A method, device and storage medium for processing virtual characters

By obtaining the statements entered by the user and extracting the character information based on the statement analysis model, generating images and converting them into virtual characters that can perform actions, the problem of mechanization of the virtual character creation process and inconsistent character design and image in the existing technology is solved, and a natural and simplified character creation process is realized.

CN113920229BActive Publication Date: 2025-03-25BEIJING XIAOMI MOBILE SOFTWARE CO LTD +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202111040172.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-06
Publication Date
2025-03-25
Estimated Expiration
2041-09-06

AI Technical Summary

Technical Problem

The existing technology is difficult to realize the complete creation process from the character design of virtual characters to the image, which leads to the mechanization of the character creation process, increases the project volume, and may lead to a sense of incongruity between the character design and the image.

Method used

By obtaining the statements input by the user, extracting the character information related to the virtual character based on the statement analysis model, generating corresponding images, and converting the target virtual character that can perform the action based on the image and action parameters.

Benefits of technology

It realizes the complete role creation process from character to image, simplifies the project volume of traditional role creation, and makes the character and image of the created virtual characters more natural and consistent.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present disclosure is about a method, device and storage medium for processing a virtual character. The method includes: obtaining a sentence input by a user; based on a sentence analysis model, extracting personality information related to the virtual character from the sentence; obtaining a first image according to the personality information; determining action parameters corresponding to the first image; obtaining a target virtual character after converting the first image according to the first image and the action parameters; wherein the target virtual character can perform actions corresponding to the action parameters. Compared with the technical solutions in the related art that only focus on the personality of the virtual character, or only focus on the image of the virtual character, the technical solutions in the embodiments of the present disclosure can realize a complete character creation process from personality to image, which not only simplifies the engineering workload required for traditional character creation, but also makes the personality and image of the created virtual character more natural.
Need to check novelty before this filing date? Find Prior Art