Alice

Project Brief

"Conversational User Interfaces (CUIs) are ready-to-use interfaces were the spoken word is the design material we, as interaction designers, work with and design for."

Overall Focus

Constructed with Voiceflow, our CUI Alice is curated to improve all aspects of commuting with a focus on efficiency and flexibility during the short-distance trip to the airport.

Through journey map making, scripting the conversation and reiteration on the Voiceflow prototype, we are able to relate our conversation to real-time, location based scenarios, in order to help user manage their time during the trip.

Research and Persona

Conducting Research

Commuting to airport is stressful. The possibility for plane delays, traffic jams, long check-in queues, and other unforeseeable events of travel chaos is endless. In addition, each airline has distinct requirements on how early a passenger should check-in, resulting in confusion. With the amount of materials required and criteria to remember, traveling by air can be very burdensome. (add need to check delays, real time data)

As a result, many passengers would need to arrive a few hours earlier at airports to avoid these events, resulting in a significant amount of time wasted waiting at terminals. Thus, CUI Alice would be an in-car voice assistant that helps users address the issues stated above for easier commuting.

Setting our Persona

Through an analysis of our research, we consolidated a persona that would be a good representation of the target user of CUI Alice.

Our user is a 32 year old businesswoman named Janet, who has her own company and frequently commute through flights between New York and Pittsburgh. The scenario begins with Janet checking out of Hilton Brooklyn at NYC and tries to catch her flight AA4797 in the morning. She will fly to Pittsburgh to meet a client for a few days, then return to NYC.

Journey Map

We created a journey map that envisions the entire routine of Janet's trip to the airport, from the time she checks out of the hotel to the time she leaves the vehicle. From this we are able to synthesize a series of pain points to address in our CUI design.

With a closer study of our journey map, we focused on designing a CUI that would primarily find the most time-efficient route to the terminal based on real-time data analysis. In addition, our CUI is also designed to update users on their live flight status, adjust car setting to accommodate user comfort needs (seats, music, etc), and make any plan changes during the trip.​​​​​​​

Setting Conversations

Conversation Example: Flight Delay

This is a diagram of an ideal conversation between our CUI Alice and user Janet. Here, Alice gets live update that Janet’s flight has been delayed, and adjusts for this schedule change by suggesting to find a breakfast location for Janet (since it’s early morning). We assume: This car belongs to Janet, so Alice would know Janet’s habits. Alice also automatically pairs with Janet’s phone and the internet.

Conversation Model + Annotated Scripts

These four scripts represent the final moments chosen for our Voiceflow prototype. After writing 16 total scripts, we decided on these four because they felt the most natural for users based on each situation. Luckily, we were able to have one of each conversational type, although it was unintentional.

After choosing our four final scripts, we annotated them with the corresponding labels:

1. Context: set of circumstances that surround a particular event, situation, etc.

2. Intent: action that fulfills a user's spoken request.

3. Utterance: set of likely spoken phrases mapped to the intents

4. Slots: replacable arguments for intents

We were able to easily convert the conversations into Voiceflow, since the prototype would be based on these annotations.

Applying Real World Context

Brainstorming Moments + Alice's Capabilities

Through the script iteration, we synthesized four moments and clarified the goals and means in each moments, related to the four major functional features in our final prototype - Navigation, Traffic/Flight Live Update, Parking Personal Assistance, Parking Arrangement.

Based on real-world physical context, we developed the final prototype by creating the map of Alice and Janet’s trip where the four moments happens. By developing the prototype with real-world interaction, Alice is able to supply real-time and location based information in the final prototype.

Conversation Flexibility + Fluidity

For each utterance, we set up multiple choices for Alice to recognize user's choice and give corresponding feedback.  Also there are three re-prompts set up in case Alice cannot receive choice-related utterances, which guarantees the fluency of the whole prototype.

We do recognize the challenge of envisioning all utterances and including them in this prototype given the limited amount of time.

Final Prototype

Summary

Our CUI, Alice, is curated to improve all aspects of commuting with a focus on efficiency and flexibility during the short-distance trip to the airport. Through the journey map making, scripting the conversation and reiteration on the prototype, we are able to relate our conversation to real-time, location based scenario, in order to help user manage their time during the trip.

Next Steps

There are still some work we are expecting continuing the project if we have more time. Overall, we would imagine to develop Alice to specialize in transporting users from and to the airport. 

Some of the future steps we could take to improve Alice include:

1. Add features so that Alice can help handling user’s work schedule (such as receiving or sending messages, planner, etc)

2. Refine how Alice provides the choices to the user

3. Expand Alice’s response in situations of sudden schedule change (other than just asking to find.a breakfast place)