30178results about "Energy efficient computing" patented technology

The invention discloses a computing resource scheduling method based on user demands and task priorities, which relates to the technical field of resource scheduling, and comprises the following steps: receiving a computing task request submitted by a user, analyzing and verifying explicit demand parameters and implicit demand parameters, and generating a standardized demand description object; acquiring cluster state data and external environment parameters in real time, constructing a user-task-environment three-dimensional feature tensor, and outputting a standardized feature vector group; and collecting a performance data flow of the container instance group, triggering an elastic scaling decision based on a pre-trained LSTM prediction model, dynamically adjusting cluster resource configuration and executing abnormal task rescheduling. According to the method, a user-task-environment three-dimensional feature tensor is constructed, and a dynamic mixed weighted priority score is generated in combination with a reinforcement learning model, so that space alignment and time sequence cumulative effect fusion of multi-dimensional features is realized.

The invention discloses an NL2SQL optimization method and device based on a large model, equipment and a medium, and relates to the technical field of artificial intelligence, the method comprises the following steps: constructing a target metadata knowledge base, and obtaining an initial natural language query request; determining each target entity corresponding to the initial natural language query request, and determining missing target SQL elements in the initial natural language query request based on each target entity; generating a first cue word based on the initial natural language query request, the target SQL element and the target metadata knowledge base, and complementing the target SQL element based on the first cue word by utilizing the target large model to obtain a target natural language query request; and generating a plurality of candidate SQL statements corresponding to the target natural language query request by using the target large model, verifying each candidate SQL statement, and determining a target SQL statement from each candidate SQL statement based on a verification result. According to the method, the accuracy of the NL2SQL can be improved by utilizing a large model.

The invention provides a multi-source heterogeneous data integration and governance-oriented data weaving method, which comprises the following steps of: performing data acquisition from an accessed multi-source heterogeneous data source to generate an original multi-source heterogeneous data stream; performing standardization processing on the original multi-source heterogeneous data stream to generate a standardized multi-source heterogeneous data set; performing active content scanning processing on the standardized multi-source heterogeneous data set to determine business metadata, and performing consanguinity tracking processing on the business metadata to generate enhanced business metadata; calling a domain ontology framework to carry out standardized constraint on the enhanced service metadata to obtain standardized service metadata without cross-data source semantic ambiguity, and carrying out implicit association mining processing on the standardized service metadata based on a graph neural network to generate a semantic knowledge graph containing core entities and relationships; and performing logic abstraction processing on the distributed data resources according to the semantic knowledge graph to generate a unified data access interface.

The invention discloses a knowledge base enhancement generation method and system based on hybrid retrieval and fact verification. The method comprises the following steps: receiving an original query of a user; performing intention analysis and rewriting on the query, identifying an intention type and generating a sub-query adapted to retrieval; executing mixed retrieval of vector retrieval, keyword retrieval and selectable knowledge graph retrieval based on the sub-query, and recalling related knowledge fragments; performing deduplication clustering, fact conflict recognition processing and correlation reordering on the knowledge fragments; according to the intention type and the reordered knowledge fragment, dynamically selecting a prompt template to construct an enhanced prompt; and sending the enhanced prompt into the large language model, and generating a target response with the reference source. According to the method, knowledge recall comprehensiveness is improved through mixed retrieval, knowledge reliability is ensured through fact verification, generation logicality is enhanced in combination with dynamic prompt construction, and response accuracy and credibility are improved.

This invention relates to a gait emotion recognition method, system, storage medium, and computer device based on spatiotemporal graph convolution. The method includes the following steps: S1, data augmentation by reversing the temporal direction of gait; S2, obtaining deep emotion features and prior emotion features respectively through a spatiotemporal graph convolutional network and prior feature statistical methods; S3, performing nonlinear mapping on the prior emotion features using a feature mapping layer; S4, inputting the fused features of the deep emotion features and prior emotion features into an emotion classifier to obtain the emotion category. The feature mapping layer of this invention achieves more effective feature fusion by performing nonlinear mapping on prior features; it also introduces causal temporal convolution to replace general temporal convolution, effectively extracting fine-grained temporal features by enhancing temporal correlation and cross-period feature fusion. Furthermore, a walking direction recognition auxiliary task is designed to accelerate the training and convergence speed of the model, enhancing the ability to extract temporal-dependent features and the performance of emotion recognition.

