Multi-agent cooperation system and method capable of realizing cross-domain mutual trust

Abstract

The invention relates to a multi-agent cooperation system and method capable of realizing cross-domain mutual trust, and the system comprises a cross-domain mutual trust decentralized agent identity identification and verification system which is used for constructing an agent identity identification based on the decentralized identity of an agent and migrating the identity of the agent to the decentralized identity; the agent interaction information evidence storage system is used for performing hash anchoring on the data file of the agent, establishing a cross-agent task execution state consensus and generating interaction information evidence storage data of the agent; and the multi-agent cooperative task execution and dynamic access control system is used for executing interactive cooperation of task execution process control, dynamic access authority control and agent state management maintenance of multiple agents according to the task execution contract, the access control contract and the agent management contract. Therefore, the problems that cross-enterprise and cross-domain agent identity mutual trust cannot be established in the prior art, and serious limitation exists in the security and credibility level of the system are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-agent collaboration, and particularly relates to a multi-agent collaboration system and method capable of cross-domain mutual trust. BACKGROUND

[0002] Under the driving of large language models (LLMs), AI-based agents (i.e., software entities or systems integrated with AI technology, having autonomous decision-making, environment perception, goal-driven, and interactive capabilities) are accelerating the penetration of end-side user applications and enterprise-side production and service pipelines. Among them, the emergence of Agent-to-Agent (A2A) interaction protocols makes it possible to achieve complex task orchestration and execution based on multi-agent collaboration, driving the comprehensive automation of information collection and processing processes of agents and improving the efficiency of enterprise production and supply chains. However, the existing multi-agent collaboration protocol (such as Google A2A) is limited to the design of communication message specifications between agents (such as agent discovery mechanisms, agent capability description specifications, and message fragmentation specifications), and the security measures rely on traditional centralized identity authentication, HTTPS-based channel security, and other means. There is no (i) cross-enterprise unified agent identity identification and identity verification mechanism, (ii) tamper-proof evidence capability for multi-agent interaction processes and data, and (iii) context-based dynamic access control capability. There are serious trust and security bottlenecks, and the multi-agent framework is greatly limited in the application process of landing deployment.

[0003] In academia and industry, the most advanced multi-agent collaboration protocols and frameworks include: Google A2A: In 2025, Google proposed the Agent2Agent (A2A) protocol, which aims to enable communication and interoperability between AI-based agents developed by different frameworks, languages, or vendors. It supports agent capability discovery, interaction mode negotiation, collaboration task management, and secure information exchange. A2A protocol proposes standardized multi-agent collaboration concepts such as A2A client (requesting agent), A2A server (service-exposing agent), agent capability description card (Agent Card), agent message (Message), agent task (Task), message fragment (Part), and data fragment (Artifact). It also designs a JSON-RPC-based agent communication message specification. In addition, A2A protocol designs a streaming processing (SSE) mechanism and task execution result push notification mechanism for large-scale agent tasks. In terms of security measures, A2A relies on the TLS protocol to implement mutual authentication between agents, and developers can implement resource access authorization based on traditional mechanisms such as OAuth. The shortcomings of Google A2A protocol are: (1) Although the agent capability description card mechanism is proposed to define agent identity and capability, there is no standardized agent identity identification mechanism. Different companies and institutions still use customized and non-uniform agent identity identification methods, making it difficult to achieve cross-institutional agent identity trust; (2) Channel protection relying on TLS can only achieve mutual trust between message senders and receivers, but cannot achieve long-term tamper-proof agent interaction data evidence. In the event of agent system failure, it is difficult to locate the source of the failure and determine the relevant agent's rights and responsibilities; (3) The protocol itself does not provide specifications for resource authorization and access control security mechanisms. In actual multi-agent system development, the implementation of resource security mechanisms is determined by the developer, which further challenges multi-agent collaboration between different vendors and institutions, as inconsistent resource security mechanisms between different institutions make it difficult to interface and align.

[0004] ANP: Agent Network Protocol, is a multi-agent collaboration protocol that attempts to apply decentralized identity (DID) to agent identity in the early stage. This protocol builds a set of agent communication specifications based on DID, similar to Google A2A, and also supports agent identity description, agent discovery and encrypted communication. However, ANP does not provide a secure migration mechanism for converting traditional vendor-specific agent identity to DID. DID is completely independent of other agent identity identification solutions, so it is difficult to promote its use. In addition, ANP does not store evidence based on DID for agent interaction related data. DID is only used as an agent identity identifier, and no association is established between the agent and the related task and data. Therefore, DID cannot play a role in automatic resource circulation and realize traceable interaction history query. At the same time, ANP also lacks resource authorization and access control mechanisms.

[0005] Large language model agent development framework / SDK, such as CAMEL, LangGraph: This kind of framework / SDK focuses on building a large language model centered agent task execution flow, and designs a series of multi-agent collaboration mechanisms, for example: Supervisor-based architecture is managed by a supervisor agent that manages other agents with different capabilities. The supervisor agent distributes different tasks to specific agents and collects the execution results of each agent. Network / Graph-based architecture builds a specific agent network based on complex task requirements. Agents communicate and write based on this network topology to complete complex task execution. Although there is no standardized description of inter-agent communication protocols, this kind of framework defines the format of agent communication messages through SDK code. The problem is that different frameworks use completely different message formats, and the agents developed by each framework cannot interconnect and collaborate, severely limiting their range of use. In addition, this kind of framework also lacks a mechanism for storing evidence of agent interaction history, making it impossible to audit the interaction history, and the real-world feasibility is poor. Its security capabilities depend on system prompt word engineering or human intervention, and its scalability and robustness are poor, making it vulnerable to emerging malicious prompt word injection attacks.

[0006] In summary, although a series of protocols and development frameworks for AI-driven multi-agent collaboration have emerged in the industry and academia in recent years, existing frameworks focus on designing communication message specifications, multi-agent collaboration modes and architectures, and security mechanisms rely on traditional TLS, prompt engineering and other methods. However, in the face of highly automated and large-scale interactions of agent ecology, and massive resource access requirements, existing technical solutions cannot establish cross-enterprise and cross-domain agent identity trust, lack tamper-proof evidence of agent interaction history (cannot support judicial audit requirements), and lack dynamic authorization and access control mechanism design, which has serious limitations in system security and trust level. SUMMARY

[0007] The present application provides a multi-agent collaboration system and method that can cross-domain mutual trust to solve the problems that existing technical solutions cannot establish cross-enterprise and cross-domain agent identity trust, lack tamper-proof evidence of agent interaction history (cannot support judicial audit requirements), and lack dynamic authorization and access control mechanism design, which has serious limitations in system security and trust level.

