Recent reports indicate that 1 in 6 people on a waiting list for mental health services will attempt suicide. Suicide becomes a global public health problem that has resulted in an increase in the demand for psychological services to address mental health issues. The waiting list and time to get such services are long. Recently there is emerging of using cell phone data, such as text or phone activities to track suicide risk in real time together with a better understanding of the ways in which people communicate or express their suicidality. However, there is lack of a unified technologies to integrate different types data such as text, voice, images and phone activities from mobile devices. We employed Geometric Unified Learning (funded by NSF SBIR Phase I) to develop cutting-edge AI technology with dynamic tracking capablity and overcome challenges in understanding suicide ideation and suicide risk to better prevent suicide simply by using functions of cell phones since they have the ability to collect real-time data.