4347 results about "Verification" patented technology

The invention discloses a large model enhanced code security detection method. The method comprises the following steps: dynamically associating CVE vulnerability features with code semantic representation through a knowledge graph construction module; extracting vulnerability features from a CVE vulnerability library by utilizing a knowledge graph construction module, and dynamically associating the vulnerability features with code semantics; based on the CodeQL standard, a query language is generated by adopting a large model and input into CodeQL for AST analysis, and code structure features are extracted; the large model generates a query language meeting the CodeQL standard, codes are analyzed through CodeQL, and key structure features are extracted; integrating a static analysis tool chain to carry out multi-dimensional credible verification on model output; integrating an SAST tool and a symbolic execution tool, and verifying the model output from different dimensions; and summarizing and fusing detection results of the enhancement layers, and determining a final detection result by adopting a decision optimization method. According to the method, through technical fusion and dynamic optimization, the problems of rule stiffness, one-sided detection and low result credibility are systematically solved.

The invention relates to the technical field of building engineering, in particular to a building data processing method and system based on multiple building specifications, and the method comprises the steps: building model data standardization processing: extracting geometric attributes, material attributes and spatial topological relations of components through a BIM software interface, and generating model data in a standard format; constructing a multi-source specification rule tree, performing semantic analysis on national standard, local standard and industrial standard provisions, extracting triple constraint conditions, and fusing to generate a unified rule tree containing hierarchical relationships and conflict marks; on the basis of a spatial topology mapping relationship between the model and the rule tree, identifying a specification conflict and generating an optimization rule set according to a specification effectiveness level and a spatial attribute priority; and finally, real-time compliance verification is executed, and a three-dimensional compliance report including conflict positioning, article basis and correction suggestions is output. According to the method, multi-source specifications can be automatically adapted, model violation components are accurately recognized, a correction scheme is given, and the specification compliance and the verification efficiency in the design stage are improved.

The invention discloses an AI model automatic deployment platform based on a containerization technology, which relates to the technical field of automatic deployment of an artificial intelligence model, and comprises a container construction and intelligent configuration module, a transmission and cache management module, a security and multi-version warehouse module, a resource scheduling and optimization module and a deployment and interface management module, the container construction and intelligent configuration module adopts a three-layer mirror image construction strategy of a base layer, a framework layer and a model layer. According to the invention, all the modules cooperate to form a closed loop, after the container construction module generates an incremental packet and the incremental packet is subjected to security signature verification, the transmission module distributes the incremental packet according to network quality, the resource scheduling module dynamically adjusts bandwidth and quota, and the deployment module starts the container and monitors the container in real time. The problems of efficiency, safety and resource optimization of model deployment in an edge environment are solved, and cross-platform compatibility and service continuity are improved.

The invention provides an industrial agent decision-making method and device, electronic equipment and a storage medium. The method comprises the following steps: loading multi-source industrial data to a knowledge graph, and constructing a domain ontology and an MCP ontology; performing parameter fine tuning on a preset base large language model; receiving an industrial process planning demand input by a user, and performing semantic analysis on the industrial process planning demand; processing the query result by utilizing an MCP context strategy to generate a prompt context; inputting the prompt context and the industrial process planning demand into a fine tuning large language model to generate a first process planning scheme; performing rule verification on the first process planning scheme based on the knowledge graph, and judging whether the first process planning scheme meets a preset rule or not according to a verification result; and converting the final process planning scheme into a control script or an interface calling sequence which can be analyzed by an industrial execution system, and outputting the control script or the interface calling sequence. According to the method, the cross-software system compliance process planning with unified knowledge, automatic generation and rule verification can be realized.

A BIM-based engineering information management system of the present invention relates to the field of constructional engineering informatization management, and comprises a data processing module, a model construction module, a block chain evidence storage module, a verification module, a data fusion module and an authority management module. The data processing module receives original engineering data and generates a structured data signal. And the model construction module generates a BIM model according to the structured data signal. And the block chain evidence storage module encrypts and stores the metadata signal, generates an evidence storage completion signal and feeds back the evidence storage completion signal to the model construction module. And the verification module analyzes the dynamic operation log signal, and generates a risk early warning signal and a repair suggestion signal when abnormality is detected. And the data fusion module generates a fusion data signal, transmits the fusion data signal to the model construction module and triggers BIM model updating. And the authority management module adjusts the user authority according to the risk early warning signal. According to the invention, the problems of data islands, safety risks, low cooperation efficiency and insufficient intelligence in engineering information management can be solved.

