Intelligent agent construction method and system based on agentive workflow

Abstract

The invention relates to the technical field of agent construction, and discloses an agent construction method and system based on agentive workflow, and the method comprises the following steps: defining an agent core function module and distributing a unique identifier, building an inter-module communication protocol standard, and determining a message format and a priority rule; the method comprises the following steps: distributing computing resources for each module, setting an elastic capacity expansion and contraction strategy, generating a module dependency graph and an architecture metadata file, detecting the loss and delay of multi-modal input data, generating compensation characteristics based on historical context, calculating the quality confidence of each modal, and carrying out dynamic weighted fusion. According to the invention, a three-level alignment architecture is provided to realize cross-modal semantic consistency, and the generated content is ensured to accord with real scene logic; a double-layer decision-making mechanism is designed to drive workflow dynamic optimization, and the system agility under a complex task is remarkably enhanced; a privacy-efficiency balanced federated architecture is constructed, and differential content generation is supported while enterprise data sovereignty is protected.

Description

Technical Field

[0001] The present invention relates to the field of agent construction, and more specifically, to a method and system for constructing an agent based on an agentic workflow. Background Art

[0002] With the rapid development of AGI (Artificial General Intelligence) technology, multi-modal generation and cross-domain collaboration capabilities have become the core challenges in constructing enterprise-level agents.

[0003] Traditional static workflows are difficult to adapt to dynamic business requirements. Agent collaboration is rigid, resulting in response delays and inefficient resource utilization. At the same time, there are semantic fragmentation problems in cross-modal content generation. Due to the lack of a fine-grained alignment mechanism for different modal information, the generated content has chaotic logic and scene mismatches. Summary of the Invention

[0004] The present invention provides a method and system for constructing an agent based on an agentic workflow, which solves the technical problems of cross-modal semantic inconsistency and low efficiency of static workflows in related technologies.

[0005] The present invention provides a method for constructing an agent based on an agentic workflow, including the following steps:

[0006] S100, defining the core functional modules of the agent and assigning unique identifiers, establishing a communication protocol standard between the modules, clarifying the message format and priority rules, allocating computing resources for each module and setting an elastic scaling policy, and generating a module dependency relationship graph and an architecture metadata file;

[0007] S200, detecting the loss and delay of multi-modal input data, generating compensation features based on historical context, calculating the quality confidence of each modality and performing dynamic weighted fusion, filtering low-confidence features according to a preset quality threshold, and recording the time consumption and quality metrics;

[0008] S300, quantifying the historical task contribution of each module, verifying the credibility of nodes through a consensus protocol, constructing a decision weight topology graph between the modules, and dynamically adjusting resource quotas according to the weights to balance the load;

[0009] S400, injecting differential noise into the model parameters at the central node, sending lightweight parameters to the edge nodes and fusing local domain knowledge, generating multi-modal content using an encryption algorithm and binding a digital watermark;

[0010] S500, constructing a three-dimensional evaluation model of quality degradation, recovery efficiency and evolution cost, dynamically adjusting the decision weights of the modules according to the evaluation results, directionally searching the model parameter space and performing incremental hot updates;

[0011] S600 injects a high-intensity load into the isolation environment to test the system's limits, dynamically replaces module components to verify output consistency, checks whether all-link metrics meet the service level agreement, and generates an encrypted audit report with an attached integrity check hash value.

[0012] Further, in S100, the specific steps are as follows:

[0013] S110, Component instantiation and registration: Define a set of intelligent agent function modules, and assign a unique identifier and version number to each module;

[0014] S120, Communication protocol modeling: Define the communication message format between modules, and establish priority and time-to-live rules;

[0015] S130, Resource quota allocation: Allocate computing resources to each module and set an elastic scaling policy;

[0016] S140, Architecture metadata generation: Output a standardized architecture description file and generate a runtime dependency graph;

[0017] The calculation formula for architecture metadata generation is as follows:

[0018] ;

[0019] ;

[0020] Where represents the architecture metadata set, which includes modules, message types, and dependencies, represents the set of intelligent agent function modules, represents the message type definition, represents the directed graph of module dependencies, represents the set of nodes, represents the set of edges.

[0021] Further, in S200, the specific steps are as follows:

[0022] S210, Spatiotemporal feature compensation: Detect sensor data loss and latency, and generate compensation features based on historical context;

[0023] S220, Credibility weighted fusion: Calculate the confidence weights of each modal feature and perform dynamic weighted feature fusion;

[0024] S230, Quality threshold filtering: Evaluate the credibility of the fused features and trigger the feature resampling mechanism;

[0025] S240, Governance feature output: Generate a standardized feature description and record the metadata of the governance process;

[0026] The calculation formula for the governance feature output is as follows:

[0027] ;

[0028] ;

[0029] where represents the governance feature set, including features, weights, quality scores, and time consumption, represents the feature output after governance, represents the set of confidence weights for each modality, represents the set of quality scores for each modality, represents the total governance delay, and the constraint of the delay is one-third of the total SLA delay, represents the maximum delay specified by the service level agreement, represents the time consumption for modality processing, represents the total number of modalities.

