1156results about How to "Improve interpretability" patented technology

The invention discloses a medical diagnosis intelligent decision-making system based on multi-modal data fusion, and the system comprises the steps: obtaining a medical image, biological features and electronic medical record data of a patient through a patient information collection unit, and extracting feature vectors from different modal data through a feature processing unit; the core of the system is a modal fusion engine, and the module combines a deep neural network and a Bayesian inference engine to realize deep learning and probability-dependent modeling of an association relationship between features; carrying out weight optimization on different modal features by adopting an attention mechanism through a self-adaptive feature optimizer, and generating optimized feature representation; the intelligent diagnosis analysis unit calculates the diagnosis probability based on the optimized features, performs auxiliary diagnosis in combination with a case knowledge base when the confidence coefficient is insufficient, and outputs a diagnosis report containing diagnosis categories, basis and suggestions; according to the method, multi-source heterogeneous data are fused, deep learning and probabilistic reasoning are combined, intelligent medical auxiliary diagnosis is achieved, and diagnosis accuracy and interpretability are improved.

The invention discloses a neurology nursing potential safety hazard monitoring system and method, and relates to the technical field of medical information safety monitoring, and the system comprises a first collection processing unit which is used for collecting monitoring data of a target patient, inputting the monitoring data into a time sequence deep network for processing, and obtaining risk feature data; the second collecting and processing unit is used for collecting physiological state data of the target patient, constructing a risk assessment rule base based on a medical knowledge graph to analyze the physiological state data, and generating risk probability data; and the risk early warning unit is used for inputting the risk feature data and the risk probability data into a Bayesian fusion network, generating risk early warning information and sending the risk early warning information to the medical care terminal. According to the invention, collaborative analysis of multi-source information is realized through the Bayesian fusion network, the problem of low early warning accuracy of a traditional single monitoring method is solved, and the reliability of potential safety hazard monitoring is improved.

The invention belongs to the technical field of electric power data security management and intelligent question answering, and particularly relates to an electric power data security policy large model question answering system and method based on relation pooling. The system comprises a power data security policy knowledge base, a language model, a question processing module, an answer generation module and a user output module. Data of the electric power data security policy knowledge base comes from an electric power data security policy file; the language model converts a natural language problem into a structured query for knowledge base retrieval; the question processing module retrieves policy terms related to the natural language question to serve as retrieval results; the answer generation module generates a final answer according to the natural language question and a retrieval result of the knowledge base; by introducing the intelligent question-answering system combining the large language model and the knowledge base, the problems of low efficiency, inaccurate interpretation, incapability of dynamically updating and the like in the existing power data security policy query and management are solved.

The invention discloses an e-commerce intelligent operation monitoring and collaborative decision-making method based on big data analysis, and the method comprises the following steps: S1, collecting multi-source heterogeneous data, and constructing an original data set; s2, performing data cleaning and characterization processing to generate a feature data set; s3, constructing a knowledge graph and dynamically updating the knowledge graph by using the graph embedding model; s4, generating potential causal paths and weights in combination with the neural relationship reasoning model and the diffusion model, and introducing a microknowledge enhancement layer to generate causal enhancement features; s5, identifying abnormal behaviors in combination with a multi-level anomaly detection mechanism; s6, designing a dynamic game optimization model, determining a collaborative optimal solution under a multi-target conflict through Nash equilibrium, and processing a dominant and subordinate relationship in combination with a Stackelberg game to generate a collaborative optimization strategy; and S7, displaying the monitoring state and the collaborative optimization strategy through a visual interface. According to the invention, big data analysis, a knowledge graph and a dynamic game technology are combined, so that e-commerce intelligent operation monitoring and collaborative decision-making are realized.

The invention provides a DCS system autonomous controllable upgrading and system fault prediction method and system, and relates to the technical field of fault prediction, and the method comprises the steps: obtaining historical operation data and real-time operation data of a DCS system, carrying out the preprocessing, and generating an autonomous controllable upgrading scheme through a deep reinforcement learning algorithm; the method comprises the following steps of: setting specified time for upgrading time, carrying out consistent backup on the state of the DCS, executing software updating, hardware configuration adjustment and system parameter optimization according to upgrading steps, analyzing indexes of the DCS in real time in the process of executing the autonomous controllable upgrading scheme, and recovering the DCS to the state before upgrading when an abnormal condition is detected. And verifying and optimizing the real-time fault prediction result based on a knowledge graph, and generating an explanatory report including a fault prediction and upgrade decision process according to the optimized fault prediction result and the autonomous controllable upgrade scheme.

