Intelligent service method and system based on natural language interaction

Abstract

The invention discloses an intelligent service method based on natural language interaction and belongs to the technical field of artificial intelligence. The intelligent service method based on natural language interaction includes the steps that natural language information input by a user is received; the natural language information is subjected to semantic parsing on multiple preset semantic scenes and a plurality of semantic parsing results are obtained; the semantic results are ranked according to a ranking model obtained through pre-training; a preset number of semantic parsing results are selected from the ranked sequence and serve as the final semantic parsing result of the natural language information; the final semantic parsing result is responded to. Due to the intelligent service method based on natural language interaction, the accuracy rate of the semantic parsing result can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an intelligent service method and system based on natural language interaction. Background technique [0002] With the continuous development of artificial intelligence technology, people's demand for convenient, efficient and accurate intelligent services is becoming stronger and stronger. As the most convenient and natural way for humans to express their thoughts, natural language has gradually become the most mainstream human-computer interaction method in the field of intelligent services. Taking the field of customer service as an example, when people want to subscribe to a data package through the SMS platform, they are often more inclined to write short messages in natural language expressions such as "I want to subscribe to a 5 yuan data package", rather than memorizing a long list of complex information. character code. Due to the openness, rand...

AI Technical Summary

Problems solved by technology

When a user wants to watch the "news all-weather" program and enters "news all-weather", it may be misrecognized as "news all-weather climate", so that it cannot match the "video" scene recognition word, but with the "weather" scene recognition word match, so that the semantic scene type is wrongly determined as "weather", which eventually leads to an error in the parsing result

[0013] Therefore, using the above-mentioned intelligent service method based on natural language interaction, it is easy to cause ambiguity in the words themselves, or inaccurate user expressions, or inaccurate speech recognition results, etc., resulting in errors in semantic scene judgment, which in turn lead to errors in analysis results, and ultimately lead to response results Completely unable to meet user needs, thus falling into an irreversible error situation

Images