7 results about "Applicability domain" patented technology

The invention discloses a deep-water explosion container dynamic response prediction method, and relates to the technical field of deep-water structure safety protection, a deep learning prediction model is established, material characteristic parameters and external load parameters are taken as inputs, container dynamic response indexes are taken as outputs, model training, verification and testing are carried out by using a sample set, and a deep-water explosion container dynamic response prediction model is obtained. And a deep-water explosion container dynamic response prediction model capable of rapidly predicting the dynamic response of the container is obtained. According to the method, a high-quality training data set is constructed through numerical simulation, so that the physical authenticity and prediction precision of a machine learning model are ensured; and the trained model can realize rapid prediction of dynamic response, so that the problem that the precision and the efficiency are difficult to balance in the existing method is effectively solved, and the requirements of rapid evaluation and real-time early warning in engineering are met. The data set contains the explosion load parameters and the deepwater environment parameters, the defect that the application range of a traditional empirical formula is narrow is overcome, and the engineering application cost is reduced.

This invention relates to the field of land consolidation carbon effect assessment technology, and discloses a system and method for quantitative assessment of carbon effects based on land consolidation type. The system includes a regional semantic layer module, a consolidation project semantic layer module, and a parameter semantic layer module. It also includes a parameter semantic processing module for constructing a structured semantic representation of carbon factor parameters. These carbon factor parameters are associated with an uncertainty descriptor ontology, which encapsulates metadata information characterizing the statistical uncertainty and applicability constraints of the carbon factor parameters. This system and method for quantitative assessment of carbon effects based on land consolidation type establishes a semantic mapping relationship between the regional semantic layer, the consolidation project semantic layer, and the parameter semantic layer through a cross-layer semantic association module. This accurately determines the applicability of parameters, avoids assessment bias caused by parameter misuse, and effectively solves the problems of low coverage and poor regional adaptability of localized parameters.

The disclosure provides a clinical detection index uniform evaluation method, system, device and medium, which combines inter-laboratory quality evaluation data and biological variation data, and performs stratification and preprocessing on the inter-laboratory quality evaluation data to form several subgroups, constructs a precise quantitative uniform evaluation index, and calculates the uniform evaluation index of each subgroup based on the inter-laboratory quality evaluation data of each subgroup, the allowable total error and the allowable total error of several levels of biological variation data, solves the limitations of the existing evaluation method, is more objective, has a wider application range, is more accurate and reliable, is more suitable for clinical actual needs, has stronger practicality, is more targeted in guiding laboratory quality improvement, improves the improvement efficiency, and can realize comprehensive, accurate, objective and extensive evaluation of the uniform level of detection results.

The invention provides a chemical risk prediction model based on interpretable machine learning and a construction method thereof, and the method comprises the steps: S1, obtaining chemical data with risk endpoints, S2, generating a high-dimensional feature set containing physicochemical properties and structural topology for a molecular structure through employing a molecular descriptor and a fingerprint calculation platform; s3, performing comparison modeling on each risk endpoint by independently adopting different types of machine learning models, re-training an optimal model on a training set, and reporting a final result in an independent prediction set; s4, the model application range of the optimal model is determined, and an application domain framework of the model is constructed based on conformal prediction, and S5, the importance of global and sample-level key descriptors is output; and finally, batch reasoning and result exporting: outputting a prediction label, a prediction probability, an application domain framework mark, a significance level and an explanatory result one by one for a chemical list corresponding to the target chemical data.

The application provides a member inference attack defense method, device, equipment and storage medium, including: training a teacher model according to a privacy data set, adjusting a target model by using a dynamic adjustment loss target algorithm; the dynamic adjustment loss target algorithm includes: combining the feedback result of test data in each round of the target model with the RelaxLoss technology, to ensure that the method is widely applicable; using the knowledge distillation technology to ensure that the model can be normally fitted; dynamically optimizing the learning path problem of the student model through the performance of the training data, to improve the attack resistance of the model; implementing member inference defense according to the continuous iteration optimization of the loss target; the determination result includes: unable to judge whether the data belongs to the training data set or the test data set, thereby solving the technical problems that the traditional regularization method focuses on the utility ability of the model, cannot effectively solve the privacy security problem of the model, and the regularization method for the member inference attack cannot be popularized and promoted due to the limitation of the loss target.

The invention provides a method for constructing an empirical prediction model for leakage flow of a sealed cavity of a gas compressor. The method comprises the following steps: S1, determining a model application range and input and output parameter definitions; s2, collecting leakage flow test data of the sealed cavity of the gas compressor; s3, preprocessing an original test data set; s4, determining a basic form of the experience prediction model; s5, model parameter fitting calculation; s6, performing preliminary model verification and error analysis; s7, optimizing and adjusting the model; and S8, verifying the applicability of the model and finally outputting the model. Through systematic test design, data processing and multi-algorithm collaborative optimization, organic unification of leakage flow prediction precision, application range and engineering practicability is realized, and a reliable tool is provided for design and optimization of a gas compressor sealing system.

The invention discloses a cross-domain recommendation method and system based on federated learning and self-distillation, and the method comprises the steps: carrying out the multi-dimensional semantic analysis and enhancement of an article in each participation domain, and generating an article semantic enhancement representation fused with world knowledge; and jointly training a global representation mapping function through a federated learning framework, and mapping semantic representation of each domain to a unified collaborative representation space. And carrying out sequence modeling in each domain based on a user historical interaction sequence to generate a user representation. Meanwhile, a teacher-student matching relationship is constructed based on semantic similarity by identifying long-tail and hot articles, and knowledge of the hot articles is migrated to the long-tail articles by using a self-distillation mechanism. And finally, each domain independently constructs a recommendation model for matching scoring and sorting based on the user representation and the optimized article representation, and a personalized recommendation list is generated. Safe migration of cross-domain knowledge and effective relieving of intra-domain data imbalance are achieved, the recommendation effect is improved, and the application range is widened.