Multi-round dialogue voice interaction method and system, storage medium and electronic equipment

Abstract

The invention provides a multi-round dialogue voice interaction method and system, a storage medium and electronic equipment. The method comprises the following steps: receiving voice query information of a user and converting the voice query information into text query information; carrying out intention classification, and extracting word slots and word slot types included in the text query information; matching a plurality of preset word slot types included in the intention corresponding to the text query information with word slot types included in the text query information, obtaining optional or necessary supplementary word slots under the condition of determining that the text query information lacks the word slots, and matching the supplementary word slots to the word slots corresponding to the preset word slot types lacking in the intention to generate response information of the text query information, thereby realizing intelligent voice interaction.

Description

technical field [0001] The present invention relates to the technical field of intelligent voice interaction, in particular to a method and system for multi-round dialog voice interaction, a storage medium, and electronic equipment. Background technique [0002] With the development of the Internet and artificial intelligence, intelligent voice interaction is becoming more and more widespread, and in voice interaction, the recognition of semantics and the processing of information are extremely important. In the traditional intelligent voice interaction technology, it usually only recognizes the user's single-sentence voice information, but cannot realize the transmission and fusion of semantic information. [0003] For example, the user said in the previous sentence, "Help me check the train ticket to Shanghai", and the next sentence said "Check the air ticket again?", the second sentence the user wants to ask is the ticket to Shanghai, the system can't understand, you may ...

AI Technical Summary

Problems solved by technology

In the traditional intelligent voice interaction technology, usually only the user's single-sentence voice information is recognized, but the transmission and fusion of semantic information cannot be realized

[0003] For example, the user said in the previous sentence, "Help me check the train ticket to Shanghai", and the next sentence said "Check the air ticket again?", the second sentence the user wants to ask is the ticket to Shanghai, the system can't understand, you may have to ask "Excuse me, where is the plane ticket?" For the information that the user said before, the follow-up conversation will continue to ask, which will affect the user experience

[0004] For another example, the user orders "a train ticket to Beijing" through voice interaction, and then asks "how's the weather over there?" The "over there" in this sentence refers to Beijing, but because the traditional voice interaction system once Only one task can be processed. When the ticket booking task is switched to the weather check task, the destination information in the ticket booking task cannot be brought to the weather check task, which also affects the user experience.

Images