Personalized pushing method based on user reading preference statistics of reading time

The invention discloses a personalized pushing method based on user reading preference statistics of reading time. The method includes following steps: step 1, establishing calculating standards of average reading time of electronic reading materials; step 2, judging reading behaviors of a user; step 3, establishing average reading speed of the user; step 4, calculating reading time for a single article of the user; step 5, judging reading completeness according to actual reading time and the average reading time of the user; step 6, establishing preference degree of the user according to the reading completeness of the user; step 7, performing matching similarity operation on user preference vector and article content feature vector to acquire interest evaluation value of the user on an un-read article, and recommending a series of articles with high interest evaluation value to the user. The preference degree of the user is judged mainly according to article reading time and text information of the user, an