1065 results about "Logistic regression" patented technology

The invention relates to the technical field of vehicle insurance marketing management, in particular to a vehicle insurance channel whole-process marketing management method and system, and the method comprises the steps: collecting and integrating various data of clients from multiple data sources to construct a resource library; carrying out customer segmentation and accurate portraying by utilizing algorithms such as clustering analysis and the like; predicting demands based on the portraits, historical behaviors and seasonal factors; personalized pricing is made in combination with characteristics such as risk levels; predicting customer loss by means of logistic regression and the like; implementing a corresponding customer management strategy according to the loss prediction; carrying out personalized recommendation by adopting a deep learning recommendation algorithm; advertisement putting is optimized in combination with a dobby machine and reinforcement learning; evaluating the risk by using multiple algorithms; fraud is prevented and controlled through anomaly detection; optimizing a claim settlement process based on the claim settlement data; and the marketing and advertising effects are evaluated through A / B testing and the like. According to the method, the precision marketing level can be improved, pricing and risk control are optimized, efficient operation and decision support are realized, and the market competitiveness and sustainable development capability of companies are enhanced.

The invention provides a science and technology finance platform data sharing method, which comprises the following steps: extracting key field information and a metadata label from a data stream of a science and technology finance platform, the key field information comprising data content and a source identifier; analyzing a data type characteristic value according to the metadata label, and determining a data type and a corresponding sensitivity level by adopting a logistic regression model; querying a source credibility rule base based on the source identifier, and determining a risk level of the data source; according to the sensitivity level, the risk level and the receiver permission identifier, calculating to obtain a dynamic sensitivity score and generating a dynamic sensitivity tag; according to the risk level mapping table, in combination with the sensitivity level, determining a final desensitization mode of the field; and performing format verification on the processed data stream, transmitting the processed data stream, and recording execution information of the dynamic sensitivity label and the desensitization strategy.

The invention discloses an antagonism prompt detection method and device based on a large language model and a medium, and belongs to the technical field of artificial intelligence safety. The technical problem to be solved by the invention is how to overcome the defects of static rule lagging, high manual maintenance cost and insufficient context understanding in the security protection process of a large language model in the prior art, and dynamic, real-time and high-precision antagonism prompt detection is realized. According to the technical scheme, the method comprises the following steps: feature extraction: comprehensively analyzing semantic information, structural information and context information in a user text, extracting semantic features, structural features and context features, performing Min-Max normalization on the semantic features, the structural features and the context features, and splicing the semantic features, the structural features and the context features into a 128-dimensional joint vector, performing feature selection on the joint vector through an L1 regularization logistic regression model, compressing to 10-dimensional core features, and removing redundant information; carrying out resistance scoring; and dynamically defending.

The invention discloses an IT asset fault propagation prediction method and system based on dynamic evolution of a knowledge graph, and relates to the technical field of cloud computing and large-scale IT operation and maintenance management. Through an asynchronous message bus and a logic clock, the knowledge graph is updated immediately when resources are abnormal and a scheduling event occurs; the knowledge graph uniformly integrates physical connection, logic dependence and multi-copy redundancy, so that the cross-machine-room asset relationship is clear at a glance. And then, based on a weighted logistic regression model, node features and relation weights in the knowledge graph are fused, the node fault probability is accurately calculated, the limitation of traditional single-dimensional analysis is solved, self-healing operation is supported, end-to-end intelligent operation and maintenance from fault detection to prediction and early warning to closed-loop self-healing are realized, and the fault detection efficiency is improved. The problems that in a cross-machine-room and multi-live-site environment, resource topology is split, real-time state and alarm information cannot be fused with an asset dependence model, and large-scale real-time deployment of a traditional single-dimensional fault analysis and high-complexity prediction algorithm is difficult are effectively solved.