The invention provides an unstructured data automatic processing method and system based on deep learning, and relates to the technical field of data processing, and the method comprises the steps: obtaining unstructured data through an intelligent data collector, building a data feature fingerprint database, constructing a data quality evaluation model through an incremental learning algorithm, and carrying out the data standardization processing; extracting dominant features and recessive features by using a multi-layer cascade network structure and a self-attention mechanism, and constructing a feature association graph and a bidirectional reasoning channel; and performing rule matching and causal reasoning based on the domain knowledge base, and finally realizing automatic structuring of the unstructured data. According to the method, the automation degree and the accuracy of data processing are improved, the manual intervention cost is reduced, and the method has relatively high universality and expandability.

The invention relates to the technical field of data processing, and discloses a multi-granularity extraction and enhancement method, device and equipment for multi-source heterogeneous data. The method comprises the following steps: performing multi-level feature extraction on a multi-modal data set and original feature parameters to obtain a multi-modal feature set; performing correlation analysis on the multi-modal feature set to obtain a feature correlation matrix and optimized feature representation; performing cross-modal knowledge migration processing on the feature incidence matrix and the optimized feature representation to obtain migration feature parameters; performing dynamic fusion processing on the migration feature parameters to obtain target fusion features; and performing multi-task segmentation processing according to the target fusion features to obtain a plurality of sub-task sequences, performing time sequence enhancement and multi-task fusion analysis on each sub-task sequence to obtain target extraction data, and performing visual display on the target extraction data. According to the method and the device, the efficiency and the accuracy of multi-granularity extraction and enhancement for multi-source heterogeneous data are improved.

The invention discloses a medical field large model pre-training and fine tuning method and device based on a knowledge graph, and the method comprises the steps: training a reward model through employing collected medical related text data and a quality marking result, and screening out high-quality data from the newly obtained medical related text data through employing the trained reward model; coding the medical knowledge graph into a text format processed by a large language model, and alternately inputting the high-quality data and the coded medical knowledge graph into the large language model in different batches for model pre-training; and designing an instruction fine tuning data format comprising an instruction, a knowledge graph reasoning path and a generated answer, inputting a training sample constructed in the instruction fine tuning data format into the pre-trained large language model for model fine tuning, and outputting a final answer and reasoning path according to the instruction newly input by the user by utilizing the fine-tuned large language model. According to the method, the professionality of the large language model in the medical field can be effectively improved, and AI application in high-risk fields such as medical treatment is promoted.

The invention belongs to the technical field of natural language processing. According to the zero resource framework-based fine-grained large model illusion processing method and system, multi-dimensional anomaly detection is carried out on a preprocessed text through a large language model, and a multi-dimensional anomaly detection result is obtained; performing anomaly correction priority ranking according to a multi-dimensional anomaly detection result; dynamically adjusting a context window range according to a syntactic analysis result and the generated syntactic dependency tree; performing priority correction on high-risk vocabularies and sentences according to an abnormal correction priority ranking result in combination with the adjusted context window range; and evaluating the corrected content, and obtaining a corrected final text when a termination condition is met. According to the method, the excessive confidence, subtle semantics and grammar deviation illusion detection of the detection content is realized, and the illusion detection processing capability of a large language model, especially the detection processing capability of a fine-grained illusion problem, is improved.

The invention belongs to the field of fault diagnosis, and particularly relates to a main shaft bending common characteristic diagnosis system based on a stacking integration method, and the system comprises the following modules: a sensor module which is used for collecting a vibration signal of a main shaft in real time; the data acquisition and processing module is used for converting an analog signal into a digital signal and preprocessing the signal acquired by the sensor; the feature extraction module is used for extracting features from the preprocessed vibration signals; the machine learning diagnosis module analyzes and classifies the extracted features by using stack integration based on a plurality of trained machine learning models, and judges the health state of the main shaft; and the output module is used for outputting the diagnosis result and sending out an alarm signal when abnormality is detected. Real-time monitoring and automatic diagnosis of the main shaft bending fault are achieved, compared with a traditional method depending on expert experience and manual detection, the fault detection efficiency and accuracy can be greatly improved, and misjudgment and missed judgment risks caused by human factors are reduced.