The invention discloses a CAPEC vulnerability management system based on a large language model, and belongs to the technical field of network security. The system comprises three modules: a vulnerability-CAPEC dynamic mapping module jointly encodes vulnerability description and code context through a bimodal large language model, accurately associates vulnerability logic with a CAPEC attack mode in combination with comparative learning and knowledge graph construction, and breaks through semantic limitation of traditional rule matching; the adversarial repair code generation module is used for generating high-robustness repair codes through adversarial training and syntax tree verification by fusing CAPEC relieving suggestions and code features on the basis of the association result, so that the secondary vulnerability risk is remarkably reduced; and the full-process automatic verification and DevOps integration module performs multi-dimensional security verification such as symbolic execution, fuzzy testing and the like on the generated repair code, and deeply integrates a development tool chain to realize real-time pushing and closed-loop management of a repair scheme.

The invention relates to the technical field of system engineering modeling, and particularly discloses an MBSE optimization method based on a large language model, which realizes MBSE whole process automation and intelligentization by constructing a'demand-knowledge-model 'dynamic closed-loop framework and fusing RAG and LLM. The method specifically comprises the following steps: constructing a domain knowledge enhancement library, and integrating LLM to construct a demand analysis engine and a dynamic modeling optimization system; a domain expert inputs a demand through a natural language interaction interface, and the demand is analyzed into structured data through LLM; generating a parameterized model conforming to the MBSE specification by combining the RAG technology with the knowledge in the library; after the model runs through a simulation tool chain, the LLM adjusts parameters according to a simulation result to generate an iteration scheme; and after the modeler passes verification, storing the model and data into a database to form a knowledge source. According to the method, domain knowledge dual-drive modeling and cross-role collaboration are achieved, the knowledge base self-evolution capacity is achieved, the problems that traditional MBSE is high in manual dependence and insufficient in semantic fault and knowledge fusion are effectively solved, and the modeling efficiency and reliability are remarkably improved.

The invention discloses a data quality intelligent auditing system and method based on a dynamic rule base, and belongs to the technical field of data auditing, and the system comprises a rule base construction module which is used for analyzing business scene parameters through a scene analysis unit according to business scene demands and data type features to generate a rule configuration instruction; the multi-source monitoring engine module is connected to the rule base construction module and is used for collecting multi-source data in real time and loading corresponding checking rules; the automatic verification execution module is used for executing normalized quality verification on the multi-source data based on the verification rule base; and the feedback optimization module analyzes a rule hit rate and a false alarm rate in a verification result through a reinforcement learning algorithm, and dynamically iteratively updates a rule threshold value and a logic combination in the rule base. By constructing a full-automatic process of rule generation, execution, feedback and updating, the problems that a traditional system depends on manual intervention, response is slow, the industry average rule updating period is 3-7 days, and real-time updating is achieved through the scheme are solved.

The invention discloses a modular reconfigurable production line control system integration method, which relates to the technical field of industrial automation, and comprises the following steps: establishing virtual mapping based on physical attribute parameters to form a production line digital twin basic model framework; collecting data in real time based on an on-site sensor, and establishing a digital twinborn dynamic mapping mechanism synchronous with a physical production line state; a reconstruction scheme is imported into a virtual environment, and key performance indexes are analyzed through a production line digital twin model rehearsal module combination process. A virtual production line model is constructed through a digital twin technology, a rehearsal and verification reconstruction scheme in a virtual environment is supported, trial and error time and cost required by traditional physical debugging are remarkably reduced, a reconstruction strategy is further optimized through a cloud AI algorithm, closed-loop optimization from virtual verification to physical execution is achieved in combination with edge end real-time control, and the real-time performance of the virtual production line is improved. The production line can quickly complete local or overall reconstruction according to production requirements, and the response speed and flexibility of the production line are greatly improved.

The invention relates to an industrial control system security policy adaptive configuration method and device and a readable storage medium. According to the method, a control instruction stream, a process variable sampling value and link layer message metadata are synchronously collected, an association hypergraph fusing network semantics, control semantics and physical semantics is constructed to represent a system state, and a sampling period is divided into a plurality of time slots with fixed lengths. In each time slot, self-supervised learning is utilized to extract a topology embedded vector group, and a system operation rule is represented. A robustness envelope interval is generated by calculating a statistical distance between a current time slot and a historical baseline, and is used for driving a reinforcement learning model to generate a security policy parameter set. And executing corresponding access control, traffic shaping and integrity verification operations in the next time slot, generating receipt vector feedback model update according to an execution result, outputting a micro-policy patch with a hash signature and a timestamp, and sending the micro-policy patch to the edge security gateway to realize deployment, thereby realizing closed-loop adaptive optimization of the security policy in the dynamic environment.