[0030] Furthermore, in S300, it specifically includes the following steps:

[0031] S310, Agent Capability Evaluation: Calculate the Shapley contribution value of each agent module to quantify the effectiveness of the module in historical tasks;

[0032] S320, BFT Consensus Protocol: Execute Byzantine Fault Tolerant Consensus at the decision-making layer to verify the credibility and weight of nodes;

[0033] S330, Dynamic Decision Topology Generation: Construct a weighted decision relationship graph and allocate decision weights between modules;

[0034] The calculation formula for dynamic decision topology generation is as follows:

[0035] ;

[0036] where represents the directed graph of decision weights, represents the set of modules, represents the decision dependence edge, represents the weight matrix, and the element is , represents from to the decision weight, represents the module , 's capability value, represents the indicator function, which is 1 when the condition is satisfied and 0 otherwise, represents the consensus reached flag;

[0037] S340, Load Balancing Optimization: Adjust resource quotas according to decision weights to prevent single-point overload.

[0038] Furthermore, in S400, it specifically includes the following steps:

[0039] S410, Central Privacy Parameter Processing: Inject differential noise into the Carrot AI base model to generate privacy-preserving parameters resistant to reverse attacks;

[0040] ;

[0041] where represents the central model parameters after injecting differential privacy noise, represents the original central model parameters, represents Gaussian noise with a mean of 0 and a variance of ; represents the standard deviation of differential privacy noise, represents the differential privacy budget parameter, represents the differential privacy failure probability, represents the parameter cascade noise operator;

[0042] S420, Federated Edge Adaptation Training: Inject domain knowledge at edge nodes and perform privacy-preserving transfer learning;

[0043] S430, Secure Content Generation: Perform multimodal generation using encrypted parameters and bind digital watermarks with access control;

[0044] S440, Cross-Domain Content Verification: Verify the compliance and privacy of the generated content and generate an auditable evidence chain.

[0045] Furthermore, in S430, the calculation formula for secure content generation is as follows:

[0046] ;

[0047] where represents the output of encrypted secure multimodal content, represents the encryption operation using the key ; represents the generation model function, represents the central parameters after differential privacy processing, represents the local adapter parameter increment, represents the processed feature output, represents the encryption key generated based on zero-knowledge proof, represents the zero-knowledge proof - public key generation algorithm, represents the actuator drive module instance.

[0048] Furthermore, in S500, it specifically includes the following steps:

[0049] S510, Three-dimensional fault tolerance index analysis: Quantify quality degradation, recovery time, and evolution cost;

[0050] ;

[0051] where represents the three-dimensional fault tolerance index vector, represents the decision weight aggregation value of S330 aggregation value, represents the modal quality score, represents the maximum value of the quality score, represents the fault recovery time, represents the maximum recovery delay specified by the service level indicator, represents the evolution cost, including in S420, represents the baseline evolution cost, represents the total number of modes;

[0052] S520, Adaptive adjustment strategy: Dynamically update module weights according to the fault tolerance index;

[0053] S530, Incremental model evolution: Perform parameter space directed search and hot update;

[0054] S540, Compliance closed-loop verification: Check the legal and ethical compliance of the evolution process.

[0055] Furthermore, the calculation formula of the adaptive adjustment strategy is as follows:

[0056] ;

[0057] where represents the decision weight, represents the learning rate, represents the current three-dimensional fault tolerance index vector, represents the enterprise preset target vector, represents the square of the two-norm.

[0058] Furthermore, in S600, it specifically includes the following steps:

[0059] S610, Extreme stress test: Inject chaos engineering events to simulate extreme loads and record system degradation and self-healing performance;

[0060] S620, Hot replacement consistency verification: Dynamically replace the agent module and verify output consistency;

[0061] S630, SLA Compliance Verification: Verify that all-link metrics meet the enterprise service level agreement;

[0062] S640, Verification Audit Report Generation: Generate a verifiable encryption performance certificate;

[0063] The calculation formula for the verification audit report is as follows:

[0064] ;

[0065] Where represents the encryption performance verification certificate, represents the encryption operation using the report key, represents the report key derived from the S430 step, represents the SLA compliance verification result, represents the hot replacement consistency verification result, represents the SHA3 hash value of

[0066] The present invention also proposes an agent construction system based on the agentic workflow, which executes the steps in the foregoing agent construction method based on the agentic workflow, including:

[0067] Architecture Management Module: Define the core function modules of the agent and assign unique identifiers, establish the communication protocol standard between modules, clarify the message format and priority rules, allocate computing resources for each module and set the elastic scaling policy, and generate the module dependency relationship graph and architecture metadata file;

[0068] Feature Governance Module: Detect the loss and delay of multi-modal input data, generate compensation features based on historical context, calculate the quality confidence of each modality and perform dynamic weighted fusion, filter low-trust features according to the preset quality threshold, and record the time consumption and quality metrics;

