Liulishuo_Customer-Reference_Logo

Founded by Yi Wang, Zheren Hu, and Hui Lin in September 2012, LAIX Inc. (NYSE: LAIX) is an “AI + Education” company. As a proponent of Intelligence Education, LAIX owns a team of professional AI specialists. After years of accumulation, Liulishuo has built a large database of Chinese speaking English. As of December 31, 2019, it has cumulatively recorded 3.2 billion minutes and 43.3 billion sentences of user conversations. On that basis, Liulishuo has independently developed an advanced speech recognition and scoring system, a writing assessment and enhancement engine, and an adaptive deep learning system. Liulishuo commits to improving users’ listening, speaking, reading, and writing skills through offering systematic English learning solutions, and has been granted a number of patents.

On September 27, 2018, as the forerunner of the “Education 3.0” model, LAIX was officially listed on the New York Stock Exchange. Currently, products under Liulishuo® include English education applications like English Liulishuo, LiuLi Reading, Kids LiuLiShuo, and English learning products like DongNi English (course), Authentic Pronunciation which further meet the needs of different customer segments.

Since its foundation, Liulishuo has been fully endorsed within and outside the industry. Awards it has received include App Store Essentials and 2013 Editors’ Choice by Apple, 2015 Shanghai Top Ten Smart City Application by Xinhua News Agency, 2017 Shanghai Top Ten New Internet Entrepreneurship Award by People’s Daily Online, “New Business” the Annual Fast-Growing Corporations by 36Kr 2017 WISE New Business, 2017 Creative Technology Product of Education Industry by Sina, 2017 AI 100 Award by CB Insights (as the only Chinese education and technology company in the group), Member of The Summer Davos Forum (the only Chinese corporation in 2017), and Top 50 Innovative Enterprises in China by Forbes China.

quote-marks

With stable and reliable technology, comprehensive security management functions and an abundant ecosystem, AWS allows us to focus on our core businesses, achieve rapid product launch and iteration, and offer our customers stable, reliable and personalized on-line learning services.

Hu Zheren

Co-founder & CTO of Liulishuo

Challenges

At the early stage of establishment, Liulishuo employed a combination of on-premise and public cloud platform to launch its first product “Liulishuo” App on February 14, 2013, integrating core technologies such as voice recognition, scoring engine and self-adaptive learning. There are situational dialogue, dubbing show, authentic pronunciation courses in diverse contents and forms, and the loaded AI English Teacher, providing gamified learning like role-playing, scoring and stage clearing to inject an element of fun into user experience. Gaining instant recognition from users, this fun and effective product hit the million-user mark within the year, and managed to multiply the number by ten shortly after.

Rapid business expansion brought new challenges to Liulishuo’s existing IT architecture. First of all, traffic flow variety. Users multiplied by ten times in only one year, while, traffic flow varies greatly throughout the day, with peak-hour traffic flow being 4 to 5 times higher than that of the off-peak period, which requires sufficient scalability for IT architecture. Secondly, business expansion, growing product portfolio and functions, and increased complexity. The start of commercial operation in 2016, in particular, was followed by a steep increase in paid users, posing higher requirements on access performance and stability. Thirdly, big data analysis brought challenges to system performance and capacity. Business expansion led to a continuous expansion of Liulishuo’s “English pronunciation database for Chinese learners” and increasing complexity of user behavior analysis and feedback to be processed by the system on a daily basis. In this context, how to allocate resources and enhance analytical efficiency, swiftly and rationally became vitally important for the company. “The key to coping with these challenges is to select a stable and secure cloud platform with powerful functions. Based on our prior knowledge of AWS, we decided to select AWS and migrate the entire existing system to it in 2014, and it proved a right choice, ” said Hu Zheren, co-founder & CTO of Liulishuo.

Why AWS?

Based on big data and artificial intelligence, Liulishuo’s flagship App “Liulishuo” was launched as an English learning product for adults. Security, stability and scalability were the main considerations in selecting the cloud platform. With its stable and reliable technology, comprehensive security management functions and an abundant ecosystem for technology development, AWS became the ultimate choice for Liulishuo.

