909 results about "Black box" patented technology

The invention discloses a big language model generation content security test system and method in a black box scene. The system comprises a jailbreak prompt word library module used for storing jailbreak prompt words for performing security test on a big language model; the violation question and answer pair module is used for storing violation question and answer pairs covering different types; the response acquisition module is used for obtaining a data request packet according to query content formed by the jailbreak prompt word and the query request; the security analysis module is used for calculating the similarity between response data corresponding to the query request and an expected violation answer, taking the similarity as a security score, and inputting the security score into the adaptive optimization module; and the adaptive optimization module is used for optimizing the jailbreak prompt words output by the jailbreak prompt word bank module by using a genetic algorithm according to the security score output by the security analysis module. According to the method and the device, the security of the large language model generation content can be effectively tested.

The invention discloses an intelligent agent network access evaluation method and system based on automatic label generation and multi-dimensional evaluation, and the method comprises the steps: automatically generating an intelligent agent multi-dimensional label through a large-scale language model, constructing an intelligent agent portrait, and combining automatic test case generation and multi-dimensional evaluation index collection. The problems that in the prior art, agent evaluation standardization is lacked, evaluation efficiency is low, and'black box 'diagnosis is difficult are solved, standardized and automatic quality evaluation is carried out on various heterogeneous agents connected to a platform, and an agent portrait capable of being used for accurate retrieval and scheduling is generated. The method and the system can be widely applied to scenes such as a multi-agent collaboration platform, an agent store and an enterprise-level agent management system, and have the remarkable advantages of remarkably improving the ecological quality of the agent, greatly reducing the manual evaluation cost, accelerating the introduction and commercialization of a new agent and the like.

The invention belongs to the technical field of cross-border data security, and provides a cross-border personal data transmission security detection method and system based on differential privacy, and the method comprises the steps of multi-dimensional situation awareness, privacy budget allocation, interpretability and audit, and execution and response. By synchronously sensing technical environment risks, multi-national regulation constraints and multi-modal data features, comprehensive control of the cross-border transmission security situation is realized, and one-sidedness of single-dimensional sensing is avoided; privacy budget is dynamically allocated under multiple constraints based on a deep Q network algorithm, so that the protection intensity of high-sensitivity data is ensured, and excessive loss of effectiveness of low-sensitivity data is avoided; an interpretable report is generated in combination with causal analysis, full-process evidence storage is realized by relying on an alliance chain, the problems of decision black box and audit tracing are solved, cross-border supervision requirements are met, and the balance of cross-border transmission in the aspects of safety, compliance and availability is improved.

A data-driven autonomous driving decision optimization system and method, comprising: a data production module, a data screening module, a model encapsulation module, and a parameter tuning module; the data production module takes human driving data as input, annotation, preprocessing, format conversion, extracts key features and performs standardization, normalization, and encoding to generate raw data for the data-driven process that meets the algorithm input requirements; the data screening module screens corresponding data from training data by the decision-making module and performs effective classification; the model encapsulation module encapsulates C++ decision code and constructs a trajectory-pair evaluation cost map required for training using a ground-truth evaluation method based on trajectory pairs; the parameter tuning module, based on screened data under different scenarios, the encapsulated decision algorithm model, and the trajectory-pair evaluation cost map, employs black-box optimization to obtain decision parameters for the corresponding scenarios under the current decision algorithm.

The invention provides a port facility management and maintenance large model report review agent construction method and system, and the method comprises the steps: collecting a cross-modal original data set, constructing a multi-modal feature fusion perception layer, and generating facility damage feature alignment data; constructing a cognitive neural network four-level architecture, and generating an inference decision tree; constructing a root cause-path-result causal chain, and generating a fault attribution analysis report; constructing a prediction-intervention-verification active defense closed loop, and generating a Pareto optimal maintenance strategy set; and executing an intervention strategy and feeding back a verification result by using the digital twin verification platform and the block chain evidence storage system. According to the method, cross-modal data deep semantic alignment is realized through the multi-modal feature fusion perception layer, a data island is broken, and the damage feature extraction accuracy is improved; an interpretable causal chain is constructed based on related architecture and modules, the decision black box problem is solved, and a maintenance strategy has causal logic support; and real-time verification and credible tracing of a strategy effect are realized through an active defense closed loop.

