37 results about "Class model" patented technology

The invention provides a rheumatoid arthritis patient low muscle quality risk prediction method based on an uncertainty perception stacked meta-learning structure, and belongs to the technical field of machine learning. The method comprises the following steps: acquiring a rheumatoid arthritis data set; constructing a base learner set comprising a table Transform class network and a gradient boosting tree class model; splicing the out-of-fold prediction probabilities of all the base learners and the statistics thereof to form a meta-feature matrix; taking the meta feature matrix as input, and constructing and training a meta learner comprising a spectrum normalization multilayer perceptron and a random feature Gaussian process output layer; collecting to-be-detected data, inputting the to-be-detected data into the trained base learner set and the trained meta learner in sequence, and performing temperature scaling and beta-calibration on a prediction result; and taking the calibrated prediction probability as a final prediction result. Through multi-source data fusion, the defects of an existing model in the aspects of practicability, probability reliability and the like are overcome.

The invention provides a question reply method and device and electronic equipment, and relates to the technical field of artificial intelligence such as human-computer interaction, natural language understanding, large models and light weight. The method comprises the steps of obtaining a to-be-processed question input by a user in a current session; a plurality of alternative models associated with the to-be-processed problem are utilized to process the to-be-processed problem in parallel to obtain a plurality of candidate replies, the alternative models comprise at least one first-class model and at least one second-class model, and the parameter scale and / or single call cost of the first-class model are / is lower than that of the second-class model; determining a target model in the plurality of alternative models according to behavior information of the user for the plurality of candidate replies; and during the duration of the current session, generating corresponding reply contents for the input subsequent questions by using the target model. According to the method, the target model conforming to user preferences can be rapidly and clearly determined by simultaneously presenting the behavior information of the multiple candidate replies to the multiple alternative models by the user, and the interaction turns and the clarification cost are reduced.

An Artificial Intelligence (AI) based computational system is used to non-invasively estimate the presence of a range of aneuploidies and mosaicism in an image of embryo prior to implantation. Aneuploidies and mosaicism with similar risks of adverse outcomes are grouped and training images are labelled with their group. Separate AI models are trained for each group using the same training dataset and the separate models are then combined, such as by using an Ensemble or Distillation approach to develop a model that can identify a wide range of aneuploidy and mosaicism risks. The AI model for a group is generated by training multiple models including binary models, hierarchical layered models and a multi-class model. In particular the hierarchical layered models are generated by assigning quality labels to images. At each layer the training set is partitioned in the best quality images and other images. The model at that layer is trained on the best quality images, and the other images are passed down to the next layer and the process repeated (so the remaining images are separated into next best quality images and other images). The final model can then be used to non-invasively identify aneuploidy and mosaicism and associated risk of adverse outcomes from an image of an embryo prior to implantation.

The invention discloses a class model inspection method, electronic equipment, a storage medium and a product. The method comprises the steps of obtaining context information of a target micro-service application in response to a class model check request from a client; performing class model compliance check based on the context information to generate a corresponding error check result; wherein the class model compliance check comprises at least one of the following items: class member reference validity check, interface and abstract method implementation integrity check, technical suite compatibility check, class name uniqueness check and request path uniqueness check; sending an error checking result to the client for visual display; receiving a correction instruction from the client; the correction instruction is associated with a target error item in the error checking result; and executing a response operation corresponding to the correction instruction. According to the scheme, the multi-dimensional compliance check is executed based on the micro-service context, and the class model design quality and efficiency are improved through visual interaction and intelligent response.

The application provides a bimodal scene lightweight vertical model construction method and system and electronic equipment, by acquiring bimodal data and preprocessing, then visual-text cross-modal importance scoring is carried out, a structured pruning strategy is adopted, the pruning proportion is dynamically adjusted according to the importance score, the key visual channel and the text neuron are retained, the model is lightened, after knowledge distillation fine-tuning, directional fine-tuning is implemented, multi-target loss is designed for multi-class text tasks for optimization; through hierarchical extraction and splicing features to form comprehensive representation, fully mining the value of text information, improve the utilization efficiency of text modal, use the loss function containing cross-modal contrast loss to enhance the modal alignment, improve the detection accuracy, improve the adaptability of the model in the specific scene.