The invention discloses a computer task scheduling method based on artificial intelligence, and the method comprises the following steps: 1, data collection: employing a double-flow feature fusion mechanism, and generating global feature representation containing long-term dependence and an instantaneous state; step 2, generating a global optimization scheduling strategy: constructing a hierarchical federal reinforcement learning system, dividing a cluster into a plurality of super nodes through an enhanced spectral clustering algorithm, independently training a Dueling DQN network by each super node, performing global strategy cooperation by adopting Shapley value weighted aggregation and differential privacy protection, and generating a scheduling strategy of global optimization; distilling a global strategy into a lightweight decision tree through a strategy distillation technology, and deploying the lightweight decision tree to a physical node; 3, task priority control and elastic resource allocation are carried out, wherein elastic control over resource allocation is carried out through a dynamic time slice bank mechanism; and 4, self-adaptive evolution: establishing a closed-loop optimization system, and carrying out strategy self-evolution by adopting a double-layer optimization architecture.

The invention discloses a hierarchical semantic-driven retrieval enhancement generation method and system, a natural hierarchical relationship and a semantic boundary of a document are effectively reserved by constructing a tree hierarchical structure based on a document chapter title, and a recursive semantic boundary splitting strategy is adopted to refine overlong text nodes, so that the semantic integrity is ensured, and the retrieval enhancement generation efficiency is improved. And the model input length limitation is met, and the semantic information is prevented from being lost. Meanwhile, node knowledge point extraction and abstract generation are achieved through a large language model, top-down multi-level title path transmission and bottom-up content aggregation are combined, the structural perception and semantic expression ability of nodes is enhanced, and in the retrieval stage, based on similarity distribution of query and node semantic expression, an adaptive retrieval threshold value is dynamically calculated, and the retrieval efficiency is improved. A fixed top-k retrieval strategy is replaced, intelligent screening of different query and hierarchical nodes is achieved, information coverage and redundancy suppression are balanced, and retrieval efficiency and accuracy are remarkably 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 relates to the technical field of data center intelligent management, in particular to a data center construction and intelligent operation and maintenance management system, which comprises a dynamic environment sensing module, a heterogeneous equipment protocol adaptation module, a multi-dimensional resource dynamic scheduling module, a hidden fault prediction module and an energy efficiency optimization execution module. Physical environment data such as temperature gradient, current harmonic component and optical fiber strain rate are acquired by deploying a multi-mode sensor, and an environment characteristic matrix is constructed; standard semantic mapping of the heterogeneous protocol is realized by using a semantic slot migration algorithm; establishing a resource topological graph based on the hypergraph neural network and dynamically updating the resource topological graph; a dual-channel space-time convolutional network is adopted to realize fault prediction; and combining the fault probability matrix to generate a dynamic tuning strategy of dimensions such as cooling, electric power, network and the like, and forming closed-loop optimization control. According to the invention, integrated collaboration of multi-source information fusion, equipment intelligent control and energy efficiency adaptive optimization is realized, and the intelligence, reliability and energy efficiency level of data center operation and maintenance are improved.

The invention relates to the technical field of cluster scheduling, and provides a GPU heterogeneous cluster scheduling method and system oriented to large model training and reasoning, which constructs a set of complete cluster scheduling system by integrating multi-source information such as hardware features, running states and historical task data and applying technologies such as a clustering algorithm, a fuzzy comprehensive evaluation method and reinforcement learning. Comprehensive, intelligent and dynamic management and scheduling of GPU cluster resources are realized, the cluster scheduling system can significantly improve the execution efficiency of GPU heterogeneous clusters in large model training and reasoning tasks, the resource utilization rate is improved, the energy consumption is reduced, and the stability and adaptability of the system are enhanced. And an efficient and reliable solution is provided for large-scale deep learning application.