[0069] Decision Coordination Module: Quantify the historical task contribution of each module, verify the credibility of nodes through the consensus protocol, construct the decision weight topology graph between modules, and dynamically adjust the resource quota according to the weight to balance the load;

[0070] Federated Generation Module: Inject differential noise into the model parameters at the central node, send lightweight parameters to the edge nodes and fuse local domain knowledge, and generate multi-modal content using encryption algorithms and bind digital watermarks;

[0071] Fault Tolerance and Evolution Module: Construct a three-dimensional evaluation model of quality degradation, recovery efficiency and evolution cost, dynamically adjust the decision weight of the module according to the evaluation result, directionally search the model parameter space and perform incremental hot updates;

[0072] Performance Verification Module: Inject a high-intensity load in an isolated environment to test the system limit, dynamically replace module components to verify output consistency, check whether all-link metrics meet the service level agreement, and generate an encrypted audit report with an attached integrity check hash value.

[0073] The beneficial effects of the present invention are as follows:

[0074] The present invention proposes a three-level alignment architecture to achieve cross-modal semantic consistency, ensuring that the generated content conforms to the logic of the real scenario; designs a two-layer decision-making mechanism to drive the dynamic optimization of the workflow, significantly enhancing the system agility under complex tasks; constructs a privacy-efficiency balanced federated architecture to support differential content generation while protecting the enterprise data sovereignty. Description of the Drawings

[0075] Figure 1 is a flowchart of an agent construction method based on an agentic workflow proposed by the present invention;

[0076] Figure 2 is a structural block diagram of an agent construction system based on an agentic workflow proposed by the present invention.

[0077] In the figure: 101, Architecture Management Module; 102, Feature Governance Module; 103, Decision Coordination Module; 104, Federated Generation Module; 105, Fault Tolerant Evolution Module; 106, Performance Verification Module. Detailed Implementation Manner

[0078] Now, the subject matter described herein will be discussed with reference to example embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein. Without departing from the protection scope of the content of this specification, changes can be made to the functions and arrangements of the elements discussed. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described relative to some examples can also be combined in other examples.

[0079] As Figure 1 shown, an agent construction method based on an agentic workflow includes the following steps:

[0080] S100, Agent Architecture Registration: Define the core function modules of the agent and assign unique identifiers, establish the communication protocol standard between modules, clarify the message format and priority rules, allocate computing resources for each module and set the elastic scaling policy, and generate a module dependency relationship graph and an architecture metadata file;

[0081] In an embodiment of the present invention, the specific steps are as follows:

[0082] S110, Component Instantiation and Registration: Define the set of agent function modules, and assign a unique identifier and version number to each module;

[0083] The expression of the set of agent function modules is as follows:

[0084] ;

[0085] where represents the set of agent function modules, represents the perception module instance with version number , represents the cross-modal alignment module instance, represents the dynamic decision-making module instance, represents the actuator drive module instance, represents the module version number;

[0086] S120, Communication Protocol Modeling: Define the communication message format between modules, and establish priority and survival time rules;

[0087] Its calculation formula is as follows:

[0088] ;

[0089] where represents the message type definition, including various attributes of the message, represents the message source module identifier (taking values from ), represents the set of target module identifiers, represents the message processing priority (positive integer), represents the maximum survival period, represents the system preset maximum survival time threshold, represents the set of positive integers;

[0090] S130, Resource Quota Allocation: Allocate computing resources to each module and set the elastic scaling policy;

[0091] Its calculation formula is as follows:

[0092] ;

[0093] where represents the resource quota triple of module , represents the CPU core quota of module , represents the memory quota, represents the network bandwidth quota, represents the total system computing resource constraint, represents the total number of modules;

[0094] S140, Architecture Metadata Generation: Output a standardized architecture description file and generate a runtime dependency graph;

[0095] Its calculation formula is as follows:

[0096] ;

[0097] ;

[0098] Where represents the architecture metadata set, including modules, message types, and dependencies, represents the set of agent function modules, represents the message type definition, represents the directed graph of module dependencies, represents the set of nodes, represents the set of edges, represents dependency output;

[0099] S200, Multimodal Feature Governance: Detect the loss and delay of multimodal input data, generate compensation features based on historical context, calculate the quality confidence of each modality and perform dynamic weighted fusion, filter low-confidence features according to a preset quality threshold, and record the time consumption and quality metrics of the governance process;

[0100] In one embodiment of the present invention, the specific steps are as follows:

[0101] S210, Spatiotemporal Feature Compensation: Detect the loss and delay of sensor data and generate compensation features based on historical context;

[0102] Its calculation formula is as follows:

[0103] ;

[0104] ;

[0105] Where represents the compensation feature of the th modality (such as vision , speech ), represents a long short-term memory network with parameter for feature prediction, represents the historical feature window, represents the th modality's data loss rate, , represents the Hadamard (element-wise) product, represents the Gaussian noise injection term, represents the noise variance;

