In order to target ads easily at an entire family, social media firm Facebook has recently filed a patent for an algorithm that will use your family photos for ad targeting.

Facebook’s recently published patent described details about a technology based on images and captions posted on the site and device information like the shared IP address, which would predict who the users’ family and other household members are and then target ads for the whole family.

The proposed system, as per Buzzfeed News, would require facial recognition and learning models trained to understand text for helping Facebook better understand whom the user live with and interact with most. The technology searchers for clues in the profile pictures on Facebook and Instagram, along with photos of the user that they or their friends have posted.

Zuckerberg orders employees to give up iPhones after Apple CEO criticized Facebook

The algorithm will note the people identified in a photo and how frequently they are included in the users’ pictures. It would then assess information from comments, captions, hashtags or anything that indicates the relation to user in order to predict what the household looks like.

The patent application read that the prediction models would also analyze ‘messaging history, past tagging history, and web browsing history’ to see if multiple people share the same IP addresses. From this, Facebook could deduce how many people were in the household along with other demographic information like age, gender, and socioeconomic status.

In one example, Facebook looked at an image a male user posted with two females tagged, “#my_boss_at_home,” and another image with a young girl marked “my angel.” The system predicted that there were three people in the household, including the male user, and two females, ‘who are likely the male user’s wife and daughter’, as per The Verge.

Moreover, the application also specifies that the data is only intended to help Facebook target ads more effectively. It reads, “Existing solutions of content delivery to a target household are not effective ... Without such knowledge of a user’s household features, most of the content items that are sent to the user are poorly tailored to the user and are likely ignored by the user.”

However, this too is just like all other patents and contains the possibility of this technology never coming to life.