Product recommending method based on voice analysis, product recommending device based on voice analysis, product recommending equipment based on voice analysis, and storage medium

Abstract

The invention relates to the field of voice recognition, and provides a product recommending method based on voice analysis. The method comprises the following steps of playing preset initial voice associated with a product inquiry request when receiving the product inquiry request; collecting first voice information replied by a customer; recognizing the first voice information to obtain the corresponding first tendency information; inquiring a preset verbal trick forest; obtaining a target node matched with the first tendency information in the preset verbal trick forest; generating and broadcasting first recommended verbal trick corresponding to the first tendency information according to the target node; receiving second voice information relied by the customer on the basis of the first recommended verbal trick; recognizing the second voice information to obtain the corresponding second tendency information; when the second tendency information is negative, performing backtrackingreaching on the target node according to the second tendency information; obtaining and broadcasting the second recommended verbal trick. The invention also discloses a product recommending device based on voice analysis, product recommending equipment based on voice analysis, and a storage medium. The product recommending accuracy is improved.

Description

technical field [0001] The invention relates to the field of computer applications, in particular to a product recommendation method, device, equipment and storage medium based on speech analysis. Background technique [0002] With the development of artificial intelligence (Artificial Intelligence), human-computer dialogue products are more and more widely used. [0003] However, in the current man-machine dialogue, when answering the customer's question, it simply recognizes the voice-to-semantics, and cannot understand the customer's intention. For example, the existing product query, through the recognition of the customer's voice information , and search for the corresponding product information according to the voice recognition results to broadcast, the products queried in this way are not accurate, and the applicability of such voice broadcast is poor, and it cannot be fully applied to real life, that is, the existing people Machine interaction realizes that the mac...

AI Technical Summary

Problems solved by technology

[0003] However, in the current man-machine dialogue, when answering the customer's question, it simply recognizes the voice-to-semantics, and cannot understand the customer's intention. For example, the existing product query, through the recognition of the customer's voice information , and search for the corresponding product information according to the voice recognition results to broadcast, the products queried in this way are not accurate, and the applicability of such voice broadcast is poor, and it cannot be fully applied to real life, that is, the existing people Machine interaction realizes product query. The machine is only for assistance, and the real product query introduction is completed by the customer service personnel of the product.

Images