Dialog interaction method, device and electronic equipment

Abstract

The present invention provides a dialogue interaction method, device and electronic equipment, which relate to the technical field of artificial intelligence. The method includes: acquiring a set of candidate answers corresponding to dialogue operations; wherein, the set of candidate answers in the set of candidate answers includes at least one search answer and / or At least one answer is generated; the dialogue question and the candidate answer set corresponding to the dialogue operation are input to the sorting model obtained in advance; wherein, the ranking model is trained based on the dialogue material sample; the dialogue question and each candidate answer set are calculated by the ranking model. The matching degree of each candidate answer; the ranking result of the candidate answer is generated based on the matching degree of each candidate answer; the dialogue operation is replied according to the ranking result. The invention can effectively improve the man-machine dialogue effect and improve user satisfaction.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and in particular, to a dialog interaction method, device and electronic device. Background technique [0002] Human-machine automatic dialogue is an important application in the field of artificial intelligence. At present, natural language processing technology is mostly used to realize automatic dialogue. In the human-machine dialogue technology, multiple matching sub-models are usually set up first, and different sub-models are used to calculate the matching degree between the candidate answers generated in different ways and the user's question; then the matching degree of the multiple sub-models is compared with the preset The artificial features related to the answer are input to the tree model based on GBDT (Gradient Boosting Decision Tree) or Xgboost, and the score of each candidate answer is output through the tree model; finally, the candidate answers are sorted...

AI Technical Summary

Problems solved by technology

[0003] However, the inventors have found through research that, in the above method, since the process of calculating the matching degree of different sub-models is not uniform, the differences between the sub-models lead to inaccurate ranking results of candidate answers, which makes it difficult for users to answer the questions. Satisfied; at the same time, the resource consumption of multiple sub-models is too large and the deployment is cumbersome, resulting in low efficiency in the generation of answer sorting results, unable to respond to users in a timely manner, resulting in poor man-machine dialogue and poor user experience

Images