Experiment #205 Applied Artificial Intelligence, the real one ??


For many people, artificial intelligence is something reserved. And for few, a future that is yet to come. But the reality is different, since we can see around us a huge number of examples where artificial intelligence is part of our daily lives. Who has not seen a series in Netflix or booked a hotel room in Booking suggested by the product recommender? Or even used Google to search the internet. 

On the other hand, as subject matter experts, we are used to companies and large organizations that do not take full advantage of their data, since data is, without a doubt, the new oilExtracting data and making the most out of it is a complex task but, if done in the right way, the return on investment is more than guaranteed. 

Today we will focus on unraveling a system capable of tracing the patterns that people follow at a shopping center; analyzing their feelings at the arrival and departurewhether they go to the fitting room, buy something and much more. This procedure is carried out with Azure and the results are shown in Power BI. 


Description of the system

Data from the shopping center`s security cameras are rarely exploited. Thanks to advances in technology, we can study our consumers, not only when they interact through our e-commerce platforms but also in the shops. 

The system will answer the following questions: 


 The simplified architecture to meet all the needs and answer the previous questions would be this one: 

Process of data sent to Azure and analysed in power BI

 We would start from the base of having n number of shops. Each shop would have several security cameras that will be used to trace the patterns and routes of each person. 

At the shop’s closing time (although it could also be done in real time), all the data stored by the security cameras would be sent to Azure’s services for further analysis. 

Let’s see it in detail: 

Data sent to Azure services

Each shop will have a database where the different data generated throughout the day will be stored. At the end of the day, an automatic process will send the images captured by the cameras to be analyzed in Azure. In order to meet the business needs, the Face and Computer Vision tools will be used to answer all the target questions that were raised before. 

Finally, all the data generated by Azure Cognitive Services will be stored in an Azure SQL Server in PaaS, for later analysis in Power BI and, thus, making it available for the analysis department.


Organization of each shop  


Each store will need to be divided into n number of areas so that we can draw a later analysis focused on the desired direction. 

For example, in a shop like this: 


The cameras would need to be strategically placed in order to visualize the shop’s: 

In addition, the shop needs to be also divided into different areas, for example, in red, green and blue zones, that may correspond to men’s, women’s and children’s departments. Like this: 


Read more of Experiment #205 here.

Stay up to date!

Leave a comment