Data processing method, data processing device, server and storage medium

Abstract

Embodiments of the invention disclose a data processing method, a data processing device, a server and a storage medium. The method comprises the steps of obtaining character data included in a targetdocument; performing structural body recognition processing on the character data to obtain a dialogue character string set, the dialogue character string set comprising a target dialogue character string, and the target dialogue character string comprising a plurality of continuous characters; determining an identity label of a target speaker corresponding to the target dialogue character set; determining a feature description character set for performing character feature description on the target speaker from the character data according to the identity identifier of the target speaker; and performing feature analysis on the feature description character set to determine sound information of the target speaker. By adopting the embodiment of the invention, the voice information of the speaker corresponding to the dialogue part in the document can be automatically identified.

Description

technical field [0001] The present application relates to the technical field of the Internet, and in particular to a data processing method, device, server and storage medium. Background technique [0002] The continuous development of science and technology has brought many conveniences to people's lives, such as human voice reading of novels, webpage information and other documents, which can reduce the time users spend staring at the terminal screen while ensuring that users can obtain the information in the documents, and can protect users. s eyes. In addition, users can select different types of reading voices to read documents according to their preferences, which increases the fun of reading documents. [0003] In the process of human voice reading, the entire document is generally read according to the type of reading voice selected by the user, that is to say, the entire document is read by one voice, so the function of human voice reading is relatively single. I...

AI Technical Summary

Problems solved by technology

[0003] In the process of human voice reading, the entire document is generally read according to the type of reading voice selected by the user, that is to say, the entire document is read by one voice, so the function of human voice reading is relatively single

Images