The invention relates to the technical field of computer systems based on specific calculation models, and discloses a control method and system for an intelligent calculation center comprehensive energy supply device, and the method comprises the steps: collecting the operation data of energy supply equipment and an environment sensor in real time through an SCADA system, and carrying out the preprocessing; based on the collected data and simulation data generated by a simulation environment, performing offline mixed training on the reinforcement learning model to generate an energy scheduling strategy; inputting a real-time state into the trained reinforcement learning model to generate a preliminary scheduling instruction, performing security verification and interpretability analysis by using a large language model, and optimizing a strategy; and fusing the preliminary scheduling instruction with the suggestion of the large language model, generating a final scheduling command through the energy router control unit, and issuing the final scheduling command to the energy supply equipment for execution. The problems that in the prior art, black box decision making and simulation are not accurate, and experience is difficult to solidify are solved, and the purposes of decision making transparency, simulation high fidelity and experience structuring are achieved.

The invention relates to the field of man-machine interaction, and particularly discloses a multi-mode man-machine interaction application system for sky-eye insight based on a pathologist visual angle, which is characterized in that firstly, a candidate focus thermodynamic diagram is generated through rapid scanning of a full-slice image, low-power lens global browsing of a doctor is simulated, and the doctor is guided to lock a key area interactively through professional judgment; therefore, the processing efficiency of the oversized image is greatly improved. And then, the system only performs high-resolution deep analysis on the focus confirmed by the doctor, and performs multi-modal fusion on the extracted microscopic visual features and the patient text information to generate a preliminary report with an interpretable basis, so that the problem that the multi-modal function deviates from a clinical core task is solved. Finally, the doctor can check and finalize the report through visual interaction, and the dominant position and the final decision making right of the doctor in the diagnosis process are ensured, so that the bottlenecks of black box operation and low clinical acceptability of a traditional AI system are overcome.

The invention relates to the technical field of training data auditing, in particular to a semantic perception black box large language model training data auditing method and system.The method comprises the following steps that content is returned based on a text generation interface, lexical elements and candidate content are analyzed for multi-round sampling distribution, and a convergence index is determined; and calculating semantic paths and weights of the real content and the candidate content, and analyzing differences between the real content and the candidate content and the reference content to obtain an affiliation adaptation judgment result. According to the method, through multi-round sampling behavior fluctuation tracking, section feature dynamic extraction, stability change judgment and sequence-level weight aggregation, fine separation of training data attribution signals is achieved, a multi-level judgment system is constructed for complex expression and diversified output, judgment accuracy is optimized through a tension comparison signal group and an attribution adaptation judgment mechanism, and the judgment accuracy is improved. And a sensitive and adaptive training data member auditing strategy is formed, so that the risk hidden danger omission is effectively prevented, and the model data security boundary control is enhanced.

The invention discloses an urban flood prediction method based on a dual-drive urban flood model, and the method comprises the steps: carrying out the early-stage preparation of model construction, constructing an urban flood hydrological and hydrodynamic coupling model frame, constructing a deep learning model frame based on a GBDT algorithm, and carrying out the prediction of the urban flood. Assimilation of predicted values and measured data of a hydrological hydrodynamic model and a deep learning model is realized through a real-time data assimilation technology, then an output result of an urban flood hydrological hydrodynamic coupling model is used as an input feature of the deep learning model, and the input feature and parameters are dynamically adjusted according to the matching degree of a confusion matrix. The TP in the confusion matrix is maximum, the TN in the confusion matrix is minimum, finally, construction of the dual-drive urban flood model is completed, and prediction is conducted through the model. According to the method, the characteristic of high calculation efficiency of the deep learning model is exerted while calculation accuracy is considered, a layered coupling architecture is provided, and the problems that the calculation efficiency of a hydrological hydrodynamic model is low and a traditional deep learning model has a black box effect are solved.

The invention relates to a trajectory prediction model robustness enhancement method based on dynamic subspace projection decomposition. Comprising the following steps: firstly, extracting hidden layer semantic features containing historical tracks and map topology through a multi-modal feature encoder; secondly, constructing a dynamic routing mechanism based on scene self-adaption, and calculating projection weights of input features on a plurality of expert subspaces; then, executing truncation projection operation based on orthogonal decomposition, retaining core semantics located in a low-dimensional space, and filtering out adversarial disturbance located in an orthogonal complementary space; and finally, introducing a feature consistency constraint training mechanism, taking the reconstructed features of the clean sample as anchor points, and compulsively aligning the purified features of the confrontation sample with the anchor points. Compared with the prior art, the method has the advantages that the robustness of the model in white box gradient attack, black box query attack and physical semantic deception scenes is remarkably improved through feature purification of a physical level and structured consistency constraint, and the prediction reliability of the automatic driving system is ensured.