The invention relates to the technical field of intelligent recommendation, and discloses a hybrid retrieval RAG-based resource recommendation method and system, and the method comprises the steps: collecting resource text data, and constructing a vector library and a tag library; expanding the user question based on the language model to obtain a plurality of semantic extension questions; performing intention recognition, judging whether the user question is a resource recommendation question, and if yes, determining a target classification type; screening the data according to the field definition in the tag library to obtain a candidate knowledge fragment set; obtaining candidate vectors, mapping the user question and the semantic extension question into query vectors, calculating the similarity between the query vectors and each candidate vector, and selecting knowledge supplement content; and performing resource splicing on all the knowledge supplement contents to generate resource recommendation answers. According to the method, a structured label screening mechanism and a semantic vector fine arrangement mechanism are fused, and the problems of recall redundancy, matching deviation and the like caused by the fact that an existing RAG system only depends on semantic similarity retrieval are solved.

The invention discloses a large model reasoning efficiency dynamic optimization and hardware sensing compression method. The method comprises the following five steps: S1, generating an input complexity signal representing calculation complexity; s2, synchronously monitoring a hardware resource index of the operation platform, and generating a hardware state signal reflecting a real-time load; s3, inputting the input complexity signal and the hardware state signal into a dynamic strategy selector, and generating a compression control signal through a pre-trained decision model; s4, according to the compression control signal, dynamic reconfiguration operation is executed on the large model weight and the activation value of the current reasoning task; and S5, performing reasoning calculation by using the reconfigured large model, and feeding back a hardware resource index to the step S2 in real time in the calculation process to form a closed-loop optimization link. According to the large model reasoning efficiency dynamic optimization and hardware perception compression method, the problems of low resource utilization rate, delay fluctuation and energy efficiency imbalance caused by a static compression method in dynamic input and heterogeneous hardware environments can be solved.

The invention discloses a computing power scheduling method and system based on dynamic load prediction and resource priority ranking. The computing power scheduling method comprises the following steps: collecting historical load data, task submission data and resource state data of each node in a computing power cluster; on the basis of the preprocessed multi-dimensional load feature data set, constructing an improved hybrid prediction model, optimizing model parameters through training, and predicting the load change trend of each computing power node in a future preset time period by using the trained model to obtain a node load prediction result; extracting a service level protocol parameter, a resource demand type and historical execution efficiency data of a to-be-scheduled task, and establishing a multi-dimensional resource priority evaluation index system; according to the computing power scheduling method, the problems of low resource utilization rate and high task response delay caused by low load prediction precision and mismatching of resource allocation and task priority in a traditional computing power scheduling method are solved, and the overall operation efficiency and service quality of a computing power cluster are improved.

The invention discloses a question and answer reasoning method and device based on key value cache compression, equipment and a medium, and relates to the technical field of natural language processing, and the method comprises the steps: segmenting a cue word in a current question and answer task into a lexical sequence, and generating an initial key value cache of the lexical sequence; dividing the lexical element sequence into context lexical elements and tail end lexical elements corresponding to each layer based on a preset tail end window size of each attention layer of the target large language model; screening out keyword elements of each attention layer from the context lexical elements according to importance scores between key matrixes of the context lexical elements and query matrix mean values of the tail end lexical elements; removing key value pairs of lexical elements except the keyword elements in the initial key value cache to obtain a compressed key value cache; and generating a reasoning result corresponding to the compressed key value cache by using the target large language model. The high computing power consumption of the large language model caused by key value cache data increase is reduced, and the dependence of an existing key value cache compression method on a complete attention weight matrix is broken through.

The invention provides a fragment data cross-modal label generation system and method based on deep transfer learning. The method comprises the following steps: extracting first high-dimensional feature vectors in different modes; mapping the first high-dimensional feature vectors of different modals into the same semantic space through a cross-modal comparison loss function to realize multi-modal alignment and fusion to obtain second high-dimensional feature vectors; labeling semantic tags corresponding to the second high-dimensional feature vectors based on the fragmented data components by adopting a small sample transfer learning algorithm; a multi-channel Hash encoder is adopted, a self-adaptive encoding strategy is called according to different modal data combinations, and the second high-dimensional feature vector is encoded into a multi-channel binary Hash code; in combination with an incremental graph neural network, the binary hash codes and the corresponding semantic tags are dynamically expanded into the historical knowledge graph; matched fine-grained tags are established for semantic differentiation features of different entity combinations in the target knowledge graph, and a cross-modal tag tree is obtained by combining three-matrix hierarchical construction.

