Multi-Agent cooperative communication method and device based on block chain, equipment and storage medium

Abstract

The embodiment of the invention discloses a multi-Agent cooperative communication method and device based on a block chain, equipment and a storage medium. The method comprises the steps that a communication request is sent to a block chain, the communication request comprises index information of a target Agent, first response information returned by the block chain is acquired, the first response information comprises a communication address of the target Agent, and the communication address is obtained by searching a node information list based on the index information by the block chain; and establishing trusted communication with the target Agent through the communication address. Visibly, the related information and the communication address of each Agent are maintained through the node information list in the block chain, so that when the source Agent has a cross-platform multi-agent cooperation demand, the communication address of the target Agent can be obtained from the block chain through the index information of the target Agent, and then point-to-point trusted communication with the target Agent is established.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and blockchain technology, and specifically to a blockchain-based multi-agent collaborative communication method and device, equipment, and computer-readable storage medium. Background Art

[0002] With the rapid development of artificial intelligence technology, large language model technology has penetrated into human social life. General large language models such as ChatGPT, Ziya, and Baichuan have become beneficial auxiliary tools for all walks of life and have shown great potential in achieving human-level intelligence. Artificial intelligence agents (AI Agents) provide users with convenient auxiliary services by perceiving the environment, making decisions, and executing actions.

[0003] Currently, BabyAGI, AutoGPT and other technologies use large language model technology to realize self-driven single agents, which can achieve goal creation, organization and execution of tasks according to predefined tools, bringing great convenience to human social life. Thanks to the development of single agents, multi-agent technology based on large language models has received widespread attention. Unlike single agents that mainly interact with the environment and tools, multi-agents emphasize the coordination and interaction between agents. Studies have found that communication between multi-agents is mainly limited to the same system environment, without considering cross-system coordination and cooperation. The designed communication mechanism only considers communication and collaboration between agents in a reliable environment or even the same system, lacking security and cross-platform considerations. Summary of the invention

[0004] To solve the above technical problems, the embodiments of the present application respectively provide a multi-agent collaborative communication method based on blockchain, a multi-agent collaborative communication device based on blockchain, a multi-agent collaborative communication device based on blockchain, a computer-readable storage medium, and a multi-agent collaborative communication system based on blockchain.

[0005] According to one aspect of an embodiment of the present application, a multi-agent collaborative communication method based on blockchain is provided, which is applied to a source Agent, and includes: sending a communication request to a blockchain, wherein the communication request includes index information of a target Agent; obtaining first response information returned by the blockchain, wherein the first response information includes a communication address of the target Agent, and the communication address is obtained by the blockchain by retrieving a node information list based on the index information; and establishing trusted communication with the target Agent through the communication address.

[0006] According to one aspect of an embodiment of the present application, a multi-agent collaborative communication device based on blockchain is provided, which is applied to a source agent and includes: a sending module, used to send a communication request to the blockchain, the communication request including index information of a target agent; a receiving module, used to obtain a first response information returned by the blockchain, the first response information including a communication address of the target agent, and the communication address is obtained by the blockchain by retrieving a node information list based on the index information; a communication module, used to establish trusted communication with the target agent through the communication address.

[0007] According to one aspect of an embodiment of the present application, a multi-agent collaborative communication system based on blockchain is provided, including a source agent, a target agent and a blockchain, wherein the source agent is used to send a communication request to the blockchain, and the communication request includes index information of the target agent; the blockchain is used to retrieve a node information list based on the index information to obtain a communication address of the target agent, and return a first response information to the source agent, and the first response information includes the communication address of the target agent; the source agent is also used to send a connection establishment request to the target agent through the communication address; the target agent is used to return a second response information to the source agent and establish trusted communication with the source agent.

[0008] According to one aspect of an embodiment of the present application, a blockchain-based multi-agent collaborative communication device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the blockchain-based multi-agent collaborative communication device implements the blockchain-based multi-agent collaborative communication method as described above.

[0009] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the blockchain-based multi-agent collaborative communication method as described above.

[0010] According to one aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the steps in the blockchain-based multi-agent collaborative communication method as described above.