The invention is suitable for the technical field of logging lithology identification, and provides a logging lithology identification method based on physical information constraint, which comprises the following steps: step 1, data processing; 2, constructing a graph; step 3, constructing a graph attention neural network; 4, constructing a mixed loss function; and 5, lithology prediction. According to the method, through the synergistic effect of data driving and physical information, the performance is obviously superior to that of various pure data driving models. Benefited from the strong regularization effect of physical constraints, the method has stronger generalization ability and prediction stability on new data. The problem that a traditional black box model may generate a result violating physical common knowledge is fundamentally solved, and the geologic rationality of an output result is ensured.

The invention discloses a lightweight knowledge graph rapid construction method and system based on an NLP technology. The method comprises the steps of preprocessing an unstructured text and segmenting the unstructured text into semantic segments; unsupervised clustering is combined with the contour coefficient to determine the optimal clustering number, and a semantic association fragment cluster is obtained; performing word segmentation, part-of-speech tagging, NER and entity linking on the fragment cluster, extracting an entity and initial relationship, and fusing semantic similarity, TF-IDF word frequency collaboration degree and co-occurrence frequency to calculate a relationship edge weight; constructing a lightweight knowledge graph; in the question and answer stage, questions are disassembled through a process engine, related sub-graphs are retrieved, and answers with reasoning links are generated. The system correspondingly comprises a text preprocessing module, a clustering module, an entity relation processing module, a graph construction module, a question and answer reasoning module and a storage module. According to the method, the construction cost is reduced, the interpretability and the module coupling degree are improved, multiple scenes such as government and enterprise public opinions and medical assistance are adapted, and the problems of weak generalization, poor real-time performance and'black box 'in the traditional technology are solved.

The invention discloses a sensitive cue word generation method and system based on parameter sensitivity quantification, relates to the technical field of artificial intelligence security, and aims to solve the problem that sensitive test samples are difficult to generate in integrity verification of a black box large language model. The method comprises the steps of obtaining an original large language model; a comprehensive parameter sensitivity index is constructed, the microscopic sensitivity used for representing tiny parameter modification and the macroscopic sensitivity used for representing large modification such as parameter quantification and pruning are fused, and therefore the sensitivity of cue words is comprehensively quantified; in the continuous embedding space, a gradient optimization algorithm is adopted to maximize the comprehensive index as a target to carry out iterative optimization, and constraints such as semantic rationality are applied to ensure that the generated cue word is natural and smooth; and finally, mapping the optimized embedded vector back to the discrete lexical element sequence to obtain a final sensitive cue word. According to the method, the low-cost and automatic test sample generation is realized, and the accuracy, efficiency and concealment of cloud model integrity verification are remarkably improved.

The invention relates to the technical field of infrared light machine system thermal deformation prediction, in particular to a multi-material structure thermally induced stress deformation prediction method based on a graph neural network. The method comprises the steps of data set establishment, graph structure establishment, graph neural network model establishment and training and model and parameter optimization. Finite element nodes correspond to graph nodes, finite element edges correspond to graph edges, an encoder-message passing-decoder architecture model is established, and node states are updated through a three-layer physical symmetry message passing mechanism. Physical constraint loss including minimum displacement smoothness constraint and stress continuity constraint is innovatively added into a loss function. Compared with traditional finite element calculation, the method has the advantages that the speed is increased by more than 100 times, high hardware adaptability is achieved, the black box limitation of a data-driven neural network model is broken through, thermally induced stress deformation analysis caused by different material coefficients can be processed, the adaptability to geometric changes is high, and good engineering application value is achieved.

The invention discloses a mobile phone thermal simulation method and system based on multi-physics field coupling, relates to the field of mobile phone thermal simulation, and constructs hybrid simulation coupling machine learning and physical solution. A machine learning agent model and a throttling logic script are innovatively introduced. The machine learning agent model is used for quickly predicting the temperature according to the current power consumption so as to instantaneously respond to the power consumption change; and the throttling logic script is used for simulating a real temperature control frequency reduction strategy and dynamically adjusting the target power consumption at the next moment according to the predicted temperature. In this way, the original black box temperature control logic is explicit, and a power consumption-temperature closed-loop feedback path is constructed. And finally, taking the adjusted power consumption as a heat source, and performing physical field solving by a traditional CAE solver. Therefore, the problem of time scale difference between heat conduction and electrical change is effectively solved, and efficient and accurate simulation of true performance and temperature performance of the mobile phone in a long-time high-load scene is realized.

