Information providing method and apparatus

Abstract

The present invention provides an information providing method and apparatus, which have advantages of being objective, high in efficiency, wide in application scope, and good in scalability. The method comprises: extracting a sample feature vector and a corresponding sample decision from historical consultancy session data, wherein an element of the sample feature vector is an attribute value extracted from the historical consultancy session data according to a preset attribute, and the sample decision is a user questioning sentence; performing training by using a plurality of sample feature vectors and corresponding sample decisions to obtain a probabilistic classification model; extracting a to-be-tested feature vector from a current client consultancy request, wherein the to-be-tested feature vector is the same as the sample feature vector in format; inputting the to-be-tested feature vector into the probabilistic classification model, then receiving one or more candidate decisions and corresponding probabilities output from the probabilistic classification model, wherein the candidate decisions are candidate user questioning sentences; choosing K candidate decisions of greatest probabilities as forecasted decisions, then providing a client with a standard reply corresponding to the forecasted decisions.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for providing information. Background technique [0002] In the application scenario of e-commerce customer service dialogue, before the customer starts to speak, the automatic customer service system usually shows the customer in advance some predicted questions that the customer may ask (referred to as "predicted questions") and the corresponding standard answer information. Through problem prediction, you can serve customers faster and make users feel more intimate. [0003] In the prior art, these prediction problems are usually recommended by counting the largest number of problems from the historical problems, or combining various rules for weighted voting, and finally recommending the problems. By formulating rules and then performing weighted voting, this method is a relatively primitive processing method, which requires manual adjustment of the wei...

AI Technical Summary

Problems solved by technology

By formulating rules and then performing weighted voting, this method is a relatively primitive processing method, which requires manual adjustment of the weights of various rules after a large number of experiments; if there are too many types of rules and there are certain correlations between them, the processing complexity will increase. It grows exponentially and is not easy to maintain; it is not easy to adjust after the rules are formulated, and the scalability is poor

Images