Back to Observatory
Research and Analysis Neural Network for the Search and Identification of Persons
Description of the service
A neural network that aims to automate and accelerate the process of matching ante and post-mortem information collected by judicial search and investigation institutions, as well as cross-checking it with other public and private databases.
Problem that it solves
RENIA responds to an emergency situation in the Mexican state of Jalisco: a humanitarian crisis resulting from criminal violence manifested in a forced disappearance. As of the date of consultation, in Jalisco, there are 10,328 missing persons, a fact that is even more disturbing when placed next to the persistent crisis experienced by the Jalisco Institute of Forensic Sciences, in its task of clarifying the identity of the Unidentified Dead Persons (PFSI). It faced its most dramatic point in 2018 when public opinion knew about the use of a refrigerated trailer transporting 273 unidentified bodies in the Metropolitan Area of Guadalajara. Despite the authorities' efforts, institutional actions have not provided a strong State response to the request for justice and reparation.
Type of AI app used
Human-computer interaction (interaction support), Recognition system (recognition)
Main results to June 30, 2021
The project is still under development, but it allows the identification of faces before death.
Three main bottlenecks faced during implementation
- Interoperability of the databases of the different agencies involved
- Adaptation to the legal system
- Inter-institutional coordination.
Lessons learned in the design or use of AI for social impact
AI systems should be understood as socio-technical designs: from the initial approach, all the system's processes and flows should be considered, and its effects should be forecasted. To design the project only considering the technological aspect, is a mistake.
Country of origin
Geographic scope of operations
Guadalajara, Jalisco.
Type of executing entity
GobiernoSector/industry
Sustainable Development Goal(s) to which your AI solution contributes
16 (peace, justice, and strong institutions)
17 (partnerships for the goals)
IA app developed internally or by a third party
Internally
Name of implementing entity
Institute of Statistical and Geographic Information of the State of Jalisco
Stakeholders involved
Search and identification institutions in the state of Jalisco. The methodological process to include groups of family members in the search for persons is underway.
Percentage of the development team that are women
30%
Year they started using AI-based models
2021It may interest you
Junto con el MIT desarrollamos un estudio en el que utilizamos por primera vez herramientas de inteligencia artificial para elegir a beneficiarios de programas sociales
Responsible and Widespread Adoption of Artificial Intelligence in Latin America and the Caribbean
Cada vez más, actores públicos y privados se plantean cómo escalar su impacto a través del uso de la tecnología.