Method and device for generating category vector

Abstract

The embodiment of the invention discloses a method and a device for generating a category vector. A specific embodiment of the method comprises the steps of obtaining a first preset number of vectorsbelonging to a preset category as a first vector set; obtaining a second preset number of vectors belonging to a preset category as a second vector set; determining a target vector meeting a preset condition from the second vector set; obtaining a to-be-replaced vector belonging to a preset category; determining whether the to-be-replaced vector meets a preset replacement condition, and if yes, replacing the target vector with the to-be-replaced vector; and based on the first vector set and the second vector set after vector replacement, determining a category vector representing a preset category and storing the category vector. According to the method, the second vector set is updated in real time, so that the representativeness of the vectors in the second vector set to the preset category is gradually enhanced, and the accuracy of generating the category vector is improved.

Description

technical field [0001] The embodiment of the present application relates to the field of computer technology, and in particular to a method and device for generating category vectors. Background technique [0002] At present, classification technology is applied in many fields. Classification technology mainly extracts feature vectors of information such as images, videos, audios, and texts, and then classifies the feature vectors. A category can include multiple eigenvectors, how to use one eigenvector to represent a category is a widely researched issue at present. Usually, a common method to represent a category with a feature vector is to select the mean (or weighted mean) vector of all vectors of the category or the vector closest to the mean (or weighted mean) vector to represent this class; set a time window and use the vector in the window The mean (or weighted mean) vector or the vector closest to the mean (or weighted mean) vector represents this class; the vector...

AI Technical Summary

Problems solved by technology

[0003] Due to the mechanical selection of representative vectors mentioned above, the above non-machine learning methods often lead to insufficient dimension information of representative vectors, or deviate from prior knowledge; while machine learning methods are slow and need to be retrained after the vectors in the category change. The situation of real-time increase is difficult to handle

Images