The invention provides an article content depth assessment method and device. The method comprises the steps of obtaining an article to be assessed; inputting the article into a preset depth scoring model; carrying out word segmentation and keyword extraction on each paragraph in the article by using a deep scoring model, obtaining a vector corresponding to each keyword, determining the vector corresponding to each paragraph according to the vector corresponding to the keyword in each paragraph, and determining the vector corresponding to the article and the content depth according to the vector corresponding to each paragraph; and the content depth output by the depth scoring model is obtained, so that content depth scoring can be carried out on the article according to the content of thearticle, the accuracy of article scoring is improved, and the article recommendation efficiency is improved.