The invention relates to the technical field of battery health management and prediction, in particular to a lithium battery capacity fading trend prediction method and system, and the method comprises the steps: enabling data driving features and electrochemical features to generate deep fusion features through a dual calibration mechanism; inputting the feature sequence into an electrochemical process perception model, and encoding the feature sequence into a potential state vector representing personalized decline; and inputting the vector as an initial condition into a neural differential equation model, and finally generating a continuous health state attenuation trajectory and obtaining a prediction result by learning a decline dynamic law and performing integral solution. According to the method, deep fusion is carried out on a physical mechanism and a data driving model, the defect that a traditional black box model is weak in generalization ability is overcome, long-term, high-precision and continuous prediction of the full-life-cycle decline trend can be achieved only through early weak signals of a battery, and the reliability and the practical value are high.

The invention provides an electric power line defect detection method and system based on visual identification, and relates to the technical field of line detection.The method comprises the steps that firstly, a visible light and infrared image dual-light registration and differential operation technology is adopted, and a fusion feature map capable of reflecting component thermal anomaly and material difference at the same time is generated; secondly, a black box type target detection model is abandoned in a part positioning link, but line segment screening and reconstruction are carried out by combining probability Hough transform with specific prior geometric knowledge of a power line, so that dependence on a large amount of labeled data is reduced, interpretability of a positioning process is enhanced, and the positioning accuracy is improved; according to the method, accurate areas of key components such as wire insulators can be extracted in a complex background, the concept of a probability saliency map is introduced in a defect identification core link, so that a defect area is enhanced and highlighted, and then a complete defect contour is determined by adopting an adaptive threshold segmentation and area growing algorithm; accurate mapping from pixel-level features to object-level defects is realized.

The invention discloses a power grid fault report decision verification method based on digital twin replay and an interpretable neural network, and relates to the technical field of intelligent operation and maintenance and artificial intelligence decision verification of a power system. According to the method, structured analysis of a fault report is generated through AI, power grid digital twinning simulation replay and neural network reasoning with characteristic interpretability are combined, report conclusions and simulation results are automatically compared, interpretability analysis such as SHAP and LIME is integrated, and transparent tracing and characteristic contribution degree quantitative verification of the fault report reasoning process are achieved. Compared with a traditional power grid fault report processing method depending on manual checking or black box AI model output, the method can achieve automatic consistency criterion verification and whole-process data traceability of a fault report reasoning conclusion, and the credibility, transparency and batch engineering application efficiency of a power grid operation and maintenance decision are effectively improved.

The invention discloses an intelligent power grid dispatching instruction optimization system based on semantic analysis, relates to the technical field of power grid dispatching instruction optimization, realizes the conversion of dispatching instruction generation from black box output to white box reasoning, constructs a new intelligent dispatching normal form with deep integration of knowledge driving and data driving, and improves the intelligent dispatching efficiency. The automation level, decision reliability and operation safety of power grid dispatching are remarkably improved, and the method has outstanding innovativeness and wide engineering application prospects.

The invention discloses a GFRP durability evaluation method based on a neural network, and belongs to the technical field of composite material performance evaluation. The method comprises the following steps: constructing a training data set containing working condition parameters, macroscopic performance data and microscopic mechanism data; a multi-head physical guidance neural network model is constructed, and the model is provided with a main output head for outputting a macroscopic performance data predicted value and an auxiliary output head which is connected to an internal physical mechanism characterization layer of the model and is used for outputting a microscopic mechanism data predicted value; performing multi-task cooperative training on the model through a composite loss function; and finally, synchronously outputting a macroscopic performance prediction result and a microcosmic mechanism diagnosis result by utilizing the trained model. According to the method, physical mechanism knowledge is fused into the neural network, and a traditional black box model is improved into an interpretable grey box model through middle layer supervision and multi-task cooperative training, so that the accuracy of macroscopic prediction is improved, and quantitative diagnosis of an internal degradation mechanism is realized.

