diff --git a/docs/03-use-cases/01-general/06-data-analysis-agent.md b/docs/03-use-cases/01-general/06-data-analysis-agent.md new file mode 100644 index 0000000..4093310 --- /dev/null +++ b/docs/03-use-cases/01-general/06-data-analysis-agent.md @@ -0,0 +1,140 @@ +--- +title: 数据分析报告 +description: 使用 AI 智能体自动生成符合企业标准的数据分析报告，支持多源数据接入、智能分析与可视化、标准格式输出。 +keywords: [数据分析, 报告生成, 可视化, Excel, 财务报告] +--- + +# 智能体生成标准数据分析报告 + +## 痛点 +每周、每月、每季度——业务部门都需要提交各种数据分析报告：销售周报、运营月报、财务季报。报告格式有严格要求，图表样式要统一，数据口径要一致。分析师花大量时间在"套模板"上：从 Excel 导数据、调格式、做图表、写结论，一份报告动辄半天。 +这个用例让 AI 智能体自动生成符合企业标准的数据分析报告，输入原始数据和报告模板，输出格式规范、图文并茂的专业报告。 + +--- + +## 它能做什么 + +### 📥 多源数据接入 + +- **Excel / CSV**：自动识别表头、数据类型，处理合并单元格 +- **数据库查询**：支持 MySQL、PostgreSQL、SQLite，自然语言转 SQL +- **API 数据源**：对接业务系统，实时拉取最新数据 + +### 📋 报告模板管理 + +- **预置模板库**：销售报告、运营报告、财务报告等常用模板 +- **自定义模板**：支持上传企业标准模板，定义章节结构 +- **样式继承**：字体、配色、图表风格与企业 VI 保持一致 + +### 📊 智能分析与可视化 + +- **自动统计分析**：汇总、环比、同比、占比等常用指标自动计算 +- **智能图表生成**：根据数据特征自动选择柱状图、折线图、饼图等 +- **异常标注**：自动识别数据异常点并在报告中高亮提示 +- **趋势解读**：基于数据变化自动生成文字分析结论 + +### 📄 标准格式输出 + +- **Word 文档**：符合企业模板的 .docx 格式，可直接编辑 +- **PDF 报告**：排版精美，适合分发和存档 +- **PPT 演示**：自动生成汇报用幻灯片 +- **在线预览**：生成前可预览，支持微调后再导出 + +--- + +## 典型使用场景 + +### 场景一：消费行业销售数据分析报告 + +![消费行业销售数据分析报告](./assets/sales-data-analysis-report.jpeg) + +文件地址： ./assets/data-analysis/case1/消费行业销售数据分析报告.docx +``` +📁 输入 + ├── 销售数据.xlsx（350 条记录，覆盖 7 大地区、140 个城市） + └── 用户指令："生成消费行业销售数据分析报告" + +⬇️ 智能体处理（约 3-5 分钟） + +📄 输出：消费行业销售数据分析报告.docx + ├── 📌 一、执行摘要 + │ └── 年度总销售额 ¥63.27 百万元，总销量 285,807 件 + ├── 📊 二、关键指标概览（表格） + │ ├── 总销售额：¥63,274,132.42 + │ ├── 总销量：285,807 件 + │ ├── 平均客单价：¥241.13 + │ └── 覆盖城市数：140 个 + ├── 🗺️ 三、地区销售分析 + │ ├── 各地区销售额占比饼图 + │ └── 结论：华东地区占比 20.5%，表现最突出 + ├── 🏷️ 四、产品品类分析 + │ ├── 各品类销售额对比柱状图 + │ └── 结论：数码家电最高达 ¥28.27 百万元 + ├── 🏪 五、销售渠道分析 + │ ├── 各渠道销售额对比图 + │ └── 结论：批发市场渠道 ¥17.66 百万元领先 + ├── 📈 六、月度销售趋势 + │ ├── 月度销售额折线图 + │ └── 结论：10 月峰值，8 月低谷，呈季节性波动 + ├── 🏙️ 七、城市销售排名 + │ ├── TOP10 城市柱状图 + │ └── 结论：长治 ¥2.79 百万元居首 + ├── 🔍 八、销量与销售额关系分析 + │ ├── 品类散点图（销量 vs 销售额） + │ └── 结论：数码家电高单价、食品饮料靠高销量 + └── 💡 九、结论与建议 + ├── 主要发现（5 条） + └── 策略建议（5 条） +``` + +### 场景二：运营月报批量生成 + +``` +📁 输入 + ├── 各业务线运营数据（5 个部门） + ├── 运营月报标准模板 + └── 用户指令："为每个部门生成独立的月报" + +⬇️ 智能体处理（约 8-10 分钟） + +📄 输出 + ├── 产品部_运营月报_202404.pdf + ├── 市场部_运营月报_202404.pdf + ├── 客服部_运营月报_202404.pdf + ├── 技术部_运营月报_202404.pdf + ├── 销售部_运营月报_202404.pdf + └── 全公司_运营汇总_202404.pdf +``` + +### 场景三：财务季度报告 + +文件地址：./assets/data-analysis/finance_q1_report +``` +📁 输入 + ├── Q1 财务数据（收入、成本、利润明细） + ├── 财务报告模板（含审计要求格式） + └── 用户指令："生成 Q1 财务分析报告" + +⬇️ 智能体处理（约 5-8 分钟） + +📄 输出：2024Q1_财务分析报告.pdf + ├── 财务摘要（关键指标一览表） + ├── 收入分析（按产品线、按区域） + ├── 成本结构（同比变化分析） + ├── 利润分析（毛利率、净利率趋势） + ├── 现金流概况 + └── 风险提示与建议 +``` + +--- + +## 效率对比 + +| 指标 | 手动制作报告 | 固定脚本生成 | AI 智能体 | +|------|--------------|--------------|-----------| +| 单份报告耗时 | ~3 小时 | ~10 分钟 | ~3 分钟 | +| 批量生成（10 份） | ~30 小时 | ~20 分钟 | ~15 分钟 | +| 模板适配成本 | 每次手动调整 | 需修改代码 | 自然语言描述 | +| 异常分析能力 | 依赖人工经验 | 需预设规则 | 智能识别 | +| 结论撰写 | 人工撰写 | 无 | 自动生成 | +| 格式一致性 | 易出错 | 高 | 高 | diff --git a/docs/03-use-cases/01-general/07-flowchart-agent.md b/docs/03-use-cases/01-general/07-flowchart-agent.md new file mode 100644 index 0000000..943b6f1 --- /dev/null +++ b/docs/03-use-cases/01-general/07-flowchart-agent.md @@ -0,0 +1,142 @@ +--- +title: 流程图生成 +description: 使用 AI 智能体根据自然语言描述或文档内容自动生成专业的流程图、架构图、时序图等，支持多格式导出。 +keywords: [流程图, 架构图, 时序图, 可视化, 图表生成] +--- + +# 智能体自动生成流程图 + +## 痛点 + +产品经理写 PRD 要画流程图，开发写技术文档要画架构图，运营写 SOP 要画业务流程——每次都要打开 Visio、ProcessOn 或 draw.io，一个个拖拽节点、连线、对齐、调样式。一张稍复杂的流程图，画完加美化，半小时起步。 + +这个用例让 AI 智能体根据自然语言描述或文档内容，自动生成专业的流程图，支持多种格式导出，省去繁琐的手动绑定。 + +--- + +## 它能做什么 + +### 📝 自然语言输入 + +- **口语化描述**："用户下单后，先检查库存，有货就生成订单，没货就提示缺货" +- **文档解析**：上传 PRD / SOP 文档，自动提取流程逻辑 +- **代码分析**：读取代码文件，生成函数调用流程图 + +### 🎨 智能图表生成 + +- **流程图**：标准 Flowchart，支持判断、循环、并行分支 +- **时序图**：系统交互、API 调用时序 +- **架构图**：系统架构、部署拓扑 +- **泳道图**：跨部门/角色的业务流程 +- **思维导图**：层级结构、知识梳理 + +### 🔧 灵活调整 + +- **自然语言修改**："把审批节点改成两级审批" +- **样式定制**：配色方案、节点形状、连线样式 +- **布局优化**：自动对齐、间距调整、方向切换 + +### 📤 多格式导出 + +- **图片格式**：PNG、SVG、PDF +- **可编辑格式**：Mermaid 代码、draw.io XML、Visio +- **在线分享**：生成分享链接，支持协作编辑 + +--- + +## 典型使用场景 + +### 场景一：产品需求流程图 + +``` +📁 输入 + └── 用户描述："画一个电商退货流程：用户申请退货， + 客服审核，通过后用户寄回商品，仓库验收， + 验收通过退款，不通过则拒绝退货" + +⬇️ 智能体处理（约 10 秒） + +📊 输出：退货流程图.png + ┌─────────┐ + │ 用户申请 │ + │ 退货 │ + └────┬────┘ + ↓ + ┌─────────┐ + │ 客服审核 │ + └────┬────┘ + ↓ + ◇ 审核结果 ◇───否──→ 【拒绝退货】 + │是 + ↓ + ┌─────────┐ + │ 用户寄回 │ + │ 商品 │ + └────┬────┘ + ↓ + ┌─────────┐ + │ 仓库验收 │ + └────┬────┘ + ↓ + ◇ 验收结果 ◇───否──→ 【拒绝退货】 + │是 + ↓ + ┌─────────┐ + │ 退款完成 │ + └─────────┘ +``` + +### 场景二：技术架构图 + +``` +📁 输入 + └── 用户描述："画一个微服务架构图，包含： + 前端 React，网关 Nginx， + 用户服务、订单服务、支付服务， + 数据库用 MySQL 和 Redis" + +⬇️ 智能体处理（约 15 秒） + +📊 输出：微服务架构图.draw.io + + +``` +![微服务架构图](./assets/microservice-architecture.png) +文件地址：./assets/flowchart/microservice-architecture.drawio + +### 场景三：从文档提取流程 + +``` +📁 输入 + ├── 员工入职SOP.docx（3页文字描述） + └── 用户指令："提取入职流程，生成泳道图" + +⬇️ 智能体处理（约 30 秒） + +📊 输出：入职流程泳道图.png + + HR │ IT部门 │ 用工部门 │ 新员工 + ────────────┼──────────────┼──────────────┼────────── + 发送offer │ │ │ + ↓ │ │ │ + 准备合同 │ │ │ 确认入职 + ↓ │ │ │ ↓ + 入职登记 ───┼→ 开通账号 ───┼→ 安排工位 ───┼→ 报到 + ↓ │ ↓ │ ↓ │ ↓ + 社保办理 │ 配发设备 │ 介绍团队 │ 入职培训 + ↓ │ │ │ ↓ + 归档 │ │ │ 试用期开始 +``` + +--- + +## 效率对比 + +| 指标 | 手动绑定（Visio/draw.io） | AI 智能体 | +|------|---------------------------|-----------| +| 简单流程图（5-10 节点） | ~15 分钟 | ~10 秒 | +| 复杂流程图（20+ 节点） | ~45 分钟 | ~30 秒 | +| 修改调整 | 手动拖拽 | 自然语言描述 | +| 样式统一 | 需手动设置 | 自动应用模板 | +| 格式转换 | 逐个导出 | 一键多格式 | +| 学习成本 | 需熟悉工具 | 零门槛 | diff --git a/docs/03-use-cases/01-general/08-web-scraping-agent.md b/docs/03-use-cases/01-general/08-web-scraping-agent.md new file mode 100644 index 0000000..9e29335 --- /dev/null +++ b/docs/03-use-cases/01-general/08-web-scraping-agent.md @@ -0,0 +1,152 @@ +--- +title: 网页信息采集 +description: 使用 AI 智能体自动完成网页浏览、信息提取和数据整理，输出结构化结果，支持定时任务和变化监控。 +keywords: [信息采集, 网页爬虫, 数据抓取, 竞品监控, 结构化数据] +--- + +# 智能体网页信息采集 + +## 痛点 + +市场调研要监控竞品价格、运营团队要收集行业资讯、销售团队要整理客户公开信息——每天花大量时间在不同网站间切换、复制粘贴、整理格式。传统爬虫需要写代码、维护脚本，网站一改版就失效；手动采集效率低下，还容易遗漏关键信息。 + +这个用例让 AI 智能体成为你的信息采集助手，只需告诉它"去哪里采集什么"，自动完成网页浏览、信息提取、数据整理，输出结构化结果。 + +--- + +## 它能做什么 + +### 🌐 智能网页浏览 + +- **多页面并行**：同时打开多个网页，批量采集 +- **动态内容处理**：支持 JavaScript 渲染页面，等待内容加载 +- **登录态保持**：支持 Cookie 管理，采集需登录的内容 +- **反爬应对**：智能控制访问频率，模拟人类浏览行为 + +### 🎯 精准信息提取 + +- **自然语言指令**："提取这个页面的产品名称、价格和评分" +- **表格数据识别**：自动识别网页表格，完整提取行列数据 +- **列表内容采集**：新闻列表、商品列表、搜索结果批量获取 +- **嵌套数据处理**：详情页链接自动跟进，采集完整信息 + +### 📋 结构化输出 + +- **Excel / CSV 导出**：标准表格格式，便于后续分析 +- **JSON 格式**：对接数据库或其他系统 +- **自定义模板**：按需定义输出字段和格式 +- **增量更新**：对比历史数据，仅输出变化部分 + +### 🔄 定时任务 + +- **周期性采集**：每日、每周自动执行 +- **变化监控**：价格变动、内容更新实时提醒 +- **历史记录**：保留采集历史，支持趋势分析 + +--- + +## 典型使用场景 + +### 场景一：官网商品采集 +![官网商品采集](./assets/gucci-products-scraping.png) +文件地址：./assets/web-scraping/gucci_handbags.xlsx + +``` +📁 输入 + ├── 目标网站：gucci.cn（Gucci 中国官网） + ├── 采集范围：手袋品类全部商品 + └── 用户指令："采集 Gucci 官网所有手袋的名称、价格和链接" + +⬇️ 智能体处理（约 3-5 分钟） + +📊 输出：gucci_handbags.xlsx（33 件商品） + ├── 商品名称 + │ ├── Gucci Giglio系列小号托特包 + │ ├── Paparazzo系列中号手提包 + │ ├── Gucci Jackie 1961系列中号手袋 + │ └── ... 