Community Recommendation in Tencent Games: Adaptive K‑Free Community Detection and Constrained Large‑Scale Community Recommendation (ComRec)

This article presents Tencent's research on community recommendation for online games, introducing an adaptive K‑Free community detection algorithm (DAG) to address cold‑start and unknown community count, a constrained large‑scale recommendation method (ComRec), their evaluation metrics, experimental results, and deployment insights.

Tencent GamesUnsupervised Learningcommunity-detection

0 likes · 20 min read

Community Recommendation in Tencent Games: Adaptive K‑Free Community Detection and Constrained Large‑Scale Community Recommendation (ComRec)

DataFunTalk

Aug 4, 2024 · Artificial Intelligence

Community Recommendation in Tencent Games: Adaptive K‑Free Community Detection and Constrained Large‑Scale Community Recommendation (ComRec)

This article presents Tencent's research on community recommendation for online games, covering the motivation behind recommending player groups, the challenges of cold‑start and data sparsity, the adaptive K‑Free community detection algorithm (DAG) with joint structural‑semantic learning, the constrained large‑scale ComRec algorithm, extensive offline and online experiments, and practical deployment insights.

Tencent GamesUnsupervised Learningcommunity recommendation

0 likes · 20 min read

StarRocks

May 14, 2024 · Artificial Intelligence

How Tencent Games Boosted AI‑Generated SQL Accuracy to 89% with a Lakehouse Architecture

Tencent Games tackled the low accuracy of AI‑generated SQL in production by combining large language models with a StarRocks lake‑warehouse, introducing a semantic layer, async materialized views, and an agent‑based multi‑intelligence framework, ultimately raising one‑shot SQL correctness to 89% and cutting delivery time from 2 hours to 0.33 hours.

AILLMLakehouse

0 likes · 13 min read

How Tencent Games Boosted AI‑Generated SQL Accuracy to 89% with a Lakehouse Architecture