Method for extracting key elements from natural language input of user

Abstract

The invention relates to a method for extracting key elements from natural language input of a user. The method includes following steps: performing semantic matching on first natural language input of the user according to a first semantic knowledge library to recognize overall semantic meaning; selecting a limiting knowledge library; shrinking the limiting knowledge library by determining entries correlated with the total semantic meaning in the limiting knowledge library and removing other entries; performing mechanical word segmentation on the first natural language input to generate a word segmentation result set of the first natural language input; using the limiting knowledge library after being shrunk to match word segmentation results to determine a word segmentation result in the word segmentation result set; selecting one or multiple words from the word segmentation result as the key elements. By the method, word segmentation efficiency and correctness can be improved greatly, so that determination of correct key elements is guaranteed.

Description

technical field [0001] The present invention generally relates to the field of natural language processing, and specifically relates to a method for extracting key elements from a user's natural language input. Background technique [0002] With the development of computer technology, artificial intelligence robots have begun to emerge in the market, such as Microsoft's "Xiaobing", Apple's "Siri", Baidu's "Durmi" and so on. These artificial intelligence robots are mainly divided into voice assistants and chats. The main function of the former is to provide users with useful information, while the latter aims to chat with users. No matter what kind of robot, it involves natural language processing technology. The natural language processing technology refers to processing the natural language input by the user so that the robot can understand the natural language. [0003] One of the core technologies of natural language processing is how to accurately extract keywords fro...

AI Technical Summary

Problems solved by technology

However, due to the huge knowledge base, this will inevitably lead to a huge amount of calculation, which greatly increases the calculation cost, and when encountering confusing expressions, such as "there is a Changchun pharmacy in Changchun City", the word segmentation system is also prone to errors

[0004] In addition, even if the word segmentation is correct and the corresponding keywords are extracted, the existing technology often cannot determine the correct semantics of the extracted keywords, but may use the wrong semantics of the keywords to generate natural language output, which will also result in failure to generate correct semantics. The natural language output of the system

This is because the core vocabulary in the user's natural language input may have multiple meanings. For example, "potato" can refer to a kind of food or a "potato" video website, and existing robots encounter these ambiguous words , the correct semantics of the vocabulary cannot be determined

Wrong semantic determination leads to "misunderstanding" of keywords, resulting in low intelligence of the robot and poor user experience

Images