[0008] The first aspect embodiment of the present application provides a multi-agent collaboration system that can cross-domain mutual trust, comprising: a cross-domain mutual trust decentralized agent identity identification and verification system, configured to construct an agent identity identification that meets a preset condition based on a decentralized identity of an agent, and build a target verification mechanism of the decentralized identity according to the agent identity identification, so as to migrate the identity of the agent to the decentralized identity by using the target verification mechanism, and generate an identity compatibility result of the agent; an agent interaction information evidence system, configured to hash anchor a data file of the agent based on the identity compatibility result, the decentralized identity and a distributed ledger, so as to establish a task execution state consensus across agents, and generate interaction information evidence data of the agent according to the task execution state consensus; a multi-agent collaboration task execution and dynamic access control system, configured to execute multi-agent task execution process control, dynamic access permission control and interaction collaboration of agent state management and maintenance based on the interaction information evidence data, a task execution contract, an access control contract and an agent management contract.

[0009] Optionally, in an embodiment of the present application, the cross-domain trust decentralized agent identity and verification system comprises: an agent identity registration module, configured to register a decentralized identity of the agent and a decentralized identity document bound to the decentralized identity; an agent message verification module, configured to generate a message verification result of the decentralized identity based on a message signature of the decentralized identity, the decentralized identity document and the target verification mechanism; an agent identity cross-domain module, configured to generate identity verification information of the agent according to cross-chain interoperability of the agent based on the message verification result; and an agent identity migration module, configured to migrate the identity of the agent to the decentralized identity based on the identity verification information to generate the identity compatibility result.

[0010] Optionally, in an embodiment of the present application, the agent identity registration module comprises: an initialization unit, configured to initialize the agent to generate a private key and a public key of the agent; a generation unit, configured to determine the decentralized identity by using a decentralized identity controller based on the private key and the public key of the agent; a construction unit, configured to construct the decentralized identity document bound to the decentralized identity; a request unit, configured to submit a hash value of the decentralized identity and the decentralized identity document to a decentralized identity storage smart contract on a block chain; and a verification unit, configured to verify whether the decentralized identity satisfies a preset legal condition based on the decentralized identity storage smart contract to generate a verification result of the agent.

[0011] Optionally, in an embodiment of the present application, the agent interaction information notarization system comprises: a task initialization module, configured to respectively implement on-chain anchoring and off-chain notarization on metadata and participant information of a task to generate an initialized task; a task state transition verification module, configured to use common signature of the multiple agents to confirm state transition information of the initialized task; a data anchoring module, configured to establish a binding relationship between off-chain storage and on-chain hash value of the data file based on the state transition information; and an off-chain trusted data access module, configured to collect a data source satisfying a preset reliable condition in the multi-agent cooperation based on the binding relationship to perform on-chain notarization on data to generate interaction information notarization data of the agent.

[0012] Optionally, in an embodiment of the present application, the data anchoring module comprises: a packaging unit configured to off-chain package the data file to generate encrypted data of the data file; a calculation unit configured to calculate a hash value of the data file based on the encrypted data; a storage unit configured to off-chain store the data file in a trusted manner to generate a file identifier of the data file; and a verification unit configured to upload the hash value of the data file, the file identifier, a timestamp and a file version to an on-chain smart contract of the agent to verify the data file.

[0013] Optionally, in an embodiment of the present application, the multi-agent collaborative task execution and dynamic access control system comprises: an agent resource access control module configured to define an access policy in the multi-agent interaction by using the access control contract, and to generate an access result by restricting identity, capability and access context information of an access subject according to the access policy; an interaction logic execution module configured to define a finite state machine of a task meeting a preset complex condition by using an interaction logic contract based on the access result, and to restrict a state transition rule according to the task finite state machine; and an agent governance module configured to maintain capability and state of the agent on-chain based on the state transition rule, to query a current state of the agent, and to supervise the agent according to the current state.

[0014] Optionally, in an embodiment of the present application, the agent resource access control module comprises: an access request unit configured to send an access request to the access control contract; a policy extraction unit configured to extract an access policy corresponding to a resource based on the access request; a policy evaluation unit configured to perform policy evaluation based on the access policy, a decentralized identity of the agent, a decentralized identity document and context information, to generate an evaluated policy, and to determine whether the evaluated policy meets a preset passing condition; a token generation unit configured to generate an access token of the agent in a case where the evaluated policy meets the preset passing condition; an access verification unit configured to request a target resource by using the token to verify whether the token meets a preset authenticity condition, and to determine whether the agent is allowed to access in a case where the token meets the preset authenticity condition; and an access confirmation unit configured to generate the access result in a case where the agent is allowed to access.

[0015] The second aspect embodiment of the application provides a multi-agent collaboration method capable of cross-domain mutual trust, comprising the following steps: based on the decentralized identity of the agent, constructing an agent identity identifier meeting a preset condition, and building a target verification mechanism of the decentralized identity according to the agent identity identifier, so as to migrate the identity of the agent to the decentralized identity by using the target verification mechanism, and generate an identity compatibility result of the agent; based on the identity compatibility result, the decentralized identity and the distributed ledger, hash anchoring the data file of the agent to establish a task execution state consensus across agents, and generating interaction information evidence data of the agent according to the task execution state consensus; based on the interaction information evidence data, according to the task execution contract, the access control contract and the agent management contract, performing the interactive cooperation of multi-agent task execution process control, dynamic access permission control and agent state management maintenance.

[0016] Optionally, in an embodiment of the application, the construction of the agent identity identifier meeting the preset condition and the building of the target verification mechanism of the decentralized identity according to the agent identity identifier to migrate the identity of the agent to the decentralized identity by using the target verification mechanism to generate the identity compatibility result of the agent comprises: registering the decentralized identity of the agent and the decentralized identity document bound with the decentralized identity; based on the message signature of the decentralized identity, the decentralized identity document and the target verification mechanism, generating a message verification result of the decentralized identity; based on the message verification result, generating identity verification information of the agent according to cross-chain interoperability of the agent; based on the identity verification information, migrating the identity of the agent to the decentralized identity to generate the identity compatibility result.

[0017] Optionally, in an embodiment of the application, the registration of the decentralized identity of the agent and the decentralized identity document bound with the decentralized identity comprises: initializing the agent to generate a private key and a public key of the agent; based on the private key and the public key of the agent, determining the decentralized identity by using a decentralized identity controller; constructing the decentralized identity document bound with the decentralized identity; submitting the hash value of the decentralized identity and the decentralized identity document to a decentralized identity storage smart contract on a block chain; based on the decentralized identity storage smart contract, verifying whether the decentralized identity meets a preset legal condition to generate a verification result of the agent.

[0018] Optionally, in an embodiment of the present application, based on the identity compatibility result, the decentralized identity and the distributed ledger, the data file of the agent is hash anchored to establish a cross-agent task execution state consensus, and the interaction information evidence data of the agent is generated according to the task execution state consensus, including: respectively implementing on-chain anchoring and off-chain evidence storage on the metadata and participant information of the task to generate an initialized task; using the multi-agent to jointly sign to confirm the state transition information of the initialized task; based on the state transition information, establishing a binding relationship between the off-chain storage of the data file and the on-chain hash value; based on the binding relationship, collecting data sources that meet the preset reliable conditions in the multi-agent cooperation to perform on-chain evidence storage on the data to generate the interaction information evidence data of the agent.

