Core skill: introduce/pre-introduce new persons from tagged photos/ group photos, even stripped web photos

A user can pre-introduce jibo to new people from tagged photos thereby priming the facial recogition and enabling Jibo to at least address a person by name.

From the photo(s), a user can tag a persons first and last name. The user can add metadata as well (gender, age group). Also, the user can add a group identifier so that a skill can retrieve the persons.

  • This would facilitate usage of any skill, core or 3rd party… particularly group oriented skills where a parent or caretaker wants to pre-introduce everyone and ensure that no one feels left out.
  • Facilitate first encounters
  • Facilitates registration of non-verbal persons, people with speech difficulties, withdrawn persons. At least, a socially inclusive Jibo can address them with their names and include/encourage them in the skill activities! :slight_smile:

Very important for situations where the person has difficulty to speak, possibly fears interaction, or is withdrawn.
(special needs kids, elderly groups, people who are withdrawn.)

I’m thinking of family and friends as well also of group homes where Jibo visits.
A caretaker pre-introduces people using group photos or a set of photos with one person

A skill could invoke this core skill by asking for a group photo and then one or more people tag the photo (touch the face and verbally add name, gender, age category??), etc
Likewise, someone can select one person from a photo to pre-introduce that person.


  • photos taken by jibo
  • photos stripped from web page
  • photos downloaded somehow to jibo cloud or jibo … ??

** Developers - please like this post if you support this functionality. Please add your other ideas