Information retrieval device and method

Abstract

The invention discloses an information retrieval device and method. The device comprises a receiving unit, a keyword obtaining unit, a comparison unit, a classification number obtaining unit and a retrieval formula building unit, wherein the receiving unit receives a specific patent number input by a user; the keyword obtaining unit automatically extracts keywords from patent information corresponding to the specific patent number; the comparison unit divides the extracted keywords into a plurality of priority levels according to the correlation degree of the keywords and the specific patent; the classification number obtaining unit extracts a classification number from the patent information corresponding to the specific patent number, and dividing the plurality of extracted patent numbers into a plurality of priority levels; the retrieval formula building unit builds a retrieval formula on the keywords and the classification number in a sequence from high priority levels to low priority levels until the retrieval formula with the retrieval result meeting the preset threshold value condition is built. The keywords and the classification number are automatically extracted; the keywords and the classification number are subjected to priority classification according to the correlation degree; the retrieval formula is built according to the priority level sequence of the keywords and the classification number; the patient information similar to the expected retrieval theme is precisely, efficiently and automatically retrieved.

Description

technical field [0001] The present invention relates to an information retrieval device and method, in particular to a device and method for retrieving technical information, such as patent information. Background technique [0002] Technical information, especially patent information, is an indispensable and important resource for the development of enterprises or research institutes. For example, before enterprises or scientific research institutes conduct R&D or investment, they can fully understand the existing technical level in a specific technical field, determine the correct research direction, avoid repeated development, and save time and research funds. [0003] However, in recent years, patent information has grown rapidly, and more than one million patent documents are published in the world every year; and the existing patent search is usually carried out in the patent database. Based on experience, input relevant keywords and their synonyms or corresponding cl...

AI Technical Summary

Problems solved by technology

[0005] Although Patent Document 1 can automatically search for and similar applications without the help of humans, the words automatically extracted by the machine usually include some meaningless words, for example, in the field of computers, "function" is a meaningless word , In addition, different words have different degrees of proximity to the subject matter. For example, when the pending patent relates to a camera lens, and when the extracted search language contains "CCD", according to the scheme of Patent Document 1, the "CCD" also needs to participate in the construction of the search formula, but obviously the correlation between "CCD" and "lens" is not great. Therefore, if "CCD" is also included in the construction of the search formula, it may be due to the introduction of too many search terms , instead causing leakage

Images