Common Optimization Points in Building a User Portrait Platform
The presentation by Zhang Xinglong, head of the user understanding center's portrait platform backend, outlines the platform's overall architecture, core module optimizations, advanced crowd creation techniques, bitmap usage, and industry trends, helping the audience understand platform importance, performance improvements, and future directions.
Zhang Xinglong is the head of the User Understanding Center's portrait platform backend at Kuaishou. He graduated from the Institute of Software, Chinese Academy of Sciences, worked at Baidu International Product Department on server-side development, and later built Kuaishou's user portrait platform from scratch, authoring the book "User Portrait: Platform Construction and Business Practice".
Talk Title: Common Optimization Points in Building a Portrait Platform
The talk introduces the overall architecture of the portrait platform, highlights engineering optimization points of each core module, and concludes with the current industry status and future trends.
Outline:
1. Introduction to the Portrait Platform
2. Common Functions and Architecture of the Portrait Platform
3. Typical Optimization Points:
• Advanced crowd creation optimization • Crowd existence (判存) solutions • Use of BitMap in the portrait platform • Generation optimization of crowd wide tables • Introduction of task mode
4. Industry Development Status and Trends
Audience Benefits:
1. Understand the importance of a portrait platform and its common architecture. 2. Familiarize with key optimization techniques such as speeding up crowd selection, efficient crowd existence checks, and special bitmap applications. 3. Learn about the current industry landscape and future trends for portrait platforms.
DataFunSummit
Official account of the DataFun community, dedicated to sharing big data and AI industry summit news and speaker talks, with regular downloadable resource packs.
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.