The invention relates to the technical field of data processing, and discloses a cross-border e-commerce commodity recommendation system and method based on multi-source data fusion. The system comprises an acquisition module for performing data acquisition to obtain a cross-border unified data warehouse and federal learning cooperation data; the classification module performs text classification processing to obtain a user preference analysis result and an interpretable attention mark; a quantization module carries out quantization processing to obtain a cross-border selection feature matrix; the fusion module carries out weighted fusion processing to obtain a basic comprehensive score and a weight convergence detection result; the evaluation module performs risk evaluation processing to obtain risk probability distribution and cross-border compliance evaluation results; and the sorting module carries out real-time processing through lightweight preprocessing and a flow-type calculation pipeline to obtain a comprehensive score sorting list of cross-border selected products. The problem that a traditional cross-border e-commerce product selection method cannot effectively integrate multi-source heterogeneous data and cannot analyze user feedback text semantic information is solved.

The invention relates to the technical field of computers, provides a heterogeneous computing cluster deployment method and a collaborative scheduling system, realizes full-process automation and intelligent management from resource evaluation, task scheduling to dynamic optimization by accurately sensing the performance and task characteristics of computing units and the running state of a heterogeneous computing cluster, and improves the scheduling efficiency compared with a traditional scheduling scheme. According to the scheduling system, the heterogeneous computing cluster resource utilization rate, the task execution efficiency and the system stability are remarkably improved, the energy consumption cost is effectively reduced, the scheduling system adapts to the cluster environment with diversified task loads and dynamic changes, and an efficient and reliable collaborative scheduling solution is provided for a large-scale heterogeneous computing scene.

The invention belongs to the technical field of electrical digital data processing and resource allocation, and provides an agent lightweight deployment method and a computing power elastic allocation method, lightweight deployment realizes one-time development of multi-platform deployment by constructing a plug-in container packaging tool and a multi-architecture compiling engine; static analysis is used for stripping redundant dependence of the model, and the model is dynamically cut in combination with edge resources; developing an intelligent resource description language, integrating a control group and a filtering technology to realize container-level resource monitoring, constructing a 12-dimensional dynamic state space fusing a node state, task characteristics and a network environment through computing power elastic distribution, and introducing a time delay, cost and reliability three-dimensional weighted reward model to quantify distribution earnings; an edge cloud cooperative training framework and an edge execution strategy are designed, experience is collected, a cloud end trains a Q network through federal learning, an optimization decision is played back in combination with priority experience, the agent deployment efficiency and the resource utilization rate are improved, and data privacy is guaranteed.

The invention provides an AI agent memory management method and system based on cold and hot stratification, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining and preprocessing the historical information of an AI agent, and carrying out the vectorization storage of the historical information; calculating a score based on the access frequency and the semantic association; constructing a dual-threshold triggering mechanism to realize data cold and hot layered migration; establishing index mapping and dynamically monitoring data popularity for returning; and a storage water level dynamic adjustment migration strategy is monitored in real time. According to the invention, the problem of low memory management efficiency of the AI agent is solved, efficient access of memory content is realized, and the storage cost is reduced.

The invention relates to the technical field of multi-modal information processing, and provides a deep semantic collaborative fusion method for heterogeneous multi-modal data. The invention provides a dynamic adaptive fusion framework aiming at the problems that a modal interaction mechanism is rigid and semantic modeling is shallow in the prior art. The method comprises the following steps: carrying out feature coding and alignment on text, audio and video modal data to generate unified-dimension single-modal representation; dynamic interaction is realized through an enhanced multi-head gating fusion module, and double-path features are generated; and carrying out cross-modal depth modeling on the basis of a stacked Transform encoder, and outputting final fusion semantics. Wherein the multi-head attention path calculates cross-modal mapping by taking a text as a query vector and taking an audio / video as a key value vector; the gating path generates a dynamic weight through cosine similarity and a learnable temperature parameter; and the dual-path adaptive fusion adopts a balance factor alpha weighted combination. According to the method, the multi-modal data fusion precision and the system robustness are improved, and the method is suitable for government affair service, man-machine interaction and other scenes.