共 33 款 + ├── 商品链接 + │ └── 每款商品的官网详情页 URL + └── 价格 + ├── 价格区间：￥6,600 ~ ￥30,000 + └── 结构化数据，可直接用于对比分析 +``` + +### 场景二：行业资讯聚合 + +``` +📁 输入 + ├── 行业媒体网站（10 个） + ├── 关键词过滤规则 + └── 用户指令："采集今天的 AI 行业新闻，按重要性排序" + +⬇️ 智能体处理（约 5-8 分钟） + +📊 输出 + ├── 今日资讯汇总.md + │ ├── 重要新闻 TOP10（含摘要） + │ ├── 按主题分类整理 + │ └── 原文链接 + ├── 关键词词云图 + └── RSS 订阅源（可导入阅读器） +``` + +### 场景三：企业信息收集 + +``` +📁 输入 + ├── 目标企业名单（50 家） + └── 用户指令："收集这些公司的基本信息、融资情况、主要产品" + +⬇️ 智能体处理（约 15-20 分钟） + +📊 输出 + ├── 企业信息库.xlsx + │ ├── 公司名称、成立时间、注册资本 + │ ├── 融资轮次、投资方、融资金额 + │ ├── 主营业务、核心产品 + │ └── 官网、联系方式 + ├── 企业画像卡片（PDF） + └── 数据来源标注 +``` + +### 场景四：招聘信息汇总 + +``` +📁 输入 + ├── 招聘平台（3 个） + ├── 职位关键词、城市、薪资范围 + └── 用户指令："找出符合条件的产品经理岗位" + +⬇️ 智能体处理（约 8-10 分钟） + +📊 输出 + ├── 职位清单.xlsx + │ ├── 公司、职位、薪资、要求 + │ ├── 发布时间、申请链接 + │ └── 匹配度评分 + └── 薪资分布分析图 +``` + +--- + +## 效率对比 + +| 指标 | 手动采集 | 传统爬虫脚本 | AI 智能体 | +|------|----------|--------------|-----------| +| 采集 100 条数据 | ~2 小时 | ~5 分钟（开发后） | ~10 分钟 | +| 技术门槛 | 无 | 高（需编程） | 低（自然语言） | +| 网站适配成本 | 无 | 高（每站写代码） | 低（自动适配） | +| 维护成本 | 持续人力 | 高（网站改版需更新） | 低（智能应对） | +| 非结构化内容 | 可处理 | 困难 | 擅长 | +| 合规性 | 人工判断 | 需配置 | 内置频率控制 | + +--- + +## 使用须知 + +⚠️ **合规提醒**： +- 请遵守目标网站的 robots.txt 和使用条款 +- 控制采集频率，避免对目标网站造成负担 +- 仅采集公开可访问的信息 +- 采集的数据仅供内部分析使用，注意数据隐私合规 diff --git "a/docs/03-use-cases/01-general/assets/data-analysis/case1/\346\266\210\350\264\271\350\241\214\344\270\232\351\224\200\345\224\256\346\225\260\346\215\256\345\210\206\346\236\220\346\212\245\345\221\212.docx" "b/docs/03-use-cases/01-general/assets/data-analysis/case1/\346\266\210\350\264\271\350\241\214\344\270\232\351\224\200\345\224\256\346\225\260\346\215\256\345\210\206\346\236\220\346\212\245\345\221\212.docx" new file mode 100644 index 0000000..6b98c3e Binary files /dev/null and "b/docs/03-use-cases/01-general/assets/data-analysis/case1/\346\266\210\350\264\271\350\241\214\344\270\232\351\224\200\345\224\256\346\225\260\346\215\256\345\210\206\346\236\220\346\212\245\345\221\212.docx" differ diff --git "a/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\345\210\206\346\236\220\346\212\245\345\221\212.docx" "b/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\345\210\206\346\236\220\346\212\245\345\221\212.docx" new file mode 100644 index 0000000..4e45866 Binary files /dev/null and "b/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\345\210\206\346\236\220\346\212\245\345\221\212.docx" differ diff --git "a/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\345\210\206\346\236\220\346\212\245\345\221\212.pdf" "b/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\345\210\206\346\236\220\346\212\245\345\221\212.pdf" new file mode 100644 index 0000000..848242c Binary files /dev/null and "b/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\345\210\206\346\236\220\346\212\245\345\221\212.pdf" differ diff --git "a/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\346\225\260\346\215\256.xlsx" "b/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\346\225\260\346\215\256.xlsx" new file mode 100644 index 0000000..fd3620b Binary files /dev/null and "b/docs/03-use-cases/01-general/assets/data-analysis/finance_q1_report/2024Q1_\350\264\242\345\212\241\346\225\260\346\215\256.xlsx" differ diff --git a/docs/03-use-cases/01-general/assets/flowchart/microservice-architecture.drawio b/docs/03-use-cases/01-general/assets/flowchart/microservice-architecture.drawio new file mode 100644 index 0000000..7f130eb --- /dev/null +++ b/docs/03-use-cases/01-general/assets/flowchart/microservice-architecture.drawio @@ -0,0 +1,161 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/docs/03-use-cases/01-general/assets/gucci-products-scraping.png b/docs/03-use-cases/01-general/assets/gucci-products-scraping.png new file mode 100644 index 0000000..de6b627 Binary files /dev/null and b/docs/03-use-cases/01-general/assets/gucci-products-scraping.png differ diff --git a/docs/03-use-cases/01-general/assets/microservice-architecture.png b/docs/03-use-cases/01-general/assets/microservice-architecture.png new file mode 100644 index 0000000..c03150c Binary files /dev/null and b/docs/03-use-cases/01-general/assets/microservice-architecture.png differ diff --git a/docs/03-use-cases/01-general/assets/sales-data-analysis-report.jpeg