锦中人工智能助手

# 示例代码：基于协同过滤的简单推荐系统

import numpy as np

# 模拟用户-物品评分矩阵（行代表用户，列代表物品）

ratings = np.array([

[5, 3, 0, 1],

[4, 0, 0, 0],

[0, 1, 2, 4],

[0, 0, 3, 4],

[2, 3, 5, 0]

])

# 计算相似度（余弦相似度）

def cosine_similarity(a, b):

return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# 为每个用户计算与其他用户的相似度

user_similarities = np.zeros((ratings.shape[0], ratings.shape[0]))

for i in range(ratings.shape[0]):

for j in range(ratings.shape[0]):

user_similarities[i, j] = cosine_similarity(ratings[i], ratings[j])

# 为每个用户预测未评分的物品分数

def predict_rating(user_id, item_id, ratings, user_similarities):

similar_users = np.argsort(user_similarities[user_id])[::-1][1:] # 排除自己

weighted_sum = 0

total_weight = 0

for sim_user in similar_users:

if ratings[sim_user, item_id] != 0:

weighted_sum += user_similarities[user_id, sim_user] * ratings[sim_user, item_id]

total_weight += user_similarities[user_id, sim_user]

if total_weight == 0:

return 0

return weighted_sum / total_weight

# 预测用户1对物品3的评分

predicted_rating = predict_rating(0, 2, ratings, user_similarities)

print(f"用户1对物品3的预测评分是：{predicted_rating:.2f}")

# Rasa配置文件示例（domain.yml）

intents:

- greet

- goodbye

- ask_course_info

- ask_schedule

entities:

- course_name

- day_of_week

responses:

utter_greet:

- text: "你好！我是校园智能助手，有什么可以帮助你的吗？"

utter_goodbye:

- text: "再见！祝你学习顺利！"

utter_course_info:

- text: "你问的是关于 {course_name} 的信息吗？"

utter_schedule:

- text: "你想知道 {day_of_week} 的课程安排吗？"

actions:

- action_default_fallback

# Rasa故事文件示例（stories.md）

## 基本问候

* greet

- utter_greet

## 询问课程信息

* ask_course_info{"course_name": "人工智能"}

- utter_course_info

## 询问课程表

* ask_schedule{"day_of_week": "星期一"}

- utter_schedule