Semantic recognition method and equipment

Abstract

The embodiment of the invention provides a semantic recognition method and equipment, and the method comprises the steps: carrying out the processing of current inquiry information through an NLP technology, and obtaining a first NLP result; wherein the first NLP result comprises a type, a keyword and an action; judging whether a second NLP result of the previous inquiry information has an answerstatement with practical significance or not; if an answer statement with practical significance exists, performing a replacement operation or a position supplementing operation according to the firstNLP result and the second NLP result to obtain a third NLP result; and obtaining a corresponding answer statement according to the third NLP result. According to the embodiment of the invention, based on the recognition result generated by context semantics, the semantics of the user can be explained more accurately, and the method adapts to the speaking habits (such as the use of substitute words and the use of thumbnails) in the communication between people, so that correct feedback is provided for the user in the man-machine conversation process, and the user experience is improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of artificial intelligence, and in particular to a semantic recognition method and device. Background technique [0002] Semantic recognition is a branch of artificial intelligence. Semantic recognition technology can analyze bright data in web pages, files, emails, audio, forums, and social media. It has a wide range of applications and can be directly applied to industries such as medical care, education, and finance. It can also be applied to all intelligent voice interaction scenarios through technical interfaces, such as smart home, in-vehicle voice, wearable devices, VR, robots, etc. In terms of interaction methods, it can also be divided into: fact question and answer, knowledge retrieval, classification questions, etc. Intelligent voice interaction is regarded as the most anticipated application scenario in future artificial intelligence technology. [0003] In the existing...

AI Technical Summary

Problems solved by technology

[0004] However, in the above scheme, the scene is single and the question pattern is fixed, which lacks flexibility and cannot adapt to people's speaking habits (such as the use of pronouns, the use of abbreviated sentences, etc.)

Images