[0019] Optionally, in an embodiment of the present application, based on the state transition information, the binding relationship between the off-chain storage of the data file and the on-chain hash value is established, including: off-chain encapsulating the data file to generate encrypted data of the data file; based on the encrypted data, calculating the hash value of the data file; off-chain storing the data file in a trusted manner to generate a file identifier of the data file; uploading the hash value of the data file, the file identifier, a timestamp and a file version to the on-chain smart contract of the agent to verify the data file.

[0020] Optionally, in an embodiment of the present application, based on the interaction information evidence data, the task execution flow control, dynamic access control and agent state management maintenance of the multi-agent are executed according to the task execution contract, the access control contract and the agent management contract, including: using the access control contract to define the access strategy in the multi-agent interaction, and generating an access result according to the identity, ability and access context information of the access person and the access strategy; based on the access result, using the interaction logic contract to define a finite state machine of the task that meets the preset complex condition, and according to the state transition rule of the task finite state machine; based on the state transition rule, maintaining the ability and state of the agent on the chain to query the current state of the agent, and supervising the agent according to the current state.

[0021] Optionally, in an embodiment of the present application, the access strategy in the multi-agent interaction is defined by the access control contract, and the identity, capability and access context information of the access are restricted according to the access strategy to generate an access result, including: sending an access request to the access control contract; extracting an access strategy corresponding to the resource based on the access request; performing policy evaluation based on the access strategy, the decentralized identity of the agent, the decentralized identity document and the context information, generating an evaluated policy, and determining whether the evaluated policy meets a preset pass condition; in the case that the evaluated policy meets the preset pass condition, generating an access token of the agent; requesting a target resource by using the token to verify whether the token meets a preset authenticity condition, and in the case that the token meets the preset authenticity condition, determining whether the agent is allowed to access; in the case that the agent is allowed to access, generating the access result.

[0022] The third aspect embodiment of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the multi-agent cooperation method across domains and mutual trust as described in the above embodiments.

[0023] The fourth aspect embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the multi-agent cooperation method across domains and mutual trust as described above.

[0024] The embodiments of the present application can support cross-enterprise and cross-domain agent identity verification and mutual trust. Through the application of DID and blockchain cross-chain technology, the difficulty of agent interconnection and intercommunication caused by different identity schemes in the existing framework can be effectively solved. At the same time, by proposing a migration protocol from traditional identity to DID, compatibility with traditional identity is achieved, and the landability of the framework is greatly improved. The data, computing process and DID involved in agent interaction are bound and hashed and anchored to the tamper-proof ledger to ensure that the whole process data is auditable and traceable, and the trust short board of the existing scheme is systematically solved. Through the automatic configuration and execution of fine-grained access strategies by smart contracts, global unambiguous task flow state monitoring and management and agent lifecycle management are realized. Thus, the problems of the prior art that the cross-enterprise and cross-domain agent identity mutual trust cannot be established, the tamper-proof evidence of agent interaction history is lacking (which cannot support the judicial audit demand), and there is a lack of dynamic authorization and access control mechanism design, and there are serious limitations in system security and trust level are solved.

[0025] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. Attached Figure Description

[0026] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0027] Figure 1 This is a schematic diagram of the structure of a cross-domain trustworthy multi-agent cooperative system provided according to an embodiment of this application;

[0028] Figure 2 This is a schematic diagram of a trusted multi-agent cooperation framework according to an embodiment of this application;

[0029] Figure 3 This is a flowchart illustrating a cross-domain, mutually trusting multi-agent collaboration method provided according to an embodiment of this application.

[0030] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0031] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0032] A cross-domain trusted multi-agent collaboration system and method of embodiments of the present application are described below with reference to the accompanying drawings. In view of the problems in the prior art that the existing technical solutions cannot establish cross-enterprise and cross-domain agent identity trust, lack tamper-proof evidence of agent interaction history (cannot support judicial audit needs), and lack dynamic authorization and access control mechanism design, which seriously limits the system security and trust level, the present application provides a cross-domain trusted multi-agent collaboration system. In the system, the application of DID and cross-chain technology of blockchain can effectively solve the problem of difficulty in interconnection and intercommunication of agents caused by different identity identification schemes in the existing framework. At the same time, by proposing a migration protocol from traditional identity to DID, compatibility with traditional identity is achieved, greatly improving the feasibility of the framework. The data, computing process and DID involved in the interaction of the agent are bound and hashed and anchored to the tamper-proof ledger, ensuring that the whole process data is auditable and traceable, and the trust gap of the existing solution is systematically solved. Through the automatic configuration and execution of fine-grained access strategies by smart contracts, global unambiguous task flow state monitoring and management, and agent lifecycle management are realized. Thus, the problems in the prior art that the existing technical solutions cannot establish cross-enterprise and cross-domain agent identity trust, lack tamper-proof evidence of agent interaction history (cannot support judicial audit needs), and lack dynamic authorization and access control mechanism design, which seriously limits the system security and trust level, are solved.

[0033] Specifically, Figure 1 A structure diagram of a cross-domain trusted multi-agent collaboration system provided by embodiments of the present application.

[0034] As Figure 1 shown, the cross-domain trusted multi-agent collaboration system includes a cross-domain trusted decentralized agent identity identification and verification system 100, an agent interaction information evidence system 200, and a multi-agent collaboration task execution and dynamic access control system 300.

[0035] Specifically, the cross-domain trusted decentralized agent identity identification and verification system 100 is configured to construct an agent identity identification that meets a preset condition based on a decentralized identity of an agent, and to build a target verification mechanism of the decentralized identity according to the agent identity identification, so as to migrate the identity of the agent to the decentralized identity by using the target verification mechanism, and to generate an identity compatibility result of the agent.

[0036] It can be understood that the preset condition in the embodiment of the application can be a general, persistent condition; the target verification mechanism can be a DID (Decentralized Identifier) generation, circulation and verification mechanism, wherein the DID does not rely on a centralized identity authentication system, and identity self-control and security verification are realized through blockchain technology, wherein the Oracle is middleware connecting the blockchain and the external world, and is responsible for securely and reliably transmitting off-chain data to the smart contract.

[0037] In actual execution, the cross-domain trusted decentralized intelligent agent identity and verification system 100 in the embodiment of the application can construct a general, persistent intelligent agent identity based on DID, build a perfect DID generation, circulation and verification mechanism, cover intelligent agent identity registration, identity certificate issuance, A2A message authenticity verification based on certificate, etc. stages, while supporting cross-domain intelligent agent identity verification and traditional identity to DID security migration capability, so as to migrate the identity of the intelligent agent to the decentralized identity by using the target verification mechanism, and generate the identity compatibility result of the intelligent agent.

