How Tencent’s Facial Recognition System Ensures Minor Gamers Stick To Curfew Regulations

China-based Tencent Games recently launched a facial recognition system to prevent minors from playing video games past their assigned time. 

The initiative, called the Midnight Patrol, will conduct a face screening for accounts registered with real names and played for a certain amount of time at night. Users who refuse or fail the facial verification will be treated as minors, and as outlined in the anti-addiction supervision of Tencent’s game health system, shall be kicked offline. 


Sign up for your weekly dose of what's up in emerging technology.

The face recognition system is designed to enforce China’s anti-addiction video game law. 

Why now?

In 2018, the Chinese government announced it was establishing a gaming regulator to respond to the growing concerns around near-sightedness in children, teenagers stealing money to top up their gaming accounts, and spending significant time at internet cafes. Soon after that, China put a freeze on the release of new video games for nine months, dealing a body blow to the industry. 

Tencent– the world’s largest video game vendor, responded by limiting gaming time to one hour for users under 12 years and two hours for users between 12 and 18 years. 

Later in November 2019, China imposed a curfew on online gaming for minors. According to the law, gamers below 18 years will be banned from playing online between 10 pm, and 8 am. Minors were also restricted to play games online for three hours on weekends, and not more than 1.5 hours on weekdays. 

Additionally, the law implied that gamers between the ages of eight and 16 years could only spend up to 200 yuan a month, and users between the ages of 16 and 18 years should not spend more than 400 yuan on their gaming accounts. At the same time, the Chinese government said it was working with law enforcement to develop a unified identification system to verify the user’s age with government-available data.

However, minors have been using different tricks to bypass these restrictions.  

The Midnight Patrol 

The Midnight Patrol is developed to detect minors who try bypassing the restrictions imposed by the government. Tencent’s artificial intelligence-based system– linked with big data from China’s central public security system, will help monitor young players. 

The Midnight Patrol requires users to take a facial scan before they can start playing a game online. If a player avoids the scan, they will automatically be assumed a minor and kicked out of the game. 

Tencent has been testing Midnight Patrol to verify gamers’ ages in Beijing and Shenzhen. With more data being collected, the efficiency of the algorithm has improved. Thus, Tencent has now planned to roll out the system to more than 60 games in China, including Glory of the Kind and Peace Elite. In addition, China’s most popular video game, League of Legends, is also slated to get the face recognition update soon. 

Owing to errors in recognition, if an adult player is mistakenly recognised as a minor and kicked out of the game, they will have to retake the facial recognition scan to be allowed to get in. 

Summing up 

China has the most number of closed-circuit TV cameras in the world. The country reportedly has at least 200 million cameras installed to watch over the public. More recently, Canon’s China offices introduced an intelligent solution– the biometric system only allows people with a smiling face inside the offices. 

Tencent’s The Midnight Patrol will use the data of minors, and it comes with a lot of risks. Additionally, the players might still figure out how to bypass or use virtual private networks to get access to these games.

More Great AIM Stories

Debolina Biswas
After diving deep into the Indian startup ecosystem, Debolina is now a Technology Journalist. When not writing, she is found reading or playing with paint brushes and palette knives. She can be reached at

Our Upcoming Events

Masterclass, Virtual
How to achieve real-time AI inference on your CPU
7th Jul

Masterclass, Virtual
How to power applications for the data-driven economy
20th Jul

Conference, in-person (Bangalore)
Cypher 2022
21-23rd Sep

Conference, Virtual
Deep Learning DevCon 2022
29th Oct

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM

What can SEBI learn from casinos?

It is said that casino AI technology comes with superior risk management systems compared to traditional data analytics that regulators are currently using.

Will Tesla Make (it) in India?

Tesla has struggled with optimising their production because Musk has been intent on manufacturing all the car’s parts independent of other suppliers since 2017.

Now Reliance wants to conquer the AI space

Many believe that Reliance is aggressively scouting for AI and NLP companies in the digital space in a bid to create an Indian equivalent of FAANG – Facebook, Apple, Amazon, Netflix, and Google.