The invention discloses an automatic control code generation and verification method and device, equipment and a storage medium, and relates to the technical field of automatic control, the method is applied to a large language model, and a natural language command is received; performing matching retrieval on the vector database according to the natural language command to obtain an example code snippet; obtaining API structured information corresponding to the example code snippets from a knowledge graph database; generating an initial control code based on the example code snippet and the API structured information; and performing multi-stage virtual operation verification on the initial control code in the software motion control system, and generating a target control code according to a multi-stage verification result confirmed by a user for multiple times and the initial control code. According to the method, the initial control code is automatically generated through double-database retrieval based on the large language model, then multi-stage code verification is performed through the software motion control system, the target control code is generated in combination with verification results confirmed by a user for multiple times, and the code generation speed and reliability are improved.

The invention provides a business module source code generation method and system based on large model business reasoning, and belongs to the technical field of code generation. The business module source code generation method comprises the steps that semantic analysis is conducted on business requirements, and a business association graph with weights is constructed; performing module division, and decomposing a complete task into a plurality of sub-tasks; calling a coordination agent, distributing a corresponding module code generation agent based on a large model for each decomposed subtask, and injecting context information to generate a corresponding module code; wherein the module code generation agent learns a corresponding relationship between tasks and injected context information and codes in advance based on field self-adaptive staged training; and calling the verification agent to perform code quality verification. The method has the beneficial effects that the module division is performed based on the business association graph with the weight, the multi-agent collaborative code generation is constructed by adopting the field-adaptive staged training, and the quality of the generated code is verified, so that the code generation efficiency and quality are improved.

Embodiments of the present disclosure include a software solution for generating a connectivity file that forms the connections between signals in a design under test (DUT) and signals in a verification IP (VIP) interface. The connecting signals from the DUT may form a DUT interface and the DUT interface may follow a protocol. The software solution may utilize a generative AI-based tool to identify example connections that also follow the protocol. These example connections may be included in a query to a large language model (LLM) for purposes of improving the results generated by the LLM.

The invention discloses an MES work order dynamic scheduling and resource self-adaption system based on real-time event triggering, and relates to the technical field of intelligent manufacturing and industrial automation, equipment states and material events are monitored in real time through interfaces such as a PLC and an OPCUA, event types and validity are analyzed through hardware filtering, feature code recognition and double verification, and the real-time event triggering is realized. Event data, MES batch information and equipment load data are integrated to generate standardized scheduling input, a preset strategy is matched, an optimal dispatching scheme is generated through a priority algorithm, material, equipment and logistics resource allocation and dispatching operation are completed, synchronization and MES interaction ensure that page logic is consistent, full-process automation of dynamic work order scheduling is achieved, and work order scheduling efficiency is improved. The equipment state and the material event are responded in real time, the production cooperation efficiency is improved by more than 30%, the resource adaptation accuracy rate reaches 95% or above, manual intervention is reduced, and the consistency of data and MES is guaranteed.

The invention relates to the technical field of engineering cost supervision, and discloses a process execution supervision system and method suitable for an engineering cost consultation project. According to the method, a project full-cycle data set is acquired through a distributed data acquisition interface, wherein the data set at least comprises a contract file and a progress payment voucher; performing structured feature analysis on the data set to generate a multi-dimensional item feature matrix including time nodes, cost indexes and resource allocation quantities; calling a pre-constructed project cost reference parameter library, and calculating a real-time deviation degree between the multi-dimensional project feature matrix and the reference parameters based on a dynamic time warping algorithm; when the real-time deviation degree exceeds a preset threshold range, automatically triggering a process abnormality recognition engine, and extracting process feature vectors including a construction period delay rate, a cost hyperbranched rate and a material loss rate from the deviation process; and inputting the process feature vector into a pre-trained compliance verification model, and outputting an abnormality diagnosis report including a violation type, a risk level and a responsibility subject.

