5results about How to "Simplify the classification process" patented technology

The application relates to a PCBA insulation voltage resistance test method, system, device and medium, terminals in a PCBA board card are grouped according to voltage resistance standards and insulation requirements, the grouping is connected with a matrix scanner, insulation voltage resistance test results are collected, a multilayer perception model is used, insulation voltage resistance risk fault prediction is obtained, including predicted insulation voltage resistance test results and a fault severity function value. Test parameters are adjusted through deep reinforcement learning, the test parameters include applied voltage and pressure application time, and an optimized test strategy is obtained. The board card is subjected to insulation voltage resistance test based on the optimized test strategy, fault prediction and risk assessment are carried out in the multilayer perception model, and risk prompting and fault alarm are carried out. Compared with the prior art, the application has the advantages of high accuracy, high efficiency and strong safety.

This application provides a training method for a classification model, a text classification method, and related equipment to address the problem of low classification flexibility in classification models. The method includes at least the following steps: based on preset multiple feature dimensions, extracting corresponding multidimensional text features, multidimensional associated label features, and at least one multidimensional other label feature for selected sample text, associated classification labels, and at least one other classification label from among multiple classification labels; determining the negative sample similarity between each of the at least one other classification label feature and the multidimensional text feature based on the hierarchical distance between each of the at least one other classification label and the associated classification label; and adjusting model parameters based on the obtained positive sample similarity and at least one negative sample similarity between the multidimensional text feature and the multidimensional associated label feature. This enables a target classification model to have feature extraction capabilities of different granularities, improving classification flexibility.

The present invention discloses a method for constructing a relationship model for identifying clastic rock lithology, which relates to the technical field of lithology identification. The method determines the target lithology type after the initial lithology type is simplified and classified by the logging characteristics corresponding to the sample clastic rock classified by the clastic rock core; and constructs a target relationship model according to the logging characteristics of the sample clastic rock and the target lithology type of the sample clastic rock. The target relationship model is used to classify and identify at least one mudstone type and sandstone types of different particle sizes. In this way, the complex initial lithology type is simplified to the target lithology type with similar logging characteristics, and the target relationship model is constructed, so that different lithology types can be classified and identified, reducing the dependence on traditional core sampling, helping to simplify the classification process of lithology identification, and being able to adapt to different geological conditions and environments.

The invention discloses an interference identification method and system based on intelligent electromagnetic spectrum sensing. The method comprises the following steps: generating a plurality of interference signals under different systems; performing data preprocessing on the generated interference signal to obtain a normalized signal; performing feature extraction on the obtained normalized signal to obtain a feature value; designing a three-layer full-connection BP neural network according to the obtained feature values and training the three-layer full-connection BP neural network; different noise signals are classified by using the designed neural network, a complex classification method is not needed, and signal feature value extraction is simple and effective.

This invention relates to a method for intelligent grading and quantitative non-destructive testing of deer antler slices. It utilizes machine learning and other methods to train an artificial intelligence recognition model, enabling rapid and high-throughput quality grading of deer antler. Simultaneously, it extracts the spectral characteristics of deer antler slices at each grade using bioinformatics and chemometrics analysis, establishing a correlation between the characteristics, physicochemical properties, and spectral features of deer antler slices. This provides a scientific basis for quantitatively predicting the quality of deer antler slices using infrared spectroscopy, thereby achieving non-destructive intelligent grading and quantitative classification of deer antler slices. This invention overcomes the problem of traditional deer antler slice quality grading relying on subjective experience through multi-data fusion, enabling rapid and accurate evaluation of deer antler slice quality.