Intention recognition method, recognition device and computer readable storage medium

Abstract

The invention discloses an intention recognition method, recognition equipment and a computer readable storage medium, and is applied to the technical field of artificial intelligence. The method comprises the following steps: receiving a to-be-identified statement input by a user, and carrying out word segmentation processing on the to-be-identified statement to obtain a plurality of segmented words forming the to-be-identified statement; traversing keywords under each intention node of a preset intention concept tree to determine each first target keyword hit by the plurality of segmented words in the keywords under each intention node; calculating an intention score of an intention corresponding to each intention node of the to-be-identified statement according to the weight corresponding to each first target keyword; determining the highest intention score in the intention scores of the intentions corresponding to the intention nodes; and if the highest intention score is greater than a first threshold, determining that the intention of the to-be-identified statement is the intention corresponding to the highest intention score. By adopting the method and the device, the intention recognition accuracy can be improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to an intention recognition method, a recognition device, and a computer-readable storage medium. Background technique [0002] The current intent recognition method is mainly based on machine learning or deep learning, which often requires a large number of training samples. However, in some fields or scenarios, there are relatively few training samples available. For example, in the field of service robots, when robots handle business consulting in specific fields, fewer training samples are involved. If you still use the machine learning or deep learning-based Method for intent recognition may cause the trained model to fail to accurately recognize the user intent or even recognize the user intent due to the small number of data training samples, resulting in the inability to provide users with more accurate business questions and answers. Contents...

AI Technical Summary

Problems solved by technology

However, in some fields or scenarios, there are relatively few training samples available. For example, in the field of service robots, when robots handle business consulting in specific fields, fewer training samples are involved. If you still use the machine learning or deep learning based Method for intent recognition may cause the trained model to fail to accurately recognize the user intent or even recognize the user intent due to the small number of data training samples, resulting in the inability to provide users with more accurate business questions and answers

Images