The invention discloses a lower limb exoskeleton rehabilitation robot joint torque prediction method and device based on an electromyographic signal, and the method comprises the steps: firstly collecting the electromyographic, joint angle, angular velocity and joint torque data of a user, and carrying out the modeling of four muscles related to a knee joint through a neuromusculoskeletal model; and identifying physiological parameters used in the model by using a sparrow optimization algorithm, and outputting an optimal solution to obtain an estimated torque. Then, the real torque and the estimated torque are endowed with the weights of # imgabs0 # respectively, and a fusion torque is obtained; and training a neural network model by using the collected data and the fusion moment, and meanwhile, enabling the neuromusculoskeletal model to participate in the training process of the neural network model by adopting a method of bringing the neuromusculoskeletal model into a loss function, so that the constraint of the model is increased. And finally, storing the trained model for subsequent calling. The method has the advantages of high precision and strong generalization, and model training can converge more quickly under the condition of less data volume.

The invention provides a prognosis risk prediction model construction method based on coexistence of acute myocardial infarction and atrial fibrillation and application. The method comprises the following steps: S1, acquiring historical patient clinical information of a target patient and death time after coexistence of diseases; s2, preprocessing clinical information of historical patients; s3, using an LASSO method and a ten-fold cross validation method to identify related clinical features related to death time after coexistence of diseases; s4, dividing a training set and a verification set; s5, performing training optimization on the four machine models by using the training set, evaluating the prediction performance of the models by using the verification set, and determining a Glmnet model with the optimal prediction performance; and S6, performing model interpretation on the Glmnet model by using an SHAP value, and determining an optimal prediction factor of which the model prediction contribution ranks the first three. The prognosis risk of coexistence of acute myocardial infarction and atrial fibrillation can be accurately predicted, and reference is provided for clinical diagnosis and treatment of patients with coexistence of acute myocardial infarction and atrial fibrillation.

The invention relates to the technical field of medical diagnosis systems, in particular to an early gonitis diagnosis system and method based on multi-modal deep learning, a data collection module is used for collecting and preprocessing multi-modal data including knee joint X-ray image data, MRI (Magnetic Resonance Imaging) image data and clinical evaluation data; the model construction module constructs a deep learning model by combining a convolutional neural network and a Transform architecture, realizes mapping from multi-modal data to a clinical assessment phenotype label by adopting a feature automatic learning module and a potential relationship mining module, and integrates a Grad-CAM interpretability method for understanding a model prediction basis; diagnostic data are continuously collected to be fed back to the data collection module for model optimization, the convolutional network is good at capturing local image features, the Transform architecture is good at modeling a long-range dependency relationship, and the feature extraction and relationship modeling capabilities of the model are greatly improved through combination of the convolutional network and the Transform architecture.

The invention relates to the technical field of intelligent evaluation and early warning methods, in particular to a nuclear radiation dose space distribution intelligent evaluation and early warning method and system, and the method comprises the following steps: obtaining multi-source monitoring data which comprises gamma radiation dose, alpha radiation dose and beta radiation dose measuring instrument data; performing fusion and enhancement processing on the multi-source monitoring data to obtain an enhanced radiation monitoring signal; based on the enhanced radiation monitoring signal, high-precision prediction of nuclear radiation dose spatial distribution is carried out through a deep probabilistic neural network model; according to the high-precision prediction result, in combination with a nuclear accident severity level standard, a radiation alert evaluation result and early warning information are generated, short-term radiation fluctuation can be captured, a long-term change trend can be identified, and the understanding ability of the system to a complex radiation field is greatly improved.

The invention is suitable for the technical field of tumor treatment and protection, and particularly relates to an intelligent classification prediction method, system and equipment for tumor treatment and protection, and the method comprises the steps: obtaining tumor-related molecular marker detection values and clinical diagnosis and treatment features of all target patients, and comprehensively integrating the multi-dimensional medical information of the patients; according to the relevance of molecular markers and clinical features, a scientific and quantitative multi-dimensional prognosis layering index set is constructed, and an accurate layering evaluation framework is formed; inputting the medical data into a pre-trained multilayer neural network model, and generating a high-resolution tumor characterization map through a cross-modal feature fusion technology; based on the dynamic matching of the atlas and the hierarchical index set, the hierarchical contribution degree parameter and the prognosis risk score are calculated in combination with the random forest model, the precise quantitative evaluation of the condition of the patient is completed, a high-credibility quantitative basis is provided for clinical decision making, the over-treatment risk is effectively reduced, and the prognosis management effect of the patient is improved.

