better：重整配置，分离表达，聊天模式区分
重整配置文件路径，添加更多配置选项 分离了人设表达方式和学习到的表达方式 将聊天模式区分为normal focus和auto
This commit is contained in:
SengokuCola
126
src/individuality/not_using/offline_llm.py
Normal file
126
src/individuality/not_using/offline_llm.py
Normal file
@@ -0,0 +1,126 @@
|
||||
import asyncio
|
||||
import os
|
||||
import time
|
||||
from typing import Tuple, Union
|
||||
|
||||
import aiohttp
|
||||
import requests
|
||||
from src.common.logger import get_module_logger
|
||||
from rich.traceback import install
|
||||
|
||||
install(extra_lines=3)
|
||||
|
||||
logger = get_module_logger("offline_llm")
|
||||
|
||||
|
||||
class LLMRequestOff:
|
||||
def __init__(self, model_name="Pro/deepseek-ai/DeepSeek-V3", **kwargs):
|
||||
self.model_name = model_name
|
||||
self.params = kwargs
|
||||
self.api_key = os.getenv("SILICONFLOW_KEY")
|
||||
self.base_url = os.getenv("SILICONFLOW_BASE_URL")
|
||||
|
||||
if not self.api_key or not self.base_url:
|
||||
raise ValueError("环境变量未正确加载：SILICONFLOW_KEY 或 SILICONFLOW_BASE_URL 未设置")
|
||||
|
||||
# logger.info(f"API URL: {self.base_url}") # 使用 logger 记录 base_url
|
||||
|
||||
def generate_response(self, prompt: str) -> Union[str, Tuple[str, str]]:
|
||||
"""根据输入的提示生成模型的响应"""
|
||||
headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
|
||||
|
||||
# 构建请求体
|
||||
data = {
|
||||
"model": self.model_name,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"temperature": 0.4,
|
||||
**self.params,
|
||||
}
|
||||
|
||||
# 发送请求到完整的 chat/completions 端点
|
||||
api_url = f"{self.base_url.rstrip('/')}/chat/completions"
|
||||
logger.info(f"Request URL: {api_url}") # 记录请求的 URL
|
||||
|
||||
max_retries = 3
|
||||
base_wait_time = 15 # 基础等待时间（秒）
|
||||
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
response = requests.post(api_url, headers=headers, json=data)
|
||||
|
||||
if response.status_code == 429:
|
||||
wait_time = base_wait_time * (2**retry) # 指数退避
|
||||
logger.warning(f"遇到请求限制(429)，等待{wait_time}秒后重试...")
|
||||
time.sleep(wait_time)
|
||||
continue
|
||||
|
||||
response.raise_for_status() # 检查其他响应状态
|
||||
|
||||
result = response.json()
|
||||
if "choices" in result and len(result["choices"]) > 0:
|
||||
content = result["choices"][0]["message"]["content"]
|
||||
reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
|
||||
return content, reasoning_content
|
||||
return "没有返回结果", ""
|
||||
|
||||
except Exception as e:
|
||||
if retry < max_retries - 1: # 如果还有重试机会
|
||||
wait_time = base_wait_time * (2**retry)
|
||||
logger.error(f"[回复]请求失败，等待{wait_time}秒后重试... 错误: {str(e)}")
|
||||
time.sleep(wait_time)
|
||||
else:
|
||||
logger.error(f"请求失败: {str(e)}")
|
||||
return f"请求失败: {str(e)}", ""
|
||||
|
||||
logger.error("达到最大重试次数，请求仍然失败")
|
||||
return "达到最大重试次数，请求仍然失败", ""
|
||||
|
||||
async def generate_response_async(self, prompt: str) -> Union[str, Tuple[str, str]]:
|
||||
"""异步方式根据输入的提示生成模型的响应"""
|
||||
headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
|
||||
|
||||
# 构建请求体
|
||||
data = {
|
||||
"model": self.model_name,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"temperature": 0.5,
|
||||
**self.params,
|
||||
}
|
||||
|
||||
# 发送请求到完整的 chat/completions 端点
|
||||
api_url = f"{self.base_url.rstrip('/')}/chat/completions"
|
||||
logger.info(f"Request URL: {api_url}") # 记录请求的 URL
|
||||
|
||||
max_retries = 3
|
||||
base_wait_time = 15
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
async with session.post(api_url, headers=headers, json=data) as response:
|
||||
if response.status == 429:
|
||||
wait_time = base_wait_time * (2**retry) # 指数退避
|
||||
logger.warning(f"遇到请求限制(429)，等待{wait_time}秒后重试...")
