131 results about "Model interpretation" patented technology

Methods, systems, and apparatus, including computer-readable media, for determining and revealing interpretations of artificial intelligence models. In some implementations, a system receives a prompt from a user. The system obtains code or instructions generated by a artificial intelligence or machine learning (AI / ML) model, where the code or instructions specify criteria to retrieve data from a data source to respond to the prompt. The system generates a set of results from the data source based on the generated code or instructions, and obtains a response to the prompt that an AI / ML model generates using at least a portion of the set of results. The system also generates an interpretation statement that indicates how the prompt was interpreted by the one or more AI / ML models. The system provides output that includes (i) the response to the prompt and (i) the generated interpretation statement.

A cloud-based, machine-learned cybersecurity command line interpretation service simplifies complex command lines using plain language. Command lines are input to the cybersecurity command line interpretation service for an interpretation by a machine learning model. If, however, a command line is known and been previously interpreted, then the cybersecurity command line interpretation service may conserve hardware and software resources by retrieving a historical command line interpretation. If the command line is unknown or not historically logged, then the cybersecurity command line interpretation service may generate a current command line interpretation using the machine learning model. The cybersecurity command line interpretation service may then generate a cybersecurity prediction associated with the command line based on the historical or current command line interpretation. The cybersecurity command line interpretation service thus provides a much faster interpretation and cybersecurity prediction for assessing command lines as malicious or benign.

The invention provides an ultra-high performance concrete multi-performance prediction method based on machine learning. The ultra-high performance concrete multi-performance prediction method comprises the following steps: Step 1, establishing a data set; step 2, data preprocessing is carried out; step 3, establishing an optimal prediction model: based on the feature subset, adopting a plurality of different machine learning algorithms for training, and selecting the machine learning algorithm with the best training effect as the optimal prediction model; step 4, selecting an optimal feature subset; step 5, explaining the influence of the features on model prediction: calculating the contribution degree of each feature to a prediction result based on the optimal prediction model and the optimal feature subset, and helping to understand the decision process of the model; and Step 6, performance prediction of the ultra-high performance concrete: inputting parameters of the to-be-predicted ultra-high performance concrete into the optimal prediction model to obtain a predicted value of the performance. The technical problems that an existing UHPC performance prediction method is incomplete in data set, insufficient in consideration of data processing and feature engineering and poor in model interpretation can be solved.

The invention discloses a depression detection method based on cross-modal knowledge distillation, belongs to the field of depression identification, and solves the defects of an existing depression detection method in the aspects of single-modal data and time sequence model interpretation. The method comprises the following steps: constructing a multi-modal teacher model, wherein the teacher model integrates electroencephalogram and pupil area signals; constructing a single-modal student model which only uses pupil area signals and learns multi-modal features from the teacher model through a knowledge distillation process; training the student model by using a knowledge distillation process, and aligning the middle layer features and output probability distribution of the student model with the teacher model through feature layer distillation and probability distribution layer distillation; and in a test stage, inputting a pupil area signal to be detected into the distilled student model, and outputting a depression classification result. According to the method, the performance of the single-mode model is improved, the dependence on multi-mode data is reduced, and the model interpretability is enhanced.

The invention belongs to the technical field of traffic pollution prediction, and particularly relates to a LightGBM-based multi-source data fusion pollutant concentration prediction method, which comprises the following steps of: 1, integrating and processing multi-source data, and constructing a plurality of feature sets; and 2, carrying out feature analysis on meteorological, pollutant and traffic index variables through correlation analysis and time sequence analysis, and providing support for modeling and model interpretation. And step 3, dividing a training test set according to a time sequence, and training and optimizing the LightGBM pollution prediction model through parameter tuning by taking minimization of RMSE as a target. And 4, verifying the performance of the model from prediction precision, spatial distribution and wind direction influence. And 5, analyzing and displaying the key driving factor and quantifying the contribution of the key driving factor. According to the invention, through feature engineering processing and model optimization of heterogeneous data such as weather and traffic, high-precision prediction and influence factor analysis of lane-level pollutant concentration are realized.

