Enhanced spurious correlation feedback model information retrieval method based on hyperspace simulation language

Abstract

The invention provides an enhanced spurious correlation feedback model information retrieval method based on a hyperspace simulation language. The method includes the steps of retrieving and feeding back first N documents according to query words Q of an initial user, using all words in the first N documents of the initial feedback as candidate extended words, and adopting a hyperspace simulationlanguage model for calculating adjacent word frequency weights according to the position distance between the candidate extended words and the initial query words; calculating adjacent word weights ofthe final candidate extended words and all the query words; conducting fusion on the adjacent word weights of the candidate extended words and importance weights of the candidate extended words in spurious correlation document sets to obtain final query word items, and obtaining a final feedback document ranking. The accuracy of information retrieval results is further improved effectively, required information are provided move quickly and better for users, searching time and resource costs are saved, and generation of the method has a significant meaning.

Description

Technical field [0001] The invention belongs to the technical field of information retrieval, and in particular relates to an enhanced pseudo-relevance feedback model information retrieval method based on a hyperspace simulation language (HAL). Background technique [0002] In the era of complex and rapid development of information, especially the explosive growth of network information, there are also various forms. A large amount of invalid and redundant information is mixed with the key information that users actually need to extract, which is a great deal of waste. In the precious time of users, it is more and more difficult to accurately and quickly identify and extract the information that users need from the massive information. Information retrieval methods in the field of natural language processing have become a key point in the research of information processing technology. Information retrieval usually includes four aspects: the representation of documents and user q...

AI Technical Summary

Problems solved by technology

[0002] In the era of complex and rapid development of information, especially the explosive growth of network information, the forms are also diverse, and a large amount of invalid and redundant information is mixed with the key information that users actually need to extract, which is largely wasted. The precious time of users, it is becoming more and more difficult to accurately and quickly identify and extract the information users need from massive amounts of information

Images