[0011] In the technical solution provided in the embodiment of the present application, the relevant information and communication address of each Agent are maintained through the node information list in the blockchain, so that when the source Agent has a cross-platform multi-agent collaboration requirement, the communication address of the target Agent can be obtained from the blockchain through the index information of the target Agent, and then point-to-point trusted communication can be established with the target Agent.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0014] Figure 1 This is a diagram of a multi-agent collaborative communication architecture based on blockchain, shown in an exemplary embodiment of the present application;

[0015] Figure 2 is a flowchart of a multi-agent collaborative communication method based on blockchain shown in an exemplary embodiment of the present application;

[0016] Figure 3 is a schematic diagram of a communication request shown in an exemplary embodiment of the present application;

[0017] Figure 4 is a connection request schematic diagram shown in an exemplary embodiment of the present application;

[0018] Figure 5 is a schematic diagram of a reliability verification process shown in an exemplary embodiment of the present application;

[0019] Figure 6 is a schematic diagram of connection establishment shown in an exemplary embodiment of the present application;

[0020] Figure 7 is a schematic diagram of a data transmission process shown in an exemplary embodiment of the present application;

[0021] Figure 8 is a flowchart of a multi-agent collaborative communication method based on blockchain shown in another exemplary embodiment of the present application;

[0022] Fig. 9 is a flowchart of a multi-agent collaborative communication method based on blockchain shown in another exemplary embodiment of the present application;

[0023] Fig.10 It is a block diagram of a multi-agent collaborative communication device based on blockchain shown in an exemplary embodiment of the present application;

[0024] Fig.11 A schematic diagram of the structure of a computer system of a blockchain-based multi-agent collaborative communication device suitable for implementing an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0026] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0027] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0028] The term "multiple" as used in this application refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0029] First of all, it should be noted that this application involves artificial intelligence and blockchain technology. The following is a brief introduction to the relevant technologies:

[0030] LLM-based AI Agent: A system driven by a large language model as its brain, which has the ability to autonomously understand, perceive, plan, remember and use tools, and can automatically perform complex tasks. It is referred to as Agent in this application.

[0031] Multi-Agent collaboration / cooperation (multi-Agent): refers to the process in which multiple autonomous and intelligent agents collaborate to achieve a common goal through information exchange in a shared environment. Its essence is data interaction, that is, the purpose of multi-agent collaboration / cooperation can be achieved through cross-platform data interaction.

[0032] Blockchain information sharing: refers to the trusted message sharing based on blockchain technology, providing a trusted peer-to-peer information interaction environment for all parties involved in the sharing.

[0033] Collaborative communication technology is a technology that enables effective collaboration and communication between multiple participants based on a communication network. Its purpose is to achieve information sharing, task allocation, and optimized resource utilization through collaboration and information exchange. The main technical principles of collaborative communication technology include distributed architecture, intelligent routing, data management, protocol design, and other components. The existing multi-agent collaborative communication mainly relies on adding relay management nodes and building a shared message pool. These solutions have the following problems that are difficult to solve in cross-system agent collaboration:

[0034] 1) Relay nodes are unreliable or have single-point failures, making cross-system collaborative communications unreliable;

[0035] 2) The shared message pool lacks a rigorous permission management mechanism, which can easily lead to increased coupling between systems and make subsequent system expansion difficult.

[0036] Therefore, in order to achieve trusted collaboration of cross-platform intelligent agents, this patent proposes a blockchain-based collaborative communication method to form a peer-to-peer intelligent agent trusted communication network based on blockchain information sharing, improve the robustness of collaboration, achieve independent development of multiple systems, and support cross-system agent trusted collaboration.

[0037] Figure 1 FIG. 1 is a diagram of a multi-agent collaborative communication architecture based on blockchain, shown in an exemplary embodiment of the present application. Figure 1As shown in the figure, the blockchain and each agent together form a multi-agent collaborative network based on the blockchain. In this architecture, all agents are in an equal communication state, and point-to-point information communication can be realized. The blockchain maintains a list of node information (such as the agent routing list), and can update or return the list information according to the agent's access requirements. As an entity that supports information sharing, the blockchain is responsible for interacting with each agent, providing a "communication address", and assisting the agent in "establishing trusted communication"; for example, after receiving a communication request from the source agent, the target agent can obtain the reliability score of the source agent from the blockchain to decide whether to agree to establish trusted communication with the source agent. The interaction between the blockchain and the agent node mainly includes three types of functions: agent registration, agent access address query, and agent exit.

