Iris: A voice-enabled smart mirror
Conversational UX | GUI Design
Overview
IRIS a Voice-Enabled Smart Mirror aims to solve this problem by offering virtual personal styling assistance
There are many challenges that come with getting dressed each day, such as choosing the right outfit and style.
This can be even more difficult if you don’t know what looks good on you. Iris is a voice-enabled smart mirror that aims to solve this problem by offering virtual personal styling as an alternative to consulting a stylist. The voice bot harmoniously fits into the users' day-to-day life and assists the user with shopping tips, customized outfit recommendations, and offers users a virtual wardrobe to save outfits and clothing items for future reference.
My Role: UX Research, Personality Design, Conversational Design,
Interface Design, Prototyping & Testing
Team Members: Anamika Menon, Akshata Karekar
Tools: Lucidchart, Voiceflow, Figma, Photoshop, After Effects
Final Prototype
A high-fidelity prototype was created t o showcase how the mirror will interact with the user with the help of both audio and visual aid
Iris is a solution to this modern-day problem. The voice-enabled AI bot has the capability to adapt to changing trends as well as personal preferences. It projects visual elements on the interactive surface of the mirror with audio output.
Scope
In today's fast-evolving fashion world it's a daunting task for people to dress up on a regular basis
Styling outfits on a daily basis can be a daunting task for many people and most times they seek recommendations from fellows, peers or look for inspiration online. There is a need for an AI bot with the capability of logically incorporating changing trends into personal styling recommendations.
Key Service Offerings
Outfit Recommendation
Stylize a look or provide recommendations that match a particular clothing or accessory
Shop
Help users shop an outfit for an event or recreate a look on limited budget
Virtual Wardrobe
A virtual outfit directory where users can add outfits, clothing, or accessories
Design Process
3 weeks
5 weeks
Discover
-
User Research
-
Competitive Analysis
Define
-
Interaction Goals
-
Level of Personification
-
Key Features
-
Tone of Voice
Design
-
Sample Scripting
-
Intents and Prompts
-
User Flows
-
UI Design
Prototype
-
Bot Prototyping
-
User Testing
User Research
Understanding users' needs and concerns
A user survey was conducted to better understand how people perceive voice-enabled smart mirrors and get insight into the potential concerns and hesitations that might limit the interaction.
The survey questionnaire created on Google forms was filled by a mix of fashion students, influencers, regular shoppers
24 participants
Questions revolved around the users' shopping behaviors and preferences, their approach towards accepting shopping assistance, their existing knowledge of smart mirrors, and their expectations from such a technology
09questions
Key Insights - User Survey
How do our potential users prefer to shop?
25%
Users seek outfit styling/recommendation & shopping assistance.
42%
Engage in online shopping one/two times a month.
Why would a voice-enabled smart mirror be a helpful tool?
65%
Participants said they found it moderately difficult to put together outfits on a daily basis.
80%
Participants concluded that they were fully or moderately interested in using a product like IRIS
Bot's Personality
Level of Personification: High
Bot should be able to keep track of user's purchase, and form an online directory to extract information for the daily recommendations. Users should be able to rely on it for day-to-day recommendations.
Considering all these factors we defined the both to have specific Interaction Goals: Secure, Fun, Consistently Creative and Personalized with complimentary Personality Traits.
It should be able to provide recommendations that align with the user's fashion preferences.
Tasteful
It should aim to make the act of shopping less of a hassle, and more of an enjoyable and seamless experience.
Vivacious
Resourceful
Personalized
Fun
IRIS
Secure
Consistently Creative
Organised
It should ensure and abide by all privacy and security norms as it requires the user's personal information.
Mindful
Adaptable
Constantly update itself on the current fashion trends and must provide a variety of suggestions.
Tone of Voice
The bot's tone of voice is a key factor in defining how its interactions will be with the user
The interactions with the bot should make the user feel like a casual conversation between a user and its stylist. The user should be able to rely on the bot's suggestions as it would if an expert is recommending them.
The bot must sound excited and always ready to help. As well as come across as cool personalities when they are chatting ad getting fashion suggestions from a friend.
Sample Scripting
Based on the personality, tone of voice, and characteristics, the scripts were written
Based on Iris's characteristics and features offered, we created sample scripts that would cover all 3 task flows:
1. Outfit Recommendation
2. Shop an outfit or recreate a look
3. Virtual Wardrobe
Challenge
While working on the scripting it was extremely difficult to take in consideration all the possible utterances and conversation routes users can take. After multiple user testings, we were able to work on limitations to make the interaction as seamless as possible.
Sample Script: Recommending outfit based on filters
Sample Script: Recreating a trending look
Conversational UX
Intents, Prompts and Slots
For the user to have a seamless conversation with the bot an extensive set of intents and prompt slots were designed. They were also altered and many additions were made based on the feedback we got from the user testing.
Check out the complete list of training data.
A complete flow diagram for each of the three major tasks performed by IRIS was created to rectify limitations in the training data.
Lucid Flow Chart: Designing the conversational flow for each task
Graphical User Interface
Visual output to help users engage in a responsive interaction
The visuals help users remember where they stand in the conversational flow thus making their interaction as seamless as possible. The visual output will act as a reinforcement for the audio output helping users gather the required information easily and reducing the overall cognitive load.
Initial Prompt Options
Users will be shown three options to begin with their flow.
Outfit Recommendation Option
Users will be asked if they require an outfit recommendation using new unowned clothing or with an item they already own in their virtual wardrobe.
Virtual Wardrobe Option
Users will be shown all the items saved in their virtual wardrobe which they can access by saying the item name.
Virtual Wardrobe Item
Users will be able to select an item with the option of styling, shopping similar items, or deleting the item from the virtual wardrobe.
Outfit Options
IRIS will present several outfit options with the selected item for users to pick from using “Option #” as a response.
Final Purchase
Users will be able to review their order with the product names, brands, and prices. Users can respond with a YES to make the purchase.
Prototyping
User Interaction with Iris
A higher fidelity interactive prototype built on Voiceflow was tested to understand how the training data influenced the nature of their interaction with the voice bot and to measure the success of the interaction.
Moderated User Testing
How were users interacting with the mirror?
Participants were recruited for each prototype testing that represented different aspects of our target audience were recruited to participate in a moderated in-person user testing. The test was set up in a way that would give users the experience of interacting with a smart mirror. The voice flow prototype on the laptop was connected to an Alexa device and placed behind a mirror so that the users would perceive that they are interacting with the mirror.
Post task completion, their responses and the observations from the test were then thoroughly analyzed to inform further decisions in the task flow and the prototype.
Future Scope
Accessibility and Inclusion
In the future, the product can be expanded to be more inclusive to people with speaking or hearing limitations. Features such as touch input and haptic feedback would enhance the user's shopping experiences.
What should be our next steps moving forward?
Future use in Retail Store
In a broader use case, IRIS can function as a virtual shopping and trial assistant in shopping malls and stores. IRIS can be integrated into store mirrors, providing the ability to virtually try on outfits in stock, creating and recreating looks on site, as well as purchasing clothing items from the store to enhance our user’s shopping experience.