Utilities supplying electricity in urban areas tend to get inundated by customer complaints of power outage, low voltage and other issues during summers and monsoon. Telephone helplines manned by humans tend to be inaccessible as small groups of workers who man the helplines cannot respond to the flood of calls.
The state-run Bengaluru Electricity Supply Company (Bescom), which supplies power to eight districts in Karnataka, has now turned to an artificial intelligence-powered system to service the over 9,000 complaints it receives on its helpline systems each day.
Bescom is tying up with the Medical Intelligence and Language Engineering (or MILE) Lab at the Indian Institute of Science (IISc) to create an AI-based complaint response system than can cater to as many as 500 calls at a time — much higher than the 60 under the system that the utility employs at present.
“What we will have is a technology where when someone calls in the machine will take over and the machine will recognise whatever the speaker says whether it is in Kannada or English. It will understand the complaint — whether it is with regard to a bill or power outage or concession for solar energy — and find an answer from the server. It will then synthesise the answer again to text and convert to speech,” said A G Ramakrishnan, the head of IISc’s MILE. The system will be capable of converting text to speech and speech to text, he said. “It will not only speed up the service but the public utility will be able to service thousands of customers parallelly. In the system what we have proposed there will be 250 customers talking and another 250 customers waiting,” he said.
Bescom, which issued an expression of interest for “implementation of artificial intelligence powered interactive chatbot integrated with helpline, mobile app, website and social media for consumer engagement” earlier this year has identified IISc’s MILE lab as a partner, officials said.
The AI system will have a feature to transfer complaints to a human assistant in the event of the system senses a customer becoming frustrated during interactions with it, Bescom’s information technology and innovation head Anil D’Souza stated.
The factors that have resulted in Bescom moving to an AI system for customer interactions include the capacity for speech recognition and speech-to-text translation in multiple languages, dialects and accents; ability to interpret the context with Natural Language Processing; ability to identify intent of a question; ability to learn and get trained; and scalability at minimal costs.
According to Bescom officials, the AI system will be the primary interface for complainants in the future while a human interface will be the secondary option. The system will begin with Kannada and English language recognition features and will later include other Indian languages.
This is not the first time that Bescom has found an innovative solution. In the past, it introduced a real-time distribution automation system for optimising its power network with Rs 417 crore funding from the Japan Bank for International Co-operation. The distributed automation system enables “remote monitoring, control and operation of the 11 kV network in Bangalore city” leading to a “reduction in downtime for fault location and quick restoration” of power services.
Bescom has also started, on a pilot basis, a smart grid network, which will allow the utility to supply power by gauging consumption, supply systems in a network in order to optimise power supply leading to “an economically efficient, sustainable power system with low losses and high quality and security of supply and safety”.