New Delhi: Stepping up efforts to resolve the problem of passengers struggling to book confirmed tickets, IRCTC More than three crore suspicious user IDs have been deactivated and another six crore have been placed under verification of authenticity to prevent misuse.The catering and ticketing arm of the Railways has also expanded the AI-based kitchen monitoring system across its network to deal with complaints about food hygiene and quality. Officials said more than 800 kitchens are now being monitored through 2,394 AI-enabled cameras that detect nine types of issues that are primarily responsible for unhygienic food in trains.These include head cap compliance, transparent glove detection, mopping, mopping, rodents, flies and cockroaches.Regarding action against suspicious users booking tickets, officials said 501 complaints related to 4.18 lakh suspicious PNRs have been registered on the National Cyber ​​Crime Portal. It has also taken action against fraudulent digital identity by blocking 13,343 suspicious email domains during the year.On kitchen surveillance, a senior IRCTC official said the AI-enabled cameras can detect anything as small as the size of an ant (7-8 mm). IRCTC to serve around 60 crore meals in 2025-26.The official said they are expanding this monitoring as more kitchens are added to its network. Cameras supported by AI tools instantly identify unhealthy practices and send alerts.“Any issue raised is forwarded to the concerned kitchen manager and if the issue is not resolved, the matter is escalated. Action is taken against the person responsible within two hours and the error is rectified,” said the official who oversees the IRCTC war room.Not wearing a headgear is the most common hygiene-related violation detected by the AI ​​system in the kitchen. On average, the system generates about 350 alerts or error tickets per day.Officials said the toughest time is during seasonal weather changes when the quality of food can be affected. Most complaints are received during this period. He said that while the AI ​​system generates about 350 tickets a day, the effective error rate is about 10%.