Fuzzy word determining method and device based on global search

Abstract

The embodiment of the invention provides a fuzzy word determining method based on global search. The method includes the steps that firstly, an input statement query set corresponding to a uniform resource locator jointly clicked is obtained on the basis of search log data; the entry weights of basic entry terms of each query in the query set are obtained; the entry weight of each term is compared with the preset weight threshold value, and the term with the entry weight smaller than the weight threshold value is set to be a secondary entry; the appearance frequency of the terms serving as the secondary entries is counted within the global search range, and the term with the appearance frequency greater than the preset frequency threshold value is set to be a fuzzy word. The fuzzy word determining method and device based on global search can accurately obtain the fuzzy word based on the jointly clicked input statement query, play a significant role in core word extraction of the input statement query and document sorting, and improve the search efficiency and results.

Description

technical field [0001] The present invention relates to the field of information push technology, in particular to a method and device for determining fuzzy words based on global search. Background technique [0002] With the rapid development of the network and information technology, the amount of information on the network has also shown an explosive growth, so quickly and correctly obtaining the correct information from these massive data has become the core issue of the current search engine technology. There are great differences. Different people receive different educations and different cultures, resulting in great differences in the expression of the same problem. At the same time, it is aimed at the role of certain terms in the query entered by the user on the search results. The effect is also very small. For example, if a user enters a query "how much is the ticket for the Forbidden City in Beijing", in the context of this query, the entry "how much" is a spam e...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of the network and information technology, the amount of information on the network has also shown an explosive growth, so quickly and correctly obtaining the correct information from these massive data has become the core issue of the current search engine technology. There are great differences. Different people receive different educations and different cultures, resulting in great differences in the expression of the same problem. At the same time, it is aimed at the role of certain terms in the query entered by the user on the search results. The effect is also very small. For example, if a user enters a query "how much is the ticket for the Forbidden City in Beijing", in the context of this query, the entry "how much" is a spam entry, which has little effect on the search results

[0003] The TF-IDF (Term Frequency–Inverse Document Frequency) technology used in the prior art solution is used to evaluate the importance of a word for a document in a document collection or a corpus, and is a method for The commonly used weighting technology for information retrieval and information mining, but this technology cannot accurately describe the importance of a certain term under global conditions, so it cannot effectively extract the core words of the query under global conditions, thus affecting search efficiency and results

Images