|
||||
await asyncio.sleep(wait_time)
|
||||
continue
|
||||
|
||||
response.raise_for_status() # 检查其他响应状态
|
||||
|
||||
result = await response.json()
|
||||
if "choices" in result and len(result["choices"]) > 0:
|
||||
content = result["choices"][0]["message"]["content"]
|
||||
reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
|
||||
return content, reasoning_content
|
||||
return "没有返回结果", ""
|
||||
|
||||
except Exception as e:
|
||||
if retry < max_retries - 1: # 如果还有重试机会
|
||||
wait_time = base_wait_time * (2**retry)
|
||||
logger.error(f"[回复]请求失败，等待{wait_time}秒后重试... 错误: {str(e)}")
|
||||
await asyncio.sleep(wait_time)
|
||||
else:
|
||||
logger.error(f"请求失败: {str(e)}")
|
||||
return f"请求失败: {str(e)}", ""
|
||||
|
||||
logger.error("达到最大重试次数，请求仍然失败")
|
||||
return "达到最大重试次数，请求仍然失败", ""
|
||||
311
src/individuality/not_using/per_bf_gen.py
Normal file
311
src/individuality/not_using/per_bf_gen.py
Normal file
@@ -0,0 +1,311 @@
|
||||
from typing import Dict, List
|
||||
import json
|
||||
import os
|
||||
from dotenv import load_dotenv
|
||||
import sys
|
||||
import toml
|
||||
import random
|
||||
from tqdm import tqdm
|
||||
|
||||
# 添加项目根目录到 Python 路径
|
||||
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))
|
||||
sys.path.append(root_path)
|
||||
|
||||
# 加载配置文件
|
||||
config_path = os.path.join(root_path, "config", "bot_config.toml")
|
||||
with open(config_path, "r", encoding="utf-8") as f:
|
||||
config = toml.load(f)
|
||||
|
||||
# 现在可以导入src模块
|
||||
from individuality.not_using.scene import get_scene_by_factor, PERSONALITY_SCENES # noqa E402
|
||||
from individuality.not_using.questionnaire import FACTOR_DESCRIPTIONS # noqa E402
|
||||
from individuality.not_using.offline_llm import LLMRequestOff # noqa E402
|
||||
|
||||
# 加载环境变量
|
||||
env_path = os.path.join(root_path, ".env")
|
||||
if os.path.exists(env_path):
|
||||
print(f"从 {env_path} 加载环境变量")
|
||||
load_dotenv(env_path)
|
||||
else:
|
||||
print(f"未找到环境变量文件: {env_path}")
|
||||
print("将使用默认配置")
|
||||
|
||||
|
||||
def adapt_scene(scene: str) -> str:
|
||||
personality_core = config["personality"]["personality_core"]
|
||||
personality_sides = config["personality"]["personality_sides"]
|
||||
personality_side = random.choice(personality_sides)
|
||||
identity_details = config["identity"]["identity_detail"]
|
||||
identity_detail = random.choice(identity_details)
|
||||
|
||||
"""
|
||||
根据config中的属性，改编场景使其更适合当前角色
|
||||
|
||||
Args:
|
||||
scene: 原始场景描述
|
||||
|
||||
Returns:
|
||||
str: 改编后的场景描述
|
||||
"""
|
||||
try:
|
||||
prompt = f"""
|
||||
这是一个参与人格测评的角色形象:
|
||||
- 昵称: {config["bot"]["nickname"]}
|
||||
- 性别: {config["identity"]["gender"]}
|
||||
