Intelligent NPC: How AI Gives Game Characters a Soul and the Art of Deep Model Inference Acceleration
The talk by Tencent Games AI lead Qiu Dongyang explores the opportunities large models bring to game NPCs, showcases the "JueZhi Anuan" intelligent NPC prototype, discusses core challenges and acceleration techniques, and outlines future plans and compliance considerations for AI‑driven characters.
Speaker : Qiu Dongyang, Technical Lead of Tencent Games "Game Zhiji" AI products. He holds a master's degree in Computer Science from Northwestern Polytechnical University and works on NLP, model inference acceleration, system architecture, and performance optimization. Notable projects include Game Zhiji Q&A, "Peace Fifth Person" AI voice assistant, accessible version of Tian Tian Xiang Qi, Zhiyin large‑model voice, "JueZhi Anuan" intelligent NPC, and LLM‑based human‑machine collaborative customer service solutions.
Talk Title : Intelligent NPC – AI Infuses Soul into Game Characters, The Art and Science of Deep Model Inference Acceleration
Talk Outline :
1. Opportunities that large models bring to NPC development.
2. A small step: the "JueZhi Anuan" NPC intelligentization attempt.
3. Core challenges of intelligent NPCs and their solutions.
4. Our future plans for NPC intelligence.
Audience Benefits :
1. How to keep LLM‑generated content consistent with game worldviews and IP character designs.
2. What safety and compliance solutions exist for large models.
3. How to address real‑time performance of multimodal interactions with large models.
For more details, click "Read the original article" to view the offline conference information.
DataFunTalk
Dedicated to sharing and discussing big data and AI technology applications, aiming to empower a million data scientists. Regularly hosts live tech talks and curates articles on big data, recommendation/search algorithms, advertising algorithms, NLP, intelligent risk control, autonomous driving, and machine learning/deep learning.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.