[0038] The embodiment of the application greatly enhances the interconnection and interworking capability through unified and globally verifiable intelligent agent identity, supports cross-enterprise and cross-domain intelligent agent identity verification and mutual trust, and can effectively solve the intelligent agent interconnection and interworking difficulty problem caused by different identity identification schemes in the existing framework through the application of DID and blockchain cross-chain technology. At the same time, by proposing a migration protocol from traditional identity to DID, compatibility with traditional identity is realized, and the landability of the framework is greatly improved.

[0039] It should be noted that the preset condition can be set by those skilled in the art according to actual conditions, which is not limited here.

[0040] Optionally, in an embodiment of the application, the cross-domain trusted decentralized intelligent agent identity and verification system 100 comprises: an intelligent agent identity registration module for registering a decentralized identity of an intelligent agent and a decentralized identity document bound to the decentralized identity; an intelligent agent message verification module for generating a message verification result of the decentralized identity based on message signature of the decentralized identity, the decentralized identity document and the target verification mechanism; an intelligent agent identity cross-domain module for generating intelligent agent identity verification information based on the message verification result according to cross-chain interoperability of the intelligent agent; and an intelligent agent identity migration module for migrating the identity of the intelligent agent to the decentralized identity based on the identity verification information to generate an identity compatibility result.

[0041] It can be understood that the agent identity registration module, the agent message verification module, the agent identity cross-domain module and the agent identity migration module in the embodiments of the present application correspond to the agent identity registration protocol, the agent message verification protocol, the agent identity cross-domain protocol and the traditional agent identity migration protocol, etc.

[0042] Specifically, the protocol description and protocol flow of each protocol in the embodiments of the present application are as follows:

[0043] I. Agent identity registration protocol: the protocol generates a unique identity identifier for the agent, i.e., a decentralized identity (DID), and a DID document bound to the identity identifier, which describes relevant information in the document, and the document hash value and the DID are bound by on-chain storage of the blockchain.

[0044] II. Agent message verification protocol: the protocol provides a message signature and verification mechanism based on DID, generates a message verification result of the decentralized identity, and realizes DID-driven message authenticity guarantee:

[0045] (1) Message signature: the agent A signs its own message m with the private key sk corresponding to the DID to obtain σ, and sends the message and the signature to the agent B;

[0046] (2) Public key extraction: the agent B queries the DID storage smart contract based on the DID of the agent A, wherein the smart contract (Smart Contract) can be an automated protocol stored on the blockchain, which automatically executes the contract terms when the preset conditions are met, obtains H(D), and at the same time, accesses the off-chain storage to extract the DID document, and verifies the consistency of the two to determine the authenticity of the DID document, and at the same time extracts the public key pk of the agent A stored in the document;

[0047] (3) Message verification: the agent B verifies the authenticity of the message m based on the signature σ and pk.

[0048] III. Agent identity cross-domain protocol: when two agents register DID through different blockchains, the protocol realizes identity verification between the two agents through cross-chain interoperation, generates identity verification information of the agent, and thus realizes identity cross-domain. In the following protocol description, it is assumed that the current target is to cross-chain the identity of the agent A in the chain X to the chain Y for verification by the agent B in the chain Y:

[0049] (1) Request identity cross-chain: the agent A submits an identity cross-chain request to the cross-chain bridge, and the request includes DID A and H(D A );

[0050] (2) Identity verification: the cross-chain bridge verifies DID A and H(DA ) is true, go to the next step;

[0051] (3) Trust Anchor Contract Update: Cross-chain bridge updates the Trust Anchor smart contract in chain Y, and stores the DID in DID A and H(D A ) and related information (such as the identifier of the source chain X) to show that the DID information has been verified;

[0052] (4) DID Document Transmission: Agent A transmits the DID A to agent B off-chain;

[0053] (5) Authenticity Verification: Agent B verifies whether the DID A and H(D A ) are in the Trust Anchor contract to determine the authenticity of the identity of agent A.

[0054] Four, traditional agent identity migration protocol: The goal of this protocol is to safely migrate the legal traditional identity of an agent (such as an agent from Google with an identity provided by Google) to a DID, thereby realizing the compatibility of the framework with traditional identity agents and generating an identity compatibility result:

[0055] (1) Request for Traditional Identity Migration: Agent A or its identity manager submits a request for identity migration to the Migration Committee (a node in the blockchain), which contains (DID, DID document, traditional identity identifier, traditional identity source platform information) and is mediated by an Oracle service (i.e., a trusted data source service of the blockchain);

[0056] (2) Traditional Identity Verification: Oracle verifies the authenticity of the traditional identity of agent A based on the traditional identity source platform certificate, and if it is true, Oracle signs the traditional identity and transmits it to the Migration Committee;

[0057] (3) Identity Binding and Certificate Issuance: Migration Committee verifies the Oracle signature, and if it is verified, Migration Committee records the binding relationship of (DID, DID document, traditional identity identifier) on the chain, and issues a Master certificate to agent A, which contains (DID, DID document, traditional identity identifier, Migration Committee information, signature, timestamp);

[0058] (4) Context-specific certificate generation: The Migration Committee can issue a context-specific certificate bound to the Master certificate to partially disclose the information related to the Master certificate, protecting the privacy of the agent A.

[0059] Optionally, in an embodiment of the present application, the agent identity registration module comprises: an initialization unit configured to initialize the agent to generate a private key and a public key of the agent; a generation unit configured to determine a decentralized identity based on the private key and the public key of the agent by using a decentralized identity controller; a construction unit configured to construct a decentralized identity document bound to the decentralized identity; a request unit configured to submit the decentralized identity and a hash value of the decentralized identity document to a decentralized identity storage smart contract on a block chain; and a verification unit configured to verify, based on the decentralized identity storage smart contract, whether the decentralized identity satisfies a preset legal condition, and generate a verification result of the agent.

[0060] Specifically, the agent identity registration protocol in the embodiment of the present application comprises:

[0061] (1) Initialization: the agent generates a pair of private key (sk) and public key (pk) ;

[0062] (2) DID generation: the agent generates a legal DID through a DID controller as its identifier;

[0063] (3) DID document generation: the agent constructs its own DID document D through the DID controller, wherein the DID document D contains DID, public key pk, service point (for example, domain name + port), agent capability (for example, code generation), verification method, and other metadata; the DID document is stored in an off-chain IPFS or a centralized database;

[0064] (4) Request chain anchoring: the agent initiates a session to a DID storage smart contract (DID Registry SmartContract) on the block chain, and submits its DID and H(D) (i.e. DID document hash value) ;

[0065] (5) Smart contract verification: the DID storage smart contract verifies the legality of the DID, and if the DID is legal, the DID and H(D) successfully establish a chain binding relationship.

[0066] The agent interaction information evidence system 200 is used for hashing anchoring the data file of the agent based on the identity compatibility result, the decentralized identity and the distributed ledger, to establish the task execution state consensus across the agents, and to generate the interaction information evidence data of the agent according to the task execution state consensus.

[0067] It can be understood that the intelligent agent interaction information evidence system 200 in the embodiment of the present application can be an anti-tampering and traceable intelligent agent interaction information evidence system.

