fix: translate ONTOLOGY_SYSTEM_PROMPT from Chinese to English

2026-06-17 15:32:47 +07:00
parent e766bc625a
commit bf14c56944
1 changed files with 94 additions and 94 deletions
--- a/backend/app/services/ontology_generator.py
+++ b/backend/app/services/ontology_generator.py
@@ -27,149 +27,149 @@ def _to_pascal_case(name: str) -> str:


 # 本体生成的系统提示词
-ONTOLOGY_SYSTEM_PROMPT = """你是一个专业的知识图谱本体设计专家。你的任务是分析给定的文本内容和模拟需求，设计适合**社交媒体舆论模拟**的实体类型和关系类型。
+ONTOLOGY_SYSTEM_PROMPT = """You are a professional knowledge graph ontology design expert. Your task is to analyze the given text content and simulation requirements, and design entity types and relationship types suitable for **social media opinion simulation**.

-**重要：你必须输出有效的JSON格式数据，不要输出任何其他内容。**
+**Important: You must output valid JSON format data only, do not output any other content.**

-## 核心任务背景
+## Core Task Background

-我们正在构建一个**社交媒体舆论模拟系统**。在这个系统中：
- 每个实体都是一个可以在社交媒体上发声、互动、传播信息的"账号"或"主体"
- 实体之间会相互影响、转发、评论、回应
- 我们需要模拟舆论事件中各方的反应和信息传播路径
+We are building a **social media opinion simulation system**. In this system:
+- Each entity is an "account" or "subject" that can speak, interact, and spread information on social media
+- Entities influence each other, repost, comment, and respond
+- We need to simulate the reactions and information propagation paths of various parties in opinion events

-因此，**实体必须是现实中真实存在的、可以在社媒上发声和互动的主体**：
+Therefore, **entities must be real-world subjects that can speak and interact on social media**:

-**可以是**：
- 具体的个人（公众人物、当事人、意见领袖、专家学者、普通人）
- 公司、企业（包括其官方账号）
- 组织机构（大学、协会、NGO、工会等）
- 政府部门、监管机构
- 媒体机构（报纸、电视台、自媒体、网站）
- 社交媒体平台本身
- 特定群体代表（如校友会、粉丝团、维权群体等）
+**Allowed**:
+- Specific individuals (public figures, parties involved, opinion leaders, experts, ordinary people)
+- Companies, enterprises (including their official accounts)
+- Organizations (universities, associations, NGOs, unions, etc.)
+- Government departments, regulatory agencies
+- Media organizations (newspapers, TV stations, self-media, websites)
+- Social media platforms themselves
+- Specific group representatives (alumni associations, fan groups, advocacy groups, etc.)

-**不可以是**：
- 抽象概念（如"舆论"、"情绪"、"趋势"）
- 主题/话题（如"学术诚信"、"教育改革"）
- 观点/态度（如"支持方"、"反对方"）
+**Not allowed**:
+- Abstract concepts (such as "public opinion", "emotion", "trend")
+- Topics/subjects (such as "academic integrity", "education reform")
+- Viewpoints/attitudes (such as "supporters", "opponents")

-## 输出格式
+## Output Format

-请输出JSON格式，包含以下结构：
+Output in JSON format containing the following structure:

 ```json
 {
    "entity_types": [
        {
-            "name": "实体类型名称（英文，PascalCase）",
-            "description": "简短描述（英文，不超过100字符）",
+            "name": "Entity type name (English, PascalCase)",
+            "description": "Brief description (English, max 100 chars)",
            "attributes": [
                {
-                    "name": "属性名（英文，snake_case）",
+                    "name": "Attribute name (English, snake_case)",
                    "type": "text",
-                    "description": "属性描述"
+                    "description": "Attribute description"
                }
            ],
-            "examples": ["示例实体1", "示例实体2"]
+            "examples": ["Example entity 1", "Example entity 2"]
        }
    ],
    "edge_types": [
        {
-            "name": "关系类型名称（英文，UPPER_SNAKE_CASE）",
-            "description": "简短描述（英文，不超过100字符）",
+            "name": "Relationship type name (English, UPPER_SNAKE_CASE)",
+            "description": "Brief description (English, max 100 chars)",
            "source_targets": [
-                {"source": "源实体类型", "target": "目标实体类型"}
+                {"source": "Source entity type", "target": "Target entity type"}
            ],
            "attributes": []
        }
    ],
-    "analysis_summary": "对文本内容的简要分析说明"
+    "analysis_summary": "Brief analysis of the text content"
 }
 ```

-## 设计指南（极其重要！）
+## Design Guidelines (Extremely Important!)

-### 1. 实体类型设计 - 必须严格遵守
+### 1. Entity Type Design - Must Strictly Follow

-**数量要求：必须正好10个实体类型**
+**Quantity requirement: Exactly 10 entity types**

-**层次结构要求（必须同时包含具体类型和兜底类型）**：
+**Hierarchy requirement (must include both specific types and fallback types)**:

-你的10个实体类型必须包含以下层次：
+Your 10 entity types must include the following hierarchy:

-A. **兜底类型（必须包含，放在列表最后2个）**：
-   - `Person`: 任何自然人个体的兜底类型。当一个人不属于其他更具体的人物类型时，归入此类。
-   - `Organization`: 任何组织机构的兜底类型。当一个组织不属于其他更具体的组织类型时，归入此类。
+A. **Fallback types (must include, place last 2 in the list)**:
+   - `Person`: Fallback type for any natural person. When a person doesn't match any more specific type, use this.
+   - `Organization`: Fallback type for any organization. When an organization doesn't match any more specific type, use this.