The invention discloses a photovoltaic power generation day-ahead prediction method based on causal inference and multi-scale feature fusion, and belongs to the technical field of photovoltaic power generation prediction. According to the method, historical meteorological characteristic data is divided into a plurality of samples, and generated power of the samples in the future M steps is used as corresponding labels. A PCMCI causal inference method is used to calculate a causal inference weight between a sample and a label, the sample is weighted and then is input into three base learners of BiLSTM, TCN and GAF-SE-ResNet50 in parallel, the trend of an input sequence is recognized from three dimensions of global, local and periodical, and a photovoltaic power generation power day-ahead preliminary prediction value is obtained through corresponding training. Wavelet features of the local weather forecast sequence of the prediction point are extracted, and a final prediction value is obtained through fusion of a cross attention mechanism and the initial prediction value of the base learning device. Accurate and stable photovoltaic power generation prediction in a complex climate change environment is realized.

The invention relates to the technical field of remote sensing, and discloses a remote sensing ecological index assessment method based on deep learning, which comprises the following steps: acquiring Landsat remote sensing image data and land utilization data of a research area, and extracting remote sensing ecological index factors of the land utilization data and the preprocessed Landsat remote sensing image data; normalizing the remote sensing ecological index factors and performing dimension reduction analysis to obtain dimension-reduced remote sensing ecological index factors, inputting the dimension-reduced remote sensing ecological index factors into a time sequence convolutional network model, and generating a comprehensive feature vector through causal convolution, extended convolution and global average pooling operations; performing linear combination on the comprehensive feature vector and the principal component analysis feature value, and constructing a time sequence convolutional neural network remote sensing ecological index model for evaluating the ecological environment quality condition of the research area; according to the method, the accuracy, the reliability and the practicability of remote sensing ecological index evaluation are improved by adding the remote sensing ecological landmark factors reflecting human disturbance and water environment change and constructing the time sequence convolutional neural network remote sensing ecological index model.

The invention provides a drug target affinity prediction algorithm based on protein three-mode and multi-feature fusion, and the algorithm makes full use of sequence information and two-dimensional and three-dimensional structural features of drugs and proteins, and realizes deep integration of data. The technical innovation point lies in that a multi-modal data fusion mechanism and an advanced graph neural network technology are introduced, and the sensitivity and recognition capability of the model to key biomarkers are enhanced through a dynamic attention mechanism. According to the technical advantage, the method has higher accuracy and stability when processing complex biological data, and compared with the prior art, the generalization ability and the interpretability are remarkably improved. In the aspect of technical maturity, the algorithm has passed multiple rounds of verification and shows good prediction performance and adaptability. The method is simple in operation and wide in market application prospect, can assist in new drug discovery and accelerate the drug design process, can also promote the development of the precision medical field, and particularly has important value in targeted therapy and disease prevention strategy formulation.

The invention relates to the technical field of logistics distribution data fusion, in particular to a data fusion method and system based on a logistics distribution knowledge graph. The method comprises the following steps: extracting original data and carrying out independent representation learning and unified representation processing; extracting uniformly expressed context information and carrying out dynamic perception embedding to obtain semantic enhancement features; fusing time-space and dependency features and physical characteristic features based on semantic enhancement features, performing message passing and relation inference by using a graph neural network, and finally determining a multi-mode relation set; global entity clustering and local feature fine matching are carried out based on semantic enhancement features, hierarchical entity alignment is carried out in combination with the multi-mode relation set, and an aligned entity set is obtained; and constructing an entity filling graph according to the aligned entity set, supplementing multi-dimensional relation attributes, and finally generating a logistics distribution knowledge graph. According to the invention, through a logistics distribution data fusion technology, a more comprehensive and more intelligent logistics distribution knowledge graph is realized.

The invention discloses a charging station loss prediction method based on an LSTM deep learning method, and relates to the technical field of charging stations, and the method comprises the following steps: 1, collecting data including real-time power load data, a power grid topological structure and time sequence data; 2, feature engineering: carrying out preprocessing and feature extraction on the data, and extracting expert knowledge features; step 3, establishing an LSTM model in combination with a PPO algorithm; 4, performing hyper-parameter tuning on the LSTM model through a random search method; and step 5, the optimized miniaturized model is then deployed to each charging station, and local real-time energy loss prediction is realized. In order to further improve the prediction accuracy, expert knowledge is creatively integrated in a feature engineering part, multi-dimensional loss feature recognition is carried out, and the performance of the model in processing a complex nonlinear relation is improved by combining the input of an electric power system expert, recognizing factors such as equipment aging and the like.

