Self-learning smart telemarketing agent assistant

Abstract

The invention discloses a self-learning smart telemarketing agent assistant. The self-learning smart telemarketing agent assistant comprises the following steps: S1: performing, by a salesman, a dialogue with a customer, recording the dialogue voice through a machine, generating candidate answers, and presenting the candidate answers to the salesman; S2: according to a mouse operation situation ofthe salesman, for example, clicking candidate options by the mouse, clicking to unfold the details of a certain option by the mouse, the time proportion of the mouse to stay on a certain option, calculating a mouse operation relevance score; and S3: transcribing the words of the salesman during the display of the candidate options by using a real-time voice recognition engine, and calculating thesemantic similarity between the words of the salesman and the candidate options by using a general semantic similarity model to serve as the relevance score of the sales adoption condition. Accordingto the self-learning smart telemarketing agent assistant disclosed by the invention, training samples are updated in real time through an online learning method, the problems of annotation data acquisition and timely model online are solved, the overall performance of the smart telemarketing agent assistant is improved, so that the self-learning smart telemarketing agent assistant is worth promoting.

Description

Technical field [0001] The invention relates to the technical field of sales agent assistants, in particular to a self-learning smart phone sales agent assistant. Background technique [0002] In the work process of sales representatives in the telemarketing call center, facing new business problems, new product advantages and selling points and other content issues, the sales representatives quickly input and search on the spot to obtain answers, answer questions, and introduce product advantages and selling points. By introducing real-time voice recognition technology and natural voice processing technology, the smart phone sales agent assistant transforms the traditional manual listening, understanding, recalling, and searching work into a machine that automatically provides candidate answers in real time, and then manually judges and selects the results. However, the machine to provide high-quality candidate answers requires a powerful question and answer model as support. Th...

AI Technical Summary

Problems solved by technology

However, the high-quality candidate answers provided by the machine require a powerful question-answering model as a support, and the quality of the model depends largely on the quantity and quality of the labeled data. However, the cost of large-scale manual labeling data is very high, and because labeling requires a certain The time period, the new question answering model can not answer in real time, and the quality of the candidate answer depends on the quantity and quality of the labeled data, the cost of obtaining a large amount of manual labeling data is high, and because of the time period brought by the labeling, the latest question answering model cannot be timely online

Images