The invention provides a power load prediction method based on a space-time diagram convolutional network in extreme weather. Comprising the following steps: collecting historical load data and regional meteorological element data of a plurality of load nodes in a power system, and screening key meteorological characteristics which have obvious influence on loads through a mode of combining model interpretation and regression analysis to construct a meteorological characteristic vector; multivariable empirical mode decomposition and singular value decomposition are adopted to carry out multi-scale reconstruction on load data, and smooth and effective load feature tensors are extracted. On the basis, a graph network structure is constructed in combination with a node physical connection relationship, and load and meteorological characteristics are fused in a time dimension to form node time sequence characteristics. And predicting the load by using the space-time diagram convolutional network model. According to the method, the space-time dependency relationship of the load data can be effectively modeled, the prediction accuracy of the load change under the extreme weather condition is enhanced, and the method has good robustness and generalization ability.

The invention discloses an engineering vehicle safety simulation and prediction system based on digital twinning, and the system comprises a data collection layer which collects multi-source heterogeneous data in real time; in the knowledge graph layer, a streaming inference engine is constructed based on an Apache Jena graph database, and an entity-relationship-attribute triple dynamic graph structure is adopted; according to the AI model layer, a physical rule serves as a loss function constraint term to be embedded into a neural network through a physical information neural network, a digital organ model concept is combined to split a vehicle into key organs for heterogeneous modeling, a simplified physical model is adopted in the core physical process, and an LSTM-AI model is adopted in external behaviors; the explanatory analysis layer is used for integrating an SHAP / LIME explanatory tool to output a visual evidence chain during fault prediction, and deploying an online incremental learning framework to allow the model to learn from new data and dynamically adjust normal range definition; and the visualization and application layer is used for performing three-dimensional visualization rendering based on WebGL or Three.js, and ensuring data transmission security through block chain evidence storage and end-to-end encryption.

The invention discloses a hepatocellular carcinoma postoperative early recurrence prediction method based on multi-modal fusion. The method comprises the following steps: firstly, integrating clinical data of a training set, a preoperative enhanced CT image and a postoperative full-view digital pathological image, and carrying out standardized correction; then, traditional image omics features and deep learning features are extracted from the CT image, cell nucleus morphological features and tumor microenvironment spatial configuration features are extracted from the pathological image, and key feature signatures are screened out through a maximum correlation minimum redundancy algorithm (mRMR) and LASSO regression in combination with clinical features. And then carrying out progressive model construction by adopting an XGBoost algorithm, sequentially establishing a clinical single-mode model, an image single-mode model, a pathological single-mode model and a multi-mode fusion model, and explaining and visualizing the models by utilizing an SHAP value and a Grad-CAM technology. Finally, the performance of the model is evaluated in a multi-dimensional mode through internal cross validation, foresight and external independent validation, risk layering is carried out based on the prediction probability, and individualized postoperative management is guided.

The invention provides an interpretable machine learning-based giant coronary artery tumor prediction method in Kawasaki disease, and belongs to the technical field of biological information processing. Comprising the following steps: S1, collecting hospitalized KD child patient cases by adopting a retrospective queue research method, and excluding cases which do not meet requirements; s2, coronary artery lesion evaluation and classification; s3, performing variable preprocessing; s4, constructing a machine learning model; s5, performing variable screening; s6, model interpretation; s7, determining an optimal intervention threshold value; and S8, developing an online prediction tool. According to the method, an SVM kernel lab model with the optimal performance is screened out through multi-model comparison, and a group of key prediction molecules are determined in combination with an SHAP method and recursive feature elimination; based on a multi-center data verification model, the model applicability is improved; and early recognition and layered management of high-risk child patients can be realized. A webpage tool is developed, and a patient with high risk is suggested to intervene in advance.