[0038] The blockchain can be a public chain, a private chain or a consortium chain. In an information sharing network based on a public chain, the relevant information of the Agent node will be disclosed to all nodes, which is suitable for nodes with global sharing needs to participate. Public chains including Ethereum can be used as basic blockchains. In an information sharing network based on a consortium chain or a private chain, the Agent node information is only published within the consortium chain or private chain network, which is suitable for nodes with information protection needs to participate, and they need to build a consortium chain or a private chain by themselves. The information stored on the chain should at least include: Agent access information (such as IP address, access port, etc.), Agent identity information (such as Agent identity, Agent public key, etc.). Optional information may include: Agent attribute information (service type, service capability, service requirements, etc.), Agent permission information, etc. Agent can obtain the collaboration record data related to itself in the blockchain at any time to support the optimization and adjustment of its own collaboration strategy. For example, Agent can determine the next collaboration target based on the collaboration record data related to itself in the blockchain to avoid repeated collaboration.

[0039] In one embodiment, in addition to the basic capabilities of an agent, each agent in a blockchain-based multi-agent collaborative network needs to be configured with a blockchain light node function, that is, the ability to access the blockchain network and access blockchain ledger information (without requiring participation in consensus, storage of ledgers, etc.), and have a public-private key pair. In addition, each agent has the ability to self-discover blockchain services. When it is necessary to collaborate with other agents to perform a task, the agent can find the adjacent blockchain network through broadcast messages to access the information-sharing blockchain.

[0040] Figure 1Any two agents (respectively serving as source agent and target agent) and blockchain can constitute a multi-agent collaborative communication system based on blockchain. The source agent is used to send a communication request to the blockchain, and the communication request includes the index information of the target agent. The blockchain is used to retrieve the node information list based on the index information to obtain the communication address of the target agent, and return the first response information to the source agent, and the first response information includes the communication address of the target agent. The source agent is also used to send a connection establishment request to the target agent through the communication address. The target agent is used to return the second response information to the source agent and establish trusted communication with the source agent.

[0041] Figure 2 This is a flowchart of a multi-agent collaborative communication method based on blockchain, shown in an exemplary embodiment of the present application. The method can be specifically executed by a server or a terminal device, such as a smart phone, a computer, a laptop or other electronic device, and the server can be, for example, an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. This embodiment does not limit the specific execution subject of the method.

[0042] like Figure 2 As shown, in an exemplary embodiment, the method includes steps S210-S230, which are described in detail as follows:

[0043] S210: Send a communication request to the blockchain.

[0044] The communication request includes the index information of the target Agent. The communication request is used to request the access address of the target Agent from the blockchain.

[0045] Figure 3 FIG. 1 is a schematic diagram of a communication request shown in an exemplary embodiment of the present application. Figure 3As shown, the communication request may include a task information field, an identity public key field, an identity information field, a message format field, a communication mode field, and a function field. Among them, the task information field is used to indicate the information interaction target (i.e., the communication intention). The identity public key field is used to indicate the public key of the target Agent. This field is an optional field and the value can be empty (such as in a communication mode based on service capabilities). The identity information field is used to indicate the identity of the target Agent. In a communication mode based on service capabilities, this field is the service capability requirement of the target Agent (i.e., the service capability is used as the retrieval condition of the Agent). The message format field is used to indicate the data encryption mode when communicating with the target Agent. The communication mode is used to indicate the access mode of the target Agent. The function field is used to indicate the type of access.

[0046] In one embodiment, the access mode includes: communication based on access address, communication based on identity information and communication based on service capability. Among them, communication based on access address requires that the agent can obtain the target agent access address by accessing the blockchain; or obtain relevant information of the target agent through the target agent access address; communication based on identity information requires that the agent can obtain the access address of the agent corresponding to the identity information (such as the target agent's identification, description information, etc.) in the blockchain; communication based on service capability requires that the blockchain can call the smart contract to match the target agent that meets the service requirements for the agent and return the access address.

[0047] Table 1 is a communication request shown in an exemplary embodiment of the present application.