The invention discloses a classroom event analysis method and an analysis model optimization method and system, and relates to the technical field of edge computing. The method comprises the following steps: acquiring real-time classroom data acquired by classroom sensing equipment by edge equipment, and storing the real-time classroom data into an offline classroom file; detecting a real-time event stream in the real-time classroom data through a preset lightweight detection model; the lightweight detection model is optimized through an off-line event stream of an off-line classroom file after class, and the off-line event stream is obtained by analyzing the off-line classroom file through a high-precision detection model; and sending the real-time event stream to visual equipment, so that the visual equipment displays the real-time event stream in real time. Through the above technical means, the lightweight detection model rapidly analyzes the real-time classroom data to obtain a high-timeliness real-time event stream, the after-class model optimization can continuously improve the detection precision of the lightweight detection model, the timeliness and precision of the real-time event stream are considered, and instant and reliable decision support is provided for current teaching.

The invention relates to the technical field of data processing, in particular to a multi-dimensional automobile accessory big data processing method and system based on a vertical class model, and the method comprises the steps: obtaining multi-dimensional data information of automobile accessories at regular time; according to key text information in the multi-dimensional data information, constructing a text feature vector of the automobile accessory; determining a first similarity between each attribute of each automobile accessory and the automobile accessory with the same name; obtaining the attribute importance degree of each attribute of each automobile accessory; based on a vertical class model, evaluating the similarity degree of the text feature vectors between any two automobile accessories obtained in a single time, and classifying the automobile accessories; and determining a first similarity between each attribute of any automobile accessory in the same kind of automobile accessories and the remaining automobile accessories, and calculating the automobile accessory similarity between the any automobile accessory and the remaining automobile accessories by combining the attribute importance of each attribute of the any automobile accessory so as to perform duplicate removal processing on the same kind of automobile accessories. Therefore, the duplicate removal effect of the automobile accessory data is improved.

The application provides a kind of training method of classification model and fundus image classification method, belong to the field of incremental learning.A kind of training method of classification model, the classification model is used for fundus image classification, the method comprises: obtaining pre-trained classification model as teacher model, it includes feature extraction network and classifier, the fundus class that the teacher model can identify is classified as old class;Student model is obtained, the feature extraction network of which is initialized with the teacher model, and its classifier is set to be able to identify the fundus class corresponding to the old class and new class, the new class is the fundus class outside the old class;For each old class used, obtain the pseudo sample corresponding to the old class;The student model is incrementally trained using the generated pseudo sample of old class and the fundus image belonging to new class, and the parameters of the student model are updated based on the total loss determined by the preset total loss function during training, to obtain the student model after incremental training.The present application can alleviate catastrophic forgetting.

The disclosed systems and methods provide a novel action prediction framework that performs personalized action prediction. According to an embodiment, the disclosed framework is able to dynamically predict which action (if any) a user might perform in response to receiving a given message. In some embodiments, for a given message, the action prediction framework can determine the probability that a user (e.g., sender, recipient) associated with the message may perform an action or set of action actions (e.g., open, forward, delete, reply, archive) related to the message. In some embodiments, the framework may be used to suggest a predicted action to the user. In some embodiments, a computing device may use the predicted actions to automatically perform the action. According to an embodiment, the action prediction framework includes a multi-label or multi-class model using a neural network.

The application discloses a kind of based on SVG technology's class model construction method and device, the method includes: monitoring class model construction information, and according to class model construction information, determine class model construction content;According to class model construction content, judge whether the current situation corresponding to class model construction information meets the set construction demand;When the judgment result is yes, according to class model construction information and class model construction content, target class model is obtained by construction.It can be seen that the SVG rendering engine can be used as the core to realize the class model intelligent construction function suitable for various class model construction scenarios, which is beneficial to improve the software class model construction convenience and construction efficiency, thereby reducing the human and material resources and time cost of class model construction development.In addition, the target class model obtained by construction is a structured data model, which is beneficial to improve the standardization and structuring of class model, and thereby improve the applicability and referability of class model.

The invention discloses an ML-ELM-AE target motion pattern recognition method containing class information, and belongs to the technical field of situation cognition. An ELM-AE model is constructed, and an ML-ELM-AE model is constructed by stacking the ELM-AE model; carrying out the mapping of the motion features of the target through the ML-ELM-AE; a CELM classification model is constructed, and according to a difference vector set formed by inter-class samples, the weight of an input layer of the CELM classification model to a hidden layer and a hidden layer node bias item are optimized, so that the mapping of the samples from a feature space to a class space has regularity, and the precision and generalization ability of target motion pattern classification are improved.

