By Prarthana Mitra
Big data and machine learning only recently made a foray in India but it is already set to disrupt Indian law enforcement. Gurugram-based startup Staqu has developed a proprietary criminal registration and search system which leverages Artificial Intelligence to trace crime suspects and persons of interest.
Staqu’s app can change the way we tackle crime
According to LiveMint, Staqu had already developed a proprietary AI technology stack comprising advanced image analysis, language and text independent proprietary speaker identification engine, facial recognition and text processing, including name entity recognition, sentiment analysis and summarisation APIs.
Late last year, they launched Artificial Intelligence Based Human Efface Detection (ABHED) that seeks to help police officers in criminal identity registration, as well as in searching and tracking missing persons. The application can also be used to search through FIR database as well as biometric information including voice, fingerprints and facial images that could be integrated with the current Crime and Criminal Tracking Network & System (CCTNS).
Speaking to LiveMint, CEO and Co-Founder of Staqu, Atul Rai said, These data attributes could be grouped under three categories: image, speech, and previously recorded non-uniform text-data. It is not feasible to utilize currently available simple software algorithms in computing such complex data structures.”
“Staqu solved this problem with its proprietary, advance hybrid AI technology which amalgamates different neural network models to process image, speech, and text to extract meaningful information that aid in decision making, he added.
Speeding up justice delivery
After a successful trial run with the Rajasthan and Punjab police forces, Staqu is now poised to deploy the app across several other police units. Every officer will have their own login password to use the app for registration and searches, with controlled access and OTP-based logins to ensure greater security. Currently available in Hindi and English, and optimized for 2G or 3G networks, ABHED can handle thousands of queries per second, simultaneously indexing and registering criminal profiles.
“Activities of police forces on ground zero have been fraught with several challenges,” said Atul, with respect to identifying criminals or predicting criminal activities based on heuristic data. “The activities further suffer due to a lack of adequate technology that can extract and connect, in real-time, an extensive range of unstructured, disparate and heterogeneous data attributes from criminal records,” he said.
With the launch of ABHED, Atul envisages machine-learning and AI, enabling police forces to “digitalize and automate profiling and search for criminals and missing people.” In an interview with the Economic Times, he said, “It has further been a humbling experience to associate with the Alwar Police Department and commission a pioneer pilot program, utilizing AI for nabbing criminals and searching missing people. Given the rising rate of crimes and child trafficking, we hope for a brighter tomorrow, where advanced technology is best deployed to aid security forces.
Staqu is currently also working with the Dubai police department to develop an Artificial Intelligence-based predictive technology.
Prarthana Mitra is a staff writer at Qrius