[0048] Table 1

[0049]

[0050] As shown in Table 1, in the communication request, "com_mode" is the communication mode field, "identity_info" is the identity information field, "identity_pubkey" is the identity public key field, and "remark" can be used to remark other descriptive information, such as capability requirements, connection intentions, etc.

[0051] S220. Obtain the first response information returned by the blockchain, where the first response information includes the communication address of the target Agent, and the communication address is obtained by retrieving the node information list based on the index information of the blockchain.

[0052] The index information may be information such as the identifier and identity information of the target Agent that can uniquely determine the access address of the target Agent, or may be screening conditions such as capability requirements.

[0053] In one implementation, the blockchain stores the identification, identity information, access address, description information (such as service capability description) of each Agent in a node information list, and periodically updates and maintains it (such as updating the service capability of the Agent, adding new Agents, etc.). In other words, the node information list is used to maintain the relevant information of each Agent in the network and can provide query / filtering services.

[0054] If the index information is the target Agent's identifier or the target Agent's identity information, the blockchain can directly retrieve the node information list based on the index information to obtain the target Agent's access address. Then, the first response information is generated based on the target Agent's access address and returned to the source Agent. Figure 3 , the first response information may include a response identifier (such as proof that the first response information is provided by the blockchain) and a task reply (such as the access address of the target Agent).

[0055] If the index information is a service capability requirement, the blockchain uses the service capability requirement as a screening condition to screen the candidate agents included in the node information list (such as through a built-in smart contract) to obtain one or more target agents that meet the screening conditions.

[0056] In one embodiment, the index information of the target agent is a service capability requirement; the service capability requirement includes a service type, an attribute, a performance index, and a distance index; the service type and the attribute of the target agent respectively match the service type and the attribute indicated by the service capability requirement, and the index deviation corresponding to the target agent is the smallest among the candidate agents; the index deviation is obtained by weighted summing a first index difference and a second index difference, the first index difference being calculated based on the actual performance of the target agent and the performance index; the second index difference being calculated based on the distance between the target agent and the source agent and the distance index.

[0057] The service capability requirements proposed by the source agent can be specifically expressed as: (T, C, L, Des); where T is the service type requirement (for example, computing support, storage support, map retrieval support, software development support, etc.); C is the support strength requirement, that is, the performance index (for example, the computing power per unit time under computing support, the software requirement analysis capability score under software development support, etc.); L is the Agent geographical distance limit, that is, the example index; Des is the Agent attribute capability described in natural language, which supports mutual understanding between Agent nodes.

[0058] Furthermore, based on the service capability requirements proposed by the source agent, the blockchain can first select the target candidate agent whose service type and attributes meet the requirements from the candidate agents, and then calculate the index deviation based on the difference between the actual performance of each target candidate agent and the performance index, as well as the difference between the actual distance of each target candidate agent (with the source agent) and the distance index, and determine the target candidate agent with the smallest index deviation as the target agent. The calculation formula of the index deviation can be specifically expressed as:

[0059]

[0060] Wherein, w1 and w2 are weights, and w1+w2=1, w1>0, w2>0. dis is the actual distance between the source agent and the target candidate agent, and L is the distance index. now is the actual performance of the target candidate agent, C is the performance index, and Po is the distance from the target requirement.

[0061] S230: Establish trusted communication with the target Agent through the communication address.

[0062] Figure 4 FIG. 1 is a schematic diagram of a connection request shown in an exemplary embodiment of the present application. Figure 4 As shown, the source Agent can establish trusted communication with the target Agent by sending a connection establishment request to the communication address. The connection establishment request may specifically include: the source Agent public key, service access request, service requirement description (regularized and natural language description), and information signature (to ensure the reliability of information).

[0063] In one implementation, the source Agent sends a connection establishment request to the target Agent via a communication address, and the connection establishment request includes the source Agent's public key and intent description information; wherein the intent description information is used to describe the purpose of establishing the connection, and specifically may include data expected to be interacted with, etc.