The invention relates to the technical field of tea leaf detection, and discloses a tea leaf quality grade detection method and system.The method comprises the steps that a tea leaf sample is collected and pretreated; extracting chemical component indexes and physical properties of the pretreated tea leaves, and performing fusion and analysis; and establishing a tea quality grade classification model, inputting characteristics of a tea sample to be detected, outputting a detection result, and generating a tea quality grade report. Through combination of the support vector machine, the gradient boosting decision tree and the improved logistic regression algorithm, the precision of the tea quality classification model is optimized. The dynamic threshold function and the segmented excitation function are introduced to further solve the boundary fuzzy problem of the high-grade tea leaves and the low-grade tea leaves, and accurate judgment of tea leaf grade classification is achieved. And data restoration is carried out through weighted compensation correction and a recheck process, so that the output tea grade report is ensured to have high accuracy and reliability.

The invention discloses a landslide disaster early warning system and method, and belongs to the technical field of geological disaster monitoring, and the method comprises the steps: carrying out the omnibearing monitoring of a target region, and collecting monitoring data; the method comprises the following steps: preprocessing collected monitoring data to obtain monitoring processing data; analyzing the monitoring processing data, and performing feature extraction to obtain a target feature vector; constructing a landslide disaster risk assessment model by adopting logistic regression and a decision tree; acquiring historical monitoring data according to a large amount of historical data and landslide cases, and training the model by using the historical monitoring data; real-time monitoring data are collected and input into the landslide disaster risk assessment model, the landslide risk level of the target area at the current moment is judged, and a corresponding early warning prompt is given; the method comprehensively considers the linear and non-linear relationship of the data, can accurately evaluate the landslide risk grade of the target area, and gives out graded early warning prompts. Compared with an existing scheme, the method has the advantage that the monitoring data source, the data processing precision and the model prediction capability are remarkably improved.

The invention relates to a construction method for predicting the film thickness of a double-sided local coating based on a machine learning simulation model, and belongs to the technical field of electroplating. According to the method, the LR logistic regression model is perfected and constructed through the machine learning simulation model, and the LR logistic regression model is trained by utilizing the constructed logistic regression model, so that the optimal electronic electroplating production conditions of semiconductor devices with different structures can be quickly determined, and the optimal plating piece double-sided local electronic electroplating control mode is further obtained; according to the method, the accuracy of predicting the thickness of the double-sided local coating of the semiconductor device can be realized, the error with the thickness of the coating of an actual electroplating product can be greatly reduced, further improvement of an electronic electroplating module can be realized, the uniformity of the thickness of the double-sided local coating of the semiconductor device can be improved, and the requirement of high quality of the semiconductor device can be met.

The invention relates to an advanced gastric cancer survival prediction system based on Lasso regression, Cox regression and an interpretable machine learning technology, and belongs to the technical field of medical artificial intelligence and intelligent decision support. According to the system, by collecting multi-modal clinical data (including demographic information, TNM staging, treatment modes, tumor grading and the like) of a patient, survival-related variables are screened by adopting Lasso regression and a Cox proportional risk model, and an optimized feature set is constructed. Based on the feature set, the system integrates various mainstream machine learning algorithms (such as XGBoost, Random Forest, SVM, Logistic regression and the like) to construct a prediction model, compares the performance of each model, and selects a model with an optimal effect as a main model. And hyper-parameter tuning is performed on the model through grid search and cross validation, so that the precision and generalization ability of the model are improved. An SHAP interpretability analysis method is introduced into the system, transparent interpretation is carried out on a model output result from the global level and the individual level, and the importance and directional effect of all variables in survival prediction are determined. Finally, the model is deployed on a terminal device, a doctor is supported to automatically output the survival probability and an explanation result after inputting patient information, and a reference basis is provided for clinical treatment decision and personalized management. The system has the advantages of high prediction precision, high interpretability, convenience in use, sustainable optimization and the like, is suitable for clinical aid decision-making scenes, and has good application prospects and popularization values.

