【Meituan Technology Salon】Sponsored by the Meituan technical team and the Meituan Association for Science and Technology, each salon invites technical experts from Meituan and other Internet companies to share practical experience from the frontline, covering all major technical fields.
From September 2020, the Meituan Technology Salon will also create a series of academic activities, including top conference paper sharing, academic hotspot discussions, etc., inviting industry and academia to discuss cutting-edge issues.
Activity time: 14:00-18 :30 , October 17, 2020
Event address: online event
Event registration: poke me to sign up
/ Seller /
Xianyunsen｜Senior Researcher, Meituan
Joined Meituan in 2015. He has been responsible for search query understanding, user interaction and comprehensive ranking in Baidu and Sogou successively. He has more than 10 years of search engine algorithm research and development experience.
| Activity Introduction
With the explosive growth of the Internet, the overload of information and resources on the Internet is becoming more and more serious. Search, recommendation, and advertising provide users with three ways to obtain information, goods and services. With the growth of Internet users and the development of big data technology, these three technical directions have also achieved rapid development, becoming one of the most important application scenarios of AI technology. Due to the complexity and uniqueness of the life service field, Meituan's search, recommendation and advertising are facing greater challenges. This technical salon will introduce Meituan’s technical exploration and practice in these three directions, hoping to exchange and learn with technical colleagues in the industry.
| Schedule
| Share Introduction
Theme 1: Meituan's cross-disciplinary recommended practice
Zhang Bin｜Meituan Technical Expert
Meituan Recommendation Center-Head of Trading Link Team. He has successively engaged in recommendation algorithm-related work in Alibaba, Kuaishou, and Meituan, responsible for Kuaishou new user recommendation, Meituan transaction link recommendation, etc., and has a very rich experience in the implementation of recommendation algorithms in ultra-large-scale scenarios.
brief introduction
First, it will introduce the business development and current situation of Meituan recommendation, as well as the challenges and difficulties faced in cross-field recommendation; secondly, share the practice of Meituan in cross-domain recommendation through the customized optimization of the full link of the recommendation; finally share the recommendation of Meituan Some reflections and future prospects for cross-field recommendations.
Theme 2: Application of Creative Optimization in the Review Information Stream
Li Yichun｜Meituan Technical Expert
Meituan Dianping recommends a smart center technical expert. He joined Meituan Dianping in 2015 and is currently responsible for the creative and recall related work of review information flow.
brief introduction
Dianping information flow is the first choice for users in the local life field to grow grass community platform. Personalized recommendation, natural language processing, and computer vision technologies have been widely used in information flow, among which creative optimization can affect what users see What I think can also guide the community atmosphere and author's creation, and share our practice for students in this direction.
Topic 3: Modeling challenges in computational advertising and solutions in Meituan
Hu Ke｜Meituan Senior Technical Expert
Senior technical expert of Meituan to-store advertising platform, worked successively in Microsoft and Alimama. Currently responsible for the research and development of Meituan search advertising quality estimation. He has won championships in KDD Cup 2017, 2018, Kaggle and other competitions.
brief introduction
1. Modeling challenges in computational advertising
2. Champion scheme in KDD Cup 2020
3. Landing in Meituan
First introduce some common challenges in computing advertising, such as deviation problems and high-dimensional sparse data expression learning, etc.; secondly, introduce the technical solutions of Meituan’s deviation problems in KDD competitions, graph learning and multi-modal competition problems; finally, the introduction The landing application of deviation elimination, map learning and multi-modal learning in store advertising.
Theme 4: Application of Intelligent Technology in Meituan Takeaway Advertising
Wang Yongkang｜Meituan Senior Technical Expert
A senior technical expert of Meituan Waimai, used to work at Baidu Fengchao. Currently, he is responsible for display advertising algorithm work at Meituan Waimai, responsible for the construction of takeaway advertising mechanism and display advertising algorithm.
brief introduction
1. Introduction to the Principles of Computing Advertising
2. Forms and challenges of takeaway advertising business
3. The intelligent technology system and key technology evolution behind takeaway advertising
Topic 5: Meituan pre- training platform MT-BERT and its application
Wang Jingang｜Meituan Senior Technical Expert
Senior technical expert of Meituan NLP Center, joined Meituan in 2018 and is currently responsible for the large-scale pre-training and platform construction of Meituan.
brief introduction
1. Introduction to pre-training background
2. Pre-training MT-BERT platform construction in the field of local life services
3. Application of MT-BERT in Meituan's business
Topic 6: Technical Practice of Search Query Understanding in Meituan
Li Chao｜Meituan Senior Technical Expert
Senior technical expert of the Meituan Search Department. He joined Meituan in 2018 and is currently responsible for the Meituan search query understanding and search open platform related work.
brief introduction
1. What is query understanding and application
2. Features and challenges in the Meituan scene
3. Ambiguity problem, long tail identification problem, location constraint, domain-related and multi-service characteristics, solution introduction
4. Future Planning
| Thanks
Event organizer: Meituan technical team, Meituan Science and Technology Association
Promotion partner: event line
| Registration method
"Meituan Technology Salon Issue No. 55: Meituan Algorithm Practice-Search, Advertising, and Recommendation Special" for registration, please poke: read the original text .
| Important reminder
Add the WeChat (MTDPtech03) of the assistant Meimei and reply: 1017 to join the event WeChat group and communicate with lecturers and peers.
For PPT and video dry goods of past events, please scan the QR code below, follow the official account of the Meituan technical team (meituantech), and then view it through the [Technical Salon] under [Menu Bar].