The invention discloses a verifiable privacy protection federated learning method based on sensitive samples, and relates to the field of fault diagnosis. According to the method, the Poisson sampling process is introduced, the sampling probability is generated based on the privacy budget, it is ensured that all recorded privacy budgets are synchronously exhausted, data disastrous forgetting is effectively prevented, and the model effectiveness is improved. In the model verification module, a sensitive sample set is generated by means of a gradient maximization algorithm, a model integrity attack is detected, a user side only needs to submit a small number of sensitive samples for prediction through an inference service API provided by a private cloud client side, and if a returned result and a real result have significant deviation, it can be judged that the model is possibly tampered. According to the method, diversified privacy requirements of users can be met, black box verification on the integrity of the model is realized, and the precision of the model is improved.

The invention relates to the technical field of boiler combustion and pollutant control, in particular to a thermal power plant boiler NOx emission prediction method based on model fusion. According to the method, firstly, a boiler furnace outlet NOx generation mechanism model is established on the basis of a NOx generation mechanism, a De Sote model is adopted, secondly, a thermal power plant boiler furnace outlet NOx generation data driving model is established on the basis of a long-short term memory (LSTM) neural network optimized by a particle swarm algorithm, and then the mechanism model (physical equation) and the data driving model (LSTM) are combined to generate a NOx generation driving model. The black box defect of a data-driven model is made up by utilizing the physical interpretability of the mechanism model, and meanwhile, the static error of the mechanism model is optimized by utilizing the dynamic adaptability of data driving. Compared with a single model, the fusion model has higher robustness and prediction precision under variable working conditions, sparse data or noise interference.

The invention discloses a deep reinforcement learning optimization method for injection molding process parameters, and belongs to the technical field of intelligent manufacturing. The method comprises the following steps: constructing a dynamic causal graph network through information entropy flow analysis and transfer entropy calculation, and revealing a causal relationship and time delay characteristics among process parameters; manifold learning is adopted to map a high-dimensional parameter space to a low-dimensional manifold, and Riemannian metric guide optimization search is constructed based on the quality gradient; generating enhanced state representation fusing causal association and manifold geometric information; identifying a production element state and selecting a corresponding optimization strategy; a geodesic line is planned in a manifold space to obtain an optimal parameter adjustment path; historical experience is utilized through memory retrieval and case adaptation; cross-task knowledge migration is realized; adopting a depth deterministic strategy gradient algorithm to optimize the decision; and online learning is realized through elastic weight consolidation. According to the method, the problems of black box decision, slow convergence, difficulty in knowledge reuse and the like in the prior art are solved, the optimization efficiency and the interpretability are improved, and the method has the capability of quickly adapting to new tasks.

The invention discloses a report system testing method and device and electronic equipment. The method relates to the field of big data, and comprises the following steps: inputting test data into a to-be-tested report system to obtain a first data processing result; comparing the first data processing result of the test data with the first standard data processing result to obtain a first test result; obtaining a sub-data processing result of the test data in each detection node in a preset processing path in the to-be-tested report system, and obtaining a second data processing result; obtaining a second standard data processing result set of the test data in the preset processing path, and determining a second test result of the test data according to the second standard data processing result set and the second data processing result; and determining a target test result of the to-be-tested report system according to the first test result and the second test result. Through the method and the device, the problem of relatively low efficiency of testing the report system by adopting a black box test method in related technologies is solved.

The invention discloses an intelligent operation and maintenance resource allocation method and device. According to the method, full-link multi-source data is collected and pre-processed to form multi-dimensional pre-processing features, the system state can be comprehensively described, a mixed deep learning model is called to capture a nonlinear relation and time sequence dependence, the prediction precision is improved, an interpretable result containing a confidence interval and a feature contribution degree is generated, and the prediction accuracy is improved. The black box characteristic of deep learning is broken; a resource scheduling strategy is generated by combining a dynamic threshold value with a multi-target optimization algorithm, adaptive adjustment can be performed according to a real-time load, multiple targets such as resource cost and service quality are balanced at the same time, and the defects of a traditional fixed threshold value and single target optimization are avoided; besides, according to the method, a prediction result is directly converted into a resource scheduling strategy, dynamic allocation is executed, a prediction-decision-execution closed loop is formed, reaction delay caused by separation of a prediction system and an allocation system in the prior art is reduced, the resource utilization rate is increased, and the method can better adapt to dynamic changes of services.