b/docs/03-use-cases/01-general/assets/sales-data-analysis-report.jpeg new file mode 100644 index 0000000..9bc5503 Binary files /dev/null and b/docs/03-use-cases/01-general/assets/sales-data-analysis-report.jpeg differ diff --git a/docs/03-use-cases/01-general/assets/web-scraping/gucci_handbags.xlsx b/docs/03-use-cases/01-general/assets/web-scraping/gucci_handbags.xlsx new file mode 100644 index 0000000..b56e289 Binary files /dev/null and b/docs/03-use-cases/01-general/assets/web-scraping/gucci_handbags.xlsx differ diff --git a/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/06-data-analysis-agent.md b/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/06-data-analysis-agent.md new file mode 100644 index 0000000..8347b60 --- /dev/null +++ b/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/06-data-analysis-agent.md @@ -0,0 +1,142 @@ +--- +title: Data Analysis Report +description: Use an AI agent to automatically generate standardized data analysis reports, supporting multi-source data ingestion, intelligent analysis and visualization, and formatted output. +keywords: [Data Analysis, Report Generation, Visualization, Excel, Financial Report] +--- + +# AI-Powered Standard Data Analysis Reports + +## Pain Points + +Every week, month, and quarter, business teams need to submit various data analysis reports: sales weekly reports, operations monthly reports, financial quarterly reports. Reports have strict format requirements, chart styles must be uniform, and ensure consistency in data definitions. Analysts spend a lot of time on "template filling": exporting data from Excel, adjusting formats, creating charts, writing conclusions — a single report takes at least half a day. + +This use case lets an AI agent automatically generate standardized enterprise data analysis reports. Input raw data and report templates, and get professionally formatted, visually rich reports. + +--- + +## What It Can Do + +### 📥 Multi-Source Data Ingestion + +- **Excel / CSV**: Automatically identifies headers and data types, handles merged cells +- **Database Queries**: Supports MySQL, PostgreSQL, SQLite; natural language to SQL +- **API Data Sources**: Connects to business systems to pull real-time data + +### 📋 Report Template Management + +- **Pre-built Template Library**: Sales reports, operations reports, financial reports, and other common templates +- **Custom Templates**: Supports uploading enterprise standard templates and defining chapter structures +- **Style Inheritance**: Fonts, color schemes, and chart styles consistent with corporate VI + +### 📊 Intelligent Analysis & Visualization + +- **Automatic Statistical Analysis**: Auto-calculates common metrics like totals, MoM, YoY, and proportions +- **Smart Chart Generation**: Automatically selects bar charts, line charts, pie charts, etc. based on data characteristics +- **Anomaly Highlighting**: Automatically identifies data outliers and highlights them in the report +- **Trend Interpretation**: Automatically generates textual analysis conclusions based on data changes + +### 📄 Standard Format Output + +- **Word Documents**: .docx format conforming to enterprise templates, directly editable +- **PDF Reports**: Beautifully typeset, suitable for distribution and archiving +- **PPT Presentations**: Automatically generates presentation slides +- **Online Preview**: Preview before generation, with fine-tuning support before export + +--- + +## Typical Use Cases + +### Scenario 1: Consumer Industry Sales Data Analysis Report + +![Consumer Industry Sales Data Analysis Report](./assets/sales-data-analysis-report.jpeg) + +File location: ./assets/data-analysis/case1/Consumer_Industry_Sales_Data_Analysis_Report.docx +``` +📁 Input + ├── Sales_Data.xlsx (350 records, covering 7 major regions, 140 cities) + └── User instruction: "Generate a consumer industry sales data analysis report" + +⬇️ Agent processing (approx. 