[0106] S220, credibility weighted fusion: Calculate the confidence weights of each modality feature and perform dynamic weighted feature fusion;

[0107] Its calculation formula is as follows:

[0108] ;

[0109] ;

[0110] where represents the confidence weight of the th modality, represents the th modality quality score, which is obtained by calculation, represents the temperature parameter, represents the th modality's original feature, represents the th modality's compensation feature, represents the feature concatenation operator, represents the fused multi-modal feature, represents the total number of modalities;

[0111] S230, quality threshold filtering: Evaluate the credibility of the fused feature and trigger the feature resampling mechanism;

[0112] Its calculation formula is as follows:

[0113] ;

[0114] ;

[0115] where represents the th modality quality score, represents the quality threshold, represents the processed feature output, represents the feature resampling function represents the fused feature, represents the maximum number of retries, represents the indicator function, which is 1 if the condition holds and 0 otherwise;

[0116] S240, processed feature output: Generate a standardized feature description and record the metadata of the processing process;

[0117] Its calculation formula is as follows:

[0118] ;

[0119] ;

[0120] Among them represents the governance feature set, including features, weights, quality scores, and time consumption, represents the feature output after governance, represents the set of confidence weights for each modality, represents the set of quality scores for each modality, represents the total governance delay, and the constraint of the delay is one-third of the total SLA delay, represents the maximum delay specified by the service level agreement, represents the time consumption of modality processing, represents the total number of modalities;

[0121] S300, Collaborative decision-making power allocation: Quantify the historical task contribution of each module, verify the credibility of nodes through the consensus protocol, construct a decision weight topology graph among modules, and dynamically adjust resource quotas according to weights to balance the load, ensuring that there is no single-point overload risk in the decision-making network;

[0122] In an embodiment of the present invention, the specific steps are as follows:

[0123] S310, Agent ability evaluation: Calculate the Shapley contribution value of each agent module to quantify the effectiveness of the module in historical tasks;

[0124] Its calculation formula is as follows:

[0125] ;

[0126] Among them module 's Shapley ability value, represents a subset of, excluding , represents the subset 's number of elements, represents the total number of modules, represents the subset 's task completion score, obtained by calculating in S240, represents the task completion score after adding , represents the factorial operation;

[0127] S320, BFT consensus protocol: Execute Byzantine fault-tolerant consensus at the decision-making layer to verify the credibility and weights of nodes;

[0128] Its calculation formula is as follows:

[0129] ;

[0130] ;

[0131] Where represents the consensus achievement flag (1 for achieved, 0 for not achieved), represents the Byzantine fault tolerance consensus algorithm, represents the set of voting results of each node, represents the maximum number of fault-tolerant nodes, represents the module 's ability value, represents the ability threshold, represents the floor function symbol;

[0132] S330, Dynamic Decision Topology Generation: Construct a weighted decision relationship graph and allocate decision weights between modules;

[0133] Its calculation formula is as follows:

[0134] ;

[0135] Where represents the directed graph of decision weights, represents the set of modules, represents the decision dependence edge, represents the weight matrix, and the element is , represents from to 's decision weight, represents the module , 's ability value, represents the indicator function, which is 1 when the condition is satisfied and 0 otherwise, represents the consensus achievement flag;

[0136] S340, Load Balancing Optimization: Adjust resource quotas according to decision weights to prevent single-point overload;

[0137] Its calculation formula is as follows:

[0138] ;

[0139] Where represents the CPU quota of the module , represents the current decision topology weight, represents the total number of modules, represents to The decision-making weight, represents the sum of weights to all modules;

[0140] Load balancing rate:

[0141] ;

[0142] S400, Federal resilience generation: Inject differential noise into the model parameters at the central node to protect privacy, send lightweight parameters to the edge nodes and fuse local domain knowledge, use encryption algorithms to generate multimodal content and bind digital watermarks, and verify the privacy compliance and quality baseline compliance of the generated results;

[0143] In one embodiment of the present invention, the specific steps are as follows:

[0144] S410, Central privacy parameter processing: Inject differential noise into the Carrot AI basic model to generate privacy-protected parameters resistant to reverse attacks;

[0145] Its calculation formula is as follows:

[0146] ;

[0147] Where represents the central model parameters after injecting differential privacy noise, represents the original central model parameters, represents Gaussian noise with a mean of 0 and a variance of , represents the standard deviation of differential privacy noise, represents the differential privacy budget parameter (privacy strength), represents the differential privacy failure probability, represents the parameter cascade noise operator;

[0148] S420, Federal edge adaptation training: Inject domain knowledge at the edge nodes and perform privacy-protected transfer learning;

[0149] Its calculation formula is as follows:

[0150] ;

[0151] Where represents the local adapter parameter increment, represents the processed feature output, represents the generation model function, represents the central parameters after differential privacy processing, represents the parameter fusion / adaptation operator, represents the private data of the edge nodes, denotes the two - norm, denotes the Frobenius norm, denotes the regularization coefficient;