The invention discloses a soil humidity fusion method based on XGB-SHAP-RFE feature optimization and SHAP interpretable analysis, and the method comprises the following steps: (1) collecting and sorting multi-source soil humidity related data, and forming a unified data set; (2) constructing an XGB-SHAP-RFE network, and preferably selecting key features from the data set; (3) training a fusion model by using the optimized key features and evaluating the performance of the fusion model; (4) interpretable analysis is carried out on model output based on an SHAP method, and contribution of each feature is quantified; (5) generating multi-source fused high-quality soil humidity data in combination with a model result; the invention aims to efficiently generate a high-precision and high-resolution soil humidity fusion product.

The invention discloses a power distribution network energy storage locating and sizing method and device and electronic equipment. The method comprises the following steps: collecting data of a target power distribution network, including branch information of the target power distribution network and historical load data of the target power distribution network; determining a topological structure of the target power distribution network based on the branch information, and establishing a topological model of the target power distribution network; based on a bilevel planning model, the historical load data and the topology model, a target locating and sizing planning scheme of the energy storage equipment of the target power distribution network is obtained, the bilevel planning model comprises an upper-layer locating planning model and a lower-layer optimization operation model, the upper-layer locating planning model is used for determining an alternative locating and sizing planning scheme of the energy storage equipment, and the lower-layer optimization operation model is used for determining the alternative locating and sizing planning scheme of the energy storage equipment; the lower-layer optimization operation model is used for determining the lowest operation cost corresponding to the alternative locating and sizing planning scheme. The technical problems that the convergence speed is low and the planning scheme is not accurate enough when the energy storage equipment in the power distribution network is subjected to site selection and sizing are solved.

The invention discloses a semi-supervised speech imagination intention decoding method based on electroencephalogram collaborative clustering. The method comprises the following steps: step 1, collecting electroencephalogram data of speech imagination; 2, performing feature extraction on the preprocessed electroencephalogram data; 3, performing feature clustering and sample clustering on the original data matrix to obtain a clustering indication matrix of features, a clustering indication matrix of samples and a coefficient matrix; step 4, completing optimization solution of the clustering indication matrix of the features, the clustering indication matrix of the samples and the coefficient matrix under a semi-supervised framework; and 5, displaying a decoding result obtained by the semi-supervised learning model based on the electroencephalogram sample and feature collaborative clustering through a visualization means. The method can fully explore and utilize a bidirectional complex interaction mode of features and samples and label information of speech imagination in speech imagination intention decoding research and system based on electroencephalogram signals.

The invention provides a battery health state prediction method, system and device and a medium, and belongs to the field of battery state estimation, and the method comprises the following steps: obtaining original electrochemical impedance spectroscopy (EIS) data of a battery; inputting the original EIS data into an automatic encoder, compressing the original EIS data into a low-dimensional vector by using the automatic encoder, and segmenting the low-dimensional vector into a plurality of time sequences; and inputting the plurality of time sequences into a domain adaptive neural network DANN, performing feature extraction on the time sequences by using the DANN to obtain domain invariant features, and predicting the health state of the battery according to the domain invariant features. According to the method, dimension reduction processing is carried out on the original EIS data through the automatic encoder, the nonlinear features in the original EIS data are extracted, the domain invariant features can be extracted in combination with the domain adaptive neural network DANN model, and the generalization ability of the model is improved.

The invention provides an interpretable AI inference method and system for self-supervised neural symbol fusion, and the method comprises the steps: S1, a self-supervised learning module: extracting feature information of unlabeled data, and obtaining a feature vector representing symbol knowledge; s2, a neural symbol fusion module: constructing a deep learning framework by using an AI intelligent learning strategy, and training feature vectors in combination with a reward function to obtain structured knowledge; s3, an explainable reasoning module: constructing an explainable prediction model based on neural symbol fusion, and obtaining a solved reasoning result; in the process of explaining the reasoning result, the complex reasoning process is simplified and displayed. Therefore, not only are the advantages of the neural network in processing complex modes and data association kept, but also the interpretability and logical reasoning ability of symbol reasoning are introduced, so that the performance and interpretability of the whole system are improved. Therefore, the model can optimize feature representation and logical reasoning at the same time in the training process.

