Intelligent shopping assistant with specialized artificial intelligence
Keywords:
artificial intelligence, ESP32-S3, embedded systems, customer service, retailAbstract
This study aimed to develop a specialized artificial intelligence-powered shopping assistant, integrated into an ESP32-S3 microcontroller, capable of querying real-time inventory information to automate customer service in retail establishments. The research was framed within the feasible project modality with a technological focus, addressing the need for small and medium-sized retailers to have accessible tools for autonomous information retrieval. The developed system, named MIA (Artificial Intelligence Module), integrates embedded hardware consisting of an ESP32-S3 microcontroller, an INMP441 digital microphone, a MAX98357A audio amplifier, and a GC9A01 circular display. The software architecture was structured into six stages: activation, voice capture, transcription, conversational processing, speech synthesis, and playback. The dynamic incorporation of inventory data through lightweight contextual retrieval allowed the assistant to generate coherent and specialized responses within the defined commercial domain. Evaluation tests yielded a global coherence index of 100%, a transcription accuracy rate of 90%, and response times between 17 and 26 seconds per cycle. The results confirm the technical and economic feasibility of incorporating conversational artificial intelligence into low-cost embedded devices for the modernization of the retail sector.
References
Arias, F. (2012). El proyecto de investigación. Introducción a la Metodología Científica. (6ª ed.). Editorial Episteme. Caracas. Venezuela.
Benito, Á. (2019). Desarrollo de aplicaciones para IoT con el módulo ESP32 [Trabajo de grado, Universidad de Alcalá Escuela Politécnica Superior]. Repositorio institucional. https://ebuah.uah.es/dspace/bitstream/handle/10017/35420/TFG_Benito_Herranz_2019.pdf
Evans, D. (2011). The Internet of Things: How the Next Evolution of the Internet Is Changing Everything. Cisco Internet Business Solutions Group. https://www.cisco.com/c/dam/en_us/about/ac79/docs/innov/IoT_IBSG_0411FINAL.pdf
IBM. (2024). What Is an API (Application Programming Interface)? IBM Cloud Topics. Recuperado de https://www.ibm.com/think/topics/api
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., y Kiela, D. (2021). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. https://arxiv.org/abs/2005.11401
Maier, A., Sharp, A., & Vagapov, Y. (2017). Comparative analysis and practical implementation of the ESP32 microcontroller module for the internet of things. In 2017 7th International Conference on Internet Technologies and Applications (ITA) (pp. 143-148). IEEE. https://doi.org/10.1109/ITECHA.2017.8101926
Russell, S., y Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4.a ed.). Pearson. http://lib.ysu.am/disciplines_bk/efdd4d1d4c2087fe1cbe03d9ced67f34.pdf
Shneiderman, B., Plaisant, C., Cohen, M., Jacobs, S., Elmqvist, N., y Diakopoulos, N. (2016). Designing the User Interface: Strategies for Effective Human-Computer Interaction. (6.a ed.). Pearson.
Vázquez García, A. (2024). Chatbots basados en IA generativa para optimizar el servicio al cliente en el contexto del mercado español [Tesis doctoral, Universidad de Alcalá]. Biblioteca Digital Universidad de Alcalá. https://ebuah.uah.es/dspace/handle/10017/63000
Wolf, W. (2017). Computers as Components: Principles of Embedded Computing System Design (3.a ed.). Morgan Kaufmann.