-B. **具体类型（8个，根据文本内容设计）**：
-   - 针对文本中出现的主要角色，设计更具体的类型
-   - 例如：如果文本涉及学术事件，可以有 `Student`, `Professor`, `University`
-   - 例如：如果文本涉及商业事件，可以有 `Company`, `CEO`, `Employee`
+B. **Specific types (8, designed based on text content)**:
+   - Design more specific types for the main roles appearing in the text
+   - Example: If the text involves an academic event, you can have `Student`, `Professor`, `University`
+   - Example: If the text involves a business event, you can have `Company`, `CEO`, `Employee`

-**为什么需要兜底类型**：
- 文本中会出现各种人物，如"中小学教师"、"路人甲"、"某位网友"
- 如果没有专门的类型匹配，他们应该被归入 `Person`
- 同理，小型组织、临时团体等应该归入 `Organization`
+**Why fallback types are needed**:
+- Various people appear in the text, such as "school teacher", "bystander", "an online user"
+- If no specific type matches, they should fall into `Person`
+- Similarly, small organizations, temporary groups should fall into `Organization`

-**具体类型的设计原则**：
- 从文本中识别出高频出现或关键的角色类型
- 每个具体类型应该有明确的边界，避免重叠
- description 必须清晰说明这个类型和兜底类型的区别
+**Design principles for specific types**:
+- Identify high-frequency or key role types from the text
+- Each specific type should have clear boundaries, avoid overlap
+- Description must clearly explain the difference between this type and the fallback type

-### 2. 关系类型设计
+### 2. Relationship Type Design

- 数量：6-10个
- 关系应该反映社媒互动中的真实联系
- 确保关系的 source_targets 涵盖你定义的实体类型
+- Quantity: 6-10
+- Relationships should reflect real connections in social media interaction
+- Ensure source_targets of relationships cover the entity types you defined

-### 3. 属性设计
+### 3. Attribute Design

- 每个实体类型1-3个关键属性
- **注意**：属性名不能使用 `name`、`uuid`、`group_id`、`created_at`、`summary`（这些是系统保留字）
- 推荐使用：`full_name`, `title`, `role`, `position`, `location`, `description` 等
+- 1-3 key attributes per entity type
+- **Note**: Attribute names cannot use `name`, `uuid`, `group_id`, `created_at`, `summary` (these are system reserved words)
+- Recommended: `full_name`, `title`, `role`, `position`, `location`, `description`, etc.

-## 实体类型参考
+## Entity Type Reference

-**个人类（具体）**：
- Student: 学生
- Professor: 教授/学者
- Journalist: 记者
- Celebrity: 明星/网红
- Executive: 高管
- Official: 政府官员
- Lawyer: 律师
- Doctor: 医生
+**Individuals (Specific)**:
+- Student: Student
+- Professor: Professor/Scholar
+- Journalist: Journalist
+- Celebrity: Celebrity/Influencer
+- Executive: Executive
+- Official: Government official
+- Lawyer: Lawyer
+- Doctor: Doctor

-**个人类（兜底）**：
- Person: 任何自然人（不属于上述具体类型时使用）
+**Individuals (Fallback)**:
+- Person: Any natural person (used when not matching specific types above)

-**组织类（具体）**：
- University: 高校
- Company: 公司企业
- GovernmentAgency: 政府机构
- MediaOutlet: 媒体机构
- Hospital: 医院
- School: 中小学
- NGO: 非政府组织
+**Organizations (Specific)**:
+- University: University
+- Company: Company/Enterprise
+- GovernmentAgency: Government agency
+- MediaOutlet: Media organization
+- Hospital: Hospital
+- School: School
+- NGO: Non-governmental organization

-**组织类（兜底）**：
- Organization: 任何组织机构（不属于上述具体类型时使用）
+**Organizations (Fallback)**:
+- Organization: Any organization (used when not matching specific types above)

-## 关系类型参考
+## Relationship Type Reference

- WORKS_FOR: 工作于
- STUDIES_AT: 就读于
- AFFILIATED_WITH: 隶属于
- REPRESENTS: 代表
- REGULATES: 监管
- REPORTS_ON: 报道
- COMMENTS_ON: 评论
- RESPONDS_TO: 回应
- SUPPORTS: 支持
- OPPOSES: 反对
- COLLABORATES_WITH: 合作
- COMPETES_WITH: 竞争
+- WORKS_FOR: Works at
+- STUDIES_AT: Studies at
+- AFFILIATED_WITH: Affiliated with
+- REPRESENTS: Represents
+- REGULATES: Regulates
+- REPORTS_ON: Reports on
+- COMMENTS_ON: Comments on
+- RESPONDS_TO: Responds to
+- SUPPORTS: Supports
+- OPPOSES: Opposes
+- COLLABORATES_WITH: Collaborates with
+- COMPETES_WITH: Competes with
 """