Data processing method, model construction method, classification method and computing equipment

Abstract

The embodiment of the invention provides a data processing method, a model construction method, a classification method and computing equipment. An output module of a newly added classification task is constructed in the object classification model; a first training sample of the current training batch is inputted into the object classification model, and a first sample feature of the first training sample is extracted; the category label of the first training sample is taken as output data of an output module, and an object classification model is trained in combination with the first sample feature of the first training sample and the object features of different categories in the first storage information; a second sample feature of the first training sample is extracted by using the trained object classification model, and the first storage information is updated based on the second sample feature of the first training sample; and when the training is finished, forming second storage information corresponding to the newly-added classification task by using the object features of the categories related to the newly-added classification task in the first storage information. According to the technical scheme provided by the embodiment of the invention, the model training cost is reduced, and the model classification accuracy is ensured.

Description

technical field [0001] The embodiments of the present application relate to the field of computer application technology, and in particular, to a data processing method, a model building method, a classification method, and a computing device. Background technique [0002] In the field of computer application technology, the classification requirements of data objects such as text classification, image classification, and audio classification are often involved. At present, machine learning methods are mostly used for object classification. By learning existing data, training the corresponding object classification model, using Object classification models can then classify new data. [0003] However, with the continuous expansion of classification requirements, many classification tasks will appear for the same type of classification requirements. If an object classification model is trained for each classification task, the training cost will be very high. Contents of th...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a data processing method, a classification method and a computing device to solve the technical problem of high model training costs in the prior art

Images