Searching method and searching system

Abstract

The invention provides a searching method and a searching system. The searching system includes a user interface module, a target database and multiple specialty work banks corresponding to a plurality of different technical fields, and further includes a feedback module, a word segmenting module, an inquiring module, an indexing module and a sequencing module. The searching method and the searching system provided by the invention can enable a user to obtain documents highly correlated with input sentences, and efficiently improve the searching accuracy.

Description

technical field [0001] The invention relates to the field of information search, in particular to a search method and a search system. Background technique [0002] With the vigorous development of computer networks, more and more information on the network. For this reason, users generally need to use search engines to better find the information they need. Now commonly used search engines are GOOGLE, Baidu, Yahoo, Bing and so on. These search engines all have the same feature: users can only enter a few keywords to search. If the user enters a long sentence or even a long article, the results returned by these search engines are often not satisfactory. And as the user enters more information, the returned results tend to get worse and worse. In this case, the user can only choose to enter one or two core words, and then find the required information in the search results. This method is dedicated to solving the defect that users cannot input too much information in se...

AI Technical Summary

Problems solved by technology

This classification structure is not conducive to user selection, and there are often situations where user needs are scattered in multiple categories or cannot be determined

[0006] 2. The classification tree will become larger and larger, which is not conducive to long-term operation

At the same time, because there is no historical data for newly registered users, it is impossible to analyze user interests, which means that the invention of this technology is only effective for users who have used the system for a long time

[0012] 2. The analysis of user interests is still at the superficial level

The default 4 analysis methods are all ordinary text analysis, the really important user interest analysis is just to propose a model, there is no specific implementation method

[0014] 3. There is no mature case for the construction of the training model

[0015] Similar to the previous question, although it is proposed to use the training model to obtain user interest, there is no specific plan on how to build the training model, what model to use, etc., and it is still in the conception stage

Images