The invention discloses a data architecture generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining micro-service data and class model data of a target project, generating a physical model of a data architecture based on the micro-service data and the class model data, and generating a data architecture file in a target format based on the physical model. According to the method, upstream design results such as micro-service data and class model data of a target project can be imported, and a conversion request can be generated through one-key operation of a client, so that a physical model of a data architecture is generated based on the micro-service data and the class model data, and a user does not need to design the data architecture from a design document; on the one hand, the problem of low accuracy caused by inconsistent understanding of design documents by different users is avoided, the efficiency and accuracy of data architecture design are improved, on the other hand, the user can select the output format of the data architecture file and can use and browse the data architecture file without installing a professional tool, and the user experience is improved. And development and communication of data architecture design are facilitated.

The invention discloses a multi-model universal operation support method, system and device for universal verification of mechanical and electronic product fault detection and diagnosis, and relates to the technical field of electronic product health diagnose.The method comprises the steps that a multi-mode algorithm used for fault detection and diagnosis is subjected to unified expression packaging, and a plurality of algorithm component models are obtained; constructing an information interaction rule among the plurality of algorithm component models; according to the plurality of algorithm component models and the interaction rule, constructing a graph flow operation mechanism of the plurality of algorithm component models; performing operation environment simulation on the plurality of algorithm component models; and based on the constructed graph flow operation mechanism simulated by the plurality of algorithm components and the plurality of algorithm component models simulated by the operation environment, establishing a fault detection and diagnosis algorithm general host machine, and based on the fault detection and diagnosis algorithm general host machine, carrying out fault detection and diagnosis verification for mechanical and electronic products. Fault detection and diagnosis general verification can be carried out on typical machinery and electronic products in various different fields and different scenes, and the verification result is accurate and reliable.

The application discloses a small sample text classification method fusing data expansion and course learning, first expands data of a labeled sample set by using a strategy, then divides the data set according to a change degree of the expanded sample, then constructs a neural network classifier and trains a classification model, and finally classifies new samples by using the trained model. The learning method is improved and reconstructed, on one hand, data expansion is performed by using multiple strategies, and on the other hand, samples are divided into grades according to change degrees from small to large, and in the learning process, a course learning strategy is used to learn gradually from easy to difficult, and the classification accuracy is significantly improved.

This invention discloses a method, device, storage medium, and processor for predicting user churn, comprising: acquiring attribute information of multiple user attributes, wherein the multiple attributes are attributes included in an attribute set; and predicting user churn based on the attribute information using a classification model trained by machine learning, wherein the classification model includes a first classifier model and a second classifier model. The attribute set includes a first subset and a second subset, and the attributes included in the first subset and the second subset are mutually exclusive. The first classifier model is trained based on the attributes in the attribute set and performs classification operations based on the attributes in the first subset. The second classifier model is trained based on the attribute set after adding new attributes. The new attributes are formed by combining at least a portion of the attributes in the second subset. This invention solves the technical problem of inaccurate prediction in existing technologies.

The invention belongs to the technical field of image recognition, and particularly relates to a CT image motion artifact classification model construction method and system based on feature prototype contrast learning. According to the classification method based on the prototype, the class center is used as feature storage, the inter-class separability and the intra-class consistency in the artifact classification task are enhanced, and the robustness and the classification precision of the model are remarkably improved. The method specifically adopts a Vision Transform (ViT) as a basic model for feature extraction, combines a strong global modeling capability, effectively captures long-range dependence and fine-grained features in artifact detection, and improves the capability of identifying the complexity of artifact types. And by introducing a prototype contrast learning strategy, the feature representation of the artifact image is optimized, and the overfitting problem of the model when training data is insufficient is relieved, so that the generalization ability and robustness of the model in practical application are improved, and an excellent classification result is obtained on a clinical data set.

The application relates to a simulation model component generation method, device, equipment and storage medium. The method comprises the following steps: displaying a component library to a target user, the component library comprising a plurality of model components, the model components comprising code class model components, user encapsulation program class model components, standard type model components or model components supporting code or user encapsulation program loading; receiving component information input by the target user, the component information comprising the identities of at least two model components and the connection relationship of each model component; generating an initial simulation model according to the component information; generating a code file according to the connection relationship in the initial simulation model, and compiling the code file to generate a target simulation model component, the target simulation model component meeting preset calling interfaces and model calculation requirements, and the internal information of the target simulation model component not being open to other users. The method can improve the security of the simulation model component.

