Facebook has submitted a patent application for technology of which might predict who your family as well as different household members are, based on images as well as captions posted to Facebook, as well as your device information, like shared IP addresses. The application, titled “Predicting household demographics based on image data,” was originally filed May 10, 2017, as well as made public today. Facebook did not immediately respond to a request for comment, although the patent suggests of which the company is usually interested in exploring the technology, which is usually intended to help Facebook target advertising more effectively.
Facebook submitted the application before This particular year’s security as well as privacy scandals — Cambridge Analytica, a massive hack, as well as backlash against its recent hardware product — although the patent’s publication comes at time when the social media giant is usually grappling with the public’s growing distrust.
The system Facebook proposes in its patent application might use facial recognition as well as learning products trained to understand text to help Facebook better understand whom you live with as well as interact with most. The technology described inside patent looks for clues in your profile pictures on Facebook as well as Instagram, as well as photos of you of which you or your friends post.
the idea might note the people identified in a photo, as well as how frequently the people are included in your pictures. Then, the idea might assess information coming from comments on the photos, captions, or tags (#family, #mom, #kids) — anything of which indicates whether someone is usually a husband, daughter, cousin, etc. — to predict what your family/household actually looks like.
According to the patent application, Facebook’s prediction products might also analyze “messaging history, past tagging history, [as well as] web browsing history” to see if multiple people share IP addresses (a unique identifier for every internet network).
In one specific example, the design looked at an image a user posted with two females tagged, “#my_boss_at_home,” as well as another image using a young girl marked “my angel.” Facebook predicted of which there were three people inside household, including the male user, as well as two females, “who are likely the male user’s wife as well as daughter.”
The social media giant didn’t specify exactly what kind of demographic information its proposed system might predict, different than the number of people in a household, although its data policy specifies of which demographics could include gender as well as age.
The application makes clear of which the information is usually intended to help Facebook target advertising more effectively: “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 of which are sent to the user are poorly tailored to the user as well as are likely ignored by the user.”
In a flowchart showing how the data might be collected as well as used, the final step for the household demographic data might be to “provide for display content items targeting the user based on the predictions.”
In June, Facebook added an ad-targeting option of which allows businesses to target an entire household at once; the idea determines of which data using shared last names, home locations, check-ins, life events, as well as where people connect to the internet, a Facebook spokesperson told Marketing Land.
Facebook collects a lot of data about you to feed its personalization algorithms, which serve you content on your news feed as well as ads the idea thinks you’ll be most likely to click on. Considering recent reports about Facebook’s struggles to protect the massive amounts of personal data the idea has collected coming from its users, of which revelation is usually probably not a surprise.