Knowledge reasoning dialogue method and device, electronic equipment and storage medium

Abstract

The invention discloses a knowledge reasoning dialogue method and device, electronic equipment and a storage medium. According to the specific implementation scheme, the method comprises steps of obtaining user utterances; importing the user utterances into a knowledge annotation model to obtain corresponding knowledge annotation information, the knowledge annotation model being used for generating knowledge annotation information of the user utterance; determining corresponding target scene element information and target semantic content corresponding to each piece of target scene element information according to the user utterance and the knowledge labeling information; and generating a reply statement conforming to the current context according to the user utterance, the knowledge labeling information, the corresponding target scene element information and the target semantic content corresponding to each piece of target scene element information. Therefore, by autonomously selecting the corresponding scene elements and the corresponding semantic content, the reply statement conforming to the current context can be generated, and by combining the selected scene elements and thecorresponding semantic content of the scene elements, knowledge content contained in the generated reply statement has better logic relevance.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular to a knowledge reasoning dialogue method, device, electronic equipment and non-transitory computer-readable storage medium storing computer instructions. Background technique [0002] In related technologies, there are mainly two methods to realize human-computer dialogue interaction, one of which is a dialogue method using KG (Knowledge Graph, knowledge map) and free text as background knowledge; the other is using API (Application Programming Interface, application program interface) to obtain and use the dialog method of environment information. Among them, the basic process of the above-mentioned first method is to select relevant content from the background knowledge based on the above information, and then generate available replies based on the above information and relevant content; When the preset trigger conditions are met, the corresponding API is cal...

AI Technical Summary

Problems solved by technology

[0003] However, the current problem is that the above-mentioned first method will only make the reply content only semantically relevant, but lacks the rationality of the overall context, and for devices that select several pieces of background knowledge and integrate them, there is often a lack of context between the background knowledge. Logical correlation or even logical contradiction; in the second method above, the acquisition and use of environmental information is completely passive, or only in a small number of preset scenarios, part of the environmental information will be used to guide the reply generation, so in In most cases, they do not have the ability to use rich environmental information, which leads to the reply only related to the context semantics, but not to the environmental information

Images