14 results about "Classification treatment" patented technology

The application relates to the technical field of agricultural intelligence, and discloses a working area accurate calculation method and device based on classification-clustering bidirectional feedback, which comprises the following steps: determining target track data generated by a farm machine during working; performing working state classification processing on the target track data by using a target classification model to determine a target working data set of the farm machine; wherein the target classification model is determined by iteratively training an initial classification model by using suspicious track data in the target track data; and performing area calculation on effective plot units in the target working data set to obtain a target working area of the farm machine. By iteratively training the initial classification model, the target classification model can continuously learn and correct classification errors, compared with a single classification model, the target classification model can effectively reduce misjudgment and missed judgment, significantly improves the accuracy of the final working area calculation result, and can meet high-standard application requirements.

This invention discloses a wastewater classification and separation system based on industrial wastewater recycling. The invention relates to the field of industrial wastewater treatment and resource recycling technology. The system includes a wastewater acquisition and pretreatment module, a multi-parameter real-time water quality detection module, a comprehensive pollution classification and determination module, a separation and control module, a classification storage and buffer module, a classification treatment module, a recycling intelligent scheduling module, and a data acquisition and intelligent management module. This invention utilizes a collaborative working mechanism of multi-parameter real-time water quality detection and comprehensive pollution classification and determination. It employs a piecewise linear dimensionless scoring function to uniformly map five water quality indicators to a scoring range of 0–10 and then performs a weighted summation. This achieves multi-dimensional, accurate, and real-time determination of the pollution level of industrial wastewater, overcoming the shortcomings of existing technologies where single-indicator judgments are inaccurate and multi-indicator dimension inconsistencies prevent comprehensive evaluation. The targetedness and effectiveness of wastewater classification and treatment are significantly improved.

This application provides a data processing method, apparatus, device, medium, and program product to improve the efficiency and accuracy of content classification. It can be applied to fields such as artificial intelligence and content moderation. The method includes: acquiring data to be classified; performing a first classification process on the data to be classified to obtain a first classification result; when the first classification result does not meet preset conditions, acquiring profile data and behavioral data of the interactive object corresponding to the data to be classified, the interactive object including the object that uploaded the data to be classified and the object to which the data to be classified belongs; performing feature encoding processing on the profile data, the behavioral data, and the data to be classified respectively to obtain feature data to be classified; performing a second classification process on the feature data to be classified to obtain a second classification result for the data to be classified; and outputting the second classification result.

This invention provides a method for managing cutting drawings of multi-process hydraulic support parts based on Creo, comprising: Step 1: determining the process features required for cutting drawings of different processes, and classifying and combining these process features; Step 2: drawing sketches with different numbers corresponding to different process features of the same part; Step 3: forming multi-process cutting drawings of the part based on the drawn sketches, and then storing the formed multi-process cutting drawings of the part in the process platform of the PLM product lifecycle management system; Step 4: writing the corresponding process judgment conditions for the part in the part relationship page of the Creo software; when drawing is required, based on the determined process features, using the Creo tool to determine the cutting drawing page number determined by the written conditions, thereby outputting the process cutting drawings required for the part. This invention can realize the output of corresponding cutting drawings for the same part according to the required process requirements.

The application discloses a short text classification method and device. The method comprises the following steps: receiving a text to be classified; performing classification processing on the text to be classified by using a pre-trained classification model to obtain a classified text, wherein the classification model is obtained by training according to a fusion loss function, the fusion loss function is determined according to a mean square deviation loss function and a cross-entropy loss function, and model parameters of the classification model are determined based on a Nesterov momentum, a degree difference momentum and a decoupled weight decay parameter; and outputting the classified text. The method provided in the application at least solves the technical problem of low short text classification accuracy in the related art.

The application discloses an entity relation extraction method, device and equipment and a storage medium thereof. The method comprises the following steps: performing entity processing on a to-be-processed text to obtain an entity sequence, wherein the entity sequence comprises a plurality of candidate entity pairs; performing feature extraction on the to-be-processed text according to a feature item contained in the to-be-processed text to obtain a text feature vector; performing feature extraction on the candidate entity pairs and candidate relations between the candidate entity pairs to obtain a knowledge feature vector; performing fusion processing on the text feature vector and the knowledge feature vector to obtain a text knowledge fusion feature; and performing classification processing on the text knowledge fusion feature to obtain a corresponding relation of each candidate entity pair. The technical scheme provided by the embodiment of the application can obtain multiple dimensions of features of the to-be-processed text to improve the accuracy of entity relation extraction.

The application discloses an object classification method and device, a storage medium, equipment and products, relates to the technical field of artificial intelligence, and can be applied to the technical field of blockchains, map Internet of Vehicles and the like. The method comprises the following steps: acquiring object information of at least one object, wherein the object information comprises at least one product category; respectively classifying objects associated with each product category to obtain same-category objects of each object under each associated product category; taking each object as a target object, respectively generating enhanced feature data under each associated product category based on the object information of the same-category objects of the target object under each associated product category; performing calculation and processing on the enhanced feature data under each associated product category and the same-category object weight to obtain object feature data of the target object; and obtaining a first classification result of the target object according to the object feature data of the target object. The application can effectively improve the accuracy of object classification.