- 年龄: {config["identity"]["age"]}岁
|
||||
- 外貌: {config["identity"]["appearance"]}
|
||||
- 性格核心: {personality_core}
|
||||
- 性格侧面: {personality_side}
|
||||
- 身份细节: {identity_detail}
|
||||
|
||||
请根据上述形象，改编以下场景，在测评中，用户将根据该场景给出上述角色形象的反应:
|
||||
{scene}
|
||||
保持场景的本质不变，但最好贴近生活且具体，并且让它更适合这个角色。
|
||||
改编后的场景应该自然、连贯，并考虑角色的年龄、身份和性格特点。只返回改编后的场景描述，不要包含其他说明。注意{config["bot"]["nickname"]}是面对这个场景的人，而不是场景的其他人。场景中不会有其描述，
|
||||
现在，请你给出改编后的场景描述
|
||||
"""
|
||||
|
||||
llm = LLMRequestOff(model_name=config["model"]["llm_normal"]["name"])
|
||||
adapted_scene, _ = llm.generate_response(prompt)
|
||||
|
||||
# 检查返回的场景是否为空或错误信息
|
||||
if not adapted_scene or "错误" in adapted_scene or "失败" in adapted_scene:
|
||||
print("场景改编失败，将使用原始场景")
|
||||
return scene
|
||||
|
||||
return adapted_scene
|
||||
except Exception as e:
|
||||
print(f"场景改编过程出错：{str(e)}，将使用原始场景")
|
||||
return scene
|
||||
|
||||
|
||||
class PersonalityEvaluatorDirect:
|
||||
def __init__(self):
|
||||
self.personality_traits = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
|
||||
self.scenarios = []
|
||||
self.final_scores = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
|
||||
self.dimension_counts = {trait: 0 for trait in self.final_scores.keys()}
|
||||
|
||||
# 为每个人格特质获取对应的场景
|
||||
for trait in PERSONALITY_SCENES:
|
||||
scenes = get_scene_by_factor(trait)
|
||||
if not scenes:
|
||||
continue
|
||||
|
||||
# 从每个维度选择3个场景
|
||||
import random
|
||||
|
||||
scene_keys = list(scenes.keys())
|
||||
selected_scenes = random.sample(scene_keys, min(3, len(scene_keys)))
|
||||
|
||||
for scene_key in selected_scenes:
|
||||
scene = scenes[scene_key]
|
||||
|
||||
# 为每个场景添加评估维度
|
||||
# 主维度是当前特质，次维度随机选择一个其他特质
|
||||
other_traits = [t for t in PERSONALITY_SCENES if t != trait]
|
||||
secondary_trait = random.choice(other_traits)
|
||||
|
||||
self.scenarios.append(
|
||||
{"场景": scene["scenario"], "评估维度": [trait, secondary_trait], "场景编号": scene_key}
|
||||
)
|
||||
|
||||
self.llm = LLMRequestOff()
|
||||
|
||||
def evaluate_response(self, scenario: str, response: str, dimensions: List[str]) -> Dict[str, float]:
|
||||
"""
|
||||
使用 DeepSeek AI 评估用户对特定场景的反应
|
||||
"""
|
||||
# 构建维度描述
|
||||
dimension_descriptions = []
|
||||
for dim in dimensions:
|
||||
desc = FACTOR_DESCRIPTIONS.get(dim, "")
|
||||
if desc:
|
||||
dimension_descriptions.append(f"- {dim}：{desc}")
|
||||
|
||||
dimensions_text = "\n".join(dimension_descriptions)
|
||||
|
||||
prompt = f"""请根据以下场景和用户描述，评估用户在大五人格模型中的相关维度得分（1-6分）。
|
||||
|
||||
场景描述：
|
||||
{scenario}
|
||||
|
||||
用户回应：
|
||||
{response}
|
||||
|
||||
需要评估的维度说明：
|
||||
{dimensions_text}
|
||||
|
||||
请按照以下格式输出评估结果（仅输出JSON格式）：
|
||||
{{
|
||||
"{dimensions[0]}": 分数,
|
||||
