Display control method, device and electronic equipment for virtual character
By generating virtual character actions and response text using strategy models and generative pre-trained language models, the high cost of editing virtual character reactions and the limited scope of scene applicability in MMORPGs are solved, thus improving the gaming experience.
CN115463424BActive Publication Date: 2026-05-05NETEASE (HANGZHOU) NETWORK CO LTD
1 Cites 0 Cited by
Patent Information
- Application Number
- CN202210850247.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-19
- Publication Date
- 2026-05-05
- Estimated Expiration
- 2042-07-19
AI Technical Summary
Technical Problem
The reactions of virtual characters in existing MMORPGs cannot meet the needs of diverse real-world scenarios, resulting in problems such as huge editing costs, limited applicability to different scenarios, and poor gaming experience.
Method used
By using a policy model to predict the behavior of virtual characters and combining it with a generative pre-trained language model to generate response text, the virtual characters are controlled to perform actions and display text, thus generating character reactions.
Benefits of technology
It reduced editing costs, improved the efficiency of character reaction generation, expanded the applicability to real-world scenarios, and enhanced the gaming experience.
✦ Generated by Eureka AI based on patent content.
Abstract
This invention provides a method, device, and electronic device for displaying and controlling virtual characters, relating to the technical field of games. The method includes: first, predicting the virtual character's actions based on its background information using a strategy model to obtain a target action; then, generating the virtual character's response text using a pre-trained generative pre-trained language model; and finally, controlling the virtual character to execute the target action and display the response text, thereby generating the virtual character's reaction. This method controls the virtual character by predicting actions and generating response text through a model, thus generating character reactions. This significantly reduces editing costs, improves the efficiency of character reaction generation, meets the needs of diverse real-world scenarios, and enhances the gaming experience.
Need to check novelty before this filing date? Find Prior Art