Task execution method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a task execution method, device and equipment and a computer readable storage medium. The method comprises the steps of obtaining a target industry label of atarget industry; extracting the feature of the target industry label to obtain a industry label feature; determining a target class cluster identifier corresponding to the industry label feature according to a preset class cluster set, the preset class cluster set being a set composed of class cluster information corresponding to the industry features of a plurality of industries; determining a target industry feature corresponding to the target class cluster identifier from a corresponding relationship between preset features and class cluster identifiers, the corresponding relationship between the preset features and the class cluster identifiers being a set formed by a corresponding relationship between each sub-industry feature in the industry features and one class cluster identifierin the preset class cluster set; and training a preset model corresponding to the target industry by using the target industry feature, so as to execute a prediction task by using the trained preset model. Through the embodiment of the invention, the training efficiency of the preset model in the field of artificial intelligence can be improved.

Description

technical field [0001] The present application relates to information processing technology in the field of artificial intelligence, and in particular to a task execution method, device, equipment and computer-readable storage medium. Background technique [0002] With the rapid development of artificial intelligence, network models have been widely used in various industries. The intelligence and efficiency of functional applications in various industries can be improved through network models; therefore, the training of network models is an important part of the rapid development of various industries. [0003] Generally speaking, for the model training of a specified industry, it is usually to use the specified industry label to hard filter the user behavior information of each industry to obtain the user behavior information of the specified industry, and then perform feature extraction and aggregation on the user behavior information of the specified industry in turn. ...

AI Technical Summary

Problems solved by technology

However, in the training process of the above-mentioned predictive model, the acquisition of the characteristics of each specified industry needs to be realized by screening user behavior information of each industry and performing model training. Participation, so the acquisition efficiency of the specified industry characteristics is low, and the efficiency of predictive model training is low

Images