Device for automatically obtaining element nouns of claims and positions of element nouns

Abstract

The invention relates to a device for automatically obtaining element nouns and positions of the element nouns in a character inter-character-space-free language character claim. The device comprises a basic exclusion character record exclusion device, a deletable character record exclusion device, a single character record exclusion device and an advanced exclusion character record exclusion device. In the character C-Text of the inter-character-space-free language character claim, the continuous characters after the basic exclusion characters are excluded serve as the continuous characters of the basic exclusion characters; the basic excluded characters exclude continuous characters after deletable characters are excluded from the continuous characters, and the basic excluded characters are used as deletable characters to delete the continuous characters; continuous characters are deleted from the deletable characters from which the single characters are excluded, and the continuous characters are taken as initial element nouns; the continuous characters after the advanced character elimination in the preliminary element nouns are used as the obtained element nouns.

Description

technical field [0001] The invention relates to a device for automatically deriving component nouns and their positions, in particular to a device for automatically deriving component nouns and their positions in language claims without spaces between words. Background technique [0002] Patent specifications are complex and not easy to read. Identifying component nouns in patent claims through artificial intelligence is the basis of the artificial intelligence patent reading aid system. The so-called component nouns refer to the definition words that constitute the components in the patent claims. The component nouns are not just nouns, but the nouns are the final words, and the definition words composed of adjectives, verbs, adverbs or nouns, such as , "receiving antenna", "signal sending mechanism", etc. By obtaining the component noun of the patent claim, the location of the component noun can be obtained, so the corresponding position corresponding to the action featu...

AI Technical Summary

Problems solved by technology

[0003] However, for languages ​​without spaces, such as Asian languages, including Chinese, Japanese, or Korean, it is more difficult to distinguish between words and characters than English because there are no spaces between words. combinations between words, so it is more difficult to come up with various combinations of words

Under this difficulty, it is difficult to realize part-of-speech analysis of natural language

Although someone proposes to establish a device for component noun thesaurus to identify component nouns by part of speech, the component nouns claimed in the patent claim have various possible changes, and it is impossible to establish such a large number of component noun databases. There are often pairs of verbs, nouns, Misjudgment of adjectives, adverbs, etc.

Furthermore, even if this huge number of component nouns can be established, it will be very time-consuming to carry out such a huge database data comparison device, so it is difficult to implement

Images