Intelligent answering system for learning machine

Abstract

The invention belongs to the field of natural language processing research and particularly discloses an intelligent answering system for a learning machine. The intelligent answering system comprises a semantic analysis unit, a second relation establishing unit, a rational analysis unit and an answer extracting unit, wherein multiple obtained candidate answers are evaluated, the candidate answer with the highest evaluated value is used as an answer, and then a system result is provided. The intelligent answering system can be effectively combined with the learning machine of the prior art, will not be influenced by the number of questions of a question bank of the existing learning machine, can conduct analysis and judgment automatically and intelligently provide answers, and effectively fills up the blank in the aspect. The intelligent answering system has the advantages that corresponding relations between semantic roles are established in authentic Chinese materials, and an induction path is formed between the questions and the answers; the granularity of reading comprehension questions and answers reaches the chuck level, and more natural and more appropriate answers are provided.

Description

technical field [0001] The invention belongs to the field of natural language processing research, and in particular relates to an intelligent answering system applied to a learning machine. Background technique [0002] The methods adopted by the early learning machines were to solidify a large number of learning resources such as dictionaries, grammar, and materials on the memory, and provide some auxiliary learning functions for buyers. But its function is also subject to great restrictions. When a consumer purchases a learning machine, the learning aids obtained are limited to the content provided by the learning machine. Its function is relatively simple and cannot be expanded. Since 2005, learning machines have evolved into audio-visual products that support different learning forms and diverse subjects. It is mainly reflected in classroom synchronous tutoring, multi-national language learning, and application of standard professional dictionaries. [0003] The emer...

AI Technical Summary

Problems solved by technology

[0005] In the prior art, there are many products about learning, such as learning machines, many learning software, etc., all of which store the answers and give them directly, especially for the two aspects of text reasoning and reading comprehension. The method is relatively simple, and the number of questions in the system such as learning machines is limited, which has many disadvantages to learning

Images