Official account of Tencent IEG Growth Platform Technology Team, showcasing cutting‑edge achievements across front‑end, back‑end, client, algorithm, testing and other domains.
This article provides a comprehensive overview of Flutter's container‑type widgets—including Padding, DecoratedBox, Transform, Container, and Scaffold—explaining their differences from layout widgets, demonstrating their APIs, and showing practical code examples for UI composition and styling.
This article explains how JavaScript processes binary data for front‑end image handling, covering core APIs such as ArrayBuffer, TypedArray, DataView, Blob, File, and FileReader, and demonstrates practical techniques for previewing, downloading, converting, compressing, and detecting image formats using code examples.
This article provides a comprehensive analysis of Go's net/http library and the Gin framework, detailing request handling flow, router implementation, middleware chaining, and context management, while presenting key source code excerpts to illustrate how HTTP services are built and extended in Go.
This article describes the end‑to‑end multimodal modeling pipeline—covering text, image, and video understanding, model evolution from shallow to deep networks, key‑frame extraction, fine‑tuning, and multimodal fusion—used in Tencent's game ad exchange platform, along with practical deployment challenges and solutions.
This article explains image compression fundamentals, compares bitmap, direct color, lossless and lossy methods, evaluates Node.js libraries imagemin, sharp, and TinyPNG through JPEG/PNG tests, and provides practical usage code and insights into plugin‑based compression algorithms.
This article introduces the concept of vector retrieval, outlines its diverse application scenarios, explains common distance metrics for both floating‑point and binary vectors, and surveys fundamental approximate nearest‑neighbor algorithms including tree‑based, graph‑based, quantization, and hashing methods.
This article presents a comprehensive overview of using reinforcement learning to solve advertising bidding ROI optimization, covering historical foundations, methodological reasoning, system architecture, practical implementation details, challenges, evaluation metrics, and recommended algorithms for real‑world ad placement scenarios.
This article explains how to design a lightweight rule engine in Go by first using JSON‑defined rules, then leveraging Go's token scanner and AST parser to evaluate boolean expressions such as header and cookie checks, and finally discusses extending the engine with custom primitives and GoYACC for more complex grammars.
This article presents a three‑part technical guide covering the fundamentals of computational advertising and real‑time bidding, detailed offline pCTR model training pipelines with feature engineering, calibration and model structure improvements, and advanced online learning techniques such as parameter freezing, sample replay and knowledge distillation, all aimed at boosting CTR performance and reducing bias in large‑scale ad platforms.
This article introduces model‑free reinforcement learning fundamentals, reviews mainstream solution methods such as Monte‑Carlo, Temporal‑Difference, and n‑step TD with eligibility traces, discusses their application in online advertising and presents Tencent's game advertising practice, including algorithm choices, reward design, and experimental results.
