Video recommendation method and apparatus

Abstract

Embodiments of the present invention disclose a video recommendation method and apparatus, which are applied to a server. The method comprises: acquiring a text string input by a user, and identifying at least one word segment included in the text string; based on text information of each identified word segment, determining a text coefficient corresponding to each word segment; separately determining whether each word segment is the same as a historical search word in a preset weighted word library, and if a determination result is yes, weighting the text coefficient corresponding to the word segment by using a weighting coefficient corresponding to the historical search word that is the same as the word segment, so as to obtain a recommendation coefficient corresponding to the word segment; if the determination result is no, weighting the text coefficient corresponding to the word segment by using a pre-determined weighting coefficient, so as to obtain a recommendation coefficient corresponding to the word segment; normalizing the recommendation coefficient of each word segment; and based on a standard recommendation coefficient that is obtained through normalization and corresponds to each word segment, recommending a video to the user in a preset manner. According to the method and apparatus disclosed by the embodiments of the present invention, video recommendation is more accurate, and user experience is better.

Description

technical field [0001] The present invention relates to a video application system, in particular to a video recommendation method and device. Background technique [0002] Now video websites are often provided with a function of recommending videos to users, which can provide users with more choices of related videos, further increasing the number of clicks and attention of video websites. [0003] When recommending a video in the prior art, it uses the text information of the text string input by the user in the search box for recommendation. A specific implementation method is: first, obtaining the text string input by the user; second, using the word frequency-reverse file frequency The (TF-IDF) algorithm determines the first weight of each participle in the text string; again, referring to the part of speech of each participle in the text string, weighting each participle on the basis of the above first weight to obtain the text coefficient ; Finally, the text coeffici...

AI Technical Summary

Problems solved by technology

In the specific implementation above, the default weighting coefficient of nouns is generally greater than that of verbs or adjectives, but when there are both nouns and verbs in the text string input by the user, and the expected weight of the verb is greater than that of the noun, for example: "password's For the text string "crack", what the user wants is mainly "crack", that is, the expected weight of the verb "crack" is greater than that of the noun "password". Inaccurate, and the video recommended to the user is also inaccurate, and the user experience is not good

Images