The invention provides a shield adaptability adjusting method based on a stratum structure, which comprises the following steps: acquiring geological parameters of a construction area of a shield tunneling machine through drilling and geophysical prospecting, and arranging sensors at key positions of the shield tunneling machine to acquire construction parameters of the shield tunneling machine in real time; a convolutional neural network CNN is adopted to analyze the geological parameters to identify stratum features, and a geological model is constructed based on the identified stratum features; constructing a disaster risk index system, and predicting a disaster risk based on the geological model and the construction parameters by adopting Logistic regression and a random forest algorithm; according to the predicted disaster risk, the cutterhead configuration of the shield tunneling machine is dynamically adjusted, and tunneling parameters are optimized or a muck improvement scheme is adopted; by monitoring geological parameters, construction parameters and environmental changes in real time, a multistage early warning mechanism is adopted to trigger emergency response measures, and construction safety is guaranteed. According to the method, the safety and efficiency of shield construction can be improved, the geological disaster risk is reduced, and reliable technical guarantee is provided for underground space development.

The invention relates to the technical field of unit detection, in particular to a unit magnetic variable on-line monitoring method and system, and the method comprises the steps: carrying out the multi-source data collection through a sensor, carrying out the correction of the multi-source data through a multi-dimensional calibration mechanism, synchronizing a timestamp through a dual-synchronization system, and carrying out the frequency-band-divided conditioning and standardization processing; environmental noise in the standardized multi-source data is eliminated through an intelligent algorithm, feature vectors are extracted, and purified feature vectors are obtained; screening effective abnormal features through an isolation forest algorithm; and inputting the effective abnormal features into an LSTM prediction model to obtain a corrected prediction value, substituting the corrected prediction value into a logistic regression formula to obtain a fault prediction probability of fault occurrence, calculating a health degree score, and performing graded early warning according to the health degree score. According to the scheme, through multi-dimensional calibration, working condition adaptive feature extraction and graded early warning, the unit monitoring data precision, the fault feature recognition accuracy and the operation and maintenance decision efficiency are improved.

The invention relates to the technical field of the Internet of Things, and particularly discloses a machine room equipment remote operation and maintenance management method and system based on the Internet of Things technology, and the method specifically comprises the steps: collecting the operation state data of machine room equipment in real time through an Internet of Things sensor network, and obtaining the mean value and standard deviation of the historical operation data of the equipment; transmitting the data to a cloud server through a 5G network; the cloud server performs data cleaning, format conversion and storage, and establishes a unified equipment operation database; performing principal component analysis on the standardized data, extracting main feature vectors, and calculating the contribution rate of each operation parameter; calculating a total weight according to the contribution rate of each operation parameter, mapping the total weight to an original parameter, and respectively calculating a weight corresponding to each operation parameter; calculating a device health degree score based on the device operation data; selecting a logistic regression model, establishing a fault prediction model and calculating a fault probability; and comparing the fault probability with a preset threshold value, and determining whether fault early warning is triggered or not.

The invention discloses an equipment abnormity monitoring method and system based on the Internet of Things, and relates to the technical field of intelligent operation and maintenance of the Internet of Things, and the method comprises the steps: collecting monitoring data to generate a high-dimensional original matrix, carrying out the optimization through employing a GCN model and combining with ACO, carrying out the updating through a comparison learning model and an FCM algorithm, and carrying out the searching of global optimum through employing a VAE model and combining with a PSO algorithm. The method comprises the steps of performing classification optimization based on K-means clustering and BSO, performing MLE calculation, updating dynamic causal KG through Granger causal test, generating a multi-modal result array through NSM, a scoring formula, a naive Bayesian model, a Mahalanobis distance formula and a logistic regression model, and performing optimization by using a fuzzy rule and GWO. According to the method, the GCN model is combined with the adaptive optimization algorithm, the precision and response speed of anomaly monitoring are improved, optimization is carried out by using the fuzzy rule and introducing the GWO based on multi-modal causal reasoning, and the reliability and efficiency of anomaly monitoring are improved.

