- Joined
- Mar 3, 2018
- Messages
- 1,713
Facebook apparently applied for a patent titled "Predicting Household Demographics Based on Image Data" in May 2017, and that patent just went public this month. True to its name, the patent suggests that Facebook intends to extrapolate relationships based on pictures posted to a user's page. The application also mentions an extension to Instagram photos, as well as "photos posted by other users that may include members of the user's household." While it's not clear if Facebook ever implemented anything mentioned in the patent, given Facebook's recent scandals and the crumbling wall between Instagram and their new owner, the timing of this release is inconvenient for Facebook, to say the least.
Abstract: An online system predicts household features of a user, e.g., household size and demographic composition, based on image data of the user, e.g., profile photos, photos posted by the user and photos posted by other users socially connected with the user, and textual data in the user's profile that suggests relationships among individuals shown in the image data of the user. The online system applies one or more models trained using deep learning techniques to generate the predictions. For example, a trained image analysis model identifies each individual depicted in the photos of the user; a trained text analysis model derive household member relationship information from the user's profile data and tags associated with the photos. The online system uses the predictions to build more information about the user and his/her household in the online system, and provide improved and targeted content delivery to the user and the user's household.
Abstract: An online system predicts household features of a user, e.g., household size and demographic composition, based on image data of the user, e.g., profile photos, photos posted by the user and photos posted by other users socially connected with the user, and textual data in the user's profile that suggests relationships among individuals shown in the image data of the user. The online system applies one or more models trained using deep learning techniques to generate the predictions. For example, a trained image analysis model identifies each individual depicted in the photos of the user; a trained text analysis model derive household member relationship information from the user's profile data and tags associated with the photos. The online system uses the predictions to build more information about the user and his/her household in the online system, and provide improved and targeted content delivery to the user and the user's household.