Classification device and classification method

A method for controlling an artificial intelligence device to perform classification, the method comprising:

• receiving data by a processor in the artificial intelligence device;
• performing, by the processor, binary classification on the data based on plurality of binary classifiers to generate a binary classification result;
• determining whether the binary classification result satisfies a preset condition, the preset condition including a case where at least two of the plurality of binary classifiers output True or a positive result, or a case where all of the plurality of binary classifiers output False or a negative result;
• in response to the binary classification result satisfying the preset condition, executing, by the processor, a multi-classifier to to perform multi-classification, inputting the data to the multi-classifier for generating a multi-classification result and outputting a final classification result based on the multi-classification, result;
• and
• in response to the binary classification result not satisfying the preset condition, not executing the multi-classifier and outputting a final classification result based on a classification result of a binary classifier, among the plurality of binary classifiers, that has output True or a positive result.

A device, comprising:

• a memory configured to store input data;
• and
• a processor configured to:
• receive data,
• perform binary classification on the data based on a plurality of binary classifiers to generate a binary classification result,
• determine whether the binary classification result satisfies a preset condition, the preset condition including a case where at least two of the plurality of binary classifiers output True or a positive result, or a case where all of the plurality of binary classifiers output False or a negative result,
• in response to the binary classification result satisfying the preset condition, execute a multi-classifier to perform multi-classification, input the data to the multi-classifier for generating a multi-classification result, and output a final classification result based on the multi-classification result, and
• in response to the binary classification result not satisfying the preset condition, not execute the multi-classifier and output a final classification result based on a classification result of a binary classifier, among the plurality of binary classifiers, that has output True or a positive result.