A system and method for automated post-mission logging of unmanned vehicle operations using generative AI. Flight telemetry, operator notes, and maintenance data are aggregated and normalized into a standardized dataset. A large language model interprets the dataset to generate user-readable debriefs, compliance records, and maintenance logs. The system ensures each post-mission report conforms to regulatory standards and automatically flags anomalies or compliance deviations. The generative AI module may be fine-tuned on domain-specific datasets to produce logs that are structurally consistent with predefined templates and compliance forms. The resulting reports can be stored, retrieved, and shared via secure cloud services, streamlining flight record-keeping and maintenance planning.

The invention discloses a cerebral hemorrhage patient tracheotomy risk prediction method and system based on machine learning, and the method comprises the steps: obtaining an initial clinical data set of a target patient, calculating laboratory inspection data according to a predefined rule, and constructing a composite physiological state index to generate a feature vector for prediction; inputting the feature vector for prediction into a risk prediction model pre-trained based on an ensemble learning algorithm to obtain a risk quantitative index; the model interpretation module generates an individualized prediction contribution decomposition result based on an SHAP value calculation framework, and explains the specific influence of each feature on the risk index; and finally comprehensively generating a risk prediction report. According to the method, the feature representation and model prediction capability is enhanced by constructing the composite indexes, and meanwhile, the decision process is transparent and credible by utilizing interpretability analysis, so that clinical risk assessment and decision support are effectively assisted.

The invention belongs to the technical field of water quality parameter inversion, and particularly relates to a machine learning-based suspended matter concentration remote sensing inversion method and system, and the method comprises the steps: collecting a satellite remote sensing image and synchronous actual measurement suspended matter concentration data, and obtaining a space gridding water body remote sensing reflectivity matrix through radiometric calibration, atmospheric correction and water body mask. Reconstructing and denoising through wavelet decomposition, and normalizing and standardizing the spectrum to obtain a spectrum numerical sequence; multi-scale waveband combination and differential features are constructed based on the sequence, and sensitive features are screened out by using XGBoost. A physical constraint term is constructed in combination with sensitive characteristics and a water body radiation transmission rule, and an intermediate inversion result is obtained through numerical iteration. And performing deviation compensation on an intermediate result by using a deep learning residual error, and finally performing spatial smoothing, consistency verification and high-concentration saturation optimization to obtain a high-precision and spatially continuous suspended matter concentration spatial distribution result. According to the method, efficient feature mining and physical mechanism deep fusion are realized, and the explanatory and generalization ability of the model is greatly improved.

The invention belongs to the field of seat control, and particularly relates to a seat control method based on multi-modal data fusion in order to solve the technical problems that in the prior art, model interpretability is poor, and adjustment logic and physiological comfort requirements of a human body are inconsistent, and the seat control method comprises the following steps that S1, after a first feature vector and a second feature vector are mapped to a quaternion space, the first feature vector and the second feature vector are mapped to the quaternion space; generating an initial interaction tensor by calculating the Hamiltonian product of the two; s2, using KL divergence between prior distribution and empirical distribution as a regular term for constraint, and resolving a human body state vector; s3, inputting the human body state vector into the generative network to obtain a fusion feature vector; and S4, based on the fusion feature vector, calculating a control signal used for adjusting the seat surface posture of the seat, the protrusion amount of the waist supporting structure and the clamping angle of the side wing wrapping structure. According to the invention, the analysis and fusion of the vehicle movement trend are realized, so that the seat control can fully foresee and cope with the influence of the vehicle movement on the driver and passengers.

The invention provides an IVIG drug resistance prediction method in KD based on an interpretable machine learning model, and belongs to the technical field of biological information processing. Comprising the following steps: S1, data acquisition; s2, data processing; s3, constructing a model; s4, a model interpretation module; and S5, webpage deployment. According to the invention, based on the large-scale electronic medical record data of the Kawasaki disease patient, a machine learning model with good interpretability is constructed for predicting the IVIG resistance, and an online webpage calculation tool is established for clinical doctors to input key indexes in real time and automatically output the IVIG resistance risk probability of the patient. According to the tool, 11.6% of the optimal prediction threshold value is set, doctors can be helped to identify high-risk individuals, treatment strategies can be adjusted in time, and coronary artery complications are reduced.

