Information processing method and device, electronic equipment and medium

Abstract

The invention provides an information processing method, which comprises the steps of obtaining sample data, the sample data representing a target user, a target article and operation information of ppredetermined operations performed on the target article by the target user at a first moment; acquiring user information of a target user and first article information of a target article; inputtingthe user information and the first article information into a feature extraction model, and extracting to obtain a feature vector; processing the feature vector by adopting a prediction model to obtain a prediction confidence coefficient of each predetermined operation in p predetermined operations executed on the target object by the target user; and optimizing the feature extraction model according to the operation information and the prediction confidence, wherein the user information and / or the first article information comprise / comprises at least two types of information: feature information, image information and text information, and p is a natural number greater than 1. The invention further provides an information processing device, electronic equipment and a computer readable storage medium.

Description

Technical field [0001] The present disclosure relates to the field of computer technology, and more specifically, to an information processing method, device, electronic equipment, and medium. Background technique [0002] In recent years, with the rapid development of e-commerce and the explosive growth of user interaction information, extracting user characteristics from multi-type and multi-dimensional information has become an important factor affecting the effectiveness of the recommendation system. [0003] In the process of realizing the concept of the present disclosure, the inventor found that there are at least the following problems in the prior art: the existing feature extraction methods include extraction based on traditional machine learning algorithms and extraction based on time series deep learning algorithms. Among them, extraction based on traditional machine learning algorithms (such as collaborative filtering) can only use user interaction information, and can...

AI Technical Summary

Problems solved by technology

Among them, extraction based on traditional machine learning algorithms (such as collaborative filtering) can only use user interaction information, and cannot process unstructured information such as text and images, resulting in a large amount of data waste and poor feature extraction.

The deep learning algorithm based on time series needs artificial feature processing in the time dimension. The processing method is relatively fixed, requires very strong prior knowledge of experts, and cannot handle time series features well.

Images