A keyword-based intelligent retrieval and recommendation method for review experts

Abstract

The invention discloses a keyword-based intelligent retrieval and recommendation method for review experts. The present invention specifically includes the following steps: Step 1: Segment the main text of the expert information into substring sequences and perform ICTCLAS word segmentation of the Chinese Academy of Sciences, perform stop word filtering on the word segmentation results to obtain a word set; Step 2: extract the characteristics of each expert information by field words; Step 3: Build an expert knowledge representation model based on the fields and weights of the feature words, and establish an expert information index library; Step 4: When the user enters keywords, it will automatically prompt according to the search term library, and at the same time use the search term statistic Real-time update of the search word thesaurus; Step 5: Calculate the retrieval correlation between keywords and expert information based on semantic and other information; Step 6: List relevant experts according to the matching degree from high to low. The invention realizes intelligent full-text retrieval and recommendation of expert information by inputting keywords, and more accurately retrieves experts matching pending scientific and technological projects.

Description

technical field [0001] The invention belongs to the technical field of information retrieval, and in particular relates to an intelligent retrieval and recommendation method for evaluation experts based on keywords, which is used for retrieving evaluation experts of scientific and technological projects. Background technique [0002] With the rapid popularization of science and technology project application management system in my country, the evaluation work of science and technology projects has developed from the previous centralized meeting mode to the current network mode. The review experts will review the project application based on the domain knowledge and the funding standards of the funding agencies, and the funding agencies will decide whether to fund or not based on the review experts' comments. The scale of scientific and technological project management systems is getting larger and larger, forming a large amount of expert database information. Since scienti...

AI Technical Summary

Problems solved by technology

When calculating the retrieval correlation, it is not considered that each field of expert information has different importance; at the same time, because there is no special index library, in the case of a huge amount of expert information, the results cannot be retrieved quickly, and the results cannot be searched according to the degree of relevance. to sort

In addition, the prior art mostly lacks the intelligent association prompt function when inputting keywords

These will lead to low recall and precision rates of retrieval results, which limits the ability of automatic analysis and intelligent processing in the field of scientific and technological project review expert retrieval, and directly restricts the social service ability of scientific and technological project review work

Today's general-purpose full-text retrieval technology has been applied in many fields, which can effectively alleviate the above problems, but it is rarely used in the field of expert information

Images