  • Stable and reliable technology
  • Comprehensive security management functions
  • Abundant ecosystem
  • Stable and reliable technology
  • Stability and reliability of AWS are determined by the stability of its various functional products and the overall technical architecture. AWS products used by Liulishuo mainly involve the functions of computing, storage and data analysis. Regarding computing, AWS provides a series of coordinated functions, including Amazon Elastic Compute Cloud (Amazon EC2), Amazon Elastic Container Registry (Amazon ECR), AWS Lambda, AWS Auto Scaling and Elastic Load Balancing. The coordination of these functions not only provide adjustable computing capacity for users to control required computer resources, expand or reduce computing capacity when computing requirements change, but also automatically detect unhealthy instances and reroute traffic to healthy ones until the unhealthy instances have been restored, thus providing greater application tolerance. Regarding storage, Amazon Simple Storage Service (Amazon S3) stores data in multiple facilities and multiple devices within the same facility with redundancy, so as to provide users with 99.999999999% data persistence. In further coordination with Amazon Glacier and AWS Storage Gateway, users can integrate on-premise storage with AWS storage safely and seamlessly, and store mass data at lower cost safely and reliably. “With its all-round stability, AWS allows our development team to focus on product R&D without worrying about any problems of basic architecture, ” said Hu Zheren.

  • Comprehensive security management functions
  • Liulishuo owns a massive “English pronunciation database for Chinese learners” as its core asset. The importance of AWS secure data management is highlighted with growing data volume. With rapid business expansion and growing product portfolio, Liulishuo must solve the problems on how to conduct cluster isolation and divide different businesses while optimizing resources. “Amazon Virtual Private Cloud (Amazon VPC) and AWS Identity and Access Management (IAM) and other security management functions have provided us with convenient ways to achieve security management objectives, ” said Hu Zheren. Amazon VPC allows users to preconfigure multiple virtual network environments in AWS and place different businesses under different virtual networks. For instance, with Amazon VPC, it is possible to create a public subnet for an application system accessed by users at the front end, while place back-end systems such as database and application server in a private subnet that cannot access the Internet, and use IAM to create and manage AWS users and groups to achieve secure management of the entire system through various security layers such as security group and access control list.

  • Abundant ecosystem
  • “As a start-up, Liulishuo must focus on its core businesses. If there are any open-source tools to meet our needs, they will definitely be our first choice. Globally, AWS is a natural choice for both open-source and closed-source products when it comes to integration with public cloud platform. It is possible for us to select application system based on specific needs and cut down on labor cost. For instance, we use open-source tool Terraform to manage our resources, and the cloud platforms it supports includes AWS, ” said Hu Zheren. Apart from a technically abundant ecosystem, AWS also has varied online and offline trainings and user and developer activities, which gather the top developers and industry users around the world to provide opportunities for them to share their success stories.

Achievements

In September 2014, Liulishuo migrated and deployed its entire system to AWS, including its official website, data analysis platform, payment process, business applications, among other systems, having maintained secure and stable operation throughout the process. Currently, applications using AWS Cloud services include by Liulisuo include Amazon EC2, Amazon S3, Amazon Relational Database Service (Amazon RDS), Amazon ElastiCache, AWS Support, Amazon Elastic Block Store, Amazon CloudWatch, AWS Data Transfer, Amazon EMR, Amazon DynamoDB, AWS Config, AWS Storage Gateway, Amazon Route 53, AWS CloudTrail, Amazon Simple Queue Service and Amazon Simple Notification Service, etc. Figure 1 is a schematic diagram for AWS - based system architecture of Lliulishuo.

liulishuo-arch-diag
Figure 1 Schematic Diagram for AWS - Based System Architecture of Lliulishuo

AWS has benefited Liulishuo in two aspects: Firstly, it has led to a remarkable improvement in overall system stability, with the availability of applications reaching 99.9%. Liulishuo’s business development exhibits two features: Rapid growth in the number of users: it took only four years for its users to increase from 1 million to 70 million; Uneven distribution of user traffic flow over 24 hours each day: the peak-hour surge in traffic at noon and after 6 p.m. is 10 times higher than during off-peak hours. AWS automatic O&M function allows Liulishuo’s entire system to cope with changes in traffic with ease, so as to provide users with stable and reliable access services and better user experience. Secondly, it saves costs of both resources and labors. In terms of resource allocation, AWS-provided functions such as AWS Auto Scaling and Amazon EC2 Spot instance have substantially reduced resource occupation cost. After the deployment of Amazon EMR, in particular, data processing speed and volume have substantially increased while low-cost instances for data processing at night effectively reduced cost. In terms of labor cost, AWS automatic management function has reduced the demand for system O&M, saving the cost of full-time O&M personnel.

Striving to improve itself as an AI-driven education technology company, Liulishuo plans to deploy more AWS products in the future, including Amazon Machine Learning and Cluster GPU Instances to accelerate data analysis and model training iteration to deliver better personalized learning experience to its users.

More Information

To learn how AWS can help customers innovate in the field of education, please visit the Cloud Computing for Education page for details.

To learn more about how AWS can help you meet your data needs, visit the Data Lake and Analysis on AWS page for details.