User problem processing method and device and server

Abstract

The invention provides a user question processing method and device and a server. The method comprises the following steps: after a server receives a question text of a user, processing the question text of the user according to a preset conceptualized knowledge base and a preset processing rule to obtain a matched target query statement, wherein the used preset conceptualized knowledge base at least comprises a preset question query template library, and the preset question query template library comprises a plurality of question query templates; and querying a preset knowledge graph according to the target query statement to obtain a target answer text corresponding to the question text of the user. By introducing and utilizing the preset conceptualized knowledge base, the method can be suitable for diversified complex scenes, efficiently and accurately determines the target answer text corresponding to the question text of the user, and feeds back the target answer text to the user in time, so that the interaction experience of the user is improved.

Description

technical field [0001] This manual belongs to the technical field of artificial intelligence, and in particular relates to a processing method, device and server for user problems. Background technique [0002] Every day, the system server of the network platform receives a large number of questions from users waiting to be answered. [0003] Based on existing methods, it is often necessary to pre-train a semantic parsing model based on traditional linguistics. Furthermore, the above-mentioned semantic analysis model can be used to process the questions raised by the users, so as to finally find out the answers corresponding to the questions raised by the users. [0004] However, the range of applicable scenarios for the semantic analysis model trained based on the above method is usually relatively limited, and the training cost and maintenance cost of the model are relatively high. In addition, due to the limited scope of application of the above-mentioned semantic analy...

AI Technical Summary

Problems solved by technology

[0004] However, the scope of applicable scenarios for the semantic analysis model trained based on the above method is usually relatively limited, and the training cost and maintenance cost of the model are relatively high

In addition, due to the limited scope of application of the above-mentioned semantic analysis model, when the scenarios faced become more complex and diverse, the accuracy of the model will be relatively poor, which will make the final answer prone to errors and affect the user's experience. interactive experience

[0005] For the above problems, no effective solutions have been proposed so far

Images