This invention relates to an automatic grading and quality-classification treatment method and device for aquaculture wastewater, specifically as follows: Data is collected in real time using multi-parameter water quality sensors, and a dataset is constructed by labeling the water quality grading results; an ecological causal weight matrix is ​​constructed based on the aquaculture ecological coupling relationship between water quality data, and missing values ​​are filled and outliers are replaced; a two-dimensional dynamic threshold calibration is performed, and parameters are determined by combining a feature library of aquaculture species and growth stages to calculate dynamic grading thresholds; a comprehensive weight is generated by integrating the analytic hierarchy process (AHP) and ecological causal weights, and the data and thresholds are standardized; water quality grading is achieved by calculating the comprehensive pollution index and grading thresholds through weighted calculation; an XGBoost prediction model is constructed to calculate the load level and sensor drift coefficient, and sensor cleaning parameters are dynamically adjusted through a load-cleaning linkage adaptive algorithm. This invention forms a management closed loop by grading aquaculture wastewater water quality data and maintaining sensors, achieving precise monitoring and efficient equipment management.

The application relates to the field of artificial intelligence, and provides an aspect-level sentiment classification method, which comprises the following steps: calling a target sentiment classification model when a target sentence needing sentiment classification and an aspect word are acquired; performing coding processing on the target sentence through an embedding layer to obtain a first embedding vector and generate a first syntax adjacency matrix of the target sentence; performing convolution processing on the first embedding vector and the first syntax adjacency matrix through a first target graph convolution network to obtain a first syntax feature vector; performing hop number classification processing on the first syntax feature vector through a first target linear layer to obtain a target hop number, and updating the first syntax adjacency matrix according to the target hop number; performing convolution processing on the first embedding vector and the updated first syntax adjacency matrix through a second target graph convolution network to obtain a second syntax feature vector; and performing sentiment classification processing on the second syntax feature vector through a second target linear layer. The method improves the accuracy of sentiment classification.

This application provides a model training method, an intelligent classification method and device for nursing record information, belonging to the field of deep learning technology. Addressing the problem of low reference value of current nursing record information, it involves collecting a hospital nursing record dataset; performing a classification process on each nursing record in the dataset to obtain sample nursing entries; inputting the sample nursing entries into a first language model to obtain the classification information of the nursing record entries output by the first language model; and based on the classification information and the classification labels, adjusting the model parameters of the first language model through iterative training to obtain a target nursing record classification model. Finally, the target nursing record classification model can be used to accurately classify nursing record information and use the classification information for labeling, which can improve the readability and reference value of nursing record information to a certain extent.

This application discloses a method, apparatus, and electronic device for constructing a waste sorting and processing model. This solution acquires training image samples labeled with waste type, extracts three types of waste features: geometric, color, and texture, and avoids the limitations of single features through multi-dimensional feature fusion. After setting training parameters, it recursively traverses features and candidate splitting thresholds starting from the initial node, selecting the optimal splitting combination to split nodes until the stopping condition is met and the leaf node output result is determined, ultimately obtaining the waste sorting and processing model. This method automatically splits nodes to replace manually setting classification rules, improving the efficiency of model construction and ensuring the stability of model classification. It also reduces the cost of model construction and enables the model to quickly and accurately determine waste categories.

The application provides a workshop wastewater treatment method, a workshop wastewater treatment device and a computer storage medium. The workshop wastewater treatment method comprises the following steps: acquiring first water quality sensor data and equipment operation logs; inputting the first water quality sensor data and the equipment operation logs into a large language model decision engine to obtain a large language model decision instruction; and performing classified treatment on the workshop wastewater according to the large language model decision instruction. The large language model decision instruction is introduced into the above-mentioned workshop wastewater treatment method, and the self-determination capability of the large language model is utilized to dynamically treat the workshop wastewater on the basis of automatic treatment. Compared with the establishment of an expert experience or a preset decision mode, a large amount of waste of human resources can be reduced, and the loss caused by human error in decision-making can be effectively reduced.

The present disclosure relates to a user classification model training method, device, medium and equipment, and belongs to the technical field of big data processing. The method comprises: encoding a first user feature sequence of a classified user based on a feature sequence encoder in a user classification model to be trained to obtain a first user vector; classifying the first user vector based on a stage transition probability predictor in the user classification model to be trained to obtain a current stage loss of the classified user at different stages; predicting a weight of the current stage loss based on a dynamic weight generation network in the user classification model to be trained to obtain a stage loss weight at different stages; constructing a target loss function based on the stage loss weight and the current stage loss, and training the user classification model to be trained based on the target loss function to obtain a trained user classification model. The present disclosure improves the accuracy of the user classification model.