The invention belongs to the technical field of deep learning and image processing, and discloses an underwater image enhancement method based on tensor learnable prior. By designing learnable prior based on a Tensor Train kernel, explicit modeling of the underwater degradation law is realized. The four Tensor Train kernels correspond to the height, the width, the channel and the image block modality respectively, so that the system can simultaneously describe the vertical structure change, the horizontal scattering, the spectral absorption difference and the regional scale attenuation, thereby obviously enhancing the description capability for the underwater multimode degradation. The Tensor Train kernel is dynamically generated based on the kernel prediction sub-network, the prior structure of the method can be adaptively adjusted along with the input image, and the stability and generalization ability of the enhancement result are improved. According to the method, color shift is effectively corrected and scattering blur is inhibited while the structure edge is kept, so that the enhancement process is changed from traditional black box type mapping to physical consistency structured reasoning, and more natural colors, higher contrast and better detail recovery effects are obtained in a complex turbid environment.

The invention discloses a river and lake backflow recognition and driving mechanism analysis method based on interpretable machine learning, and relates to the technical field of hydrology and water resource analysis and artificial intelligence application, and the method comprises the steps: collecting long-sequence hydrology data of a river and lake system; taking operation nodes of the large hydro-junction project as boundaries, and dividing the time sequence into different characteristic periods; constructing a multi-dimensional input feature set; a class weight balance strategy and a Bayesian optimization algorithm are adopted to train a backward flow recognition model based on a gradient lifting decision tree; a marginal contribution value of each hydrological driving factor is calculated by using an SHAP interpretability method, a physical threshold for inducing backward flow is identified by combining an SHAP dependency graph with a binary box plot, analysis results in different periods are compared, and an evolution rule of a backward flow driving mechanism is revealed. The method effectively solves the problems that a traditional method is difficult to capture nonlinear hydrological response and the black box model lacks physical mechanism explanation, and can accurately recognize the backward flow event.

The invention relates to the technical field of big data management, in particular to a data tracing method based on big data mining, which comprises the following steps of: acquiring an unstructured operation log, analyzing the unstructured operation log into a structured event record, and associating to generate a heterogeneous operation session set; performing access mode association analysis on the session set to extract a read-write path mode, and combining association strength and a time decay factor to determine a dependency weight and construct a blood relationship map; eliminating a loop of the graph to generate a directed acyclic graph, constructing a spanning tree serving as a retrieval trunk and a node index coding interval, and mapping a cross-branch associated edge to a bitmap index to generate a probability skeleton tree index; and positioning a trunk path by using the interval, calling a bitmap to perform multi-path verification, and outputting a traceability path and confidence. A probability consanguinity map and a probability skeleton tree index are constructed through mining logs, and data consanguinity reconstruction and large-scale node low-delay retrieval in the heterogeneous black box environment are achieved.

The invention provides an interpretable trajectory prediction method and device for an autonomous system with cognitive driving, and relates to the technical field of autonomous systems. The method comprises the following steps: acquiring multi-source sensing data, including agent state data and scene context data; based on the scene context data and the agent state data, calculating the attention weight of each agent through a scene attention mechanism, and filtering non-key agents to obtain key agents and key agent attention weights; constructing a social influence theoretical diagram based on the state data of the key agent; converting the social influence theoretical diagram into physical force; and dynamically modulating the physical force through the attention weight of the key agent to obtain the processing priority of the key agent, and predicting the trajectory of the key agent according to the processing priority of the key agent. The method is used in the interpretable trajectory prediction process of an autonomous system with self-cognition driving, and solves the technical problem that the decision process is not transparent due to the black box characteristic in the prior art.

The invention provides a medical image visualization analysis system based on deep learning, and relates to the field of artificial intelligence. The objective of the invention is to overcome the defects of an existing system in the aspects of deep learning model interpretability, clinical interactivity and multi-modal data fusion. The system comprises an image data acquisition and standardization module, a deep feature extraction and representation learning module, a multi-task intelligent analysis module, an interpretability analysis module, a multi-dimensional visualization and interaction module, a clinical knowledge fusion and feedback learning module and a system management and integration module. Through the system, the diagnosis efficiency and accuracy can be improved, the trust of doctors is enhanced, the obstacle of a traditional black box model is overcome, and a new man-machine cooperation intelligent diagnosis normal form is constructed.