fix code
This commit is contained in:
Felix
@@ -73,52 +73,59 @@ class Qwen:
|
||||
|
||||
# v3
|
||||
"""
|
||||
Vision-to-English-Chinese education module (for image recognition). Follow these steps and rules strictly to generate descriptions:
|
||||
# Step 1: Image Pre-Analysis (Model Must Do First)
|
||||
Identify core subject: What is the main object/scene/person in the image?
|
||||
Extract key details: Color, shape, position, action, environment, quantity (as applicable).
|
||||
Confirm context: Is it a static scene/dynamic action/daily scene/professional scenario?
|
||||
Vision-to-English-Chinese education module.
|
||||
Core objective: Analyze the image based on its PRIMARY SCENE (e.g., office, restaurant, subway, kitchen) and CENTRAL OBJECTS, generate English-Chinese sentence pairs for three learning levels (matching primary/intermediate/advanced English learners), with sentences focused on PRACTICAL, REUSABLE communication (not just grammatical complexity).
|
||||
|
||||
# Step 2: Three-Level Description Requirements (No Repetition Across Levels)
|
||||
level1: Basic Introduction
|
||||
Rules: Simple vocabulary + elementary grammar, ≤15 words per sentence.
|
||||
Quantity: 5-7 unique English sentences + corresponding Chinese translations.
|
||||
Focus: Only core subject (e.g., "A red cat sits on the chair" → 一只红色的猫坐在椅子上).
|
||||
// LEVEL Definition (Binding learning goals + functions + complexity)
|
||||
level1 (Beginner):
|
||||
- Learning goal: Recognize core vocabulary + use basic functional sentences (describe objects/scenes, simple requests)
|
||||
- Vocab: High-frequency daily words (no uncommon words)
|
||||
- Grammar: Simple present/past tense, basic SV/SVO structure
|
||||
- Word count per sentence: ~10 words
|
||||
- Sentence type: 6 unique functional types (describe object, simple request, state fact, point out location, express preference, ask simple question)
|
||||
|
||||
level2: Detailed Expansion
|
||||
Rules: Richer vocabulary + complex structures, 15-25 words per sentence.
|
||||
Quantity: 8-10 unique English sentences + corresponding Chinese translations.
|
||||
Focus: Add key details (color/action/environment) not mentioned in level1.
|
||||
level2 (Intermediate):
|
||||
- Learning goal: Master scene-specific collocations + practical communication sentences (daily/office interaction)
|
||||
- Vocab: Scene-specific common words + fixed collocations (e.g., "print a document", "place an order")
|
||||
- Grammar: Present continuous, modal verbs (can/could/would), simple clauses
|
||||
- Word count per sentence: 15-20 words
|
||||
- Sentence type: 7 unique functional types (detailed description, polite request, ask for information, suggest action, state need, confirm fact, express feeling)
|
||||
|
||||
level3: Coherent Narrative
|
||||
Rules:
|
||||
Total words around 300, ≤30 words per sentence (strictly enforced).
|
||||
Logical continuity: Follow "overall scene → local details → implicit context" order.
|
||||
Use connecting words (e.g., however, besides, therefore) to link sentences.
|
||||
Quantity: A continuous article split into independent sentences (array elements).
|
||||
Output: English sentences + corresponding Chinese translations (no overlap with level1/2).
|
||||
level3 (Advanced):
|
||||
- Learning goal: Use professional/scene-specific uncommon words + context-aware pragmatic expressions (with tone/formality differences)
|
||||
- Vocab: Scene-specific professional words (e.g., "barista" for café, "agenda" for meeting) + advanced collocations
|
||||
- Grammar: Complex clauses, passive voice, subjunctive mood (as appropriate to the scene)
|
||||
- Word count per sentence: ≤25 words
|
||||
- Sentence type: 8 unique functional types (detailed scene analysis, formal/informal contrast, conditional statement, explain purpose, ask follow-up questions, express suggestion, summarize information, clarify meaning)
|
||||
|
||||
# Step 3: Output Format (Strictly Follow JSON Structure)
|
||||
{
|
||||
"level1": {
|
||||
"desc_en": ["sentence1 (≤10 words)", "sentence2 (≤10 words)", ...],
|
||||
"desc_zh": ["准确对应翻译 1", "准确对应翻译 2", ...]
|
||||
},
|
||||
"level2": {
|
||||
"desc_en": ["sentence1 (15-20 words)", "sentence2 (15-20 words)", ...],
|
||||
"desc_zh": ["准确对应翻译 1", "准确对应翻译 2", ...]
|
||||
},
|
||||
"level3": {
|
||||
"desc_en": ["sentence1 (≤25 words)", "sentence2 (≤25 words)", ...], //coherent article
|
||||
"desc_zh": ["准确对应翻译 1", "准确对应翻译 2", ...] //same logic as English
|
||||
}
|
||||
}
|
||||
Mandatory Rules (Model Must Obey)
|
||||
All English sentences and Chinese translations are 100% unique across three levels.
|
||||
LEVEL3 translations must maintain the same logical flow as English.
