New Delhi: Bharti Airtel Wednesday announced an AI-powered solution that will alert users in real-time to all suspected spam calls and messages.
The free-of-cost solution, which will be auto-activated for Airtel customers starting Thursday, processes one trillion records on a real-time basis, the company said.
Once the system has doubts about a message or a call, it will flag it as “suspected SPAM” to alert smartphone users before they answer a call or click on a link.
Airtel claimed this solution would detect 97 percent spam calls and 99 percent spam messages.
Bharti Airtel (India & South Asia) managing director and chief executive officer Gopal Vittal said they spent the last 12 months “comprehensively” solving the “menace” of spam messages. “Today marks a milestone as we launch the country’s first AI-powered spam free network that will shield our customers from the continuous onslaught of intrusive and unwanted communications,” he said.
Vittal added the AI algorithm analysed around 250 parameters, including velocity of calls, number of incoming calls vs outgoing calls, and IMEI changes. By cross-referencing this information against known spam patterns, the system will accurately detect suspected spam calls and messages, he said.
If a spam message includes a suspicious link, the system will scan it in real-time and warn users not to click on it. Airtel has created a special database of dangerous links, called “blacklisted URLs,” and messages are checked against this database.
Vittal explained that the solution has two filters: one at the network layer, and the other at the IT systems layer. “Every call and SMS passes through this dual-layered AI shield. In two milliseconds, our solution processes 1.5 billion messages and 2.5 billion calls every day. This is equivalent to processing 1 trillion records on a real-time basis using the power of AI,” he said.
The company added that so far the solution had been able to successfully identify 100 million potential spam calls and 3 million spam text messages originating every day.
(Edited by Tikli Basu)