📘 中文版提示词

🎯 请针对 “中国当代年轻人（18–35岁）” 群体，完成一份关于 手机购物App 的深度用户需求分析报告。分析必须覆盖以下九个维度，且每个维度需提供数据支撑或典型洞察：

1️⃣ 用户特征 —— 包含人口统计学基本属性：年龄分布、性别比例、主要城市层级（一线/新一线/二线等）、受教育程度（本科及以上占比）、月均可支配收入区间，以及移动设备使用偏好（iOS/Android占比、常用购物时段）。

2️⃣ 用户需求 —— 深挖使用动机：他们为何选择手机购物而非PC或线下？（便捷性、比价效率、社交化推荐、直播带货吸引力等）；他们试图解决哪些核心痛点（时间成本、选择困难、价格敏感、信任问题）；对产品的功能期望（个性化推荐、流畅支付、售后保障、会员权益等）。

3️⃣ 用户行为 —— 操作习惯与购买路径：包括日均打开次数、平均停留时长、搜索与浏览比例、加购与收藏行为、下单高峰期（周内/周末差异）、支付方式偏好（微信支付/支付宝/花呗/银行卡），以及受促销活动（如618、双11）影响的购买波动。

4️⃣ 用户反馈 —— 基于主流应用商店评论、社交媒体舆情及调研数据，汇总正面评价（如界面美观、物流快、客服响应好）与负面投诉（如价格欺诈、虚假宣传、退换货繁琐），并提炼出高频改进建议。

5️⃣ 用户转化率 —— 量化关键漏斗节点：注册转化率（从访客到注册用户）、首单购买率（注册后30天内完成首购）、复购转化率（二次及以上购买），以及不同渠道来源（自然搜索、社交分享、广告投放）的转化差异。

6️⃣ 用户留存率 —— 提供次日、7日、30日留存率数据，并分析影响留存的Top 3驱动因素（如push推送效果、会员积分体系、新功能使用率）及流失预警阈值。

7️⃣ 用户满意度 —— 采用NPS（净推荐值）及CSAT（客户满意度评分）量化指标，分层展示高满意用户与低满意用户的行为差异，并评估忠诚度（如推荐意愿、跨品类购买广度）。

8️⃣ 用户行为漏斗 —— 绘制从“启动App → 浏览首页 → 搜索/浏览商品 → 查看详情 → 加入购物车 → 提交订单 → 支付成功 → 完成评价”的完整转化路径，标注每个步骤的流失率及主要流失原因（如加载慢、价格不透明、支付失败）。

9️⃣ 用户使用场景 —— 描绘典型场景画像：包括时间（通勤途中、午休、睡前）、地点（家中、办公室、地铁/公交）、伴随状态（独处/社交、碎片化/沉浸式）、触发事件（收到优惠通知、朋友分享链接、急需某类商品）等，并区分主动搜索型场景与被动种草型场景。

📌 最终输出需以结构化报告形式呈现，每维度下含子标题、关键数据图表描述（无需真实图表，用文字描述趋势即可）、核心结论及 actionable 建议。语言专业、客观，适合用于产品决策或投资汇报场景。

🇬🇧 English Version Prompt

🎯 Please conduct a comprehensive user demand analysis for mobile shopping apps targeting contemporary Chinese young adults (aged 18–35). The analysis must systematically cover the following nine dimensions, each backed by data or typical insights:

1️⃣ User Demographics —— Basic attributes: age distribution, gender ratio, city tier breakdown (Tier 1 / emerging Tier 1 / Tier 2, etc.), education level (percentage with bachelor’s degree or above), monthly disposable income brackets, and mobile device preferences (iOS/Android share, peak usage hours).

2️⃣ User Needs & Motivations —— Why they choose mobile apps over PC or offline (convenience, price comparison efficiency, social recommendations, livestream appeal); core pain points (time cost, choice overload, price sensitivity, trust issues); feature expectations (personalised recommendations, seamless checkout, after‑sales service, membership benefits).

3️⃣ User Behaviours —— Interaction habits and purchase paths: daily launch frequency, average session duration, search‑vs‑browse ratio, add‑to‑cart and favourites actions, peak ordering times (weekday/weekend differences), payment preferences (WeChat Pay, Alipay, Huabei, bank cards), and fluctuation patterns driven by promotional events (e.g., 618, Double 11).

4️⃣ User Feedback —— Synthesise from app store reviews, social media sentiment, and survey data: highlight positive comments (UI aesthetics, delivery speed, responsive support) and negative complaints (price discrepancies, misleading ads, complicated returns), and distil recurring improvement suggestions.

5️⃣ Conversion Rates —— Quantify key funnel nodes: registration conversion (visitor → registered user), first‑purchase rate (within 30 days of registration), repurchase conversion (second and subsequent orders), and conversion differences across acquisition channels (organic search, social sharing, paid ads).

6️⃣ Retention Rates —— Provide Day‑1, Day‑7, and Day‑30 retention figures; analyse the top 3 drivers impacting retention (e.g., push notification effectiveness, loyalty points system, adoption of new features) and early churn warning thresholds.

7️⃣ User Satisfaction —— Use NPS (Net Promoter Score) and CSAT (Customer Satisfaction Score) as quantitative metrics; segment high‑ vs low‑satisfaction users and assess loyalty (willingness to recommend, cross‑category purchase breadth).

8️⃣ Behavioural Funnel —— Map the complete conversion path: App Launch → Homepage Browsing → Search/Browse Products → View Details → Add to Cart → Place Order → Payment Success → Post‑purchase Review. Indicate drop‑off rates at each stage and primary reasons for abandonment (slow loading, opaque pricing, payment failures).

9️⃣ Usage Scenarios —— Paint typical scenario portraits: time (commuting, lunch breaks, before bed), location (home, office, public transport), contextual state (alone/socialising, fragmented/immersive), and triggers (discount notifications, friend‑shared links, urgent need for a product). Differentiate between active‑search scenarios and passive‑inspiration scenarios.

📌 Deliver the final output as a structured report, with subsections per dimension, descriptive data trends (without requiring actual charts), key conclusions, and actionable recommendations. Use professional, objective language suitable for product decision‑making or investor presentations.