[0064] Figure 5 FIG. 1 is a schematic diagram of a reliability verification process shown in an exemplary embodiment of the present application. Figure 5As shown, after the target Agent obtains the connection establishment request sent by the source Agent, it can confirm the access reliability to the blockchain. Specifically, the target Agent can provide the public key of the source Agent to the blockchain so that the blockchain can score the reliability of the source Agent. After obtaining the public key of the source Agent, the blockchain can query the historical collaboration records (and communication information) of the source Agent in the network, and obtain the reliability score of the source Agent based on the historical collaboration records (and communication information) of the source Agent. The specific scoring rules can be dynamically adjusted based on the actual situation, and this application does not limit this. The blockchain returns an access reliability response (including the reliability score of the source Agent) to the target Agent. If the reliability score of the source Agent is greater than the scoring threshold, the target Agent returns a second response information to the source Agent. In other words, the second response information is returned by the target Agent when the reliability score of the source Agent is greater than the scoring threshold. The reliability score is obtained by the blockchain based on the historical collaboration records (and communication information) of the source Agent. The historical collaboration records of the source Agent are retrieved in the blockchain using the public key of the source Agent as an index. The public key of the source Agent can be provided by the target Agent to the blockchain.

[0065] It should be noted that the reliability analysis can be completed by the blockchain or by the target Agent, and this application does not limit this. Compared with being completed by the target Agent, being completed by the blockchain is more secure (data of the source Agent will not be leaked).

[0066] Figure 6 FIG. 1 is a schematic diagram of connection establishment shown in an exemplary embodiment of the present application. Figure 6 As shown, the source Agent obtains the second response information (i.e., the response information of the connection establishment request) and interacts with the target Agent to optimize its own service capabilities. The data interaction process can use plain text data or cipher text data. Compared with plain text data, using cipher text data for interaction is more secure.

[0067] In one embodiment, the source agent signs the target data with its own public key, obtains the target data digest, and sends the target data and the target data digest to the target agent. Accordingly, after obtaining the target data and the target data digest, the target agent can detect the target data with the target data digest to prevent the target data from being tampered with.

[0068] Figure 7 FIG. 1 is a schematic diagram of a data transmission process shown in an exemplary embodiment of the present application. Figure 7As shown in the figure, the source agent encrypts the target data with the public key of the target agent to obtain the ciphertext corresponding to the target data, and signs the ciphertext of the target data with its own public key to obtain the summary of the ciphertext, and then sends the ciphertext and the summary of the ciphertext to the target agent. Accordingly, after obtaining the ciphertext and the summary of the ciphertext, the target agent can detect tampering of the ciphertext through the summary of the ciphertext. If it is determined that the ciphertext has not been tampered with, it decrypts the ciphertext with its own private key to obtain the target data.

[0069] Furthermore, after acquiring the target data, the target agent can extract key information, use its own task understanding and decision-making capabilities to execute and complete the task, and then return the execution results to the source agent.

[0070] It can be understood that according to the above method, collaborative communication between three or more Agents can also be established; that is, the blockchain-based multi-agent collaborative communication method provided in this application is also applicable to establishing collaborative communication between three or more Agents; among them, the method for establishing collaborative communication between any two Agents can refer to the above method, which will not be repeated here.

[0071] In the embodiment itself, a communication request is sent to the blockchain, the communication request includes the index information of the target Agent, and the first response information returned by the blockchain is obtained. The first response information includes the communication address of the target Agent. The communication address is obtained by retrieving the node information list based on the index information of the blockchain, and a trusted communication is established with the target Agent through the communication address. It can be seen that the relevant information and communication address of each Agent are maintained through the node information list in the blockchain, so that when the source Agent has a cross-platform multi-agent collaboration requirement, the communication address of the target Agent can be obtained from the blockchain through the index information of the target Agent, and then a point-to-point trusted communication is established with the target Agent. In the process of establishing point-to-point trusted communication, the interaction between the target Agent and the blockchain is supported, and cross-system Agent trusted mutual authentication is realized to ensure reliable communication between Agents.

[0072] Figure 8 is a flowchart of a multi-agent collaborative communication method based on blockchain shown in another exemplary embodiment of the present application. The multi-agent collaborative communication method based on blockchain is Figure 2 The embodiment shown in the figure is further proposed. Figure 8 As shown, the exemplary blockchain-based multi-agent collaborative communication method further includes steps S810 and S820 before step S210, which are described in detail as follows:

[0073] Step S810: broadcast a blockchain access request to obtain an access interface of the blockchain.