[0152] S430, Secure Content Generation: Perform multi - modal generation using encryption parameters, bind digital watermarking and access control;

[0153] Its calculation formula is as follows:

[0154] ;

[0155] where denotes the output of encrypted secure multi - modal content, denotes the encryption operation (such as AES - 256 - CTR) using the secret key , denotes the generation model function, denotes the central parameter after differential privacy processing, denotes the local adapter parameter increment, denotes the output of the processed features, denotes the encryption key generated based on zero - knowledge proof, denotes the zero - knowledge proof - public key generation algorithm, denotes the actuator drive module instance;

[0156] S440, Cross - domain Content Verification: Verify the compliance and privacy of the generated content, generate an auditable evidence chain;

[0157] Its calculation formula is as follows:

[0158] ;

[0159] where denotes the verification result of content compliance and privacy (1 for compliant, 0 for non - compliant), denotes the content quality score after decryption, denotes the lowest quality score threshold, denotes the parameter leakage risk coefficient, denotes the norm of the vector / parameter, denotes the indicator function, using the constraint in S130 Training time consumption, inheriting the in S330 to determine the collaboration priority of edge nodes;

[0160] Output verification:

[0161] Privacy protection: (Central parameter leakage rate ≤ 1%);

[0162] Generation aging: (2 / 3 of the total remaining time delay);

[0163] S500, Fault-tolerant evolution evaluation: Construct a three-dimensional evaluation model for quality degradation, recovery efficiency, and evolution cost, dynamically adjust the module decision weights according to the evaluation results, directionally search the model parameter space and perform incremental hot updates, and verify the legal and ethical compliance of the evolution process;

[0164] In an embodiment of the present invention, the specific steps are as follows:

[0165] S510, Three-dimensional fault-tolerant index analysis: Quantify quality degradation, recovery aging, and evolution cost;

[0166] The calculation formula is as follows:

[0167] ;

[0168] Where represents the three-dimensional fault-tolerant index vector, represents the decision weight of S330 aggregation value, represents the modal quality score, represents the maximum quality score, represents the fault recovery time, represents the maximum recovery time delay specified by the service level indicator, represents the evolution cost, including in S420, represents the baseline evolution cost, represents the total number of modes;

[0169] S520, Adaptive adjustment strategy: Dynamically update the module weights according to the fault-tolerant index;

[0170] The calculation formula is as follows:

[0171] ;

[0172] Where represents the decision weight, represents the learning rate, represents the current three-dimensional fault-tolerant index vector, represents the enterprise preset target vector (such as [1, 0.5, 0.8]), represents the square of the two-norm;

[0173] S530, Incremental model evolution: Perform directional search and hot update of the parameter space;

[0174] The calculation formula is as follows:

[0175] ;

[0176] ;

[0177] ;

[0178] where represents the new model parameters after evolution, represents the central parameters after differential privacy processing, represents before taking the gradient direction dimensions, represents the parameter gradient, represents the mathematical expectation, represents the quality score of the secure content, represents the maximum parameter offset, represents the norm of the vector / parameter, represents the parameter update operator;

[0179] S540, Compliance Closed - Loop Verification: Check the legal and ethical compliance of the evolution process;

[0180] Its calculation formula is as follows:

[0181] ;

[0182] where represents the compliance verification result (1 for compliance, 0 for non - compliance), represents the total number of compliance indicators, represents the th compliance indicator value, represents the th compliance threshold, represents the parameter leakage risk coefficient, represents the fairness deviation caused by weight adjustment, represents the indicator function;

[0183] The input in S440 is used to calculate and inherits the constraint on the weight update amplitude ;

[0184] Output Verification:

[0185] Quality Evolution Gain:

[0186] ;

[0187] represents the first dimension (quality) of the three - dimensional fault - tolerance index vector;

[0188] Recovery efficiency constraint:

[0189] ;

[0190] where represents the second dimension (recovery efficiency) of the three-dimensional fault tolerance index vector;

[0191] Full compliance: ;

[0192] S600, Sandbox effectiveness verification: Inject a high-intensity load into the isolation environment to test the system limit, dynamically replace module components to verify output consistency, check whether all-link metrics meet the service level agreement, generate an encrypted audit report and append an integrity check hash value;

[0193] In one embodiment of the present invention, it specifically includes the following steps:

[0194] S610, Extreme pressure test: Inject chaos engineering events to simulate extreme loads and record system degradation and self-healing performance;

[0195] Its calculation formula is as follows:

[0196] ;

[0197] where represents the set of pressure test events, represents the type of request intensity, represents the parameter Pareto distribution of, represents the test duration, represents the maximum delay of the service level agreement, represents the second dimension (recovery efficiency) of the three-dimensional fault tolerance index in S510;

[0198] S620, Hot replacement consistency verification: Dynamically replace the agent module and verify output consistency;

[0199] Its calculation formula is as follows:

[0200] ;

