Method and device of predicting user problems based on data driving

Abstract

The invention discloses a method and a device of predicting user problems based on data driving. The method comprises steps that when a problem posed by a user is received, user behavior data is acquired and pre-treated, and to-be-selected behavior data having contribution to the problem posed by the user is intercepted from the pre-treated user behavior data; the to-be-selected behavior data included by a target behavior data set is screened from the above mentioned to-be-selected behavior data, and the screened to-be-selected behavior data is input in a trained classifier model, and a category, to which the problem posed by the user belongs, is predicted. The device comprises a pre-treatment module, an interception module, and a prediction module. By adopting the method and the device provided by the invention, prediction effect is obviously improved.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a method and device for predicting user problems based on data driving. Background technique [0002] Users often encounter problems that they cannot handle when using products or services, and then seek customer service for help. Usually customer service personnel need to go through several rounds of dialogues with the user to determine what problem the user is encountering, which requires a lot of labor costs. If it is possible to predict the problems that users may encounter in advance, it can intelligently push relevant answers or help customer service personnel locate user problems more effectively. [0003] Predicting the problems that users may encounter in advance is a typical multi-classification problem, which usually consists of two parts: feature selection and model modeling. In the existing methods, when the feature selection end extracts featur...

AI Technical Summary

Problems solved by technology

There are two problems: 1. It is not data-driven, but requires strong human intervention, and requires the intervener to fully understand and be familiar with the corresponding product or business, which will introduce a lot of inconvenience when the product changes frequently or the business coverage expands, which can be expanded Sex is not strong

2. Failure to consider the relationship between the user's behavior in the short period of time before seeking help from customer service personnel and the user's problem. Usually, the user will have a series of behaviors in a short period of time (for example, within 2 hours) before seeking customer service personnel's help. These behaviors include but are not limited to mobile phone, tablet client clicks, PC web browsing and other operations performed by the user, which includes the user's behavior track information before asking questions. In theory, these behavior tracks are strongly related to the user's subsequent help seeking

Images