The invention discloses an intelligent financial question and answer system based on a large language model, and relates to the technical field of financial question and answer, the system solves the problems of financial term ambiguity and context ambiguity through cooperative work of a plurality of modules, and the system comprises the following modules: a context recognition module, a query module and a query module, a natural language processing algorithm is combined with a context analysis technology in the financial field to automatically extract context clues in user questions; and a financial term knowledge base module. According to the method, context recognition and a financial term knowledge base are combined, and the accuracy of understanding the term ambiguity and the complex context is improved through the graph neural network. And the intelligent recommendation module dynamically provides personalized financial suggestions by using collaborative filtering and content recommendation algorithms in combination with user history and market data, and performs real-time adjustment. The risk assessment and prompt module assesses risks through a Bayesian network and a logistic regression model, and the adaptive learning module continuously optimizes risk prediction and helps users to avoid financial risks.

The invention relates to the technical field of electric power operation and maintenance management, in particular to a transformer area intelligent operation and maintenance device and method based on a machine learning expert model, and the device comprises a logistic regression machine learning module and a robot process automation module. Real-time perception and data analysis of a business scene are realized by means of artificial intelligence, total data information of a master station measurement domain and an operation and maintenance work task is dynamically collected, incremental data is continuously utilized for data analysis and rule mining, a machine learning expert model is introduced, and the operation and maintenance efficiency is improved. A transformer area intelligent operation and maintenance system integrating human-computer interaction such as operation and maintenance index intelligent monitoring and analysis, intelligent abnormity diagnosis, intelligent operation list generation, intelligent dispatching, intelligent path planning and field operation guidance is constructed, service data is analyzed in real time, meanwhile, a robot process automation technology is integrated, automatic operation of a part of processes is achieved, and operation efficiency is improved. And support is provided for on-site acquisition operation and maintenance work.

The invention discloses an on-load tap-changer vibration fault diagnosis algorithm based on tensor feature and adaptive weighted Stacking integration, relates to the technical field of on-load tap-changer fault diagnosis, and is used for improving the fault diagnosis precision. Comprising the following steps: S1, data acquisition; s2, feature extraction; the method comprises the following steps: extracting multi-scale time-frequency characteristics of an on-load tap-changer vibration signal by using wavelet scattering transform WST, and realizing low-rank decomposition and dimensionality reduction characterization of high-dimensional characteristics by combining a non-negative tensor decomposition model NTF; s3, fault diagnosis; a multi-base learner Stacking integration framework is adopted, and a prediction matrix is generated through K-fold cross validation; through a swarm intelligent optimization algorithm SRA, hyper-parameters and fusion weights of all base learners are adjusted, L2 regularization suppression over-fitting is introduced, and finally fault classification is realized by adopting a logic regression element learner with Softmax cross entropy. According to the invention, through fault diagnosis of multi-model adaptive fusion and optimization, the fault identification precision, stability and on-line monitoring capability are improved.

The invention discloses a dynamic library management method and system based on artificial intelligence, and relates to the technical field of library management, and the method comprises the following five steps: firstly, constructing a reader portrait through collecting basic information, borrowing history and other data of a reader by using TF-IDF analysis and a machine learning algorithm; secondly, a positioning tag and a sensor are deployed to be combined with a book RFID tag, a path is optimized according to reader behavior data, and the book retrieval efficiency is improved; monitoring and analyzing borrowing behavior data and reader portraits, establishing a borrowing risk assessment model, assessing risks by adopting a logistic regression algorithm, providing decision suggestions for workers, quantitatively adjusting the borrowing quantity, and reducing the risk of overdue or damaged books; through application of the artificial intelligence technology, automation, intellectualization and individuation of library management are realized, the management efficiency and the service quality are remarkably improved, and the operation effect of the library is enhanced.

The invention relates to the technical field of medical emergency monitoring, in particular to an ICU emergency response system which comprises a preliminary risk assessment module, an emergency recognition module, a treatment scheme optimization module, a vital sign monitoring module, an emergency response coordination module, a disease evolution prediction module, a resource allocation management module and a medical decision support module. According to the method, feature engineering and logistic regression analysis are combined with medical history and real-time vital signs of a patient, emergency medical events are recognized by applying pattern recognition and natural language processing, a treatment scheme is optimized by using a support vector machine and a decision tree, personalized treatment suggestions are provided, and the time sequence and a biometric method are used for finely monitoring the vital signs; health risks are early warned, resources are reasonably allocated in emergency response through a resource scheduling algorithm and a priority queue, illness state prediction is assisted through machine learning and probability statistics, resource utilization is improved through linear programming and a resource optimization strategy, and waste is reduced.