[0074] In the initial stage, each Agent (node) participating in the collaboration needs to register shared information on the blockchain. The blockchain generates a node information list based on the registration information of each Agent and maintains the node information list.

[0075] In one embodiment, the agent has the ability to self-discover blockchains. When the agent needs to collaborate with other agents to perform a task, it can find neighboring blockchains through broadcast messages to access information-sharing blockchains. For example, the agent can broadcast a blockchain interface acquisition request and access the blockchain based on the blockchain interface returned by other nodes.

[0076] For a registered Agent, step S210 may be directly executed; for an unregistered Agent, step S820 is continued to be executed.

[0077] Step S820: Send the node registration information through the access interface of the blockchain so that the blockchain updates the node information list based on the node registration information.

[0078] In one implementation, the source agent selects the type of shared information blockchain (such as a public chain, a private chain, a consortium chain, etc.) and initiates a service information registration transaction (the consortium chain and the private chain need to provide authentication information to ensure successful joining). The service registration information includes at least one of the following: the source agent's functional description (in the form of a natural language description or a specific number description), its own communication address, collaboration requirements, and other content that needs to be explained. The agent that completes the registration will obtain a unique service identifier to support the subsequent agent access address information acquisition. The service identifier example is as follows:

[0079] [Service number-Service type-Service capability assessment-Random placeholder]

[0080] In the embodiment of the present application, in the initial stage, each agent registers shared information in the blockchain to obtain a node information list. The blockchain maintains the node information list, which includes the agent access address, identity information, etc., to support cross-system multi-agent collaborative discovery and effectively obtain the corresponding agent access address, break the barriers between cross-system agents, and establish a trusted connection.

[0081] Fig. 9 is a flowchart of a multi-agent collaborative communication method based on blockchain shown in another exemplary embodiment of the present application. The multi-agent collaborative communication method based on blockchain is Figure 2 The embodiment shown in the figure is further proposed. Fig. 9 As shown, the exemplary blockchain-based multi-agent collaborative communication method further includes steps S910 to S930 after step S230, which are described in detail as follows:

[0082] Step S910: In response to completing the data interaction, a communication release request is sent to the target Agent.

[0083] The communication release request is used to disconnect the trusted communication between the source Agent and the target Agent. If the target Agent accepts the communication release request, the process continues to execute step S920.

[0084] Step S920: In response to the target Agent sending a communication release request, the trusted communication with the target Agent is released, and the state of the agent is updated to the collaborative preparation state.

[0085] The collaborative preparation state is used to indicate that the source agent can currently establish trusted communication with other agents. Correspondingly, if the source agent is in a non-collaborative preparation state (such as when it is in trusted communication with the target agent), it means that the source agent cannot currently establish trusted communication with other agents.

[0086] Step S930: Send the collaborative optimization record corresponding to this communication to the blockchain, so that the blockchain updates the status of the source Agent according to the status update request.

[0087] The collaborative optimization record can record the content of this collaborative optimization so that the source agent can obtain the collaborative optimization information related to itself in the blockchain and optimize its own services. The status of the source agent can include but is not limited to: update of the source agent's service capabilities, update of the collaborative preparation status, update of the description information, and update of the version.

[0088] It should be noted that step S930 can be executed before step S920, or can be executed synchronously with step S920, and this application does not impose any restrictions on this.

[0089] In summary, the blockchain-based multi-agent collaborative communication method provided by this application includes a three-stage communication process of "connection establishment-information transmission-connection release". A reliable connection is established with the support of blockchain, and asymmetric encryption technology is used to achieve secure information transmission, ensuring information security in the Agent collaboration process without human intervention.

[0090] Fig.10 : is a block diagram of a multi-agent collaborative communication device based on blockchain, shown in an exemplary embodiment of the present application. Fig.10 As shown, the device comprises:

[0091] The sending module 1010 is configured to send a communication request to the blockchain, wherein the communication request includes the index information of the target Agent; the receiving module 1020 is configured to obtain the first response information returned by the blockchain, wherein the first response information includes the communication address of the target Agent, and the communication address is obtained by the blockchain by retrieving the node information list based on the index information; the communication module 1030 is configured to establish trusted communication with the target Agent through the communication address.

