Overview

Innovation Design

| Human-Machine Interaction

| Concept Design

At UC Berkeley’s entrepreneurship project Harmony, I transformed voice-biomarker ML into an empathetic, context-aware VUI that supports natural, compassionate home interactions—bridging cutting-edge AI and human-centered care.

Client:

Siemens Healthineers

Industry:

MedTech, B2B

Role:

UX Researcher

Timeline:

2025 Summer

Bridged structural biology and engineering to turn complex CV/AI pipelines into an intuitive web platform adopted by 200+ researchers and powering 2M+ processing runs.

What Are Happening In The Room?

Context @Siemens Healthineers

What are happening in the room?

Their initial purpose is to analysis images from Cryo-ET assisted by visualization tool (typically IMOD). However, 他们在繁复的弹窗中迷失,对着逻辑交错且顺序复杂的参数设置苦恼,等待图像处理的未知焦虑,面对任务失败需要花大量时间debug找原因沮丧,同时老版软件跟不上AI技术的进步没能集成上最前沿的辅助科技,也不适用于现代lab的协作环境……对此我们能做什么?

Design Objectives

CT inventional

Traditionally, structural biologists worked in this way:

Field Visit

Understand who are in the loop?

极大锻炼了我在真实落地开发、服务甲方的环境中做设计的能力,我收获了与PM、甲方高效沟通对齐需求,掌握基础前端技能与前端开发沟通交付,学习后端算法优化UI流程等宝贵经验。

Contextual Inquiry

Understand what they need & want?

Traditionally, structural biologists worked in this way:

Literature Review

Cross-industry learning and inspiring

Traditionally, structural biologists worked in this way:

OR Role Map

How we evaluate

Traditionally, structural biologists worked in this way:

User Journey Map

Concept Design & Dissemination

Traditionally, structural biologists worked in this way:

Takeaway

Traditionally, structural biologists worked with images in this way:

Their initial purpose is to analysis images from Cryo-ET assisted by visualization tool (typically IMOD). However, 他们在繁复的弹窗中迷失,对着逻辑交错且顺序复杂的参数设置苦恼,等待图像处理的未知焦虑,面对任务失败需要花大量时间debug找原因沮丧,同时老版软件跟不上AI技术的进步没能集成上最前沿的辅助科技,也不适用于现代lab的协作环境……对此我们能做什么?

Let's
Have a
Chat :)

belinda-liu@berkeley.edu