The invention provides an intelligent optimization advertisement putting method, which belongs to the technical field of advertisement putting channel strategies, and is characterized in that interaction between users and advertisements is enhanced through multi-dimensional user feature extraction, double-tower model matching and a multi-head self-attention mechanism, advertisement matching scores are accurately calculated, and contribution of the advertisements to GMV is evaluated in combination with a multi-contact attribution model; the advertisement conversion rate is predicted through a logistic regression dichotomy model, the payment capacity of a user is evaluated in combination with a user lifetime value model, and an ROI prediction model is constructed to optimize advertisement budget allocation; the advertisement effect and the ROI are monitored in real time, the putting strategy is dynamically adjusted, and high efficiency and sustainability of advertisement putting are ensured. According to the method, accurate user matching, efficient cost control and global optimization are realized, the return on investment of advertisers and the long-term value of the users are improved, the flexibility and adaptability of advertisement putting are ensured, and a transparent and explainable putting solution is provided for the advertisers.

The invention discloses an intelligent and automatic transformer substation information acquisition system, which relates to the technical field of information acquisition, and is characterized in that an information change coefficient and an information priority coefficient are acquired and substituted into a logistic regression model to obtain an information potential evaluation coefficient, the information potential evaluation coefficient is analyzed with a preset potential threshold to obtain a comparison result, and the transformer substation information is acquired according to the comparison result. Dividing to obtain a real-time acquisition potential information set and a non-real-time acquisition potential information set, substituting into a default score combination mechanism, determining an actual classification acquisition result of each piece of information, obtaining a network state when each piece of information is uploaded, obtaining a network delay degree and a bandwidth utilization rate from the network state, and substituting into fuzzy logic for fuzzy reasoning to obtain a real-time acquisition potential information set and a non-real-time acquisition potential information set; according to the method, the reasonability result of the default score combination mechanism is determined, then the network delay degree and the bandwidth utilization rate when each piece of information is uploaded are substituted into set parameters in the default score combination mechanism, the score combination mechanism is determined and adjusted, and the information redundancy and the system burden are reduced.

The invention relates to the technical field of case retrieval and analysis, in particular to a method and a system for retrieving and analyzing unhealthy asset cases. The method comprises the following steps of performing cleaning, standardization and feature extraction on collected enterprise financial data, market information and historical cases; performing primary screening on the cleaned structured data based on a dynamic weight logistic regression rule, performing feature extraction on the high-risk candidate case set to obtain structured features # imgabs0 # of the high-risk candidate case set, and constructing a multi-layer knowledge graph based on an SPO triple; taking the spliced mixed feature # imgabs1 # as the input of a graph enhanced mixed gradient lifting model, and obtaining a finely screened high-risk case; and a progressive training strategy is adopted to train the graph enhanced mixed gradient lifting model, and the contribution of the structured features and the graph features to the prediction result is balanced. A multi-layer knowledge graph with space-time attributes introduced is constructed, the risk propagation weight is dynamically calculated in combination with a space-time diagram attention network, and the dynamism and accuracy of risk path identification are improved.

The invention provides an insurance product pushing method and system for modeling by using user interests, which can accurately capture relevance and characteristics between user behaviors by constructing target interaction behavior graph structure data, and perform user interest modeling by using a logistic regression network and a random forest tree network respectively, so as to improve the user interests. And two types of modeling data are fused, so that the interests, preferences and potential demands of the user can be reflected more comprehensively. In addition, network parameter learning is carried out by adopting different example product interaction behavior data sequences, so that the accuracy and robustness of user interest modeling are further improved. Finally, insurance product pushing is carried out based on the target user interest modeling data, the pushing accuracy and the user satisfaction degree can be remarkably improved, and data support is provided for personalized and intelligent recommendation of insurance products.