"{dimensions[1]}": 分数
|
||||
}}
|
||||
|
||||
评分标准：
|
||||
1 = 非常不符合该维度特征
|
||||
2 = 比较不符合该维度特征
|
||||
3 = 有点不符合该维度特征
|
||||
4 = 有点符合该维度特征
|
||||
5 = 比较符合该维度特征
|
||||
6 = 非常符合该维度特征
|
||||
|
||||
请根据用户的回应，结合场景和维度说明进行评分。确保分数在1-6之间，并给出合理的评估。"""
|
||||
|
||||
try:
|
||||
ai_response, _ = self.llm.generate_response(prompt)
|
||||
# 尝试从AI响应中提取JSON部分
|
||||
start_idx = ai_response.find("{")
|
||||
end_idx = ai_response.rfind("}") + 1
|
||||
if start_idx != -1 and end_idx != 0:
|
||||
json_str = ai_response[start_idx:end_idx]
|
||||
scores = json.loads(json_str)
|
||||
# 确保所有分数在1-6之间
|
||||
return {k: max(1, min(6, float(v))) for k, v in scores.items()}
|
||||
else:
|
||||
print("AI响应格式不正确，使用默认评分")
|
||||
return {dim: 3.5 for dim in dimensions}
|
||||
except Exception as e:
|
||||
print(f"评估过程出错：{str(e)}")
|
||||
return {dim: 3.5 for dim in dimensions}
|
||||
|
||||
def run_evaluation(self):
|
||||
"""
|
||||
运行整个评估过程
|
||||
"""
|
||||
print(f"欢迎使用{config['bot']['nickname']}形象创建程序！")
|
||||
print("接下来，将给您呈现一系列有关您bot的场景（共15个）。")
|
||||
print("请想象您的bot在以下场景下会做什么，并描述您的bot的反应。")
|
||||
print("每个场景都会进行不同方面的评估。")
|
||||
print("\n角色基本信息：")
|
||||
print(f"- 昵称：{config['bot']['nickname']}")
|
||||
print(f"- 性格核心：{config['personality']['personality_core']}")
|
||||
print(f"- 性格侧面：{config['personality']['personality_sides']}")
|
||||
print(f"- 身份细节：{config['identity']['identity_detail']}")
|
||||
print("\n准备好了吗？按回车键开始...")
|
||||
input()
|
||||
|
||||
total_scenarios = len(self.scenarios)
|
||||
progress_bar = tqdm(
|
||||
total=total_scenarios,
|
||||
desc="场景进度",
|
||||
ncols=100,
|
||||
bar_format="{l_bar}{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}]",
|
||||
)
|
||||
|
||||
for _i, scenario_data in enumerate(self.scenarios, 1):
|
||||
# print(f"\n{'-' * 20} 场景 {i}/{total_scenarios} - {scenario_data['场景编号']} {'-' * 20}")
|
||||
|
||||
# 改编场景，使其更适合当前角色
|
||||
print(f"{config['bot']['nickname']}祈祷中...")
|
||||
adapted_scene = adapt_scene(scenario_data["场景"])
|
||||
scenario_data["改编场景"] = adapted_scene
|
||||
|
||||
print(adapted_scene)
|
||||
print(f"\n请描述{config['bot']['nickname']}在这种情况下会如何反应：")
|
||||
response = input().strip()
|
||||
|
||||
if not response:
|
||||
print("反应描述不能为空！")
|
||||
continue
|
||||
|
||||
print("\n正在评估您的描述...")
|
||||
scores = self.evaluate_response(adapted_scene, response, scenario_data["评估维度"])
|
||||
|
||||
# 更新最终分数
|
||||
for dimension, score in scores.items():
|
||||
self.final_scores[dimension] += score
|
||||
self.dimension_counts[dimension] += 1
|
||||
|
||||
print("\n当前评估结果：")
|
||||
print("-" * 30)
|
||||
for dimension, score in scores.items():
|
||||
print(f"{dimension}: {score}/6")
|
||||
|
||||
# 更新进度条
|
||||
progress_bar.update(1)