[0092] In another exemplary embodiment, the communication module 1030 includes a sending unit and a receiving unit:

[0093] A sending unit, configured to send a connection establishment request to the target Agent via the communication address, wherein the connection establishment request includes a public key and intention description information of the source Agent;

[0094] A receiving unit, used to obtain the second response information and perform data interaction with the target Agent to optimize its own service capability;

[0095] The second response information is returned by the target Agent when the reliability score of the source Agent is greater than the score threshold, the reliability score is obtained by the blockchain based on the historical communication record of the source Agent, the historical communication record of the source Agent is retrieved by using the public key of the source Agent as an index, and the public key of the source Agent is provided by the target Agent to the blockchain.

[0096] In another exemplary embodiment, the specific embodiment of the receiving unit performing data interaction with the target Agent is:

[0097] Sign the target data with its own public key to obtain a summary of the target data, and send the target data and the summary of the target data to the target Agent; or

[0098] The target data is encrypted by the public key of the target Agent, and the ciphertext of the target data is signed by its own public key to obtain a summary of the ciphertext, and the ciphertext and the summary of the ciphertext are sent to the target Agent.

[0099] In another exemplary embodiment, the apparatus further comprises:

[0100] The sending module 1010 is configured to send a communication release request to the target Agent in response to completing the data interaction, wherein the communication release request is used to disconnect the trusted communication with the target Agent;

[0101] The communication module 1030 is configured to release the trusted communication with the target Agent in response to the target Agent sending the communication release request, and update its own state to the collaborative preparation state;

[0102] The sending module 1010 is configured to send the collaborative optimization record corresponding to this communication to the blockchain, so that the blockchain updates the state of the source Agent according to the state update request.

[0103] In another exemplary embodiment, the index information of the target Agent is a service capability requirement; the service capability requirement includes a service type, an attribute, a performance indicator, and a distance indicator; the service type and the attribute of the target Agent respectively match the service type and the attribute indicated by the service capability requirement, and the indicator deviation corresponding to the target Agent is the smallest among the candidate Agents; the indicator deviation is obtained by weighted summing a first indicator difference and a second indicator difference, the first indicator difference being calculated based on the actual performance of the target Agent and the performance indicator; the second indicator difference being calculated based on the distance between the target Agent and the source Agent and the distance indicator.

[0104] In another exemplary embodiment, the apparatus further comprises:

[0105] The sending module 1010 is configured to broadcast a blockchain access request to obtain an access interface of the blockchain;

[0106] A sending module 1010 is configured to send node registration information through an access interface of the blockchain, so that the blockchain updates the node information list based on the node registration information;

[0107] The node registration information includes at least one of the following: Agent identification, communication address, communication authority, and function description information.

[0108] It should be noted that the multi-agent collaborative communication device based on blockchain provided in the above embodiment and the multi-agent collaborative communication method based on blockchain provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the multi-agent collaborative communication device based on blockchain provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0109] An embodiment of the present application also provides a blockchain-based multi-agent collaborative communication device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the blockchain-based multi-agent collaborative communication device implements the blockchain-based multi-agent collaborative communication method provided in the above-mentioned embodiments.

[0110] Fig.11 The schematic diagram of the structure of the computer system of the multi-agent collaborative communication device based on blockchain suitable for implementing the embodiment of the present application is shown. It should be noted that: Fig.11 The computer system 1100 of multi-agent collaborative communication devices based on blockchain is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0111] like Fig.11 As shown, the computer system 1100 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1102 or the program loaded from the storage part 1108 to the random access memory (RAM) 1103, such as executing the method described in the above embodiment. In the RAM 1103, various programs and data required for system operation are also stored. The CPU 1101, the ROM 1102 and the RAM 1103 are connected to each other through the bus 1104. The input / output (I / O) interface 1105 is also connected to the bus 1104.

[0112] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0113] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 1109, and / or installed from a removable medium 1111. When the computer program is executed by a central processing unit (CPU) 1101, various functions defined in the system of the present application are executed.

[0114] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a 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 above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0115] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0117] Another aspect of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the multi-agent collaborative communication method based on blockchain as described above is implemented. The computer-readable storage medium may be included in the multi-agent collaborative communication device based on blockchain described in the above embodiment, or may exist independently without being assembled into the multi-agent collaborative communication device based on blockchain.