The invention provides an AI-based clinical research scheme optimization method and system, and relates to the technical field of clinical research, and the method comprises the steps: collecting current clinical test data, and extracting basic features and derivative features related to the recruitment efficiency and shedding rate of a patient from the current clinical test data; the extracted basic features and derivative features are input into a plurality of different pre-trained multivariable regression models at the same time, preliminary optimization suggestions are output through the multivariable regression models, and the multiple different multivariable regression models comprise a multiple linear regression base model, a Logistic regression base model and a random forest base model; inputting the preliminary optimization suggestions output by each multivariable regression model into a pre-trained meta-model, and generating a final optimization suggestion by integrating the multiple preliminary optimization suggestions by the meta-model; and based on the final optimization suggestion, executing the optimization of the clinical research scheme, and achieving the purposes of improving the recruitment efficiency of the patient and reducing the falling-off rate.

The invention provides an automatic risk control management system for financial credit business. The automatic risk control management system comprises a data acquisition module used for acquiring user credit behavior data and third-party credit investigation data in real time; the feature processing module is used for performing cleaning, dimension reduction and feature enhancement on the data; the risk assessment module outputs a user risk score based on an improved logistic regression model; the decision execution module generates a loan decision according to the risk score and the dynamic threshold; and the model optimization module performs adaptive adjustment on model parameters through feedback data. According to the invention, efficient and accurate risk assessment and decision can be realized, the risk management capability of credit business is improved, the default risk is reduced, and the business efficiency and the user experience are improved at the same time.

The invention discloses a health care service data management method based on machine learning, and relates to the technical field of data management. The method comprises the following steps: collecting health care service data in real time, constructing a health care knowledge graph, and carrying out feature dynamic alignment on the health care knowledge graph by adopting agency attention and multi-scale contrast learning to obtain a dynamic alignment feature vector; based on the dynamic alignment feature vectors, training CatBoost, XGBoost and a random forest model through Bayesian optimization, and obtaining a health prediction model through stacking generalization fusion of a logistic regression model; inputting the dynamic alignment feature vector into a health prediction model, and outputting to obtain a prediction result; corresponding service measures are executed according to the prediction result, new data are collected again after the service measures are executed, the health care knowledge graph is updated, and therefore management of health care service data is achieved.

The invention discloses a real-time power generation load estimation method and system for photovoltaic power generation, relates to the technical field of photovoltaic power generation load estimation, and aims to solve the problems of state judgment delay and model mismatching and misestimation caused by short-time cloud shadow rapid movement. The method comprises the following steps: collecting power, current, voltage, irradiance and temperature signals through a multi-array sensor, separating a high-frequency characteristic signal from a low-frequency characteristic signal through high-pass / low-pass filtering, and generating a static baseline multi-dimensional characteristic vector; based on the power spectrum entropy, adaptively adjusting a time window and extracting dynamic characteristics; fusing the static and dynamic characteristics to generate discrimination input; performing state judgment by adopting a logistic regression model, and starting extended Kalman filtering online correction when an energy residual exceeds a threshold; and model drift is detected based on CUSUM and Shewhart algorithms, and an incremental training set is automatically constructed to update model parameters. And high-precision and low-delay real-time power generation load estimation and operation and maintenance support under a short-time cloud shadow condition are realized.

The invention relates to a construction method of a metabolic syndrome phlegm syndrome lipid metabolism characteristic diagnosis model. The construction method comprises the following steps: S1, acquiring a serum sample; s2, carrying out lipid metabolite analysis through a full-quantitative lipidomics formula; s3, carrying out primary screening on differential metabolites; s4, optimizing the characteristic indexes by using a random forest algorithm and stepwise regression; and S5, constructing a differential metabolite diagnosis model through Logistic regression analysis. By analyzing differential lipid metabolites of patients with MetS phlegm syndromes and non-phlegm syndromes, the invention reveals that abnormal accumulation of lipid and lipid metabolites may be the core pathological parenchyma of MetS phlegm syndromes. By integrating lipid metabonomics data, using a random forest algorithm, stepwise regression and other methods to screen feature difference lipid metabolites and construct a MetS phlegm syndrome specific diagnosis model, a novel combined biomarker and evidence-based basis are provided for early diagnosis of MetS phlegm syndromes, and a scientific basis can also be provided for objective diagnosis of traditional Chinese medicine phlegm syndromes.

