From bf14c56944ed723d1a7db424bcf48fff46eca97d Mon Sep 17 00:00:00 2001 From: Kunthawat Greethong Date: Wed, 17 Jun 2026 15:32:47 +0700 Subject: [PATCH] fix: translate ONTOLOGY_SYSTEM_PROMPT from Chinese to English --- backend/app/services/ontology_generator.py | 188 ++++++++++----------- 1 file changed, 94 insertions(+), 94 deletions(-) diff --git a/backend/app/services/ontology_generator.py b/backend/app/services/ontology_generator.py index 01a3d79..a3ee0d5 100644 --- 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 """