[0201] where represents the hot replacement consistency verification result (1 for consistent, 0 for inconsistent), represents the new output after hot replacement, represents the old output before hot replacement, represents the generation model function, represents the new model parameters after evolution, represents the governance feature set, represents data distribution offset noise ( ), represents the feature concatenation operator, represents the maximum allowable deviation threshold, represents the norm of a vector / parameter, represents the indicator function;

[0202] S630, SLA compliance verification: Verify that all - link metrics meet the enterprise service - level agreement;

[0203] Its calculation formula is as follows:

[0204] ;

[0205] where represents the SLA compliance verification result (1 for compliance, 0 for non - compliance), represents the total number of performance metrics, represents the decision - weight matrix slice of S330, represents the th performance metric contains of S440, of S510, represents the th performance target value, represents the number of performance metrics, represents the indicator function;

[0206] S640, verification audit report generation: Generate a verifiable encryption efficiency certificate;

[0207] Its calculation formula is as follows:

[0208] ;

[0209] where represents the encryption efficiency verification certificate, represents the encryption operation using the report key, represents the report key derived from S430, represents the SLA compliance verification result, represents the hot - swap consistency verification result, represents 's SHA3 hash value (integrity check), input of S340 is used to calculate the stress - test degradation strategy, inheriting the constraint test boundary conditions;

[0210] Output verification:

[0211] Hot - swap success rate:

[0212] ;

[0213] wherein represents probability;

[0214] Full SLA compliance:

[0215] ;

[0216] Audit non-tamperability:

[0217] ;

[0218] wherein represents the Hamming distance, verifying the non-tamperability of the audit report.

[0219] wherein the mapping relationship of the agentic workflow is shown in Table 1:

[0220] Table 1: Mapping Relationship of Agentic Workflow

[0221]

[0222] As Figure 2 shown, based on the above-mentioned method for constructing an agent based on the agentic workflow, an agent construction system based on the agentic workflow is given, including the following modules:

[0223] Architecture Management Module 101: Define the functional boundaries and interaction protocols of the core components of the agent, allocate unique identifiers and version numbers for modules such as perception, alignment, decision-making, and execution, formulate the message format, priority rules, and lifecycle policies for inter-module communication, establish a resource quota allocation mechanism and an elastic scaling policy, and generate a module dependency relationship graph and an architecture metadata description file;

[0224] Feature Governance Module 102: Real-time monitor the integrity and timeliness of multi-modal input data, perform context-aware compensation for missing or delayed data, calculate the quality confidence weights of each modal feature, perform dynamic weighted fusion and filter low-trust data, record the latency and quality metrics of the feature governance process, and provide a standardized feature set for downstream tasks;

[0225] Decision Coordination Module 103: Evaluate the historical task contribution and real-time load status of each functional module, verify the credibility of nodes through a distributed consensus protocol, construct a dynamic decision weight topology network between modules, adjust the resource quota allocation policy according to environmental changes, and maintain the load balancing and fault tolerance of the decision network;

[0226] Federated Generation Module 104: Inject privacy protection noise into the basic model parameters at the central node, send lightweight parameters to the edge nodes and integrate domain knowledge, generate multimodal content through encryption algorithms and embed digital watermarks, verify the compliance of the generation results with privacy compliance requirements, and achieve a balance between data security and generation efficiency;

[0227] Fault Tolerant Evolution Module 105: Build a multi-dimensional evaluation model to quantify the quality degradation, recovery time and evolution cost of the system, dynamically optimize the decision weights and resource allocation of the module based on the evaluation results, directionally search the parameter space and execute incremental hot updates of the model, and continuously verify the compliance and fairness of the evolution process;

[0228] Performance Verification Module 106: Inject high-concurrency loads in an isolated sandbox environment to test the extreme performance of the system, dynamically replace functional modules to verify service continuity, check whether all-link metrics meet the predefined service level agreement, generate encrypted audit reports and attach integrity verification information to ensure that the system meets the production environment deployment standards.

[0229] Based on the above construction method and system, the following process example is proposed: Enterprises need to deploy AG1 application scenarios such as intelligent customer service and digital human live broadcast;

[0230] Input Information:

[0231] Multimodal Data: User consultation text, product images, voice instructions;

[0232] Business Goals: Response speed < 2 seconds, content accuracy > 95%;

[0233] Network Conditions: Bandwidth fluctuation of edge nodes (packet loss rate ≤ 15%);

[0234] The execution unit includes: CarrotAl industry large model, Agentic dynamic scheduling engine, federated security generation node;

[0235] The execution steps are as follows:

[0236] Semantic Alignment and Feature Fusion:

[0237] Extract text keywords and image region associations, and build a cross-modal mapping dictionary;

[0238] Dynamically analyze the dependency relationship of multimodal data and adjust the feature fusion weight;

[0239] Revise the generated semantics based on the enterprise knowledge base to ensure compliance with industry terminology specifications;

[0240] Dynamic Task Collaboration:

[0241] Decompose the user request into atomic tasks that can be executed in parallel (such as intent recognition, image parsing);

[0242] Monitor the load of each module in real time and dynamically allocate the priority of computing resources;

