After-sales service method and device, electronic equipment and storage medium

Abstract

The invention provides an after-sales service method and device, electronic equipment and a storage medium. The after-sales service method comprises the steps of obtaining evaluation information of acommodity; under the condition that the evaluation information is determined to be negative evaluation, determining a first meta event of the evaluation information; based on the first meta-event anda pre-stored cause map, determining a target cause for making the evaluation information for the commodity, the cause map including the cause of the first meta-event; and outputting the target reasonto enable the user to perform after-sales service based on the target reason.

Description

technical field [0001] The present application relates to the technical field of e-commerce, in particular to a method, device, electronic equipment and storage medium for after-sales service. Background technique [0002] As e-commerce gradually enters people's lives, online shopping has become a common way for people to shop. After people shop online, they usually comment on the products, and merchants will conduct after-sales visits to buyers who have negative comments on the products. Usually, The method is to manually select negative comments or use sentiment analysis to select corresponding buyers, conduct after-sales return visits one by one, track their shortcomings to the product and make records to support future optimization of the product. However, traditional sentiment analysis can only distinguish obvious product reviews, and it is difficult to analyze the emotional bias of irony, rhetorical questions, and metaphorical sentences. Negative comments for this par...

AI Technical Summary

Problems solved by technology

However, traditional sentiment analysis can only distinguish obvious product reviews, and it is difficult to analyze the emotional bias of irony, rhetorical questions, and metaphorical sentences.

Negative comments for this part cannot be identified, resulting in data omission

In addition, after extracting the seller's evaluation, the relationship between the evaluation and the entity is displayed through the knowledge graph to facilitate customer service. However, the relationship in the knowledge graph is relatively definite and static knowledge, and often many comments are logical. For example, when the washing machine is working, the sound is a bit loud, and when extracting the knowledge map, it can only be mentioned, washing machine-work->the sound is loud, but the loud sound of the washing machine is often caused by the imbalance of the balance liquid during the rolling process of the washing tub. This part of the information cannot be seen in the knowledge graph, resulting in the customer service unable to understand the user's true expression, and the efficiency of after-sales service is low

Images