Searching method and system for identifying user retrieval intention

Abstract

The invention discloses a searching method and a system for identifying user retrieval intention and is applied to the field of information retrieval. The method comprises the following steps: receiving a retrieval request of the user; calculating three measurements, namely the intention characteristic similarity of the retrieval request, entity word association and syntax pattern similarity; determining the user retrieval intention of the three calculated measurements; and searching according to the determined user retrieval intention and outputting a searching result. According to the embodiment of the invention, the similarity between the retrieval words and intention characteristic library is considered, the special function of the entity word and an integral retrieval syntax structure are considered, the retrieval keywords are locally and integrally subjected to intention identification, the information support is provided for a search engine as much as possible, and the method does not completely depend on the result information of the on-line search engine and is easy to realize.

Description

technical field [0001] The invention relates to the field of information retrieval, in particular to a search method and system based on identifying user retrieval intentions. Background technique [0002] The emergence of search engines has given users tools to find information from massive amounts of data. But not every user understands the principles of search engines, so users generally organize their own search keywords to search when using search engines, and change the search keywords to regain search results when the results are not satisfactory. How to enable users to input less and use search engines to obtain the information they need faster is a very important task - how to mine and identify users' potential retrieval intentions according to the retrieval requests entered by users. Once the search engine can grasp the user's search intention, it can use less resources to meet the greater needs of users. [0003] So far, the methods for identifying user retrieva...

AI Technical Summary

Problems solved by technology

Its shortcomings are: firstly, it has high requirements for search engines, requiring search engines to calculate the score of each click in real time, and the online load will be high; secondly, it requires search engine performance and effect to be stable, and search results can basically meet the needs of users , otherwise the recorded click feedback on the results will be too far from the actual needs of the user; again, the click of the user during the search process is changeable, most of the time it is random, see a link on a topic, an advertisement link, You may click to view it. Such click information is actually a kind of noise, which has little to do with the retrieval request, but it will still be recorded.

This method does not depend on the user's search result information, it is a method of pre-processing, but the shortcoming is how to do different analysis according to different types of retrieval intentions, there is no clear method

[0006] Retrieval intent recognition based on post-mortem search relies too much on search results and user responses, and it is easy to introduce some unnecessary noise (such as advertisements, other information, etc.), and has high requirements for search engines. The system performance is stable and the effect is relatively good. Only when it is good can it be supported

And in the application of the obtained user's search intention, it can only be used as a reference when the subsequent user enters the same search, so the recall rate is low

[0007] Based on the pre-retrieval intention recognition, the information used is less, and it is limited to the complete matching of the local words retrieved. It has a certain effect on the retrieval of obvious retrieval intentions, but it is also easy to cause local optimal problems, and it is not obvious to more The search for the search intent word cannot give the intended result

Although it is possible to perform semantic analysis on search keywords, different types of searches contain different part-of-speech distributions. If each part of speech is separated, the analysis results will be diverse, and it is not easy to further select the best.

Images