The invention discloses a road structure performance catastrophe early warning method and system. The method comprises the following steps: S1, synchronously acquiring data by using a three-dimensional ground penetrating radar and a deflectometer; s2, introducing a dielectric constant correction signal, quantifying a volume defect, and taking the volume defect as a physical constraint inversion mechanical parameter; s3, fusing the multi-dimensional parameters to construct a damage potential index, and predicting the residual life by using a graph space-time neural network; and S4, on-line mutation detection is carried out based on a Bayesian and cumulative sum control chart algorithm, and the weight of the model is updated through a treatment feedback closed loop. According to the method, physical-data dual-drive modeling is adopted, the problems of one-sided detection means, poor model interpretability and parameter solidification are solved, and accurate evaluation of road performance degradation and continuous evolution of the model are achieved.

The invention relates to the technical field of medical image auxiliary diagnosis, and provides an intervertebral joint osteoarthritis image feature evaluation method based on deep learning, which can synchronously identify five types of FJOA image features such as joint space stenosis, osteophyte, hypertrophy, subchondral bone erosion and subchondral cyst, and improves the comprehensiveness and efficiency of evaluation. The nnU-Net model is adopted to perform high-precision segmentation on an intervertebral joint region, so that the positioning precision is effectively improved; by introducing a shared feature extraction network based on ResNet-18 and five parallel classification sub-networks, joint modeling of multi-scale semantic information is realized, and the recognition accuracy and generalization ability of the model are improved; according to the method, a Grad-CAM technology is combined to generate an activation thermodynamic diagram, a model interpretation basis is superposed to an original image, visual display of an evaluation result is realized, interpretability and clinical applicability of the model are enhanced, and FJOA image features in axial lumbar vertebra CT images from two central data sets can be quantitatively evaluated so as to comprehensively quantify individual FJOA image features.

The invention discloses a remote sensing multi-parameter integrated inversion normal form method, system and equipment based on AI-Agent. According to the method, a deep learning neural network is dynamically driven through AI-Agent, a refining mechanism (RM)-Transformer-MoE size nested model, a physical method, a statistical method and expert knowledge are coupled, a DL-C-PSK normal form is constructed, a high-precision multi-source database is established based on the normal form, an appropriate radiation transfer equation is constructed through geophysical logical reasoning, and a high-precision multi-source database is established. And inversion of parameters such as surface temperature, surface emissivity, atmospheric water vapor content and near-surface air temperature is realized. According to a causal relationship between an input wave band and an output parameter, a direct synchronous inversion or iterative inversion mode is adopted to ensure multi-parameter high-precision synchronous inversion. Wherein the core of the deep learning neural network comprises RM logic derivation, SHAP model interpretation, Transform model architecture and a Transform-MoE size nested model, so that the interpretability, the adaptability and the precision of the model are improved. Through an AI-Agent driven RM-Transform-MoE nested model, deep coupling of physics-statistics-knowledge is realized, compared with a traditional SW method, the inversion precision is greatly improved, and verification shows that the technology is suitable for the fields of global climate observation, environment monitoring and the like.

The invention discloses an intelligent fusion reactor optimization system and method integrating interpretable deep learning and multi-source perception control. The system is composed of a fusion reactor, a rotary kiln, an information perception assembly, a data processing unit, an intelligent prediction engine, an adjustment execution system and an industrial-grade visual interaction platform. Technological parameters in the smelting process are collected in real time through a multi-source sensing assembly and input into an intelligent prediction engine after data processing, and the engine dynamically predicts an optimal technological parameter interval based on a convolutional neural network, a bidirectional long-short-term memory network and an attention mechanism and provides interpretable analysis through an SHAP value. And the adjustment execution system carries out closed-loop feedback adjustment according to the prediction result, process parameters are optimized, the metal extraction rate is increased, and energy consumption is reduced. The industrial-grade visual interaction platform supports real-time monitoring, trend prediction display, abnormity early warning and model interpretation graphical output, and is convenient for operators to intervene and optimize.

