fix: translate remaining Chinese in sim config and profile prompts
- Time config: translate all Chinese instructions and field descriptions - Event config: translate hot topics/narrative direction instructions - Agent config: translate entity type descriptions and field labels - Profile generator: translate all persona prompt fields and instructions - Country field: changed from 'use Chinese' to 'use English'
This commit is contained in:
Kunthawat Greethong
@@ -544,24 +544,24 @@ class SimulationConfigGenerator:
|
||||
|
||||
{context_truncated}
|
||||
|
||||
## 任务
|
||||
## Task
|
||||
Please generate time config JSON.
|
||||
|
||||
### 基本原则（仅供参考，需根据具体事件和参与群体灵活调整）：
|
||||
### Basic Principles (for reference only, adjust flexibly based on specific event and participant group):
|
||||
- Please infer the target user group's timezone and daily routine based on the simulation scenario. Below is a reference example for UTC+8
|
||||
- 凌晨0-5点几乎无人活动（活跃度系数0.05）
|
||||
- 早上6-8点逐渐活跃（活跃度系数0.4）
|
||||
- 工作时间9-18点中等活跃（活跃度系数0.7）
|
||||
- 晚间19-22点是高峰期（活跃度系数1.5）
|
||||
- 23点后活跃度下降（活跃度系数0.5）
|
||||
- 一般规律：凌晨低活跃、早间渐增、工作时段中等、晚间高峰
|
||||
- **重要**：以下示例值仅供参考，你需要根据事件性质、参与群体特点来调整具体时段
|
||||
- 例如：学生群体高峰可能是21-23点；媒体全天活跃；官方机构只在工作时间
|
||||
- 例如：突发热点可能导致深夜也有讨论，off_peak_hours 可适当缩短
|
||||
- Midnight 0-5am: almost no activity (activity multiplier 0.05)
|
||||
- Morning 6-8am: gradually active (activity multiplier 0.4)
|
||||
- Work hours 9-18pm: moderately active (activity multiplier 0.7)
|
||||
- Evening 19-22pm: peak hours (activity multiplier 1.5)
|
||||
- After 23pm: activity decreases (activity multiplier 0.5)
|
||||
- General pattern: low activity late night, increasing morning, moderate during work hours, peak in evening
|
||||
- **Important**: The example values above are for reference only. You must adjust specific time periods based on event nature and participant characteristics
|
||||
- Example: Student groups may peak at 21-23pm; media is active all day; government agencies only during work hours
|
||||
- Example: Breaking hot topics may cause late-night discussions, off_peak_hours can be shortened accordingly
|
||||
|
||||
### 返回JSON格式（不要markdown）
|
||||
### Return in JSON format (no markdown)
|
||||
|
||||
示例：
|
||||
Example:
|
||||
{{
|
||||
"total_simulation_hours": 72,
|
||||
"minutes_per_round": 60,
|
||||
@@ -574,15 +574,15 @@ Please generate time config JSON.
|
||||
"reasoning": "Explanation of time config for this event"
|
||||
}}
|
||||
|
||||
字段说明：
|
||||
- total_simulation_hours (int): 模拟总时长，24-168小时，突发事件短、持续话题长
|
||||
- minutes_per_round (int): 每轮时长，30-120分钟，建议60分钟
|
||||
- agents_per_hour_min (int): 每小时最少激活Agent数（取值范围: 1-{max_agents_allowed}）
|
||||
- agents_per_hour_max (int): 每小时最多激活Agent数（取值范围: 1-{max_agents_allowed}）
|
||||
- peak_hours (int数组): 高峰时段，根据事件参与群体调整
|
||||
- off_peak_hours (int数组): 低谷时段，通常深夜凌晨
|
||||
- morning_hours (int数组): 早间时段
|
||||
- work_hours (int数组): 工作时段
|
||||
Field descriptions:
|
||||
- total_simulation_hours (int): Total simulation duration, 24-168 hours, shorter for breaking events, longer for ongoing topics
|
||||
- minutes_per_round (int): Minutes per round, 30-120 minutes, recommended 60 minutes
|
||||
- agents_per_hour_min (int): Minimum agents activated per hour (range: 1-{max_agents_allowed})
|
||||
- agents_per_hour_max (int): Maximum agents activated per hour (range: 1-{max_agents_allowed})
|
||||
- peak_hours (int array): Peak hours, adjust based on event participant group
|
||||
- off_peak_hours (int array): Off-peak hours, typically late night/early morning
|
||||
- morning_hours (int array): Morning hours
|
||||
- work_hours (int array): Work hours
|
||||
- reasoning (string): Brief explanation of why this config was chosen"""
|
||||
|
||||
system_prompt = "You are a social media simulation expert. Return pure JSON format. Time config must match the target user group's daily routine in the simulation scenario."