[0118] Another aspect of the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the multi-agent collaborative communication method based on blockchain provided in the above-mentioned embodiments.

[0119] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person skilled in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. A multi-agent collaborative communication method based on blockchain, characterized in that: Applied to the source Agent, the method includes: Send a communication request to the blockchain, wherein the communication request includes index information of the target Agent; Obtaining first response information returned by the blockchain, where the first response information includes a communication address of the target Agent, where the communication address is obtained by the blockchain by retrieving a node information list based on the index information; Establish trusted communication with the target Agent through the communication address.

2. The method according to claim 1, characterized in that The establishing trusted communication with the target Agent through the communication address includes: Sending a connection establishment request to the target Agent via the communication address, wherein the connection establishment request includes the public key and intent description information of the source Agent; Obtaining second response information, and performing data interaction with the target Agent to optimize its own service capability; The second response information is returned by the target Agent when the reliability score of the source Agent is greater than the score threshold, the reliability score is obtained by the blockchain based on the historical communication record of the source Agent, the historical communication record of the source Agent is retrieved by using the public key of the source Agent as an index, and the public key of the source Agent is provided by the target Agent to the blockchain.

3. The method according to claim 2, characterized in that The data interaction with the target Agent includes: Sign the target data with its own public key to obtain a summary of the target data, and send the target data and the summary of the target data to the target Agent; or The target data is encrypted by the public key of the target Agent, and the ciphertext of the target data is signed by its own public key to obtain a summary of the ciphertext, and the ciphertext and the summary of the ciphertext are sent to the target Agent.

4. The method according to claim 1, characterized in that The method further comprises: In response to completing the data interaction, sending a communication release request to the target Agent, wherein the communication release request is used to disconnect the trusted communication with the target Agent; In response to the target Agent sending the communication release request, releasing the trusted communication with the target Agent and updating its own state to a collaborative preparation state; Send the collaborative optimization record corresponding to this communication to the blockchain, so that the blockchain updates the state of the source Agent according to the state update request.

5. The method according to claim 1, characterized in that The index information of the target Agent is the service capability requirement; the service capability requirement includes service type, attribute, performance index and distance index; The service type and attribute of the target Agent match the service type and attribute indicated by the service capability requirement, respectively, and the indicator deviation corresponding to the target Agent is the smallest among the candidate Agents; The indicator deviation is obtained by weighted summing the first indicator difference and the second indicator difference, wherein the first indicator difference is calculated based on the actual performance of the target Agent and the performance indicator; The second index difference is calculated based on the distance between the target agent and the source agent and the distance index.

6. The method according to claim 1, characterized in that The method further comprises: Broadcast blockchain access request to obtain the blockchain access interface; Sending node registration information through the access interface of the blockchain, so that the blockchain updates the node information list based on the node registration information; The node registration information includes at least one of the following: Agent identification, communication address, communication authority, and function description information.

7. A multi-agent collaborative communication system based on blockchain, characterized in that: The multi-agent collaborative communication system based on blockchain includes: a source agent, a target agent and a blockchain; The source Agent is used to send a communication request to the blockchain, wherein the communication request includes index information of the target Agent; The blockchain is used to retrieve the node information list based on the index information to obtain the communication address of the target Agent, and return first response information to the source Agent, where the first response information includes the communication address of the target Agent; The source Agent is further configured to send a connection establishment request to the target Agent via the communication address; The target Agent is used to return second response information to the source Agent and establish trusted communication with the source Agent.

8. A multi-agent collaborative communication device based on blockchain, characterized in that: Applied to the source Agent, the device comprises: A sending module, used to send a communication request to the blockchain, wherein the communication request includes index information of the target Agent; A receiving module, configured to obtain first response information returned by the blockchain, wherein the first response information includes a communication address of the target Agent, and the communication address is obtained by the blockchain by retrieving a node information list based on the index information; The communication module is used to establish trusted communication with the target Agent through the communication address.

9. A multi-agent collaborative communication device based on blockchain, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the blockchain-based multi-agent collaborative communication device to implement the blockchain-based multi-agent collaborative communication method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the blockchain-based multi-agent collaborative communication method described in any one of claims 1 to 6.

Images