[0068] In actual execution, the intelligent agent interaction information evidence system 200 in the embodiment of the present application can realize the hash anchoring of important data files and important multi-party interaction milestone events through DID and distributed ledger, prevent tampering and denial of interaction history by related intelligent agents, further effectively establish cross-intelligent agent task execution state consensus in combination with a multi-party signature mechanism, and generate intelligent agent interaction information evidence data according to the task execution state consensus, effectively clarifying the rights and responsibilities of each party in intelligent agent cooperation.

[0069] The embodiment of the present application can perform judicial-level intelligent agent interaction history evidence, greatly improve the credibility, bind the data, calculation process and DID involved in intelligent agent interaction, and hash anchor to the anti-tampering ledger, ensuring that the whole process data is auditable and traceable, and systematically solving the trust short board of the existing scheme.

[0070] Optionally, in an embodiment of the present application, the intelligent agent interaction information evidence system 200 comprises: a task initialization module configured to implement on-chain anchoring and off-chain evidence of metadata and participant information of a task respectively to generate an initialized task; a task state transition verification module configured to utilize multi-agent common signature to confirm state transition information of the initialized task; a data anchoring module configured to establish a binding relationship between off-chain storage and on-chain hash value of data files based on the state transition information; and an off-chain trusted data access module configured to collect data sources meeting a preset reliable condition in multi-agent cooperation based on the binding relationship to perform on-chain evidence of the data and generate intelligent agent interaction information evidence data.

[0071] It can be understood that the task initialization module, the task state transition verification module, the data anchoring module and the off-chain trusted data access module in the embodiment of the present application correspond to a task initialization protocol, a task state transition verification protocol, a data anchoring protocol and an off-chain trusted data access protocol respectively; and the data source meeting the preset reliable condition can be a reliable and authoritative data source.

[0072] Specifically, the function description and flow description of each protocol in the embodiment of the present application are as follows:

[0073] I. Task initialization protocol: the goal of the protocol is for the initiator (intelligent agent) of multi-agent cooperation task to perform on-chain anchoring and off-chain evidence of metadata and participant information of a task to generate an initialized task.

[0074] (1) The initiator agent collects task-related metadata off-chain, including the task initiator agent DID, task participant agent DID, detailed task description, and deadline timestamp;

[0075] (2) Metadata hash calculation: the task initiator agent concatenates the above metadata to calculate the task metadata hash value H task ;

[0076] (3) On-chain anchoring: the task initiator submits H task to the on-chain smart contract, and records the task status as "Initiated";

[0077] (4) Off-chain storage: the complete task metadata is saved through off-chain storage (IPFS or centralized database);

[0078] (5) Confirmation: the on-chain smart contract and off-chain storage return a prompt indicating that the task initialization is successful.

[0079] II. Task state transition verification protocol: In this framework, to prevent malicious agents from pushing false task state transition information and interfering with the multi-agent collaboration process, the framework requires multiple agents to jointly sign and confirm task state transitions, confirm state transition information, and effectively resist malicious agents while clearly defining agent task responsibilities.

[0080] (1) Multi-agent signature: relevant agents sign the latest task milestone (indicating task state transition) with BLS signature;

[0081] (2) Signature aggregation: an aggregator (which can be one of the multiple agents) aggregates the BLS signatures of each agent to obtain Σ;

[0082] (3) State transition information on-chain: the aggregator uploads the task hash H task , aggregated signature Σ, milestone event name, and relevant participant DID to the on-chain smart contract;

[0083] (4) State transition verification: the smart contract extracts the public key corresponding to the task-related participant DID through Oracle and verifies the BLS signature;

[0084] (5) Task status update: if the verification in the previous step is successful, the smart contract updates the task status recorded on the chain and marks it as "Verified".

[0085] III. Data anchoring protocol: The goal of this protocol is to establish a binding relationship between off-chain storage of large data files and on-chain hash values to achieve long-term data tamper resistance.

[0086] Four, off-chain trusted data access protocol: to ensure that the data collected by participating multi-agent collaboration is from reliable and authoritative data sources, and to ensure the long-term tamper-proofing of reliable data, the trusted data access protocol realizes off-chain trusted data access based on distributed trusted Oracle, and further stores the data on-chain.

[0087] (1) Identity verification and key exchange: the agent requesting access to data, Oracle and authoritative data source jointly perform three-party TLS handshake protocol, where the former two are TLS clients and the latter is a TLS server, to establish a session key;

[0088] (2) Secure data request: the agent and the Oracle construct an encrypted data request based on two-party secure computation (where the agent has data access rights);

[0089] (3) Data response and decryption: the authoritative data source server responds to the request and returns the encrypted data, and the agent and the Oracle jointly decrypt the data and verify the data integrity through MAC;

[0090] (4) Data hash on-chain: the Oracle uses the data anchoring protocol to store the data hash on-chain to realize long-term tamper-proofing of the data.

[0091] Optionally, in an embodiment of the present application, the data anchoring module comprises: an encapsulation unit configured to encapsulate a data file off-chain to generate encrypted data of the data file; a calculation unit configured to calculate a hash value of the data file based on the encrypted data; a storage unit configured to store the data file off-chain to generate a file identifier of the data file; and a verification unit configured to upload the hash value, the file identifier, a timestamp and a file version of the data file to an on-chain smart contract of an agent to verify the data file.

[0092] In the embodiment of the present application, the data anchoring module comprises:

[0093] (1) Off-chain data preparation: the agent encapsulates a data file to be sealed off-chain, and performs necessary data operations such as encryption to generate encrypted data of the data file;

[0094] (2) Hash generation: the agent calculates a hash value of the data file based on the SHA-256 algorithm;

[0095] (3) Off-chain complete data storage: the agent stores the complete data file to an off-chain trusted storage such as IPFS to obtain a unique file identifier CID;

[0096] (4) Hash on-chain: the agent uploads the file hash value H, the file identifier CID, the timestamp and the file version to an on-chain smart contract, and thereafter a file visitor can verify the file integrity in combination with the on-chain hash value.

[0097] The multi-agent collaborative task execution and dynamic access control system 300 is used for storing data based on interaction information, performing task execution flow control, dynamic access permission control and agent state management maintenance of multi-agents according to a task execution contract, an access control contract and an agent management contract.

[0098] It can be understood that the multi-agent collaborative task execution and dynamic access control system 300 in the embodiments of the present application can be an automated multi-agent collaborative task execution and dynamic access control system.

[0099] In actual execution, the multi-agent collaborative task execution and dynamic access control system 300 in the embodiments of the present application stores data based on interaction information, and through the design of smart contracts such as a task execution contract, an access control contract and an agent management contract and corresponding interaction protocols, strict and automated task flow control and resource access control, enhanced security, automatic configuration and execution of fine-grained access strategies through smart contracts, task flow state monitoring and management, agent lifecycle management, global unambiguous, automated multi-agent task execution flow control, context-aware dynamic access permission control and agent state management maintenance are achieved.