The invention discloses a code generation system based on a natural language and meta-model drive, and the system comprises an AI layer which comprises a plurality of agents which work cooperatively, and is configured to receive a natural language instruction, and carry out the intention recognition, entity extraction, context analysis and constraint verification through the agents, so as to generate structured metadata; the meta-model engine is configured to be used for constructing and instantiating one or more meta-model objects according to the structured metadata generated by the AI layer; and the code template engine is configured to be used for matching one or more corresponding code templates from the code template library according to the content and the type of the meta-model object, and generating executable codes or configuration files of one or more target languages through rendering. By means of the scheme, the natural language is converted into the meta-model decoupled from the technology through the AI, and then the high-quality standardized code is automatically generated through the template engine, so that the development efficiency is improved, and developers can focus on core business innovation.

The invention belongs to the technical field of equipment knowledge engineering and natural language processing, and discloses an LLM-based constraint and self-repairing uniformization equipment knowledge graph automatic construction method. The method comprises the following steps: firstly, acquiring equipment related document data through network collection, document arrangement and database query; then, utilizing an equipment domain ontology and constraints as preposed soft and hard constraints, driving LLM to generate semantic intermediate representation, and obtaining candidate triples through structured compiling; then, a self-repairing closed loop is formed through semantic unit testing, logic consistency detection and evidence binding verification, and triples which violate constraints and have conflicts or illusions are automatically recognized and repaired; and finally, entity standard identification, cross-document duplicate removal combination and conflict resolution are realized through cross-segment unification and incremental alignment. According to the method, the fragile path that the LLM directly generates the triple and blindly stores the triple is avoided, the illusion and inconsistency problems are effectively inhibited, and the correctness, interpretability and maintainability of the equipment knowledge graph are remarkably improved.

The invention discloses an SQL statement structure verification system based on large model and knowledge graph fusion enhancement. The SQL statement structure verification system comprises a knowledge graph construction module, an input design module, a verifier design module and an output design module. According to the method, a knowledge graph is introduced as a structured semantic support, and a closed-loop enhancement processing flow of SQL statements from generation, verification to optimization is realized in combination with a structure perception cue word design, a rule verification mechanism and a Function Call feedback interface; the defects that an existing Text2SQL method is insufficient in structural understanding, lack of semantic reasoning, weak in generalization ability, dependent on computing power and the like are overcome. According to the method, triple guarantee of semantic perception, rule driving and model assistance is realized, the accuracy, robustness and interpretability of SQL generation are remarkably improved, and the cognitive load and operation risk of non-professional users in database interaction are effectively reduced.

The invention discloses an integrated verification and test system and method for complex rules of a substation monitoring system, and the system comprises a rule editing module which provides a visual interface to support a user to edit the complex rules containing various types of variables and time sequence constraints; the analysis and verification module is used for performing grammar, variable conflict and business compliance multi-level verification on the rules; the intelligent test case generation module is used for automatically generating test cases covering normal, boundary and abnormal conditions based on the rule tree structure; the simulation test interface module converts the use case into a standard test script, submits the standard test script to a simulation tool for execution, and outputs the standard test script to a monitoring system through protocol conversion; the result analysis module is used for comparing an execution result with an expected result and generating a structured test report; according to the invention, full-process automation of rule verification and testing is realized, the verification efficiency is remarkably improved, and the test requirements of various transformer substation business scenes are met.

The invention provides a legacy system-oriented large-model-driven API document automatic generation system, belongs to the crossing field of artificial intelligence and software development, and provides a multi-modal data fusion and closed-loop verification mechanism aiming at the defects of a traditional API document generation method in the aspects of semantic comprehension, dynamic context capture and multi-technology stack adaptation. A code static feature and a dynamic track during operation are analyzed through a multi-source data acquisition module, and an interface semantic feature is extracted in combination with a field self-adaptive large model of a semantic enhancement analysis module; deducing an implicit service rule by fusing static / dynamic characteristics through a graph neural network, and generating a standardized document conforming to an OpenAPI specification through a parameterized template generative adversarial network (PT-GAN); and finally, performing three-level verification and closed-loop optimization through a sandbox environment. The method supports a heterogeneous system of 16 programming languages such as Java / C + + / Python, interface version changes can be automatically recognized, document patches are generated, the problems of missing and outdated system documents and low maintenance efficiency are solved, and maintainability and integration efficiency of enterprise-level systems are remarkably improved.