[0243] Select the optimal execution path through an autonomous negotiation mechanism and support mid-task strategy adjustment;

[0244] Privacy protection generation:

[0245] Add noise protection to the model at the central node to generate encryption parameters resistant to reverse inference;

[0246] The edge node fine-tunes the model based on local data to generate customized content with invisible watermarks;

[0247] Encrypt and transmit the generation results across the entire link and detect potential privacy leakage risks in real time;

[0248] Execution results:

[0249] Aligned content: A customer service response solution with synchronized graphics and text / audio and video;

[0250] Optimization strategy: Dynamic resource allocation topology diagram (including fault rollback path);

[0251] Secure deliverable: A multi-modal content package with enterprise digital watermarks;

[0252] Verification effect:

[0253] Accuracy rate of advertisement graphic matching: 89% → 94%;

[0254] Emergency task response speed: 4.1 seconds → 1.7 seconds;

[0255] Pass rate of privacy compliance audit: 100%;

[0256] This process has been applied to an e-commerce customer service system, supporting 7×24-hour multilingual digital human live broadcasts, and reducing the labor cost by 67%.

[0257] The above describes the embodiments of the present invention, but the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms, all of which fall within the protection scope of the present invention.

Claims

1. A method for constructing an agent based on an agent workflow, characterized in that: The following steps are involved: S100, define the core functional modules of the intelligent agent and assign unique identifiers, establish inter-module communication protocol standards, clarify message formats and priority rules, allocate computing resources to each module and set elastic expansion and contraction strategies, and generate module dependency graphs and architecture metadata files; S200, detects loss and delay of multimodal input data, generates compensation features based on historical context, calculates quality confidence of each modality and performs dynamic weighted fusion, filters low-confidence features according to preset quality thresholds, and records time consumption and quality indicators; S300, quantifies the historical task contribution of each module, verifies the node credibility through the consensus protocol, builds a topological diagram of decision weights between modules, and dynamically adjusts resource quotas according to weights to balance the load; S400 injects differential noise into the model parameters at the central node, sends lightweight parameters to the edge nodes and integrates local domain knowledge, uses encryption algorithms to generate multimodal content and binds digital watermarks; S500 builds a three-dimensional evaluation model of quality degradation, recovery efficiency and evolution cost, dynamically adjusts module decision weights according to the evaluation results, searches the model parameter space in a targeted manner and performs incremental hot updates; S600 injects high-intensity loads in an isolated environment to test system limits, dynamically replaces module components to verify output consistency, verifies whether full-link indicators comply with service level agreements, and generates encrypted audit reports with attached integrity verification hash values.

2. According to claim 1, a method for constructing an agent based on an agent workflow, characterized in that: In S100, the specific steps are as follows: S110, component instantiation registration: define a set of intelligent agent function modules and assign a unique identifier and version number to each module; S120, communication protocol modeling: define the format of communication messages between modules, and establish priority and lifetime rules; S130, resource quota allocation: allocate computing resources to each module and set elastic expansion and contraction strategies; S140, architecture metadata generation: output standardized architecture description files and generate runtime dependency graphs; The calculation formula for schema metadata generation is as follows: ； ； in Represents a collection of architectural metadata, including modules, message types, and dependencies. Represents a set of intelligent agent function modules, Indicates the message type definition. Represents a directed graph of module dependencies. Represents a collection of nodes. Represents a set of edges.

3. The method for constructing an agent based on an agent workflow according to claim 2, characterized in that: In S200, the specific steps are as follows: S210, spatiotemporal feature compensation: detect sensor data loss and delay, and generate compensation features based on historical context; S220, credibility weighted fusion: calculating the confidence weight of each modality feature and performing dynamic weighted feature fusion; S230, quality threshold filtering: evaluate the credibility of fusion features and trigger feature resampling mechanism; S240, Governance feature output: Generate standardized feature descriptions and record governance process metadata; The calculation formula for the governance feature output is as follows: ； ； in represents the governance feature set, including features, weights, quality scores, and time consumption, represents the feature output after governance, represents the set of confidence weights of each modality, represents the quality score set of each modality, Indicates the total governance delay. The delay constraint is one third of the total SLA delay. Indicates the maximum delay specified in the service level agreement. Indicates Modal processing is time-consuming, Represents the total number of modes.

4. The method for constructing an agent based on an agent workflow according to claim 3, characterized in that: In S300, the following steps are specifically included: S310, Agent Capability Evaluation: Calculate the Shapley contribution value of each agent module and quantify the effectiveness of the module in historical tasks; S320, BFT consensus protocol: implements Byzantine fault-tolerant consensus at the decision-making level to verify node credibility and weight; S330, dynamic decision topology generation: construct a weighted decision relationship graph and assign decision weights between modules; The calculation formula for dynamic decision topology generation is as follows: ； in represents a directed graph of decision weights, Represents a collection of modules. represents the decision dependency edge, represents the weight matrix, whose elements are , Indicates from arrive The decision weight of Representation Module , The ability value, Represents an indicator function, the condition is 1, otherwise it is 0. It indicates that consensus has been reached; S340, load balancing optimization: adjust resource quotas based on decision weights to prevent single point overload.

