Infographic Dễ Thương Giải Thích Tách Từ Tiếng Trung

A cute, hand-drawn scrapbook-style horizontal educational infographic in Chinese on a warm beige paper background with rounded borders, pastel doodles, washi tape stickers, tiny star accents, and a cozy notebook aesthetic. Header section: - Top center title in playful handwritten Chinese: "什么是分词？" with "什么是" in dark brown and "分词？" in coral pink. - Upper left: A chibi Shiba Inu teacher standing facing forward in a pale yellow shirt and blue necktie, holding an upward pointer stick, with a speech bubble reading: "今天来学习分词(Tokenization)!". - Upper right: A friendly smiling blue square token mascot labeled "TOKEN" with blushed cheeks, tiny legs, tiny arms, and a magnifying glass, next to a speech bubble reading: "我是 Token！被切得越合理，模型越聪明！". Near the right edge, a small hanging notepad clip reads "知识点 收藏夹" with a small heart icon. - Below the title: A rounded dashed-line box containing the definition: "分词是将人类可读的文本切分成 Token 的过程。" (with "Token" highlighted in blue). Below this box, an introductory text line: "下面以 “程序员Left” 和 “人工智能” 为例，看看不同的分词方式：" (with "程序员Left" highlighted in light blue and "人工智能" in coral pink). Main content (4 rounded pastel panels arranged horizontally side by side): 1. Mint Green Panel: Header badge "1 词级分词", subtitle "按完整语义划分文本". Contains 3 pill-shaped token bubbles: "程序员", "Left", "人工智能". Bottom shows the Shiba Inu teacher giving a thumbs up with a speech bubble: "语义完整，容易理解！". 2. Pale Yellow Panel: Header badge "2 字符级分词", subtitle "逐字切分文本". Contains round token bubbles in a grid: "程", "序", "员", "L", "e", "f", "t", "人", "工", "智", "能". Bottom shows the blue token mascot holding a pencil with a speech bubble: "粒度最细，但序列会很长~". 3. Pale Pink Panel: Header badge "3 子词分词", subtitle "按词根以及前后缀划分". Contains 5 token bubbles: "程序", "员", "Left", "人工", "智能". Bottom shows the Shiba Inu teacher with a thinking pose and question mark, with a speech bubble: "折中方案，效果 often 很好！". 4. Pale Blue Panel: Header badge "4 字节级分词", subtitle "将字词转为字节编码，根据转换后的内容进行组合和划分". Displays multiple small circular byte code bubbles: "E7", "A8", "8B", "...", "66", "74", "E4", "BA", "BA", "E8", "83", "BD". Bottom shows the blue token mascot smiling beside a small light bulb doodle with a speech bubble: "适合处理任意文本！". Footer section: - Across the bottom, a curved pastel banner note reads: "不同分词方式各有优势，实际应用中会根据任务和数据选择合适的方案哦！". - Dark brown legible handwritten lettering, clean composition, warm cozy classroom atmosphere, high clarity.