|
||||
|
||||
# if i < total_scenarios:
|
||||
# print("\n按回车键继续下一个场景...")
|
||||
# input()
|
||||
|
||||
progress_bar.close()
|
||||
|
||||
# 计算平均分
|
||||
for dimension in self.final_scores:
|
||||
if self.dimension_counts[dimension] > 0:
|
||||
self.final_scores[dimension] = round(self.final_scores[dimension] / self.dimension_counts[dimension], 2)
|
||||
|
||||
print("\n" + "=" * 50)
|
||||
print(f" {config['bot']['nickname']}的人格特征评估结果 ".center(50))
|
||||
print("=" * 50)
|
||||
for trait, score in self.final_scores.items():
|
||||
print(f"{trait}: {score}/6".ljust(20) + f"测试场景数：{self.dimension_counts[trait]}".rjust(30))
|
||||
print("=" * 50)
|
||||
|
||||
# 返回评估结果
|
||||
return self.get_result()
|
||||
|
||||
def get_result(self):
|
||||
"""
|
||||
获取评估结果
|
||||
"""
|
||||
return {
|
||||
"final_scores": self.final_scores,
|
||||
"dimension_counts": self.dimension_counts,
|
||||
"scenarios": self.scenarios,
|
||||
"bot_info": {
|
||||
"nickname": config["bot"]["nickname"],
|
||||
"gender": config["identity"]["gender"],
|
||||
"age": config["identity"]["age"],
|
||||
"height": config["identity"]["height"],
|
||||
"weight": config["identity"]["weight"],
|
||||
"appearance": config["identity"]["appearance"],
|
||||
"personality_core": config["personality"]["personality_core"],
|
||||
"personality_sides": config["personality"]["personality_sides"],
|
||||
"identity_detail": config["identity"]["identity_detail"],
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def main():
|
||||
evaluator = PersonalityEvaluatorDirect()
|
||||
result = evaluator.run_evaluation()
|
||||
|
||||
# 准备简化的结果数据
|
||||
simplified_result = {
|
||||
"openness": round(result["final_scores"]["开放性"] / 6, 1), # 转换为0-1范围
|
||||
"conscientiousness": round(result["final_scores"]["严谨性"] / 6, 1),
|
||||
"extraversion": round(result["final_scores"]["外向性"] / 6, 1),
|
||||
"agreeableness": round(result["final_scores"]["宜人性"] / 6, 1),
|
||||
"neuroticism": round(result["final_scores"]["神经质"] / 6, 1),
|
||||
"bot_nickname": config["bot"]["nickname"],
|
||||
}
|
||||
|
||||
# 确保目录存在
|
||||
save_dir = os.path.join(root_path, "data", "personality")
|
||||
os.makedirs(save_dir, exist_ok=True)
|
||||
|
||||
# 创建文件名，替换可能的非法字符
|
||||
bot_name = config["bot"]["nickname"]
|
||||
# 替换Windows文件名中不允许的字符
|
||||
for char in ["\\", "/", ":", "*", "?", '"', "<", ">", "|"]:
|
||||
bot_name = bot_name.replace(char, "_")
|
||||
|
||||
file_name = f"{bot_name}_personality.per"
|
||||
save_path = os.path.join(save_dir, file_name)
|
||||
|
||||
# 保存简化的结果
|
||||
with open(save_path, "w", encoding="utf-8") as f:
|
||||
json.dump(simplified_result, f, ensure_ascii=False, indent=4)
|
||||
|
||||
print(f"\n结果已保存到 {save_path}")
|
||||
|
||||
# 同时保存完整结果到results目录
|
||||
os.makedirs("results", exist_ok=True)
|
||||
with open("results/personality_result.json", "w", encoding="utf-8") as f:
|
||||
json.dump(result, f, ensure_ascii=False, indent=2)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