The invention discloses a software automatic testing system based on generative artificial intelligence, which is characterized in that a software analysis module identifies attribute information of a UI component based on a multi-modal large model for a test object, and constructs a UI component knowledge graph according to a structured information document; the knowledge retrieval module receives the test requirements and retrieves related historical test cases, test scripts and related test data; the organization interaction module sends a test intention and demand information to the knowledge retrieval module for retrieval according to the input user test intention, and test demand knowledge is returned; sending the UI component knowledge graph to the software analysis module for searching the knowledge graph of the test object, and returning the UI component knowledge graph; a test generation module receives test demand knowledge and the UI component knowledge graph, and generates a test case and a test script; and the script execution module receives the test case and the test script, starts a test process and records a test result.

The invention discloses a cloud computing resource optimization method based on intelligent scheduling, and belongs to the technical field of cloud computing resource processing. The method comprises the steps of obtaining real-time operation data of target data in a data optimization detection range, collecting historical resource scheduling records and task execution logs, and constructing a multi-dimensional resource state data set; according to the method, multi-objective optimization, simulation verification and reinforcement learning feedback in the step S5 are carried out, a perception-prediction-scheduling-monitoring-optimization closed-loop mechanism is constructed, the resource utilization rate, the response time and the energy consumption cost of a multi-objective optimization function are balanced, and a particle swarm optimization algorithm is combined with simulation verification to generate a global optimal strategy; and reinforcement learning dynamically adjusts model parameters by taking the execution deviation as a reward signal, continuously updates a resource perception dimension and a prediction model, realizes continuous iterative upgrade of a resource optimization effect, and performs optimization processing on cloud computing resource optimization based on intelligent scheduling.

The invention discloses a multi-path recall mixed retrieval method and system based on intelligent dynamic weight distribution, and aims to solve the problems that semantic comprehension and keyword matching are difficult to balance and the adaptability is poor due to the adoption of a fixed weight in the existing retrieval technology. The invention provides a multi-path recall mechanism fusing vector semantic retrieval, BM25 keyword retrieval and entity retrieval. A query feature vector containing 13-dimensional features such as semantic complexity, keyword density and entity coverage rate is constructed, a query type is recognized in combination with an SVM and a random forest integration model, a dynamic weight distribution algorithm is designed, and the final weight of each retrieval path is calculated in real time. And an adaptive multi-source enhanced reciprocal ranking fusion (AMSE-RRF) algorithm is further adopted to carry out optimization fusion on multiple paths of results, and a depth reordering model can be selected to improve the precision. According to the method, the accuracy and robustness of retrieval can be remarkably improved in multiple scenes of medical treatment, finance, government affairs and the like according to a millisecond-level self-adaptive adjustment strategy of query features.

The invention discloses a matrix calculation adaptive optimization method and system based on an ARM architecture. The method comprises the following steps: preprocessing to-be-processed matrix data; performing local activeness calculation and hot spot region identification on the preprocessed matrix data, and determining long-tail distribution characteristics of the matrix; calculating the optimal block size range of the matrix based on the long tail distribution characteristics of the matrix and the multi-level cache capacity parameters in the processor information, and generating an asymmetric block scheme; based on an asymmetric partitioning scheme, establishing a mapping relation between matrix features and optimal partitioning parameters; calculating the calculation density and the memory access mode of each block based on the asymmetric block scheme and the mapping relation, and generating a task scheduling scheme; based on the task scheduling scheme, matrix calculation is executed on the processor, and a final calculation result is output. According to the method, self-adaptive blocking and heterogeneous core scheduling are realized by identifying the long tail distribution characteristics of the matrix, and the performance and energy efficiency of matrix calculation on ARM are improved.

The invention provides a method for generating an SQL (Structured Query Language) by a natural language based on bidirectional mapping and semantic parsing, which relates to the technical field of database query and comprises the following steps of: extracting natural language query elements and packaging the natural language query elements into structured data, and establishing a mapping relationship from a query field to a service attribute and a physical data table by adopting a bidirectional Hash index technology; and automatically identifying multi-table association keys, performing semantic extension and compliance verification, generating an abstract syntax tree, performing processing according to user permission, and finally converting the abstract syntax tree into an SQL statement conforming to a target database syntax specification. According to the method, the accuracy and the efficiency of converting the natural language into the SQL are improved, and the flexibility and the safety of the system are enhanced.