Embodiments of the present application provide a model interpretation method and apparatus, a storage medium, and a computer program product. The method comprises: determining an attention weight value of first multimedia data in a forward propagation process in a first model, and determining a gradient value of the first multimedia data in a backward propagation process in the first model, wherein the first multimedia data is any input data input to the first model; using the attention weight value and the gradient value to determine an attention value of the first multimedia data; and using the attention value as interpretability information of the first multimedia data, so as to use the interpretability information to interpret a decision-making process of the first model.

Explanatory dropout systems and methods for improving a computer implemented machine learning model are provided using on-manifold / on-distribution evaluation of dropout of key features to explain model outputs. The machine learning model is trained using a plurality of input examples, including input records with explicit dropout operators applied effectuating the removal of influence of features associated with an explanation reason class. One or more dropout operators may be stochastically applied to one or more input examples. The procedure includes on-manifold / on-distribution evaluation of the machine learning model under conditions of absence or presence of the one or more dropout operators for reliable calculation of numerical statistics associated with reason classes to yield model explanations. The training and evaluation procedures present advantages over traditional off-manifold or off-distribution perturbative explanation procedures.

The technical scheme of the invention discloses a method for judging weights of associated elements of process parameter data and quality data. The invention provides a method for analyzing relevance between process parameter data and quality data and endowing the process parameter data with weights. Aiming at the current situations that the industrial quality data acquisition sample size is small and part of values are easily identified as abnormal values when a traditional method similar to standard deviation is used, the method adopts a grouping comparison strategy when abnormal data are removed in data preprocessing, and effectively retains part of quality characteristics with large deviation. And a small amount of data still having dispute after deletion and selection is subjected to artificial expert review, so that the quality characteristics are further reserved, and the dependence on artificial deletion and selection is reduced. According to the method disclosed by the invention, in order to solve the problems that a model generated by machine learning is relatively poor in interpretability and relatively few in verification, an SHAP algorithm is adopted to carry out association construction on the model, process parameter weights are output, meanwhile, an output result is verified, and the correctness of a weight conclusion is ensured.

The invention discloses a Grad-CAM improvement method based on gradient flow direction correction and feature contribution degree redistribution, and relates to the technical field of deep learning model interpretation. Aiming at the defects that in a traditional Grad-CAM algorithm, gradient averaging causes positioning fuzziness, feature relevance is not considered in channel weight calculation, and the channel weight calculation only depends on single-level features, optimization is achieved through three key improvement steps that firstly, gradient flow direction tracking is adopted to replace global averaging to calculate channel weight, and gradient space distribution information is reserved; secondly, feature contribution degree redistribution is carried out based on channel cosine similarity, and weight superposition of redundant features is avoided; and finally, fusing the features of the intermediate layer to perform detail compensation, and enhancing the positioning precision of the thermodynamic diagram. The accuracy and robustness of model explanation are remarkably improved while the lightweight characteristic of an original algorithm is kept, and the method is particularly suitable for scenes needing high-precision explanation, such as model explanation analysis in the deep learning field.

The application discloses an interpretable heart sound anomaly recognition method and system based on a fractional domain Fourier transform, which comprises preprocessing, feature extraction, model establishment and model interpretation. The preprocessing comprises shearing, downsampling, filtering, amplitude normalization, heart cycle segmentation, frame segmentation and windowing in sequence; the feature extraction is configured to firstly perform fractional domain Fourier transform on the preprocessed heart sound, then extract frame-level Shannon entropy features of one-dimensional fractional domain heart sound signals, and calculate 13 statistical functions on the frame-level features as final features; the model establishment selects an XGBoost classifier; and the model interpretation selects a SHAP (SHapley Additive exPlanation) interpretation model. The application is easy to realize, simple in method, low in feature dimension, fast in model fitting, and has model prediction interpretability.