[0100] The embodiments of the present application can propose a multi-agent collaboration framework with trusted identity, traceable interaction and secure resources, named BlockA2A, to solve the short board of existing multi-agent collaboration protocols and frameworks in cross-domain identity mutual trust, interaction history storage and dynamic resource access permission control, and provide a bottom trust foundation for large-scale, cross-enterprise autonomous and secure agent collaboration. By organically combining and using technical components such as decentralized identity, distributed ledger and smart contract, BlockA2A comprehensively covers the security of the identity layer, the interaction layer and the execution layer of multi-agent collaboration. The specific implementation scheme of the multi-agent collaboration framework BlockA2A is shown in Figure 2 The protocol flow design of the multi-agent collaboration framework in the agent identity layer, the interaction layer and the execution layer is introduced.

[0101] Optionally, in an embodiment of the present application, the multi-agent collaborative task execution and dynamic access control system 300 comprises: an agent resource access control module, configured to define an access policy in multi-agent interaction by means of an access control contract, and to generate an access result by constraining the identity, capability and access context information of an accesser according to the access policy; an interaction logic execution module, configured to define a finite state machine of a task meeting a preset complex condition by means of an interaction logic contract based on the access result, and to constrain a state transition rule according to the task finite state machine; and an agent governance module, configured to maintain the capability and state of the agent on a chain based on the state transition rule, to query the current state of the agent, and to supervise the agent according to the current state.

[0102] It can be understood that the agent resource access control module, the interaction logic execution module and the agent governance module in the embodiments of the present application correspond to an agent resource access control protocol, an interaction logic execution protocol and an agent governance protocol respectively.

[0103] In actual execution, the protocol description and protocol flow of each protocol in the embodiments of the present application are as follows:

[0104] I. Agent resource access control protocol: the core of the protocol is an ACC (Access Control Contract), which defines an access policy for a certain resource involved in multi-agent interaction through an access control contract, and the access policy constrains the identity, capability and access context information of an accesser. The access control contract is responsible for policy evaluation (i.e. judging whether the current access is allowed), access token issuance and token verification, and generates an access result.

[0105] II. Interaction logic execution protocol: the core of the protocol is an interaction logic contract (ILC), which defines a finite state machine of a complex task and constrains the state transition rule through the definition of a state transition guard. The interaction logic execution protocol relies on the ILC for automatic task execution and task state management:

[0106] (1) ILC initialization and deployment: a task-related agent (or a task administrator) formulates an ILC, which defines a task finite state set, an initial state through a member variable, and a state transition guard through a member function, to constrain the state transition condition, and the ILC is deployed to a blockchain;

[0107] (2) Task state transition verification: the precondition of task state transition is consistent with the foregoing task state transition verification protocol, and is implemented through off-chain multi-party signature generation and on-chain signature verification. In addition, the evaluation of the state transition guard condition is added to constrain the time and context conditions of state transition.

[0108] (3) Task status update and notification: if the task state transition verification is passed, the ILC updates the task state and generates an on-chain event to notify the relevant agents;

[0109] (4) Task execution history storage: the task execution history is stored on the chain in relation to the ILC deployment and the task state transition related on-chain transaction, which can be tamper-proof for a long time.

[0110] III. Agent governance protocol: this protocol takes the agent DID as the core to maintain the on-chain ability and state of the agent, and supports the relevant parties in multi-agent collaboration to query the current state of a specific agent. The goal is to effectively regulate the agent:

[0111] (1) Registration: the agent registers its identity through the agent identity registration protocol, and the identity information (DID, ) is synchronized to the corresponding agent governance protocol. The initial state is "Active";

[0112] (2) Capability update: the agent manager (through the smart contract require syntax constraint) can update the agent's ability, which is presented to the DID document and synchronized to the on-chain storage;

[0113] (3) DID revocation: when the agent is detected as malicious or high-risk, the agent state is set to "Revoked", and an event is generated to notify all relevant parties;

[0114] (4) DID retrieval: supports retrieval based on DID.

[0115] Optionally, in an embodiment of the present application, the agent resource access control module includes: an access request unit configured to send an access request to an access control contract; a policy extraction unit configured to extract an access policy corresponding to a resource based on the access request; a policy evaluation unit configured to perform policy evaluation based on the access policy, a decentralized identity of the agent, a decentralized identity document, and context information, generate an evaluated policy, and determine whether the evaluated policy meets a preset passing condition; a token generation unit configured to generate an access token of the agent if the evaluated policy meets the preset passing condition; an access verification unit configured to request a target resource using the token to verify whether the token meets a preset authenticity condition, and determine whether the agent is allowed to access if the token meets the preset authenticity condition; and an access confirmation unit configured to generate an access result if the agent is allowed to access.

[0116] In the embodiments of the present application, the agent resource access control module can include:

[0117] (1) Access request: Agent A as an access requester sends an access request to the ACC, with its DID, the action needed to be performed on the resource, and the identifier of the target resource;

[0118] (2) Policy extraction: The ACC extracts the access policy corresponding to the resource based on the request;

[0119] (3) Policy evaluation: The ACC performs policy evaluation based on the DID of the agent, the DID document (which can be obtained through an Oracle), and the context information, to determine whether an access token can be generated;

[0120] (4) Token generation: If the policy evaluation is passed, an access token is generated, which indicates the DID of the access requester, the resource identifier, the resource operation, and the token expiration time. The token is uniquely identified by random characters and is stored on the chain, and is fed back to the agent A;

[0121] (5) Resource access and verification based on the token: Agent A requests the target resource based on the token, and the manager of the target resource can verify the token authenticity through the verification function of the ACC to determine whether to allow access;

[0122] (6) Access confirmation: The manager of the target resource feeds back the access result to the agent A.

[0123] According to the multi-agent collaboration system with cross-domain mutual trust proposed in the embodiments of the present application, through the application of DID and cross-chain technology of the blockchain, the interconnection and intercommunication difficulties of agents caused by different identity identification schemes in the existing framework can be effectively solved. At the same time, by proposing a migration protocol from traditional identity to DID, compatibility with traditional identity is achieved, greatly improving the landability of the framework. The data, computing process and DID involved in the interaction of the agent are bound and hashed and anchored to the tamper-proof ledger, ensuring that the whole process data is auditable and traceable, and the trust short board of the existing scheme is systematically solved. Through the automatic configuration and execution of fine-grained access policies by smart contracts, global unambiguous task flow state monitoring and management and agent lifecycle management are realized. Thus, the problems of the prior art that the agent identity mutual trust cannot be established across enterprises and across domains, the tamper-proof evidence of the agent interaction history is lacking (which cannot support the judicial audit demand), and there is a lack of dynamic authorization and access control mechanism design, which seriously limits the system security and credibility.

[0124] Next, the method for multi-agent collaboration with cross-domain mutual trust according to the embodiments of the present application is described with reference to the accompanying drawings.

[0125] Figure 3FIG. 1 is a flowchart of a cross-domain trustable multi-agent collaboration method according to an embodiment of the present application.