The application relates to the technical field of data processing, in particular to a multi-dimensional automobile accessory big data processing method and system based on a vertical class model, which comprises the following steps: acquiring multi-dimensional data information of automobile accessories at regular time intervals; constructing a text feature vector of the automobile accessories according to key text information in the multi-dimensional data information; determining a first similarity between each attribute of each automobile accessory and a same-name automobile accessory; acquiring an attribute importance of each attribute of each automobile accessory; evaluating the similarity degree of the text feature vectors between any two automobile accessories in the automobile accessories acquired at a single time based on a vertical class model, and classifying the automobile accessories; determining the first similarity between each attribute of any automobile accessory in the same-type automobile accessories and the remaining automobile accessories, combining the attribute importance of each attribute of the any automobile accessory, and calculating the automobile accessory similarity between the any automobile accessory and the remaining automobile accessories, so that the same-type automobile accessories are subjected to deduplication processing, thereby improving the deduplication effect of the automobile accessory data.

The application provides a launch vehicle erecting system modeling method based on Simulink and Simscape. The method aims to build a comprehensive and hierarchical launch vehicle erecting system model library and quickly and accurately realize the construction and simulation of the launch vehicle erecting system model. The modeling platform adopted by the method is Simulink, wherein the device class model library is constructed based on the Simscape multi-physical domain modeling toolbox, is divided into a basic element level, a component level and a subsystem level, and each level contains replaceable models to meet the modeling requirements of different launch vehicle erecting systems. Based on the top-level design of MBSE, the hierarchical division of the model library is clear and reasonable, so that the rapid design and development of the launch vehicle erecting system are realized.

The invention relates to the field of medical data management, in particular to a DRG grouping method and system based on a hierarchical hybrid model.The method comprises the steps that firstly, a medical record home page, an electronic medical record text and inspection time sequence data are obtained and fused; carrying out depth feature engineering by utilizing natural language processing and vectorization technologies, and constructing a comprehensive feature vector; the feature vectors are input into a multi-stage hierarchical model formed by cascading an MDC classification model, an ADRG classification model and a DRG subdivision model, input of a back-stage model comprises probability distribution vectors output by a front-stage model, and layer-by-layer information transmission is achieved; particularly, the DRG subdivision model adopts a hybrid architecture combining unsupervised clustering and supervised classification, clustering is carried out in the ADRG based on resource consumption differences, and then a classifier is trained to carry out accurate division. According to the invention, automation, high precision and strong robustness of DRG grouping are realized.

The class incremental learning method based on multi-granularity distillation and weight alignment comprises the steps that under a given wireless electromagnetic signal data set, an incremental deep learning classification model is initialized, and the model dynamically expands an output layer to adapt to a newly-added class; for a training sample of a current task, inputting the training sample into the model for forward propagation, obtaining a prediction score vector of the model on each category, and calculating cross entropy classification loss for learning discriminant features of a newly introduced category in the task; after training of each task is completed, forward propagation is carried out on all training samples of the current task by using the current model to obtain logs representation of the training samples, and clustering is carried out; in each iteration in the training process, calculating cross entropy loss by using a training sample of a current task, and forming a loss function of a historical task sample; after task training is finished, weight alignment operation is executed, and the difference of new and old category classifiers in weight amplitude is eliminated; and repeating the above steps, performing incremental learning task by task, and continuously performing model parameter updating and memory bank maintenance until all incremental learning tasks are completed.

The application realizes a modular method of a neural network model by methods in the fields of software engineering and artificial intelligence, and generally includes three parts of a search space, a performance evaluation strategy and a search strategy; an original model is an N-class pre-training model composed of a plurality of neural network layers and having L weights, and a K-class image or text dataset of a target task is input at the same time, and six steps are used to realize the modularization of the pre-training neural network model for the classification task; the obtained module only retains the relevant part of the weights of the N-class model related to the target task and is used to classify the image or text data to be classified of the target task; the method provided by the application adopts a gradient-based discrete space search method, improves the recognition accuracy of the relevant weights through the accuracy index of the target task, and at the same time, reduces the time and calculation overhead in the classification of the image or text by setting the irrelevant weights to zero.