The invention relates to the technical field of building engineering cost intelligent estimation, and discloses a building engineering cost intelligent estimation and checking method fusing a domain knowledge graph and a large language model, and the method comprises the following steps: S1, building a building engineering domain knowledge graph (KG), integrating a quota library, a material price library and historical project data, and carrying out the calculation of a building engineering domain knowledge graph (KG); and defining an entity relationship and a dynamic updating rule. According to the intelligent building engineering cost estimation and checking method fusing the domain knowledge graph and the large language model, a closed loop of knowledge structuring (KG) + semantic comprehension (LLM) + multi-modal reasoning is realized for the first time, engineering cost management is promoted to be transformed from experience driving to data-knowledge dual driving, a reusable technical normal form is provided for the field of intelligent construction, and the engineering cost is estimated and checked. The method solves the problems of efficiency, precision, dynamics and interpretability of traditional cost management, has technical innovation and practical value, and provides core technical support for digital transformation of constructional engineering.

The invention relates to the technical field of block chains, and discloses a block chain and privacy computing collaborative verification system, which comprises a data fragmentation module, a privacy fusion module, a collaborative verification module, a consensus correction module and a fragmentation graph optimization module. The data fragmentation module constructs a multi-stage data collaborative topology through a preprocessing node and a dynamic fragmentation protocol; the privacy fusion module realizes privacy protection by using a ciphertext analysis unit to switch links in a multi-state manner and a zero-knowledge verification unit; a collaborative verification module generates a reference verification strategy through a consensus modeling node multi-dimensional fusion model, and a state optimization unit dynamically aggregates and sorts fragmentation states; the consensus correction module corrects the fragmentation state through an isolation verification unit and a delay compensation unit and calibrates ciphertext parameters; and the fragment atlas optimization module constructs a stability evaluation network monitoring synchronization rate and performs closed-loop adjustment on a verification strategy. The system realizes dynamic fragmentation, privacy fusion and intelligent verification, and improves the efficiency, security and stability of block chain data processing.

The invention discloses a building equipment fault rapid attribution and self-optimization method, which relates to the field of intelligent operation and maintenance of building equipment, establishes a multi-dimensional association relationship among equipment, building space, sensors and fault modes, and deeply combines a fault attribution engine with system dynamics. Data driving flexibility and physical logic preciseness are simultaneously realized in fault attribution, and reasoning from abnormal data to root cause analysis is realized. According to the method, the optimization efficiency is remarkably improved through a specific incremental learning / local updating mode, the weight of the knowledge graph and the Bayesian network conditional probability table are adjusted according to the maintenance result, physical equation parameters are calibrated, and dynamic updating of node attributes of the knowledge graph is achieved; through dynamic weight optimization, the adaptive ability of real-time reasoning confidence evaluation and scene context is improved; a physical equation is used as an executable knowledge unit to be embedded into a knowledge graph through establishment and deep integration of a system dynamics model, and a safety and reliability mechanism is designed for verification.

The invention discloses a mold and formwork design system based on virtual simulation, and particularly relates to the field of mold design, the mold and formwork design system comprises a multi-mode perception fusion module, a digital twin modeling module, a multi-physics field coupling simulation module, a hybrid intelligent optimization module, a digital twin closed loop verification module and a data center module, and each module forms a design closed loop through a data center. The multi-modal sensing fusion module adaptively collects and fuses multi-source signals to generate high-credibility data; the digital twin modeling module constructs and iteratively corrects a model based on the data; the multi-physics field coupling simulation module realizes multi-solver co-simulation under a dynamic boundary; the hybrid intelligent optimization module accelerates to generate an optimal solution through secondary optimization and an agent model; the digital twin closed-loop verification module detects defects and generates a correction instruction; the data center module is responsible for data management, cross-module scheduling and precision control; the system improves the design precision and efficiency of the mold frame, reduces the physical mold testing cost, and is suitable for a high-precision mold development scene.

The invention relates to the technical field of engineering management and intelligent operation and maintenance, and discloses a digital twinning-based engineering consumable management and operation and maintenance system, which collects construction data in real time through multi-modal perception, identifies operation behaviors through a behavior twinning module, verifies behavior compliance through a grammar verification module, and sends the construction data to the engineering consumable management and operation and maintenance system after verification is passed. The dynamic consumption cancel-after-verification module is combined with behaviors, working conditions and tool data to predict consumable consumption and automatically cancel-after-verification inventory, the self-adaptive correction module continuously optimizes the prediction model, and meanwhile, the predictive maintenance module monitors the tool state, generates a maintenance work order and binds related consumables when discovering abnormity. According to the method, through multi-source data fusion, intelligent behavior identification, process logic verification, dynamic accurate verification, model adaptive optimization and tool predictive maintenance, fine management of engineering consumable consumption and intelligent operation and maintenance of operation tools are realized, and the aims of improving construction efficiency, reducing consumable consumption and prolonging the service life of the tools are achieved.