The present disclosure provides a variable-bit-rate image compression method and system, an apparatus, a terminal, and a storage medium. The variable-bit-rate image compression method includes: obtaining an initial feature map from a to-be-encoded image; quantizing the initial feature map by a dead-zone quantizer; performing entropy encoding on the quantized feature map and hyper-prior information to obtain a compressed bit-stream; performing entropy decoding on the compressed bit-stream, and recovering quantized hyper-prior information and the quantized feature map; performing inverse quantization on the quantized feature map to obtain a reconstructed feature map; obtaining a reconstructed image from the reconstructed feature map; and adjusting quantization and inverse quantization parameters according to a target bit-rate or target distortion. The present disclosure provides a precise bit-rate control solution, makes the bit-rate of the compressed bit-stream better adapt to the dynamic change of a network bandwidth, and has an extremely high actual application value.

The invention provides a computer room energy consumption and computing power balance optimization method and system based on swarm intelligence, and relates to the technical field of data center management, and the method comprises the steps: collecting server node real-time operation data, constructing a multi-objective optimization function, predicting an energy consumption and computing power change curve through a recurrent neural network, and generating an initial task distribution scheme; and a global optimal allocation scheme is searched by adopting a parallel ant colony algorithm, the running state of the server is monitored, and task migration and energy consumption adjustment are executed, so that collaborative optimization of energy consumption reduction of the machine room and balanced allocation of computing power is realized, and the service quality and the resource utilization efficiency are improved.

The invention provides a multi-modal knowledge extraction method and system based on multi-agent collaborative optimization, and relates to the technical field of knowledge extraction, and the method comprises the steps: carrying out the multi-modal deconstruction of an original document to be extracted; constructing a multi-modal agent, respectively executing feature extraction and preliminary knowledge extraction, and outputting a single-modal multi-component system; based on a cross-modal knowledge graph, mapping information of different modals to a unified semantic node, and establishing cross-modal association and analyzing a logic chain through a graph neural network and a causal reasoning module; dynamically allocating resources according to the importance of map nodes, and screening structured knowledge; and through confidence analysis and node traceability evaluation, an intelligent agent cooperation mechanism is optimized, and increment correction is carried out on a result. According to the method and the device, the technical problem of low knowledge extraction accuracy and efficiency caused by insufficient multi-modal knowledge collaborative mining capability due to knowledge extraction of literatures by adopting a single agent in the prior art can be solved, and the knowledge extraction quality and efficiency are improved.

The invention relates to the technical field of data center heat dissipation, and particularly provides a single-phase and two-phase immersion liquid cooling method and system based on AI intelligent decision, and the method comprises the steps: injecting coupled data into a dynamic feature extraction engine, and outputting a thermodynamic state evolution tensor which comprises the characteristics of a temperature change rate, a load-heat flux density coupling coefficient and the like; the thermodynamic state evolution tensor is input into the deep neural network model, the temperature and pressure matched with the current thermodynamic state evolution tensor are calculated, and a closed-loop control instruction set capable of being executed by equipment is generated; a closed-loop control instruction set is injected into an execution mechanism set, execution mechanisms execute power reconstruction and flow channel switching according to instructions, gaseous fluorinated liquid is liquefied and flows back through an efficient condenser in a two-phase mode, and heat dissipation mode self-adaptive switching and heat cycle reconstruction are achieved. The system comprises a server, an AI algorithm controller, a cooling liquid storage device, a condenser, a circulating pump, an electric valve, a pressure release valve and a temperature sensor. The heat dissipation efficiency and the system reliability are remarkably improved.

The invention relates to the cross technical field of business intelligence and natural language processing, in particular to an interactive AI report generation method and system based on intelligent semantic driving, and the method comprises the steps: (1) a large language model analyzes user question semantics, calculates the matching degree with a report subject, and dynamically selects a question correction or report generation process; (2) the fuzzy query is converted into a deterministic request based on the domain knowledge base, and semantic ambiguity is eliminated; (3) analyzing field association in combination with database metadata, and generating an executable SQL (Structured Query Language); (4) dynamically rewriting SQL (Structured Query Language) according to user roles, adding permission filtering conditions, executing query and desensitizing sensitive data; (5) analyzing result features, automatically matching a visual form and generating natural language interpretation; and (6) collecting user feedback, and optimizing a semantic model and a query strategy. According to the scheme, the accuracy of natural language query and the adaptive capacity of the system can be remarkably improved, and the security of data access is guaranteed.