Method and device for pre-judging intention

Abstract

The invention discloses an intention pre-judgment method and device and relates to the technical field of computers. A specific embodiment of the method comprises the following steps of acquiring personalized feature data and system key feature data of a user; performing pattern recognition on the personalized feature data of the user and the key feature data of the system to obtain abstract features; performing statistical analysis on the abstract features to obtain specified mode features; and performing intention pre-judgment on the user according to the specified mode characteristics. According to the method, the range of data needing to be fitted during intention pre-judgment can be greatly reduced, so intention pre-judgment accuracy is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for intention prediction. Background technique [0002] In the field of intelligent customer service, if the intelligent customer service system can predict the intention of new users who join the consultation more accurately before the user has described the problem, the user experience will be significantly improved. For example: when the user first enters the consultation interface, the intelligent customer service system will directly present the user with a list of possible consultation questions, or directly present the user with the most likely question-and-answer pairs, or directly provide the user with a detailed page of the most likely consultation questions (such as It is predicted that the user may inquire about the logistics status of the order with a probability of 80%, and the logistics progress will be directly displayed), etc., which...

AI Technical Summary

Problems solved by technology

[0005] 1. For the technical solution of intention prediction through the classification model, directly use various comprehensive features in the current system to train the classification model. Because the various features in the system are too complex, there may be thousands of features in the system Therefore, it is very difficult to directly predict the potential intentions of users from massive amounts of data, and it is difficult to improve the accuracy of model predictions;

[0006] 2. For the technical solution of intention prediction by manually writing rules, the accuracy of user intention prediction is not high because the rules are difficult to write and maintain, and the applicable scenarios of the rules may become invalid with time.

Images