The invention discloses a high-temperature equipment fault identification method and system based on cooperative imaging, and particularly relates to the technical field of fault identification, and the method comprises the steps: building an offline ROI identification model in combination with historical data, achieving the initial ROI region configuration of high-temperature equipment before the high-temperature equipment is online, and achieving the fault identification of the high-temperature equipment through an online mechanism driven by a multi-modal image and real-time data in the operation process. And continuously and dynamically updating the ROI, performing first-order and second-order differential analysis on temperature gradients of the standard high-temperature equipment and the actual equipment in a monitoring interval based on ROI imaging data of the standard and actual high-temperature equipment, and determining image information of the ROI by using KL divergence calculation based on a kernel density estimation result of a grayscale image, geometric features and spatial positions of initial defects of the high-temperature equipment are extracted, PCA analysis and Euclidean distance calculation are combined, a logistic regression model is constructed, influence information of the ROI is determined, and the fault identification comprehensiveness and accuracy can be improved.

The invention belongs to the technical field of health assessment, and particularly relates to an aging clock construction method based on a causal machine joint model. The method comprises the steps of 1, obtaining a multi-modal data set of a target crowd based on multi-modal data fusion and standardization preprocessing; 2, performing two-stage screening on the multi-modal data set to obtain core features; 3, analyzing interaction among multiple groups of schools based on the extended proportion advantage logistic regression hybrid model, and then carrying out P value calibration based on a fused saddle point approximation method; 4, constructing an aging clock based on a mixed causal effect graph model, evaluating a multi-dimensional causal relationship, and calculating the biological age of the individual; according to the method, clinical phenotype data and multi-omics data are fused, a machine learning and causal inference combined method is adopted, the individual aging degree and health risk are accurately analyzed, a high-performance aging clock model is provided for primary medical institutions, and scientific basis and decision support are provided for health management and early disease intervention.

The invention relates to the technical field of artificial intelligence, finance and medical health, and provides a retrieval method, device and equipment based on attention guidance and a medium. Training data is constructed according to the correlation between each specified lexical element and a retrieval question and a retrieval answer and the attention feature vector of each specified lexical element; a logistic regression classifier is trained to obtain a detector, and the light-weight detector can be used for recognizing utilized lexical elements in real time in the reasoning process, so that the higher-degree explanation of the generation process is realized; when the retrieval model is used for retrieval, the detector is used for detecting the target lexical elements which are being used in real time, the original probability distribution is corrected according to the utilization probability of each target lexical element so as to control the retrieval model to output the retrieval result, and the output probability of the used lexical elements is dynamically enhanced. Therefore, the attention mechanism of the guide model is dynamically focused on the context information highly related to the user query, and the context illusion phenomenon is fundamentally reduced.

The invention discloses an HER2 state recognition method and system based on an IHC and HE bimodal image, and relates to the medical image processing and analysis technology, and the method comprises the steps: carrying out the preprocessing of a full-slice image WSI containing IHC and HE, and cutting the WSI into designated image blocks; constructing a multi-task learning framework to classify image blocks obtained by cutting the IHC image, and determining HER2 expression intensity in the tumor region; calculating the area ratio of the image block corresponding to each grade in the tumor region to calculate an IHC HER2 score; taking each image block of the cut HE image as the input of a Prov-GigaPath model, and aggregating the multi-dimensional features of each image block by using an ABMIL model, and taking the aggregated multi-dimensional features as an HE HER2 score; and converting the IHC HER2 score and the HE HER2 score into one-hot codes, and outputting an HER2 judgment result by using a logistic regression model. The HER2 state interpretation result can be quickly output, a pathologist is assisted in diagnosis, and the diagnosis efficiency and accuracy are improved.