The application is suitable for the field of model explanation, and relates to a rule mining method and device for recommending model explanation, equipment and medium. For any user-item pair in graph data, a corresponding neighborhood graph and a connected subgraph are determined, a candidate subgraph is determined from the connected subgraph, a target subgraph is determined from the candidate subgraph according to a graph evaluation score, a target graph pattern is extracted from the target subgraph, for any variable in a pattern path of the target graph pattern, a target predicate is determined from all predicates corresponding to the variable, a candidate premise condition is formed by the variable and the target predicate, a candidate explanation rule is obtained according to the target graph pattern and a candidate premise condition set corresponding to all pattern paths in the target graph pattern, and a candidate explanation rule satisfying a preset condition is determined as a target explanation rule from all candidate explanation rules. The target explanation rule reflecting the prediction principle of the recommendation model is mined from the graph data as the global explanation of the recommendation model, and the effectiveness of the explanation is improved.

The invention relates to a medical waste intelligent identification method based on improved YOLOv11, and belongs to the field of medical waste intelligent identification. According to the method, a P4-ECA module is embedded in a YOLOv11 framework in a fixed point mode, a SlideLoss dynamic weighted regression function is introduced, SCID / MCID subsets are distinguished, a Grad-CAM + + interpretable mechanism is fused, system improvement is formed in the three aspects of structural design, loss optimization and model interpretation, and high-precision, high-robustness and interpretable intelligent recognition of the medical waste is achieved.

The invention relates to a cancer patient mental health prediction model based on multi-source data and application. The model comprises the following steps: utilizing electronic health record (EHR) data and longitudinal data of cancer patients in prospective queue research; constructing and verifying a prediction model in combination with multiple factors; carrying out model training and verification by utilizing a machine learning algorithm so as to realize early prediction of anxiety, depression and psychotic disorders; and quantifying the contribution of each factor to the psychological health risk through model interpretive analysis. Through multi-source data fusion and an advanced algorithm, the early recognition rate of the psychological health problem of the cancer patient can be effectively improved, resource waste and diagnosis delay are reduced, and the treatment effect and life quality of the patient are improved.

The invention discloses a method for constructing an intelligent colorectal cancer prediction model based on mass spectrum serum proteomics, which comprises the following steps of: screening out candidate micropeptides with diagnostic potential by combining high-precision mass spectrum quantification with AI function prediction, and further constructing the model by adopting an ensemble learning algorithm. The method is rigorous in process, and by introducing an advanced normalization algorithm, integrating a feature selection strategy and targeted sample imbalance processing, the biomarker screening robustness and the prediction model accuracy are remarkably improved. Meanwhile, through model interpretive analysis, theoretical support is provided for clinical application of the marker.

A method for security assessment of a malicious code detection model based on reconstruction of API sequence features belongs to the field of software security technology. The present invention focuses on this defect of the malicious code detection model. For the malicious code detection model that uses API sequence as a feature, a large-scale sample set is constructed, and the API sequence is extracted from the sample set. After being processed by feature engineering, it is used as the input of the model to construct a fitting model of the model to be detected. The features are interpreted by the model interpretation algorithm, and the influence of each feature on the model classification result is analyzed, wherein black features are conducive to the model classifying the sample as malicious, and white features are conducive to the model classifying the sample as benign. Without changing the original function of the sample, the binary rewriting method of inserting new sections is used to try to destroy the black features, and a test sample is generated to evaluate the security of the model. The present invention can effectively verify the security of the malicious code detection model and assist in the reinforcement and repair of the malicious code detection model.

The invention relates to the technical field of urban landscaping, and discloses a street tree crown coverage benefit evaluation and optimization method, which comprises the following steps: S1, collecting multi-source data of street trees in a target area; s2, performing fusion processing on the multi-source data, extracting feature parameters for evaluation, inputting the feature parameters into a pre-trained crown benefit evaluation model, and outputting a comprehensive benefit score of crown coverage by the model; wherein the crown benefit evaluation model is a machine learning model obtained by training sample data with expert score labels; and S3, based on the comprehensive benefit score and a benefit restriction factor identified through model interpretive analysis, matching and generating a targeted crown optimization scheme from a pre-constructed optimization strategy knowledge base. According to the method, the street tree crown coverage benefit evaluation and optimization of the complex urban environment can be systematically completed, the evaluation accuracy is relatively high, and the method has dynamics and operability.