least one intelligent agent, and the at least one intelligent agent processes the relevant data of the execution task during the process of processing the execution task.

[0084] In one embodiment, the allocation module 303 includes: A second sending unit, configured to send a request indication to the first terminal when the type of the execution task is a preset type, wherein the request indication is used to request the first terminal to confirm whether to execute the execution task; An allocation unit is used to allocate the execution task to at least one intelligent agent and send the execution plan to the at least one intelligent agent when a confirmation indication is received. The confirmation indication is an indication that the first terminal confirms the execution of the execution task after receiving the request indication.

[0085] In one embodiment, when the at least one intelligent agent is an intelligent agent created based on the computing power of the intelligent computing center, the at least one intelligent agent is an intelligent agent created based on a sandbox environment, and the sandbox environment is used to isolate the internal data of the at least one intelligent agent from the outside.

[0086] The multi-agent sharing device of an intelligent computing center for inclusive computing power provided in an embodiment of the present invention is capable of realizing the various processes of the various embodiments of the above-mentioned multi-agent sharing method of an intelligent computing center for inclusive computing power. The technical features correspond one to one and can achieve the same technical effects. To avoid repetition, they will not be described here.

[0087] It should be noted that the multi-agent sharing device of the intelligent computing center for inclusive computing power in the embodiment of the present invention can be a device, or a component, integrated circuit, or chip in an electronic device.

[0088] The embodiment of the present invention further provides an electronic device, see Figure 4 , Figure 4 4 is a schematic diagram of a structure of an electronic device provided by the present invention, the electronic device includes a memory 401, a processor 402 and a program or instruction stored in the memory 401 and running on the memory 401. When the program or instruction is executed by the processor 402, Figure 1 Any steps in the corresponding embodiment of the multi-agent sharing method of the intelligent computing center for universal computing power and the same beneficial effects achieved will not be repeated here.

[0089] The processor 402 may be a CPU, an ASIC, an FPGA or a GPU.

[0090] A person of ordinary skill in the art can understand that all or part of the steps of the above-mentioned embodiment of the multi-agent sharing method of the intelligent computing center for universal computing power can be completed by hardware related to program instructions, and the program can be stored in a readable medium.

[0091] The embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above Figure 1 Any steps in the corresponding embodiments of the multi-agent sharing method of the intelligent computing center for universal computing power can achieve the same technical effect, and will not be repeated here to avoid repetition. The storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0092] The terms "first", "second" etc. in the embodiments of the present invention are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. In addition, "and / or" is used in the present application to represent at least one of the connected objects, such as A and / or B and / or C, representing the inclusion of separate A, separate B, separate C, and A and B all exist, B and C all exist, A and C all exist, and 7 situations in which A, B and C all exist.

[0093] 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.

[0094] 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 application, 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 disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a second terminal device, etc.) to execute the methods of each embodiment of the present application.

[0095] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A multi-agent sharing method for intelligent computing centers for universal computing power, characterized in that: include: Step S1, receiving an execution instruction sent by a first terminal; Step S2: creating an execution task based on the execution instruction, and formulating an execution plan for the execution task; Step S3, assigning the execution task to at least one agent, and sending the execution plan to the at least one agent, wherein the at least one agent includes at least one of the following: an agent created based on the computing power of the intelligent computing center, and an agent created based on the computing power of the second terminal; Step S4: receiving the execution result of the at least one agent, and sending the execution result to the first terminal, wherein the execution result is the result obtained by the at least one agent executing the execution task based on the execution plan.

2. The method according to claim 1, characterized in that Before step S1, the method further includes: Step S0, receiving registration information of the at least one intelligent agent, wherein the registration information is used for registering the at least one intelligent agent to the intelligent computing center; The registration information includes description information of the tool capabilities of the at least one intelligent agent, computing power billing information, security-related information, interface information, and server environment information that the runtime depends on.

3. The method according to claim 1 or 2, characterized in that After step S3, the method further includes: Step S5, receiving feedback information from the at least one intelligent agent, wherein the feedback information is information sent by the at least one intelligent agent based on the execution plan after receiving the execution plan; Step S6: adjusting the execution plan based on the feedback information; Step S7: Send the adjusted execution plan to the at least one agent.

4. The method according to claim 1 or 2, characterized in that: The step S3 comprises: Step S31, encrypting the execution task, the relevant data of the execution task and the execution plan; Step S32: assign the encrypted execution task to the at least one intelligent agent, and send the encrypted execution plan to the at least one intelligent agent, and the at least one intelligent agent processes the relevant data of the execution task during the processing of the execution task.

5. The method according to claim 1 or 2, characterized in that: The step S3 comprises: Step S33: When the type of the execution task is a preset type, sending a request indication to the first terminal, wherein the request indication is used to request the first terminal to confirm whether to execute the execution task; Step S34: upon receiving a confirmation indication, assigning the execution task to at least one agent and sending the execution plan to the at least one agent, wherein the confirmation indication is an indication that the first terminal confirms the execution of the execution task after receiving the request indication.

6. The method according to claim 1 or 2, characterized in that: In the case where the at least one intelligent agent is an intelligent agent created based on the computing power of the intelligent computing center, the at least one intelligent agent is an intelligent agent created based on a sandbox environment, and the sandbox environment is used to isolate the internal data of the at least one intelligent agent from the outside.

7. A multi-agent sharing device for intelligent computing centers for universal computing power, characterized in that: include: A first receiving module, configured to receive an execution instruction sent by a first terminal; A creation module, used to create an execution task based on the execution instruction and formulate an execution plan for the execution task; an allocation module, configured to allocate the execution task to at least one intelligent agent and send the execution plan to the at least one intelligent agent, wherein the at least one intelligent agent includes at least one of the following: an intelligent agent created based on the computing power of the intelligent computing center, and an intelligent agent created based on the computing power of the second terminal; The first sending module is used to receive the execution result of the at least one intelligent agent and send the execution result to the first terminal. The execution result is the result obtained by the at least one intelligent agent executing the execution task based on the execution plan.

8. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the multi-agent sharing method of an intelligent computing center for universal computing power as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the multi-agent sharing method of an intelligent computing center for universal computing power as described in any one of claims 1 to 6.

10. A computer program product, characterized in that It includes computer instructions, which, when executed by a processor, implement the steps of the multi-agent sharing method of an intelligent computing center for universal computing power as described in any one of claims 1 to 6.

Images