The invention discloses a large-model-driven automatic knowledge graph construction method based on a confidence feedback mechanism, and aims to improve the structural accuracy and semantic consistency in a structured triple generation process, and perform structural constraint guidance by using a few-sample prompt mechanism and a cross validation mechanism of a heterogeneous large model. And the control capability of the large language model on the triple format is enhanced, so that format offset and semantic redundancy in the generation process are reduced. And meanwhile, a multi-dimensional confidence evaluation system is constructed, model consensus judgment, semantic rationality analysis and knowledge consistency verification are fused, and refined quantification and screening of triple quality are realized. According to the method, a confidence backtracking feedback strategy is introduced, a generation-verification-optimization closed-loop process is constructed, the expression and correction capability of the system on a complex knowledge structure is enhanced, the dependence on an external API is effectively reduced, the consumption of computing resources is reduced, and the operation efficiency of the system and the feasibility of engineering deployment are remarkably improved.

The invention discloses a streaming knowledge injection and adversarial self-optimization large language model training method and system, and the method comprises the steps: collecting the newest knowledge of an authoritative information source in real time, converting the newest knowledge into a structured constraint rule through a semantic analyzer, and dynamically updating a knowledge base; based on the updated knowledge base, adopting a PPO algorithm to optimize a generator, actively constructing a high-risk adversarial sample, and forcing the model to expose security vulnerabilities; after user input and adversarial samples are input into the model, total loss is calculated through constraint detection, gradient updating is blocked if the total loss exceeds a threshold value, and otherwise, a multi-level safety verification stage is started; and finally, fusing a security verification result and the adversarial loss, updating a total loss function and cooperatively adjusting model parameters to form a continuous self-optimization training cycle. According to the method, compliance is guaranteed through streaming knowledge injection, vulnerabilities are actively mined in combination with adversarial training, verification precision is improved by means of multi-level detection and dynamic threshold adjustment, and safety and reliability of a large language model in a complex scene are enhanced.

The invention discloses an operation and maintenance knowledge intelligent question and answer interaction method, device and equipment based on an LLM large model. According to the method, questions of operation and maintenance personnel are received through a natural language interaction interface, semantics are analyzed through a pre-trained LLM, candidate answers are generated, the accuracy of the answers is verified in combination with a dynamic operation and maintenance knowledge graph (including equipment model and fault code mapping, a historical case library and a real-time updating knowledge base), and finally a verification result is returned. The device comprises an input module, a processing module, a verification module and an output module, the processing module integrates domain knowledge fine tuning and real-time data integration functions, and the verification module supports multi-source data fusion and confidence evaluation. The platform adopts a multi-tenant architecture, supports visual diagnosis, automatic equipment operation and knowledge use report generation, and ensures that data cannot be tampered through a block chain technology.

The invention relates to an SQL (Structured Query Language) optimization interaction method and device based on a deep learning framework large model. The method comprises the steps that a statement construction model used for generating and optimizing SQL statements is deployed in a target system; in response to a natural language demand input by a user in the target system, identifying key elements in the natural language demand, and verifying whether the key elements exist in an enterprise data platform connected with the target system in combination with the enterprise data dictionary; inputting the target key elements passing the verification into a statement construction model, and generating a target SQL statement and a corresponding performance optimization suggestion; converting the target SQL statement into a service execution step according to the execution logic, and generating service description information; displaying the target SQL statement and the corresponding generation progress to a user in real time in an interactive interface; and displaying performance optimization suggestions and / or business description information matched with the target SQL to a user in an interactive interface to assist the user in realizing SQL operation related to enterprise business.

The invention discloses a software development method and device based on artificial intelligence, equipment and a medium, and the method comprises the steps: receiving a development demand of a user through a natural language interaction interface, and capturing context state information of a current development environment; and a historical solution of the development demand is retrieved based on the dynamic knowledge graph through the product agent. And when the historical solution based on the development demand is retrieved, generating an executable code by encoding according to the hierarchical code generation strategy based on the historical solution through the architect agent. And performing grammar verification, operation verification and demand conformity detection on the executable code by combining the context state information based on a hierarchical verification mechanism through a test agent to obtain a verification result. And when the test agent judges that the verification result meets the development requirement, summarizing the executable code into a final code implementation scheme through the summarizing agent, and pushing the final code implementation scheme to a user. And the reuse rate and the quality control capability of code development are improved.