A hidden factor model weapon task recommendation method with a correction vector

Abstract

The invention provides a hidden factor model weapon task recommendation method with feature vectors. According to the technical scheme, the method is used for solving the problem of information overload appearing in a Weiguan platform and recommending suitable tasks to users, and mainly comprises the following steps: firstly, carrying out user interest degree quantification and feature set construction, quantifying original behavior data, reading the original behavior data into a feature set, and introducing negative sampling to enrich the original behavior set; then establishing a hidden factor model with a correction vector, carrying out training, and generating a recommendation result; and finally, for users and tasks which newly enter and do not have behavior information, providing cold start recommendation based on the correction vector group. According to the characteristics of the Weiguan platform data, the user characteristics and the task characteristics correspond to the correction vectors and are introduced into the hidden factor model, more accurate modeling is carried out on the interest of the user, meanwhile, the cold starting problem when a new user and a new task enter is solved by utilizing the user characteristic vectors and the task characteristic vectors in the model, and the practicability is high.

Description

technical field [0001] The invention relates to a recommendation method for freelance tasks, in particular to a recommendation algorithm based on a latent factor model and an application method thereof which introduces a correction vector refined according to user characteristics and task characteristics. Background technique [0002] With the acceleration of the process of informatization, many emerging Internet concepts have emerged, and Witkey mode is one of them. The concept of Witkey was put forward in about 2005, which converts people's knowledge, wisdom, experience, and skills into actual income through the Internet, so as to achieve a new Internet model where everyone gets what they need [0003] While the Witkey model was developing rapidly, it also fell into the dilemma of information overload. The influx of a large amount of information has made it difficult for users to obtain information. Taking a large domestic Witkey website as an example, its total demand (t...

AI Technical Summary

Problems solved by technology

This kind of recommendation method also has obvious shortcomings. When a new user or new item is added to the system, there is no behavior about it in the system, so it is difficult to make corresponding recommendations, resulting in what is called "cold start". question

Images