Response method and device

Abstract

The embodiment of the invention provides a response method and device. The method comprises the following steps: in a machine response link, obtaining an interactive dialogue which has occurred before a response moment; determining the category to which each expression in the interactive dialogue belongs; forming a condition category of the interactive dialogue according to the dialogue sequence of each expression in the interactive dialogue by the category to which each expression belongs; in each historical dialogue, according to the condition category, determining a target category of which the target value meets a set condition; and determining the response expression of the machine response link according to each historical dialogue of the target category meeting the target value and the set condition. The condition category is determined by acquiring at least one round of conversation, and the interaction logic between the machine and the user in the conversation is more considered, so that the determined response is more reasonable and accords with the interaction logic of the conversation. The response words determined through the method are more reasonable, and due to the support of practical data, manual optimization is not needed, and manpower and time are saved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of artificial intelligence, and in particular, to a response method, device, computing device, and computer-readable storage medium. Background technique [0002] The intelligent voice robot provides automatic outbound calls and natural responses, helping enterprises reduce labor costs and improve outbound call efficiency. In terms of implementation technology, the intelligent voice robot integrates ASR (Automatic Speech Recognition, speech recognition), NLP (Natural Language Processing, natural language processing) and TTS (Text-To-Speech, speech synthesis) modules. During the dialogue process, the ASR module first converts the voice from the client into text, the NLP module analyzes the text and predicts and generates a response, the TTS module converts the response into voice, and finally the voice is transmitted to the user through the line to form a round Dialogue interaction....

AI Technical Summary

Problems solved by technology

This results in the design of process branches being strongly dependent on expert experience

Experts relying on experience enumeration will make the answer coverage rate low

And the answer is highly subjective, without the support of practical data

The rationality of the response is questionable

At the same time, in order to ensure the effect of the response, it is necessary to manually read the dialogue history, find out the response language with a bad dialogue experience, and update and optimize it. It can be found that the optimization method is also very time-consuming and labor-intensive, and it is not systematic.

Images