[0126] As shown in FIG. 1, the cross-domain trustable multi-agent collaboration method includes the following steps: Figure 3

[0127] In step S301, based on the decentralized identity of the agent, an agent identity satisfying a preset condition is constructed, and a target verification mechanism of the decentralized identity is built according to the agent identity, so as to migrate the identity of the agent to the decentralized identity by using the target verification mechanism, to generate an identity compatibility result of the agent.

[0128] In step S302, based on the identity compatibility result, the decentralized identity and the distributed ledger, the data file of the agent is hash anchored to establish a cross-agent task execution state consensus, and the interaction information evidence data of the agent is generated according to the task execution state consensus.

[0129] In step S303, based on the interaction information evidence data, the task execution flow control, dynamic access control and interaction collaboration of the agent state management and maintenance of the multi-agent are executed according to the task execution contract, the access control contract and the agent management contract.

[0130] Optionally, in an embodiment of the present application, the agent identity satisfying the preset condition is constructed, and the target verification mechanism of the decentralized identity is built according to the agent identity, so as to migrate the identity of the agent to the decentralized identity by using the target verification mechanism, to generate an identity compatibility result of the agent, including: registering the decentralized identity of the agent and the decentralized identity document bound with the decentralized identity; generating a message verification result of the decentralized identity based on the message signature of the decentralized identity, the decentralized identity document and the target verification mechanism; generating identity verification information of the agent according to the cross-chain interoperability of the agent based on the message verification result; migrating the identity of the agent to the decentralized identity based on the identity verification information, to generate the identity compatibility result.

[0131] Optionally, in an embodiment of the present application, the registration of the decentralized identity of the agent and the decentralized identity document bound with the decentralized identity includes: initializing the agent to generate a private key and a public key of the agent; determining the decentralized identity by using the decentralized identity controller based on the private key and the public key of the agent; constructing the decentralized identity document bound with the decentralized identity; submitting the hash value of the decentralized identity and the decentralized identity document to the decentralized identity storage smart contract on the block chain; verifying whether the decentralized identity satisfies the preset legal condition based on the decentralized identity storage smart contract, to generate a verification result of the agent.

[0132] ​Optionally, in an embodiment of the present application, based on the identity compatibility result, the decentralized identity and the distributed ledger, the data file of the hash anchor agent is anchored to establish the task execution state consensus across the agent, and the interaction information evidence data of the agent is generated according to the task execution state consensus, including: respectively implementing on-chain anchoring and off-chain evidence of metadata and participant information of the task to generate an initialized task; using multi-agent common signature to confirm the state transition information of the initialized task; based on the state transition information, establishing the binding relationship between the off-chain storage of the data file and the on-chain hash value; based on the binding relationship, collecting data sources that meet the preset reliable conditions in the multi-agent cooperation to on-chain evidence the data and generate the interaction information evidence data of the agent.

[0133] Optionally, in an embodiment of the present application, based on the state transition information, the binding relationship between the off-chain storage of the data file and the on-chain hash value is established, including: off-chain encapsulating the data file to generate encrypted data of the data file; based on the encrypted data, calculating the hash value of the data file; off-chain storing the data file in a trusted manner to generate a file identifier of the data file; uploading the hash value, the file identifier, the timestamp and the file version of the data file to the on-chain smart contract of the agent to verify the data file.

[0134] Optionally, in an embodiment of the present application, based on the interaction information evidence data, the task execution flow control, the dynamic access control and the interaction cooperation of the agent state management and maintenance of the multi-agent are executed according to the task execution contract, the access control contract and the agent management contract, including: using the access control contract to define the access strategy in the multi-agent interaction, and generating the access result according to the identity, the ability and the access context information of the visitor constrained by the access strategy; based on the access result, using the interaction logic contract to define the finite state machine of the task meeting the preset complex condition, and according to the state transition rule constrained by the task finite state machine; based on the state transition rule, on-chain maintaining the ability and the state of the agent to query the current state of the agent, and supervising the agent according to the current state.

[0135] Optionally, in an embodiment of the present application, the access control contract is used to define the access strategy in the multi-agent interaction, and the identity, capability and access context information of the access are constrained according to the access strategy, and an access result is generated, including: sending an access request to the access control contract; based on the access request, extracting the access strategy corresponding to the resource; based on the access strategy, the decentralized identity of the agent, the decentralized identity document and the context information, performing strategy evaluation to generate an evaluated strategy, and judging whether the evaluated strategy meets a preset passing condition; in the case that the evaluated strategy meets the preset passing condition, generating an access token of the agent; using the token to request a target resource to verify whether the token meets a preset authenticity condition, and in the case that the token meets the preset authenticity condition, judging whether the agent is allowed to access; in the case that the agent is allowed to access, generating an access result.

[0136] It should be noted that the foregoing explanation and description of the multi-agent collaboration system embodiment capable of cross-domain trust also apply to the multi-agent collaboration method embodiment capable of cross-domain trust, which will not be described here.

[0137] The multi-agent collaboration method capable of cross-domain trust provided by the embodiment of the present application can effectively solve the problem of difficulty in interconnection and intercommunication of agents caused by different identity identification schemes in the existing framework through the application of DID and cross-chain technology of the blockchain, and at the same time, the compatibility with the traditional identity is realized through the proposed migration protocol from the traditional identity to the DID, which greatly improves the landability of the framework; the data, calculation process and DID involved in the agent interaction are bound and hashed and anchored to the tamper-proof ledger, ensuring the data auditability and traceability of the whole process, and solving the trust short board of the existing scheme; the fine-grained access strategy is automatically configured and executed through the smart contract, and the global unambiguous task flow state monitoring and management and agent life cycle management are realized. Thus, the problem that the existing technical scheme cannot establish cross-enterprise and cross-domain agent identity trust, lacks tamper-proof evidence of agent interaction history (cannot support judicial audit demand), and lacks dynamic authorization and access control mechanism design, which has serious limitations in system security and credibility, is solved.

[0138] Figure 4 The structure schematic diagram of the electronic device provided by the embodiment of the present application is provided. The electronic device can include:

[0139] The memory 401, the processor 402 and the computer program stored in the memory 401 and executable on the processor 402.

[0140] The processor 402 implements the multi-agent collaboration method capable of cross-domain trust provided in the above embodiment when executing the program.

[0141] Further, the electronic device further includes:

[0142] The communication interface 403 is configured to communicate between the memory 401 and the processor 402.

[0143] The memory 401 is configured to store a computer program executable in the processor 402.

[0144] The memory 401 can include a high-speed RAM memory, and can further include a non-volatile memory, for example, at least one disk memory.

[0145] If the memory 401, the processor 402 and the communication interface 403 are independently implemented, the communication interface 403, the memory 401 and the processor 402 can be connected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 4 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0146] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0147] The processor 402 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0148] The embodiments also provide a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the cross-domain mutual trust multi-agent collaboration method as above.

[0149] In the description of the application, reference to "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that a particular feature, structure, material, or characteristic being described is included in at least one embodiment or example of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. In addition, the usage of "N" means at least two, for example, two, three or the like, unless explicitly stated otherwise.

