Method and system for calculating retrieval precision of internet keyword

Abstract

The invention discloses a method and system for calculating retrieval precision of an internet keyword, and relates to the field of internet keyword retrieval. The method comprises the first step of adding up clicks of each retrieval result corresponding to a keyword of which retrieval precision needs to calculated; the second step of selecting in order three retrieval result groups, namely, a first hit retrieval result group, a second hit retrieval result group and a third hit retrieval result group in the descending order of the clicks of all the retrieval results, wherein the number of the retrieval results of each retrieval result group is at least 10 and all the retrieval results which are not selected serve as a non-hit retrieval result group; the third step of calculating a grade S of the retrieval precision of a current keyword. According to the method and system for calculating the retrieval precision of the internet keyword, the grade of the calculated retrieval precision is identical with the practical retrieval precision, the result of the grade of the retrieval precision is very accurate, thus accurate data are provided for development of a secondary statistics of a search platform, and the applicability of the method and system is very strong.

Description

technical field [0001] The invention relates to the retrieval field of Internet keywords, in particular to a method and system for calculating the retrieval accuracy of Internet keywords. Background technique [0002] With the rapid development of the Internet industry, the competition among Internet platforms is increasingly intensified. How to quickly and effectively analyze pre-research user behavior has become an important issue for all Internet platforms; The search behavior of the platform is an important analysis link. [0003] Currently, traditional Internet search platforms generally use the following methods to calculate keyword retrieval accuracy: [0004] 1. After the user enters the keyword, the full-text search is carried out on the Internet, that is, after the keyword is segmented according to certain rules, the word segmentation is matched with the source data, and the score is scored according to the number of occurrences of the word segmentation, the adjac...

AI Technical Summary

Problems solved by technology

In order to get the results they want, users will choose some lower-ranked search results; therefore, for the "Chinese" data, the search results of the keyword "China" have low accuracy, which makes the recommendation effect poor

Images