The invention discloses a model splitting method and system based on class models, electronic equipment and a storage medium, and the method comprises the steps: responding to a splitting instruction of a user for a first model element in a source class model, creating or assigning at least one target class model, each target class model being used for bearing at least one first model element; for each first model element, determining a second model element associated with the first model element; according to a predefined meta-model association rule, reconstructing an association relationship between the second model element and the source class model; and splitting the first model element from the source class model to each target class model, and synchronously updating the association relationship between the second model element and the source class model to the target class model. By automatically identifying the second model element associated with the first model element and intelligently reconstructing the association relationship of the source class model based on the meta-model association rule, the integrity of the dependency relationship and the business logic in the model splitting process is ensured, and the consistency of system behaviors before and after splitting is ensured.

The computer-implemented method includes obtaining a data input and determining its eligibility using an eligibility model. This eligibility is assessed by identifying the language and subject of the data and confirming whether they fall within a predefined set of acceptable languages and subjects. If eligible, the input is classified as a practice-test-type using a data classification model. Subsequently, a text classification model identifies and classifies a first selection from the practice-test-type input as a candidate question. The candidate question is represented using a first word embedding, while a generative model produces a suggested question based on the candidate question, represented using a second word embedding. A similarity score between these embeddings is calculated, and if it exceeds a selected threshold, the suggested question is selected as the practice test question. Based on the suggested question, the generative model produces a suggested answer. Subsequently, the method includes generating a practice test.

This invention proposes a wafer surface defect classification method based on deep learning networks. This method can quickly and accurately identify wafer surface defect patterns and pinpoint their causes. The method aims to address the problems of high manual labor intensity and low detection efficiency in traditional wafer defect detection methods. The specific process includes: constructing and training a wafer defect detection and classification model based on the WM-811K dataset. The defect detection model is a binary classification model used to determine the presence of defects in the wafer image, while the classification model is a multi-class model used to determine the specific defect pattern category. The sample to be tested is input into the trained wafer defect detection and classification model to determine its defect pattern. Finally, by analyzing the causes of defect patterns in known samples, the causes of defect patterns in the sample to be tested are inferred, continuously optimizing the process flow and improving wafer product yield.

The disclosed systems and methods provide a novel action prediction framework that performs personalized action prediction. According to an embodiment, the disclosed framework is able to dynamically predict which action (if any) a user might perform in response to receiving a given message. In some embodiments, for a given message, the action prediction framework can determine the probability that a user (e.g., sender, recipient) associated with the message may perform an action or set of action actions (e.g., open, forward, delete, reply, archive) related to the message. In some embodiments, the framework may be used to suggest a predicted action to the user. In some embodiments, a computing device may use the predicted actions to automatically perform the action. According to an embodiment, the action prediction framework includes a multi-label or multi-class model using a neural network.

The application relates to the technical field of surrounding rock image processing, and discloses a surrounding rock structure small sample analysis model training and identification method, device, equipment and medium, the method comprises the following steps: obtaining an unannotated surrounding rock sample image, extracting a local texture direction based on a structure tensor field, and constructing a superpixel region conforming to the texture direction; taking the superpixel region as a semantic unit to perform region-level contrast learning, and obtaining an inter-class feature model; performing unsupervised clustering based on the region features extracted by the inter-class model, and performing intra-class contrast learning in each clustering set to obtain a plurality of intra-class expert models; distilling a student model by taking the inter-class model as a leading teacher and the intra-class expert as an expert teacher, and obtaining a target feature extraction model; and performing migration training on the target model by adding a task head to the target model using an annotated surrounding rock image, so that lithology classification and structure surface identification are realized. The application can improve the identification accuracy of a model for surrounding rock structure under the condition that a large amount of artificial annotation is lacking.

Embodiments described herein relate to methods and apparatus for training a plurality of clustering machine learning (ML) models and performing tasks using one or more of the plurality of clustering machine learning models. A computer-implemented method of training a plurality of clustering machine learning models to perform a task includes: applying a clustering process to an initial training sample set to generate a plurality of final training sample clusters; for each final training sample cluster, training a cluster ML model by using the final training sample cluster to execute a task; and initiating execution of the task using at least one of the plurality of clustering ML models in response to an input query from the client entity.

Systems and methods for model evaluation. A protected class model that satisfies an accuracy threshold is built by using: data sets for use by a modeling system being evaluated, and protected class membership information for each data set. A target for the protected class model is a protected class membership variable indicating membership in a protected class. Each predictor of the protected class model is a predictor of an evaluated model used by the modeling system. A target of the evaluated model is different from the target of the protected class model. Each predictor is a set of one or more variables of the data sets. For each predictor of the protected class model, a protected class model impact ranking value and a modeling system impact ranking value are determined.