142
src/individuality/not_using/questionnaire.py
Normal file
142
src/individuality/not_using/questionnaire.py
Normal file
@@ -0,0 +1,142 @@
|
||||
# 人格测试问卷题目
|
||||
# 王孟成, 戴晓阳, & 姚树桥. (2011).
|
||||
# 中国大五人格问卷的初步编制Ⅲ:简式版的制定及信效度检验. 中国临床心理学杂志, 19(04), Article 04.
|
||||
|
||||
# 王孟成, 戴晓阳, & 姚树桥. (2010).
|
||||
# 中国大五人格问卷的初步编制Ⅰ:理论框架与信度分析. 中国临床心理学杂志, 18(05), Article 05.
|
||||
|
||||
PERSONALITY_QUESTIONS = [
|
||||
# 神经质维度 (F1)
|
||||
{"id": 1, "content": "我常担心有什么不好的事情要发生", "factor": "神经质", "reverse_scoring": False},
|
||||
{"id": 2, "content": "我常感到害怕", "factor": "神经质", "reverse_scoring": False},
|
||||
{"id": 3, "content": "有时我觉得自己一无是处", "factor": "神经质", "reverse_scoring": False},
|
||||
{"id": 4, "content": "我很少感到忧郁或沮丧", "factor": "神经质", "reverse_scoring": True},
|
||||
{"id": 5, "content": "别人一句漫不经心的话，我常会联系在自己身上", "factor": "神经质", "reverse_scoring": False},
|
||||
{"id": 6, "content": "在面对压力时，我有种快要崩溃的感觉", "factor": "神经质", "reverse_scoring": False},
|
||||
{"id": 7, "content": "我常担忧一些无关紧要的事情", "factor": "神经质", "reverse_scoring": False},
|
||||
{"id": 8, "content": "我常常感到内心不踏实", "factor": "神经质", "reverse_scoring": False},
|
||||
# 严谨性维度 (F2)
|
||||
{"id": 9, "content": "在工作上，我常只求能应付过去便可", "factor": "严谨性", "reverse_scoring": True},
|
||||
{"id": 10, "content": "一旦确定了目标，我会坚持努力地实现它", "factor": "严谨性", "reverse_scoring": False},
|
||||
{"id": 11, "content": "我常常是仔细考虑之后才做出决定", "factor": "严谨性", "reverse_scoring": False},
|
||||
{"id": 12, "content": "别人认为我是个慎重的人", "factor": "严谨性", "reverse_scoring": False},
|
||||
{"id": 13, "content": "做事讲究逻辑和条理是我的一个特点", "factor": "严谨性", "reverse_scoring": False},
|
||||
{"id": 14, "content": "我喜欢一开头就把事情计划好", "factor": "严谨性", "reverse_scoring": False},
|
||||
{"id": 15, "content": "我工作或学习很勤奋", "factor": "严谨性", "reverse_scoring": False},
|
||||
{"id": 16, "content": "我是个倾尽全力做事的人", "factor": "严谨性", "reverse_scoring": False},
|
||||
# 宜人性维度 (F3)
|
||||
{
|
||||
"id": 17,
|
||||
"content": "尽管人类社会存在着一些阴暗的东西（如战争、罪恶、欺诈），我仍然相信人性总的来说是善良的",
|
||||
"factor": "宜人性",
|
||||
"reverse_scoring": False,
|
||||
},
|
||||
{"id": 18, "content": "我觉得大部分人基本上是心怀善意的", "factor": "宜人性", "reverse_scoring": False},
|
||||
{"id": 19, "content": "虽然社会上有骗子，但我觉得大部分人还是可信的", "factor": "宜人性", "reverse_scoring": False},
|
||||
{"id": 20, "content": "我不太关心别人是否受到不公正的待遇", "factor": "宜人性", "reverse_scoring": True},
|
||||
{"id": 21, "content": "我时常觉得别人的痛苦与我无关", "factor": "宜人性", "reverse_scoring": True},
|
||||
{"id": 22, "content": "我常为那些遭遇不幸的人感到难过", "factor": "宜人性", "reverse_scoring": False},
|
||||
{"id": 23, "content": "我是那种只照顾好自己，不替别人担忧的人", "factor": "宜人性", "reverse_scoring": True},
|
||||
{"id": 24, "content": "当别人向我诉说不幸时，我常感到难过", "factor": "宜人性", "reverse_scoring": False},
|
||||
# 开放性维度 (F4)
|
||||
