Cross-skill multi-round conversation method and system for voice conversation platform

Abstract

The embodiment of the invention provides a cross-skill multi-round conversation method and system for a voice conversation platform. The method includes the steps of identifying an input statement hitfirst skill of a user, feeding back a first output statement based on the first skill, and at least storing keywords included in the first output statement and common types corresponding to the keywords to a multi-round conversation keyword table; obtaining history keywords as the same as a certain keyword in type from the multi-round conversation keyword table if the certain keyword is missing when a subsequent input statement jumps to a hit second skill; and supplementing the subsequent input statement according to the obtained history keywords, and feeding back a second output statement based on the second skill. The embodiment of the invention further provides the cross-skill multi-round conversation system for the voice conversation platform. According to the cross-skill multi-roundconversation method and system, semantic results of the hit skills are extracted and stored in the multi-round conversation keyword table using the common types, and usage of contexts across skills invoice conversations can be achieved through a series of processing.

Description

technical field [0001] The invention relates to the field of intelligent voice dialogue, in particular to a multi-round dialogue method and system for a voice dialogue platform across skills. Background technique [0002] Multi-round dialogue In human-computer interaction, the user sends a dialogue request (which can be regarded as an intention), and after the user's intention is initially clarified, the necessary information is obtained to finally obtain a clear user instruction, and then the dialogue service responds to the user according to the skill customization Give feedback. [0003] Even in the communication between people, the information contained in a sentence itself only accounts for a part of the total amount of information transmitted, and the other part of the information comes from a series of information such as the speaker's identity, current time, and location. For example, a user is going on a business trip to Suzhou for a week and asks the smart assista...

AI Technical Summary

Problems solved by technology

[0006] In order to at least solve the problem in the prior art that due to the different data structures defined by each skill, it is impossible to use the context to complete the utterances input by the user in the voice dialogue caused by cross-skills

Images