|
||||
@@ -679,27 +679,27 @@ Simulation requirements: {simulation_requirement}
|
||||
|
||||
{context_truncated}
|
||||
|
||||
## 可用实体类型及示例
|
||||
## Available Entity Types and Examples
|
||||
{type_info}
|
||||
|
||||
## 任务
|
||||
## Task
|
||||
Please generate event config JSON:
|
||||
- 提取热点话题关键词
|
||||
- 描述舆论发展方向
|
||||
- 设计初始帖子内容，**每个帖子必须指定 poster_type（发布者类型）**
|
||||
- Extract hot topic keywords
|
||||
- Describe the narrative direction of public opinion
|
||||
- Design initial post content, **each post must specify poster_type (publisher type)**
|
||||
|
||||
**重要**: poster_type 必须从上面的"可用实体类型"中选择，这样初始帖子才能分配给合适的 Agent 发布。
|
||||
例如：官方声明应由 Official/University 类型发布，新闻由 MediaOutlet 发布，学生观点由 Student 发布。
|
||||
**Important**: poster_type must be selected from the "Available Entity Types" above, so initial posts can be assigned to suitable Agents.
|
||||
For example: Official statements should be posted by Official/University types, news by MediaOutlet, student opinions by Student.
|
||||
|
||||
Return in JSON format (no markdown):
|
||||
{{
|
||||
"hot_topics": ["关键词1", "关键词2", ...],
|
||||
"narrative_direction": "<舆论发展方向描述>",
|
||||
"hot_topics": ["keyword1", "keyword2", ...],
|
||||
"narrative_direction": "<description of public opinion direction>",
|
||||
"initial_posts": [
|
||||
{{"content": "帖子内容", "poster_type": "实体类型（必须从可用类型中选择）"}},
|
||||
{{"content": "post content", "poster_type": "entity type (must be from available types)"}},
|
||||
...
|
||||
],
|
||||
"reasoning": "<简要说明>"
|
||||
"reasoning": "<brief explanation>"
|
||||
}}"""
|
||||
|
||||
system_prompt = "You are a public opinion analysis expert. Return pure JSON format. Note: poster_type must exactly match available entity types."
|
||||
@@ -834,33 +834,33 @@ Return in JSON format (no markdown):
|
||||
|
||||
Simulation requirements: {simulation_requirement}
|
||||
|
||||
## 实体列表
|
||||
## Entity List
|
||||
```json
|
||||
{json.dumps(entity_list, ensure_ascii=False, indent=2)}
|
||||
```
|
||||
|
||||
## 任务
|
||||
## Task
|
||||
Generate activity config for each entity, noting:
|
||||
- **Time must match target user group routine**: Below is a reference (UTC+8), please adjust based on simulation scenario
|
||||
- **官方机构**（University/GovernmentAgency）：活跃度低(0.1-0.3)，工作时间(9-17)活动，响应慢(60-240分钟)，影响力高(2.5-3.0)
|
||||
- **媒体**（MediaOutlet）：活跃度中(0.4-0.6)，全天活动(8-23)，响应快(5-30分钟)，影响力高(2.0-2.5)
|
||||
- **个人**（Student/Person/Alumni）：活跃度高(0.6-0.9)，主要晚间活动(18-23)，响应快(1-15分钟)，影响力低(0.8-1.2)
|
||||
- **公众人物/专家**：活跃度中(0.4-0.6)，影响力中高(1.5-2.0)
|
||||
- **Government agencies** (University/GovernmentAgency): Low activity (0.1-0.3), active during work hours (9-17), slow response (60-240 min), high influence (2.5-3.0)
|
||||
- **Media** (MediaOutlet): Medium activity (0.4-0.6), active all day (8-23), fast response (5-30 min), high influence (2.0-2.5)
|
||||
- **Individuals** (Student/Person/Alumni): High activity (0.6-0.9), mainly evening (18-23), fast response (1-15 min), low influence (0.8-1.2)
|
||||
- **Public figures/experts**: Medium activity (0.4-0.6), medium-high influence (1.5-2.0)
|
||||
|
||||
Return in JSON format (no markdown):
|
||||
{{
|
||||
"agent_configs": [
|
||||
{{
|
||||
"agent_id": <必须与输入一致>,
|
||||
"agent_id": <must match input>,
|
||||
"activity_level": <0.0-1.0>,
|
||||
"posts_per_hour": <发帖频率>,
|
||||
"comments_per_hour": <评论频率>,
|
||||
"active_hours": [<活跃小时列表，考虑中国人作息>],
|
||||
"response_delay_min": <最小响应延迟分钟>,
|
||||
"response_delay_max": <最大响应延迟分钟>,
|
||||
"sentiment_bias": <-1.0到1.0>,
|
||||
"posts_per_hour": <posting frequency>,
|
||||
"comments_per_hour": <commenting frequency>,
|
||||
"active_hours": [<list of active hours, consider target user routine>],
|
||||
"response_delay_min": <min response delay in minutes>,
|
||||
"response_delay_max": <max response delay in minutes>,
|
||||
"sentiment_bias": <-1.0 to 1.0>,
|
||||
"stance": "<supportive/opposing/neutral/observer>",
|
||||
"influence_weight": <影响力权重>
|
||||
"influence_weight": <influence weight>
|
||||
}},
|
||||
...
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user