The invention provides a learning-based map-free autonomous navigation obstacle avoidance method, a medium and equipment. The method comprises the following steps: carrying out map-free autonomous navigation obstacle avoidance on the mobile robot by adopting a reusable planning capability library; the multiplexing planning capability library comprises a global planning module and a local planning module; the global planning module is used for guiding a global navigation direction and generating ordered and discrete path points; the local planning module generates real-time actions based on a learned local navigation obstacle avoidance model; and controlling the mobile robot to move according to the action generated by the local planning module so as to sequentially navigate the mobile robot to each path point generated by global planning. According to the method, through a global and local combined planning architecture, an algorithm is modularized, so that the method adapts to different navigation tasks, a large amount of retraining based on a deep reinforcement learning navigation method is avoided, and the universality and interpretability of a model are improved.

The invention discloses a GNN and GRU-based bridge structure time-varying fire response prediction method and system, and the method comprises the steps: building a to-be-detected bridge structure FEM model, randomly generating a fire curve, and generating a data set through the combination of the FEM model and the fire curve; establishing a graph structure according to the FEM model, and embedding static and dynamic characteristics for temperature, stress and displacement prediction in nodes of the graph structure; a message transmission layer is constructed, the GNN is responsible for space information transmission, and the GRU is responsible for time information transmission; simulating a heat conduction formula by using a message passing formula combining the two; receiving node input vectors including temperature, stress and displacement prediction characteristics from the graph structure; determining a loss function and separately training GNN + GRU networks for temperature, stress and displacement prediction; and when the to-be-detected bridge structure encounters a fire, acquiring a fire response condition of the to-be-detected bridge structure through the trained model. The problem that a traditional GNN model can only predict non-time-varying boundary fire response is solved.

The invention provides a sedimentary body lithology identification system and method for oil-gas exploration, and the system comprises a data collection module which is used for collecting seismic data and logging data; the data processing module is used for preprocessing the seismic data and the logging data; the data fusion module is used for fusing the preprocessed seismic data, logging data and a geologic model to generate a comprehensive data set; the lithology identification module is used for analyzing the comprehensive data set by using a machine learning algorithm and identifying the lithology type of the sedimentary body; the result verification module is used for performing comparison verification on the identification result and actual core analysis data; and the display module is used for visualizing the recognition result. The system provided by the invention not only can identify the lithology of the sedimentary body, but also can generate a visual three-dimensional lithology distribution diagram through three-dimensional geological modeling and a visualization technology. The visualization results enable geologists and engineers to clearly understand the underground structure and lithologic distribution so as to make more accurate exploration decisions and development plans.

The invention discloses an electrical element magnetic core loss prediction method based on a soft gating hybrid expert model, and relates to an electrical element magnetic core loss prediction method, which adaptively adjusts the expert weight, so that the model is more flexible and has strong adaptability when facing different types of data. Diversified expert model combinations can complement respective advantages, so that the overall robustness and generalization ability are improved, and the risk of overfitting is reduced; in addition, the modular design enables the model to be easy to expand and maintain, and the interpretability of the model can be enhanced by analyzing the output weight of the gating network; furthermore, automatic parameter adjustment and end-to-end training are carried out through an intelligent optimization algorithm, so that the performance of the model is further improved; and finally, the soft gating hybrid expert model can effectively process non-linear and complex relationships, the powerful non-linear modeling capability of the MLP is utilized to capture a complex mode in the data, and the calculation efficiency is improved through parallel calculation and dynamic resource allocation. The advantages enable the soft gating hybrid expert model to show higher accuracy and reliability when processing complex tasks such as magnetic core loss prediction and the like.

The invention discloses a document content auditing method and system based on combined artificial intelligence, and relates to the technical field of content auditing. According to the method, an original document is converted and standardized into a unified format, a natural language processing technology and a regular expression are applied to extract text fragments, images and meta-information of the text fragments, the images and the meta-information of the text fragments, the images and the meta-information; the method comprises the following steps: inputting a file into a combined artificial intelligence model to respectively detect semantic violation, keyword violation and image violation, generating violation condition description and correction cases through a large language model, marking the auditing result in the file through highlighting to form an auditing report, and providing an auditing conclusion and a modification suggestion for file content auditing.