[0150] Furthermore, the terms "first", "second", or the like, are used merely as a designation, and do not imply or connote relative importance or a quantity of the specified technical features. Thus, a feature defined with "first", "second" can explicitly or implicitly include at least one of the feature. In the description of the application, the meaning of "N" is at least two, for example, two, three, etc., unless explicitly specified otherwise.

[0151] Any process or method descriptions or blocks in flow charts or otherwise described herein represent embodiments which can be managed as one or more modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions or steps, and alternate implementations are possible. In some embodiments, the processes and methods described can be executed by one or more apparatuses or devices, either directly or after conversion to another language.

[0152] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0153] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0154] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0155] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0156] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A multi-agent collaboration system that can be cross-domain trusted, characterized by, The application relates to a cross-domain mutual trust decentralized intelligent agent identity and verification system, which is used for constructing an intelligent agent identity meeting preset conditions based on a decentralized identity of the intelligent agent, building a target verification mechanism of the decentralized identity according to the intelligent agent identity, and migrating the identity of the intelligent agent to the decentralized identity by using the target verification mechanism to generate an identity compatibility result of the intelligent agent. An intelligent agent interaction information notarization system is used for hashing anchoring data files of the intelligent agent based on the identity compatibility result, the decentralized identity and a distributed ledger, establishing a cross-intelligent agent task execution state consensus, and generating interaction information notarization data of the intelligent agent according to the task execution state consensus. A multi-intelligent agent cooperation task execution and dynamic access control system is used for executing multi-intelligent agent task execution process control, dynamic access permission control and intelligent agent state management and maintenance interaction cooperation according to a task execution contract, an access control contract and an intelligent agent management contract based on the interaction information notarization data. The cross-domain mutual trust decentralized intelligent agent identity and verification system comprises an intelligent agent identity registration module, an intelligent agent message verification module, an intelligent agent identity cross-domain module and an intelligent agent identity migration module. 2.The cross-domain trustable multi-agent collaboration system of claim 1, wherein, The intelligent agent identity registration module is used for registering the decentralized identity of the intelligent agent and a decentralized identity document bound with the decentralized identity. The intelligent agent message verification module is used for generating a message verification result of the decentralized identity based on message signature of the decentralized identity, the decentralized identity document and the target verification mechanism. The intelligent agent identity cross-domain module is used for generating identity verification information of the intelligent agent according to cross-chain interoperation of the intelligent agent based on the message verification result. The intelligent agent identity migration module is used for migrating the identity of the intelligent agent to the decentralized identity based on the identity verification information to generate the identity compatibility result. The intelligent agent identity registration module comprises an initialization unit, a generation unit, a construction unit, a request unit and a verification unit. 3.The cross-domain trustable multi-agent collaboration system of claim 2, wherein, The initialization unit is used for initializing the intelligent agent to generate a private key and a public key of the intelligent agent. The generation unit is used for determining the decentralized identity by using a decentralized identity controller based on the private key and the public key of the intelligent agent. The construction unit is used for constructing the decentralized identity document bound with the decentralized identity. The request unit is used for submitting hash values of the decentralized identity and the decentralized identity document to a decentralized identity storage smart contract on a blockchain. The verification unit is used for verifying whether the decentralized identity meets preset legal conditions based on the decentralized identity storage smart contract to generate a verification result of the intelligent agent. The intelligent agent interaction information notarization system comprises a task initialization module, a task state transition verification module and a data anchoring module. 4.The cross-domain trustable multi-agent collaboration system of claim 1, wherein, The task initialization module is used for respectively implementing on-chain anchoring and off-chain notarization on metadata and participant information of a task to generate an initialized task. The task state transition verification module is used for confirming state transition information of the initialized task by using common signature of the multi-intelligent agent. The data anchoring module is used for establishing a binding relationship between off-chain storage and on-chain hash values of the data files based on the state transition information. ​ A chain-offline trusted data access module is configured to collect data sources that meet preset reliable conditions in the multi-agent cooperation based on the binding relationship, to store data on a chain to generate interaction information storage data of the agent.

5. The cross-domain trustable multi-agent collaboration system of claim 4, wherein, The data anchoring module includes: An encapsulation unit is configured to encapsulate the data file off-chain to generate encrypted data of the data file; A calculation unit is configured to calculate a hash value of the data file based on the encrypted data; A storage unit is configured to store the data file off-chain to generate a file identifier of the data file; An inspection unit is configured to upload the hash value of the data file, the file identifier, a timestamp, and a file version to a smart contract on a chain of the agent to inspect the data file. 6.The cross-domain trustable multi-intelligent entity collaboration system of claim 1, wherein, The multi-agent cooperation task execution and dynamic access control system includes: An agent resource access control module is configured to define an access strategy in the multi-agent interaction by using the access control contract, to constrain identity, capability, and access context information of an access person according to the access strategy, and to generate an access result; An interaction logic execution module is configured to define a finite state machine of a task that meets a preset complex condition by using an interaction logic contract based on the access result, and to constrain a state transition rule according to the task finite state machine; An agent governance module is configured to maintain capability and state of the agent on a chain based on the state transition rule, to query a current state of the agent, and to supervise the agent according to the current state.

7. The cross-domain trustable multi-intelligent entity collaboration system according to claim 6, characterized in that, The agent resource access control module includes: An access request unit is configured to send an access request to the access control contract; A strategy extraction unit is configured to extract an access strategy corresponding to a resource based on the access request; A strategy evaluation unit is configured to perform strategy evaluation based on the access strategy, a decentralized identity of the agent, a decentralized identity document, and context information, to generate an evaluated strategy, and to determine whether the evaluated strategy meets a preset passing condition; A token generation unit is configured to generate an access token of the agent in a case where the evaluated strategy meets the preset passing condition; An access verification unit is configured to request a target resource by using the token to determine whether the token meets a preset authenticity condition, and to determine whether the agent is allowed to access in a case where the token meets the preset authenticity condition; An access confirmation unit is configured to generate the access result in a case where the agent is allowed to access.

8. A multi-agent cooperation method capable of cross-domain mutual trust, characterized in that, The method includes the following steps: An agent identity that meets a preset condition is constructed based on a decentralized identity of the agent, a target verification mechanism of the decentralized identity is built according to the agent identity, the identity of the agent is migrated to the decentralized identity by using the target verification mechanism to generate an identity compatibility result of the agent; A data file of the agent is hash anchored based on the identity compatibility result, the decentralized identity, and a distributed ledger to establish a task execution state consensus across agents, and interaction information storage data of the agent is generated according to the task execution state consensus. Based on the interaction information evidence data, according to a task execution contract, an access control contract and an agent management contract, a multi-agent task execution flow control, dynamic access permission control and agent state management maintenance are performed.

9. An electronic device, comprising: Comprise: A memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the multi-agent collaboration method across domains with mutual trust as claimed in claim 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor for implementing the multi-agent collaboration method across domains with mutual trust as claimed in claim 8.

Images