3-5 minutes) + +📄 Output: Consumer_Industry_Sales_Data_Analysis_Report.docx + ├── 📌 I. Executive Summary + │ └── Annual total sales ¥63.27 million, total volume 285,807 units + ├── 📊 II. Key Metrics Overview (table) + │ ├── Total Sales: ¥63,274,132.42 + │ ├── Total Volume: 285,807 units + │ ├── Avg. Order Value: ¥241.13 + │ └── Cities Covered: 140 + ├── 🗺️ III. Regional Sales Analysis + │ ├── Regional sales proportion pie chart + │ └── Conclusion: East China region accounts for 20.5%, best performance + ├── 🏷️ IV. Product Category Analysis + │ ├── Category sales comparison bar chart + │ └── Conclusion: Digital & home appliances highest at ¥28.27 million + ├── 🏪 V. Sales Channel Analysis + │ ├── Channel sales comparison chart + │ └── Conclusion: Wholesale market channel leads at ¥17.66 million + ├── 📈 VI. Monthly Sales Trend + │ ├── Monthly sales line chart + │ └── Conclusion: October peak, August trough, seasonal fluctuation + ├── 🏙️ VII. City Sales Ranking + │ ├── TOP10 cities bar chart + │ └── Conclusion: Changzhi ¥2.79 million tops the list + ├── 🔍 VIII. Volume vs. Sales Relationship Analysis + │ ├── Category scatter plot (volume vs. sales) + │ └── Conclusion: Digital & home appliances high unit price, food & beverage relies on high volume + └── 💡 IX. Conclusions & Recommendations + ├── Key Findings (5 items) + └── Strategic Recommendations (5 items) +``` + +### Scenario 2: Batch Operations Monthly Report Generation + +``` +📁 Input + ├── Operations data from each business line (5 departments) + ├── Standard operations monthly report template + └── User instruction: "Generate independent monthly reports for each department" + +⬇️ Agent processing (approx. 8-10 minutes) + +📄 Output + ├── Product_Ops_Monthly_Report_202404.pdf + ├── Marketing_Ops_Monthly_Report_202404.pdf + ├── Customer_Service_Ops_Monthly_Report_202404.pdf + ├── Tech_Ops_Monthly_Report_202404.pdf + ├── Sales_Ops_Monthly_Report_202404.pdf + └── Company-wide_Ops_Summary_202404.pdf +``` + +### Scenario 3: Financial Quarterly Report + +File location: ./assets/data-analysis/finance_q1_report +``` +📁 Input + ├── Q1 financial data (revenue, cost, profit details) + ├── Financial report template (including audit-required format) + └── User instruction: "Generate Q1 financial analysis report" + +⬇️ Agent processing (approx. 5-8 minutes) + +📄 Output: 2024Q1_Financial_Analysis_Report.pdf + ├── Financial Summary (key metrics overview table) + ├── Revenue Analysis (by product line, by region) + ├── Cost Structure (YoY change analysis) + ├── Profit Analysis (gross margin, net margin trends) + ├── Cash Flow Overview + └── Risk Alerts & Recommendations +``` + +--- + +## Efficiency Comparison + +| Metric | Manual Report Creation | Fixed Script Generation | AI Agent | +|--------|------------------------|-------------------------|----------| +| Single report time | ~3 hours | ~10 minutes | ~3 minutes | +| Batch generation (10 reports) | ~30 hours | ~20 minutes | ~15 minutes | +| Template adaptation cost | Manual each time | Code modification required | Natural language description | +| Anomaly analysis capability | Relies on human experience | Requires preset rules | Intelligent identification | +| Conclusion writing | Manual | None | Auto-generated | +| Format consistency | Error-prone | High | High | diff --git a/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/07-flowchart-agent.md b/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/07-flowchart-agent.md new file mode 100644 index 0000000..243b683 --- /dev/null +++ b/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/07-flowchart-agent.md @@ -0,0 +1,152 @@ +--- +title: Flowchart Generation +description: Use an AI agent to automatically generate professional flowcharts, architecture diagrams, and sequence charts from natural language descriptions or documents, with multi-format export support. +keywords: [Flowchart, Architecture Diagram, Sequence Diagram, Visualization, Chart Generation] +--- + +# AI-Powered Automatic Flowchart Generation + +## Pain Points + +Product managers need flowcharts for PRDs, developers need architecture diagrams for technical docs, and operations teams need business process diagrams for SOPs — every time you have to open Visio, ProcessOn, or draw.io, dragging nodes one by one, connecting lines, aligning, and adjusting styles. For a moderately complex flowchart, drawing and beautifying takes at least half an hour. + +This use case lets an AI agent automatically generate professional flowcharts based on natural language descriptions or document content, supporting multiple export formats, eliminating tedious manual work. + +--- + +## What It Can Do + +### 📝 Natural Language Input + +- **Conversational Descriptions**: "After user places an order, check inventory first. If in stock, generate the order; if out of stock, show out-of-stock alert" +- **Document Parsing**: Upload PRD / SOP documents to automatically extract process logic +- **Code Analysis**: Read code files to generate function call flowcharts + +### 🎨 Intelligent Chart Generation + +- **Flowcharts**: Standard Flowchart, supporting decisions, loops, parallel branches +- **Sequence Diagrams**: System interactions, API call sequences +- **Architecture Diagrams**: System architecture, deployment topology +- **Swimlane Diagrams**: Cross-department/role business processes +- **Mind Maps**: Hierarchical structures, knowledge organization + +### 🔧 Flexible Adjustments + +- **Natural Language Modifications**: "Change the approval node to two-level approval" +- **Style Customization**: Color schemes, node shapes, connector styles +- **Layout Optimization**: Auto-alignment, spacing adjustment, direction switching + +### 📤 Multi-Format Export + +- **Image Formats**: PNG, SVG, PDF +- **Editable Formats**: Mermaid code, draw.io XML, Visio +- **Online Sharing**: Generate shareable links with collaborative editing support + +--- + +## Typical Use Cases + +### Scenario 1: Product Requirements Flowchart + +``` +📁 Input + └── User description: "Draw an e-commerce return process: user applies for return, + customer service reviews, after approval user ships item back, warehouse inspects, + if inspection passes then refund, if not then reject the return" + +⬇️ Agent processing (approx. 10 seconds) + +📊 Output: Return_Process.png + ┌─────────┐ + │ User │ + │ Applies │ + │ Return │ + └────┬────┘ + ↓ + ┌─────────┐ + │ Customer│ + │ Service │ + │ Review │ + └────┬────┘ + ↓ + ◇ Review ◇───No──→ 【Return Rejected】 + │Yes + ↓ + ┌─────────┐ + │ User │ + │ Ships │ + │ Item │ + └────┬────┘ + ↓ + ┌─────────┐ + │ Warehouse│ + │ Inspection│ + └────┬────┘ + ↓ + ◇ Inspection ◇───No──→ 【Return Rejected】 + │Yes + ↓ + ┌─────────┐ + │ Refund │ + │ Complete│ + └─────────┘ +``` + +### Scenario 2: Technical Architecture Diagram + +``` +📁 Input + └── User description: "Draw a microservices architecture diagram including: + Frontend React, Gateway Nginx, + User Service, Order Service, Payment Service, + Database using MySQL and Redis" + +⬇️ Agent processing (approx. 15 seconds) + +📊 Output: Microservices_Architecture.draw.io + + +``` +![Microservices Architecture](./assets/microservice-architecture.png) +File location: ./assets/flowchart/microservice-architecture.drawio + +### Scenario 3: Extract Process from Document + +``` +📁 Input + ├── Employee_Onboarding_SOP.docx (3 pages of text description) + └── User instruction: "Extract onboarding process and generate a swimlane diagram" + +⬇️ Agent processing (approx. 