{"id": 25, "content": "我的想象力相当丰富", "factor": "开放性", "reverse_scoring": False},
|
||||
{"id": 26, "content": "我头脑中经常充满生动的画面", "factor": "开放性", "reverse_scoring": False},
|
||||
{"id": 27, "content": "我对许多事情有着很强的好奇心", "factor": "开放性", "reverse_scoring": False},
|
||||
{"id": 28, "content": "我喜欢冒险", "factor": "开放性", "reverse_scoring": False},
|
||||
{"id": 29, "content": "我是个勇于冒险，突破常规的人", "factor": "开放性", "reverse_scoring": False},
|
||||
{"id": 30, "content": "我身上具有别人没有的冒险精神", "factor": "开放性", "reverse_scoring": False},
|
||||
{
|
||||
"id": 31,
|
||||
"content": "我渴望学习一些新东西，即使它们与我的日常生活无关",
|
||||
"factor": "开放性",
|
||||
"reverse_scoring": False,
|
||||
},
|
||||
{
|
||||
"id": 32,
|
||||
"content": "我很愿意也很容易接受那些新事物、新观点、新想法",
|
||||
"factor": "开放性",
|
||||
"reverse_scoring": False,
|
||||
},
|
||||
# 外向性维度 (F5)
|
||||
{"id": 33, "content": "我喜欢参加社交与娱乐聚会", "factor": "外向性", "reverse_scoring": False},
|
||||
{"id": 34, "content": "我对人多的聚会感到乏味", "factor": "外向性", "reverse_scoring": True},
|
||||
{"id": 35, "content": "我尽量避免参加人多的聚会和嘈杂的环境", "factor": "外向性", "reverse_scoring": True},
|
||||
{"id": 36, "content": "在热闹的聚会上，我常常表现主动并尽情玩耍", "factor": "外向性", "reverse_scoring": False},
|
||||
{"id": 37, "content": "有我在的场合一般不会冷场", "factor": "外向性", "reverse_scoring": False},
|
||||
{"id": 38, "content": "我希望成为领导者而不是被领导者", "factor": "外向性", "reverse_scoring": False},
|
||||
{"id": 39, "content": "在一个团体中，我希望处于领导地位", "factor": "外向性", "reverse_scoring": False},
|
||||
{"id": 40, "content": "别人多认为我是一个热情和友好的人", "factor": "外向性", "reverse_scoring": False},
|
||||
]
|
||||
|
||||
# 因子维度说明
|
||||
FACTOR_DESCRIPTIONS = {
|
||||
"外向性": {
|
||||
"description": "反映个体神经系统的强弱和动力特征。外向性主要表现为个体在人际交往和社交活动中的倾向性，"
|
||||
"包括对社交活动的兴趣、"
|
||||
"对人群的态度、社交互动中的主动程度以及在群体中的影响力。高分者倾向于积极参与社交活动，乐于与人交往，善于表达自我，"
|
||||
"并往往在群体中发挥领导作用；低分者则倾向于独处，不喜欢热闹的社交场合，表现出内向、安静的特征。",
|
||||
"trait_words": ["热情", "活力", "社交", "主动"],
|
||||
"subfactors": {
|
||||
"合群性": "个体愿意与他人聚在一起，即接近人群的倾向；高分表现乐群、好交际，低分表现封闭、独处",
|
||||
"热情": "个体对待别人时所表现出的态度；高分表现热情好客，低分表现冷淡",
|
||||
"支配性": "个体喜欢指使、操纵他人，倾向于领导别人的特点；高分表现好强、发号施令，低分表现顺从、低调",
|
||||
"活跃": "个体精力充沛，活跃、主动性等特点；高分表现活跃，低分表现安静",
|
||||
},
|
||||
},
|
||||
"神经质": {
|
||||
"description": "反映个体情绪的状态和体验内心苦恼的倾向性。这个维度主要关注个体在面对压力、"
|
||||
"挫折和日常生活挑战时的情绪稳定性和适应能力。它包含了对焦虑、抑郁、愤怒等负面情绪的敏感程度，"
|
||||
"以及个体对这些情绪的调节和控制能力。高分者容易体验负面情绪，对压力较为敏感，情绪波动较大；"
|
||||
"低分者则表现出较强的情绪稳定性，能够较好地应对压力和挫折。",
|
||||
"trait_words": ["稳定", "沉着", "从容", "坚韧"],
|
||||
"subfactors": {
|
||||
"焦虑": "个体体验焦虑感的个体差异；高分表现坐立不安，低分表现平静",
|
||||
"抑郁": "个体体验抑郁情感的个体差异；高分表现郁郁寡欢，低分表现平静",
|
||||
"敏感多疑": "个体常常关注自己的内心活动，行为和过于意识人对自己的看法、评价；高分表现敏感多疑，"
|
||||
"低分表现淡定、自信",
|
||||
"脆弱性": "个体在危机或困难面前无力、脆弱的特点；高分表现无能、易受伤、逃避，低分表现坚强",
|
||||
"愤怒-敌意": "个体准备体验愤怒，及相关情绪的状态；高分表现暴躁易怒，低分表现平静",
|
||||
},
|
||||
},
|
||||
"严谨性": {
|
||||
