Human-computer interaction method and intelligent robot

Abstract

The embodiment of the invention relates to the technical field of artificial intelligence, and discloses a human-computer interaction method and an intelligent robot. In the present invention, the human-computer interaction method includes: conducting man-machine question-and-answer with the user based on the last optimized intelligent model; when the current round of question-and-answer is over, establishing a human-machine question correspondence between the real machine questions and the human questions in the current round of question-and-answer Among them, the real machine question is the corresponding machine question answered by the last machine in this round of question answering; the intelligent model is optimized by using the corresponding relationship between human and machine questions. The embodiment of the present invention also provides an intelligent robot. The human-computer interaction method and intelligent robot of the present invention can continuously optimize the intelligent model according to actual questions and answers, so that developers do not need to collect a large amount of data in advance, saving labor costs; To accurately identify the real orientation of human problems and realize the "intelligence" of machines.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of artificial intelligence, and in particular to a human-computer interaction method and an intelligent robot. Background technique [0002] Chatbots have been an important direction of human research since artificial intelligence was proposed. During this period, there have been ideas for implementing question-answering robots based on AIML (Artificial Intelligence Markup Language, AIML for short), but the data structure is cumbersome and laborious, and it belongs to keyword retrieval technology after all, without much "intelligence" at all. [0003] In the past two years, intelligent question-answering robots in the field of natural language processing have been put back on the agenda, and various small and medium-sized enterprises are scrambling to investigate and initially build question-answering systems (that is, question-answering robots in specific fields) based on their res...

AI Technical Summary

Problems solved by technology

[0005] 1. Identify "human problems" through the pre-trained intelligent model, so as to find the "answer" corresponding to the knowledge base; and an effective intelligent model needs to rely on high-quality big data for model training, and high-quality big data needs to be developed Pre-acquisition of personnel, resulting in high labor costs

[0006] 2. In real-world chatting, human dialogue is relatively random and often mixed with a lot of context. Different questions raised by people may actually lead to the same machine problem, and even intelligent models trained with high-quality big data , it is still difficult to converge with human thinking, and there are still large errors in judging problems

Images