Search request classification method and device, electronic equipment and storage medium

Abstract

The invention discloses a search request classification method and device, electronic equipment and a storage medium, and relates to the technical field of search. The specific implementation scheme is as follows: recalling a search request corresponding to a core lexicon and a recall rule by adopting the core lexicon and the recall rule of a preset classification; wherein the core word bank comprises at least one core word related to the preset classification and the correlation of the core words; performing word segmentation on the recalled search request to obtain a plurality of segmented words; and obtaining the correlation of each segmented word, and expanding the core lexicon by adopting each segmented word and the correlation thereof. The search request classification efficiency canbe improved, and the cost is saved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a search technology field. Background technique [0002] A search engine is a product and system that helps users quickly obtain desired information based on a user inputting a search request (also known as a search query). Whether the search engine can well meet the user's needs depends on whether it can accurately understand the search request entered by the user. When optimizing search engine products, it is impossible to do targeted optimization for every search request. Therefore, if the category of the search request can be identified, targeted optimization can be performed uniformly for one type of search request, thereby improving optimization efficiency. [0003] The existing search request classification methods generally fall into the following two categories: [0004] The first one is to train a dedicated classification algorithm model for each category...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that training the classification algorithm model requires high time and labor costs, and cannot meet the frequent analysis requirements required for product optimization

This method also requires high time and labor costs

[0006] It can be seen that the cost of the existing search request classification method is high, and the efficiency is low

Images