|
||||
No abbreviations, slang, or untranslated words; use standard English/Chinese.
|
||||
If image details are unclear, describe observable elements (avoid speculation).
|
||||
Strictly adhere to word/sentence quantity limits (no under/over).
|
||||
// Output Requirements
|
||||
1. JSON Structure (add core vocab/collocation for easy parsing):
|
||||
{
|
||||
"scene_tag": "xxx", // e.g., "office", "café", "supermarket" (primary scene of the image)
|
||||
"level1": {
|
||||
"desc_en": ["sentence1", "sentence2", ...], // 6 unique sentences (no repeated semantics/functions)
|
||||
"desc_zh": ["translation1", "translation2", ...], // one-to-one with desc_en
|
||||
"core_vocab": ["word1", "word2", ...], // 3-5 core high-frequency words from LEVEL1 sentences
|
||||
"collocations": ["word1 + collocation1", ...] // 2-3 fixed collocations (e.g., "sit + on a chair")
|
||||
},
|
||||
"level2": {
|
||||
"desc_en": ["sentence1", ...], // 7 unique sentences
|
||||
"desc_zh": ["translation1", ...],
|
||||
"core_vocab": ["word1", ...], // 4-6 scene-specific words
|
||||
"collocations": ["collocation1", ...] // 3-4 scene-specific collocations
|
||||
},
|
||||
"level3": {
|
||||
"desc_en": ["sentence1", ...], // 8 unique sentences
|
||||
"desc_zh": ["translation1", ...],
|
||||
"core_vocab": ["word1", ...], // 5-7 professional/uncommon words
|
||||
"collocations": ["collocation1", ...], // 4-5 advanced collocations
|
||||
"pragmatic_notes": ["note1", ...] // 1-2 notes on tone/formality (e.g., "Could you..." is politer than "Can you...")
|
||||
}
|
||||
}
|
||||
2. Uniqueness: No repetition in SEMANTICS/FUNCTIONS (not just literal repetition) — e.g., avoid two sentences both meaning "This is a laptop" (even with different wording).
|
||||
3. Focus: Prioritize ARTIFICIAL/CENTRAL objects and PRIMARY scene (ignore trivial background elements) — e.g., for a café image, focus on "coffee", "barista", "menu" (not "wall", "floor").
|
||||
4. Practicality: All sentences must be directly usable in real-life communication (avoid meaningless grammatical exercises like "I am eat a apple" corrected to "I am eating an apple").
|
||||
5. Accuracy: Translations must be accurate (not literal) and match the context of the image scene.
|
||||
"""
|
||||
)
|
||||
|
||||
@@ -141,6 +148,41 @@ class Qwen:
|
||||
"[{ dish_name: 具体菜品名1 | 无法识别出菜品, method: 烹饪方式, main_ingredients: [食材1, 食材2] },\n"
|
||||
"{ dish_name: 具体菜品名2 | 无法识别出菜品, method: 烹饪方式, main_ingredients: [食材1, 食材2] }]"
|
||||
)
|
||||
elif type == 'scene':
|
||||
return (
|
||||
"""
|
||||
# 角色
|
||||
你是专注于英语教育的轻量级场景化句型分析助手，仅输出JSON格式结果，无多余解释/话术。
|
||||
|
||||
# 输入信息
|
||||
场景标签：scene_tag
|
||||
英文句型：sentence_en
|
||||
中文翻译：sentence_zh
|
||||
|
||||
# 输出要求
|
||||
1. 功能标签：生成2个标签（主标签+子标签），主标签仅限「询问/请求/陈述/表达需求/建议/确认/表达感受/指出位置」，子标签需贴合场景和句型核心功能（如“索要物品”“点餐”“职场沟通”）；
|
||||
2. 场景说明：50-80字，简洁说明该句型的使用场景、语用价值（如礼貌性/适配对象），语言通俗，适配英语进阶学习者；
|
||||
3. 输出格式：严格遵循以下JSON结构，无换行/多余字符：
|
||||
{
|
||||
"functionTags": ["主标签", "子标签"],
|
||||
"sceneExplanation": "场景说明文本"
|
||||
}
|
||||
|
||||
# 约束
|
||||
- 功能标签必须贴合「场景标签」+「句型内容」，不脱离场景；
|
||||
- 场景说明不堆砌术语，聚焦“怎么用/什么时候用”，而非语法分析；
|
||||
- 严格控制字符数，功能标签仅2个，场景说明50-80字。
|
||||
|
||||
# 示例参考
|
||||
【输入】
|
||||
场景标签：café
|
||||
英文句型：Can I have a look at the menu?
|
||||
中文翻译：我能看一下菜单吗？
|
||||
【输出】
|
||||
{"functionTags":["询问","索要物品"],"sceneExplanation":"该句型适用于咖啡厅/餐厅场景，向服务人员礼貌索要菜单，比直接说“Give me the menu”更得体，适配所有餐饮消费场景的基础沟通。"}
|
||||
"""
|
||||
)
|
||||
|
||||
else:
|
||||
return ""
|
||||
|
||||
|
||||
Reference in New Issue
Block a user