Method, device and system for calculating network video real-time attention

Abstract

Provided are a method, a device and a system for calculating network video real-time attention. The method includes: step 1, setting statistic granularity of network video playing time; step 2, obtaining network video playing data needing statistic processing according to the set statistic granularity of the network video playing time; step 3, calculating the playing time of each network video in the statistic granularity; step 4, calculating the playing attention of each network video in the category according to the playing time of each network video; and step 5, counting up the playing time of each network video playing time and category information of the network video playing attention of each network video, using the sum as the real-time playing time of each network video in a specific time period, and obtaining the real-time attention of each network video according to the playing time. The method, the device and the system for calculating network video real-time attention increase reaction speed of network videos high in attention of a network searching engine, timely provide video hot topics for users and enable a search server to response to hot events as soon as possible.

Description

technical field [0001] The invention belongs to the technical field of Internet data statistical processing, and in particular relates to a method, device and system for calculating the real-time attention degree of network video. Background technique [0002] The current online video search ranking is mainly based on the historical cumulative playback volume, upload time, and online video title semantic score. This method solves the problem of TF-IDF (term frequency-inverse document frequency, that is, term frequency-inverse document frequency) .That is a statistical method for evaluating the importance of a word to a document in a set of documents or a corpus. The importance of a word increases in proportion to the number of times it appears in a document, but At the same time, it will decrease inversely proportional to the frequency of its appearance in the corpus. Various forms of TF-IDF weighting are often used by search engines as a measure or rating of the degree of r...

AI Technical Summary

Problems solved by technology

That is a statistical method to assess the importance of a word to a document in a collection or a corpus, the importance of a word increases in proportion to the number of times it appears in a document, but at the same time It will decrease inversely proportional to the frequency of its appearance in the corpus. Various forms of TF-IDF weighting are often used by search engines as a measure or rating of the degree of relevance between a document and a user query to determine whether a document appears in search results The order of order) using semantics alone to sort the effect is not good, but on the other hand, since the current cumulative playback volume is generally used, even online videos that are currently attracting more attention due to the lower historical hits Small can't be sorted to the front in time by the background, which reflects the impact of playback statistics lag on search ranking

Images