Similar problem generation method and system based on text similarity algorithm, electronic device and storage medium

Abstract

The invention relates to a similar question generation method and system based on a text similarity algorithm, an electronic device and a storage medium, and the similar question generation method based on the text similarity algorithm comprises the steps: obtaining interaction scene text data, and generating a question and answer pair text; calculating the text similarity between the answer text in the question and answer pair text and the answer text in the industry question and answer pair, and determining the industry question and answer pair with the maximum similarity; calculating the text similarity between the question text in the question and answer pair text and the question text in the industry question and answer pair with the maximum similarity, and determining the maximum value of the question text similarity; and comparing the maximum similarity value of the question text with a preset threshold value, and if the preset threshold value is met, supplementing the question text in the question and answer pair text corresponding to the maximum similarity value of the question text into the corresponding industry question and answer pair corpus to serve as a similar question of the question text. Through the method and the system, the problem that similar problem statements generated in related technologies are not smooth and contain redundant contents is solved.

Description

technical field [0001] The present application relates to the technical field of natural language processing, in particular to a method, system, electronic device and storage medium for generating similar questions based on a text similarity algorithm. Background technique [0002] In the process of intelligent interaction, it is necessary to recognize the user's textual intent, and then trigger the corresponding process. [0003] The current intelligent customer service robot technology mainly uses machine learning algorithms for intent recognition. The machine learning algorithm needs to be trained based on a large amount of similar corpus, so a large amount of labeled data needs to be prepared in the early stage of the construction of the intelligent customer service robot. At present, training data is generally generated by manual annotation by business personnel, which has problems such as long cycle time and high annotation cost. Therefore, how to automatically obtain...

AI Technical Summary

Problems solved by technology

[0007] The embodiment of the present application provides a method, system, electronic device and storage medium for generating similar questions based on a text similarity algorithm, so as to at least solve the problem that similar questions generated in the related art are not smooth and contain redundant content.

Images