"description": "反映个体在目标导向行为上的组织、坚持和动机特征。这个维度体现了个体在工作、"
|
||||
"学习等目标性活动中的自我约束和行为管理能力。它涉及到个体的责任感、自律性、计划性、条理性以及完成任务的态度。"
|
||||
"高分者往往表现出强烈的责任心、良好的组织能力、谨慎的决策风格和持续的努力精神；低分者则可能表现出随意性强、"
|
||||
"缺乏规划、做事马虎或易放弃的特点。",
|
||||
"trait_words": ["负责", "自律", "条理", "勤奋"],
|
||||
"subfactors": {
|
||||
"责任心": "个体对待任务和他人认真负责，以及对自己承诺的信守；高分表现有责任心、负责任，"
|
||||
"低分表现推卸责任、逃避处罚",
|
||||
"自我控制": "个体约束自己的能力，及自始至终的坚持性；高分表现自制、有毅力，低分表现冲动、无毅力",
|
||||
"审慎性": "个体在采取具体行动前的心理状态；高分表现谨慎、小心，低分表现鲁莽、草率",
|
||||
"条理性": "个体处理事务和工作的秩序，条理和逻辑性；高分表现整洁、有秩序，低分表现混乱、遗漏",
|
||||
"勤奋": "个体工作和学习的努力程度及为达到目标而表现出的进取精神；高分表现勤奋、刻苦，低分表现懒散",
|
||||
},
|
||||
},
|
||||
"开放性": {
|
||||
"description": "反映个体对新异事物、新观念和新经验的接受程度，以及在思维和行为方面的创新倾向。"
|
||||
"这个维度体现了个体在认知和体验方面的广度、深度和灵活性。它包括对艺术的欣赏能力、对知识的求知欲、想象力的丰富程度，"
|
||||
"以及对冒险和创新的态度。高分者往往具有丰富的想象力、广泛的兴趣、开放的思维方式和创新的倾向；低分者则倾向于保守、"
|
||||
"传统，喜欢熟悉和常规的事物。",
|
||||
"trait_words": ["创新", "好奇", "艺术", "冒险"],
|
||||
"subfactors": {
|
||||
"幻想": "个体富于幻想和想象的水平；高分表现想象力丰富，低分表现想象力匮乏",
|
||||
"审美": "个体对于艺术和美的敏感与热爱程度；高分表现富有艺术气息，低分表现一般对艺术不敏感",
|
||||
"好奇心": "个体对未知事物的态度；高分表现兴趣广泛、好奇心浓，低分表现兴趣少、无好奇心",
|
||||
"冒险精神": "个体愿意尝试有风险活动的个体差异；高分表现好冒险，低分表现保守",
|
||||
"价值观念": "个体对新事物、新观念、怪异想法的态度；高分表现开放、坦然接受新事物，低分则相反",
|
||||
},
|
||||
},
|
||||
"宜人性": {
|
||||
"description": "反映个体在人际关系中的亲和倾向，体现了对他人的关心、同情和合作意愿。"
|
||||
"这个维度主要关注个体与他人互动时的态度和行为特征，包括对他人的信任程度、同理心水平、"
|
||||
"助人意愿以及在人际冲突中的处理方式。高分者通常表现出友善、富有同情心、乐于助人的特质，善于与他人建立和谐关系；"
|
||||
"低分者则可能表现出较少的人际关注，在社交互动中更注重自身利益，较少考虑他人感受。",
|
||||
"trait_words": ["友善", "同理", "信任", "合作"],
|
||||
"subfactors": {
|
||||
"信任": "个体对他人和/或他人言论的相信程度；高分表现信任他人，低分表现怀疑",
|
||||
"体贴": "个体对别人的兴趣和需要的关注程度；高分表现体贴、温存，低分表现冷漠、不在乎",
|
||||
"同情": "个体对处于不利地位的人或物的态度；高分表现富有同情心，低分表现冷漠",
|
||||
},
|
||||
},
|
||||
}
|
||||
43
src/individuality/not_using/scene.py
Normal file
43
src/individuality/not_using/scene.py
Normal file
@@ -0,0 +1,43 @@
|
||||
import json
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
|
||||
def load_scenes() -> dict[str, Any]:
|
||||
"""
|
||||
从JSON文件加载场景数据
|
||||
|
||||
Returns:
|
||||
Dict: 包含所有场景的字典
|
||||
"""
|
||||
current_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
json_path = os.path.join(current_dir, "template_scene.json")
|
||||
|
||||
with open(json_path, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
PERSONALITY_SCENES = load_scenes()
|
||||
|
||||
|
||||
def get_scene_by_factor(factor: str) -> dict | None:
|
||||
"""
|
||||
根据人格因子获取对应的情景测试
|
||||
|
||||
Args:
|
||||
factor (str): 人格因子名称
|
||||
|
||||
Returns:
|
||||
dict: 包含情景描述的字典
|
||||
"""
|
||||
return PERSONALITY_SCENES.get(factor, None)
|
||||
|
||||
|
||||
def get_all_scenes() -> dict:
|
||||
"""
|
||||
获取所有情景测试
|
||||
|
||||
Returns:
|
||||
Dict: 所有情景测试的字典
|
||||
"""
|
||||
return PERSONALITY_SCENES
|
||||
Reference in New Issue
Block a user