5. The method for constructing an agent based on an agent workflow according to claim 4, characterized in that: In S400, the following steps are specifically included: S410, central privacy parameter processing: differential noise injection is performed on the Carrot AI basic model to generate privacy parameters that are resistant to reverse attacks; ； in represents the central model parameters after differential privacy noise is injected, represents the original parameters of the central model, It means the mean is 0 and the variance is Gaussian noise, represents the standard deviation of differential privacy noise, represents the differential privacy budget parameter, represents the probability of differential privacy failure, represents the parameterized cascade noise operator; S420, Federated Edge Adaptive Training: Inject domain knowledge into edge nodes and perform privacy-preserving transfer learning; S430, secure content generation: performing multimodal generation using encryption parameters, binding digital watermarks and access control; S440, cross-domain content verification: Verify the compliance and privacy of generated content and generate an auditable chain of evidence.

6. The method for constructing an agent based on an agent workflow according to claim 5, characterized in that: In S430, the calculation formula for generating the security content is as follows: ； in Represents encrypted secure multimodal content output, Indicates the use of a key The encryption operation, represents the generative model function, represents the central parameter after differential privacy processing, Indicates the local adapter parameter increment, represents the feature output after governance, represents the encryption key generated based on zero-knowledge proof, represents the zero-knowledge proof-public key generation algorithm, Represents an actuator driver module instance.

7. The method for constructing an agent based on an agent workflow according to claim 6, characterized in that: In S500, the following steps are specifically included: S510, Three-dimensional fault tolerance index analysis: quantifying quality degradation, recovery time and evolution cost; ； in represents the three-dimensional fault tolerance index vector, Indicates the decision weight of S330 Aggregate value, Indicates Modal quality score, Indicates the maximum value of quality score, Indicates the fault recovery time. Indicates the maximum recovery delay specified by the service level indicator. Indicates the evolution cost, including S420 , represents the baseline evolution cost, represents the total number of modes; S520, adaptive adjustment strategy: dynamically update module weights according to fault tolerance indicators; S530, incremental model evolution: performing parameter space directed search and hot update; S540, Compliance closed-loop verification: Checking the legal and ethical compliance of evolving processes.

8. The method for constructing an agent based on an agent workflow according to claim 7, characterized in that: The calculation formula of the adaptive adjustment strategy is as follows: ； in represents the decision weight, represents the learning rate, represents the current three-dimensional fault tolerance index vector, represents the enterprise preset target vector, represents the squared two-norm.

9. The method for constructing an agent based on an agent workflow according to claim 8, characterized in that: In S600, the following steps are specifically included: S610, extreme stress test: inject chaos engineering events to simulate extreme loads and record system degradation and self-healing performance; S620, hot replacement consistency verification: dynamically replace the intelligent agent module and verify the output consistency; S630, SLA compliance verification: Verify that all-link indicators meet the enterprise service level agreement; S640, verification audit report generation: generating a verifiable encryption effectiveness certificate; The calculation formula for the verification audit report is as follows: ； in Indicates encryption performance verification certificate, represents a cryptographic operation using the reporting key, Indicates the report key derived in step S430, Indicates the SLA compliance verification result. Indicates the hot replacement consistency verification result. express SHA3 ​​hash of the .

10. An agent construction system based on agent workflow, characterized in that: Executing the steps in the agent construction method based on agent workflow as described in any one of claims 1 to 9, comprising: Architecture management module: defines the core functional modules of the intelligent agent and assigns unique identifiers, establishes inter-module communication protocol standards, clarifies message formats and priority rules, allocates computing resources to each module and sets elastic expansion and contraction strategies, and generates module dependency graphs and architecture metadata files; Feature governance module: detects loss and delay of multimodal input data, generates compensatory features based on historical context, calculates the quality confidence of each modality and performs dynamic weighted fusion, filters low-confidence features according to preset quality thresholds, and records time consumption and quality indicators; Decision-making coordination module: quantify the historical task contribution of each module, verify the credibility of the node through the consensus protocol, build the decision weight topology diagram between modules, and dynamically adjust the resource quota according to the weight to balance the load; Federation generation module: Inject differential noise into model parameters at the central node, send lightweight parameters to edge nodes and integrate local domain knowledge, use encryption algorithms to generate multimodal content and bind digital watermarks; Fault-tolerant evolution module: builds a three-dimensional evaluation model of quality degradation, recovery efficiency and evolution cost, dynamically adjusts the module decision weight according to the evaluation results, searches the model parameter space in a targeted manner and performs incremental hot updates; Performance verification module: Inject high-intensity loads in an isolated environment to test system limits, dynamically replace module components to verify output consistency, verify whether full-link indicators comply with service level agreements, generate encrypted audit reports and attach integrity verification hash values.

Images