30 seconds) + +📊 Output: Onboarding_Process_Swimlane.png + + HR │ IT Dept │ Hiring Dept │ New Employee + ────────────┼──────────────┼───────────────┼───────────── + Send Offer │ │ │ + ↓ │ │ │ + Prepare │ │ │ Confirm + Contract │ │ │ Onboarding + ↓ │ │ │ ↓ + Onboarding ─┼→ Account ────┼→ Assign ──────┼→ Report + Register │ Setup │ Workspace │ ↓ + ↓ │ ↓ │ ↓ │ ↓ + Social │ Distribute │ Introduce │ Onboarding + Insurance │ Equipment │ Team │ Training + ↓ │ │ │ ↓ + Archive │ │ │ Probation + │ │ │ Starts +``` + +--- + +## Efficiency Comparison + +| Metric | Manual Drawing (Visio/draw.io) | AI Agent | +|--------|--------------------------------|----------| +| Simple flowchart (5-10 nodes) | ~15 minutes | ~10 seconds | +| Complex flowchart (20+ nodes) | ~45 minutes | ~30 seconds | +| Modification & Adjustment | Manual drag | Natural language description | +| Style Uniformity | Manual setup required | Auto-applied templates | +| Format Conversion | Export one by one | One-click multi-format | +| Learning Curve | Need to learn tool | Zero barrier | diff --git a/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/08-web-scraping-agent.md b/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/08-web-scraping-agent.md new file mode 100644 index 0000000..1078c87 --- /dev/null +++ b/i18n/en/docusaurus-plugin-content-docs/current/03-use-cases/01-general/08-web-scraping-agent.md @@ -0,0 +1,152 @@ +--- +title: Web Data Collection +description: Use an AI agent to automatically browse web pages, extract information, and organize data, outputting structured results with scheduled tasks and change monitoring support. +keywords: [Data Collection, Web Scraping, Data Extraction, Competitor Monitoring, Structured Data] +--- + +# AI-Powered Web Data Collection + +## Pain Points + +Market research requires monitoring competitor prices, operations teams need to collect industry news, and sales teams need to organize publicly available client information — every day spent switching between different websites, copying and pasting, and formatting. Traditional web scrapers require writing code and maintaining scripts; a single website redesign breaks them. Manual collection is inefficient and prone to missing key information. + +This use case makes an AI agent your data collection assistant. Just tell it "where to collect what," and it automatically completes web browsing, information extraction, and data organization, outputting structured results. + +--- + +## What It Can Do + +### 🌐 Intelligent Web Browsing + +- **Multi-Page Parallel**: Open multiple web pages simultaneously for batch collection +- **Dynamic Content Handling**: Supports JavaScript-rendered pages, waits for content loading +- **Login State Preservation**: Supports Cookie management for content requiring login +- **Anti-Scraping Countermeasures**: Intelligent access frequency control, simulating human browsing behavior + +### 🎯 Precise Information Extraction + +- **Natural Language Instructions**: "Extract product names, prices, and ratings from this page" +- **Table Data Recognition**: Automatically identifies web tables and fully extracts row and column data +- **List Content Collection**: News lists, product lists, search results — all batch collected +- **Nested Data Processing**: Detail page links automatically followed for complete information collection + +### 📋 Structured Output + +- **Excel / CSV Export**: Standard table format for subsequent analysis +- **JSON Format**: Integration with databases or other systems +- **Custom Templates**: Define output fields and formats on demand +- **Incremental Updates**: Compare with historical data, output only changes + +### 🔄 Scheduled Tasks + +- **Periodic Collection**: Execute automatically daily or weekly +- **Change Monitoring**: Real-time alerts for price changes and content updates +- **History Records**: Retain collection history for trend analysis + +--- + +## Typical Use Cases + +### Scenario 1: Official Website Product Collection +![Official Website Product Collection](./assets/gucci-products-scraping.png) +File location: ./assets/web-scraping/gucci_handbags.xlsx + +``` +📁 Input + ├── Target website: gucci.cn (Gucci China official site) + ├── Collection scope: All products in handbags category + └── User instruction: "Collect names, prices, and links for all handbags on Gucci official site" + +⬇️ Agent processing (approx. 3-5 minutes) + +📊 Output: gucci_handbags.xlsx (33 products) + ├── Product Name + │ ├── Gucci Giglio Small Tote Bag + │ ├── Paparazzo Medium Top Handle Bag + │ ├── Gucci Jackie 1961 Medium Shoulder Bag + │ └── ... 33 styles total + ├── Product Link + │ └── Official detail page URL for each product + └── Price + ├── Price range: ¥6,600 ~ ¥30,000 + └── Structured data ready for comparison analysis +``` + +### Scenario 2: Industry News Aggregation + +``` +📁 Input + ├── Industry media websites (10 sites) + ├── Keyword filtering rules + └── User instruction: "Collect today's AI industry news, sorted by importance" + +⬇️ Agent processing (approx. 5-8 minutes) + +📊 Output + ├── Today_News_Summary.md + │ ├── Top 10 Important News (with summaries) + │ ├── Organized by topic + │ └── Original article links + ├── Keyword word cloud chart + └── RSS feed (importable into readers) +``` + +### Scenario 3: Company Information Collection + +``` +📁 Input + ├── Target company list (50 companies) + └── User instruction: "Collect basic information, funding status, and main products for these companies" + +⬇️ Agent processing (approx. 15-20 minutes) + +📊 Output + ├── Company_Information_Database.xlsx + │ ├── Company name, founding date, registered capital + │ ├── Funding rounds, investors, funding amounts + │ ├── Main business, core products + │ └── Official website, contact information + ├── Company profile cards (PDF) + └── Data source annotations +``` + +### Scenario 4: Job Recruitment Aggregation + +``` +📁 Input + ├── Recruitment platforms (3 platforms) + ├── Job keywords, city, salary range + └── User instruction: "Find qualified Product Manager positions" + +⬇️ Agent processing (approx. 8-10 minutes) + +📊 Output + ├── Job_Listing.xlsx + │ ├── Company, position, salary, requirements + │ ├── Post date, application link + │ └── Match score + └── Salary distribution analysis chart +``` + +--- + +## Efficiency Comparison + +| Metric | Manual Collection | Traditional Web Scraper | AI Agent | +|--------|-------------------|-------------------------|----------| +| Collect 100 data points | ~2 hours | ~5 minutes (after development) | ~10 minutes | +| Technical Barrier | None | High (requires programming) | Low (natural language) | +| Website Adaptation Cost | None | High (code per site) | Low (auto-adaptation) | +| Maintenance Cost | Continuous labor | High (updates needed on redesign) | Low (intelligent handling) | +| Unstructured Content | Handleable | Difficult | Strong | +| Compliance | Human judgment | Requires configuration | Built-in frequency control | + +--- + +## Usage Notes + +⚠️ **Compliance Reminder**: +- Please comply with target website's robots.txt and terms of use +- Control collection frequency to avoid burdening target websites +- Only collect publicly accessible information +- Collected data is for internal analysis use only; ensure data privacy compliance