使用Python实现深度学习模型：智能旅游路线规划

pip install numpy pandas matplotlib tensorflow keras

import pandas as pd

# 读取景点数据
data = pd.read_csv('tourist_spots.csv')

# 查看数据结构
print(data.head())

import numpy as np

def haversine(lat1, lon1, lat2, lon2):
    R = 6371  # 地球半径，单位为公里
    dlat = np.radians(lat2 - lat1)
    dlon = np.radians(lon2 - lon1)
    a = np.sin(dlat / 2) ** 2 + np.cos(np.radians(lat1)) * np.cos(np.radians(lat2)) * np.sin(dlon / 2) ** 2
    c = 2 * np.arctan2(np.sqrt(a), np.sqrt(1 - a))
    distance = R * c
    return distance

# 计算距离矩阵
num_spots = len(data)
distance_matrix = np.zeros((num_spots, num_spots))

for i in range(num_spots):
    for j in range(num_spots):
        distance_matrix[i, j] = haversine(data['latitude'][i], data['longitude'][i], data['latitude'][j], data['longitude'][j])

# 打印距离矩阵
print(distance_matrix)

from sklearn.model_selection import train_test_split

# 假设我们有历史旅游路线数据
routes = pd.read_csv('historical_routes.csv')
X = routes[['start_spot', 'end_spot', 'time_of_day']]
y = routes['travel_time']

# 数据分割
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

def build_model():
    model = Sequential([
        Dense(64, activation='relu', input_shape=(3,)),
        Dense(32, activation='relu'),
        Dense(1)
    ])

    model.compile(optimizer='adam', loss='mse', metrics=['mae'])
    return model

model = build_model()
model.summary()

# 训练模型
model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2)

# 保存模型
model.save('route_planning_model.h5')

from tensorflow.keras.models import load_model

# 加载模型
model = load_model('route_planning_model.h5')

def predict_travel_time(start_spot, end_spot, time_of_day):
    input_data = np.array([[start_spot, end_spot, time_of_day]])
    travel_time = model.predict(input_data)
    return travel_time[0][0]

# 示例：预测从景点1到景点2在上午10点的旅行时间
travel_time = predict_travel_time(1, 2, 10)
print(f'预计旅行时间：{travel_time}分钟')

import matplotlib.pyplot as plt

def plot_route(route):
    latitudes = [data['latitude'][spot] for spot in route]
    longitudes = [data['longitude'][spot] for spot in route]

    plt.figure(figsize=(10, 6))
    plt.plot(longitudes, latitudes, 'bo-', markersize=10)
    for i, spot in enumerate(route):
        plt.text(longitudes[i], latitudes[i], data['name'][spot], fontsize=12)
    plt.title('Tourist Route')
    plt.xlabel('Longitude')
    plt.ylabel('Latitude')
    plt.show()

# 示例：绘制从景点1到景点2的路线
plot_route([1, 2])

def is_open(spot, time_of_day):
    opening_hours = data['opening_hours'][spot]
    open_time, close_time = map(int, opening_hours.split('-'))
    return open_time <= time_of_day <= close_time

# 示例：检查景点1在上午10点是否开放
print(is_open(1, 10))

def calculate_total_cost(route):
    total_cost = sum([data['ticket_price'][spot] for spot in route])
    return total_cost

# 示例：计算从景点1到景点2的总门票价格
total_cost = calculate_total_cost([1, 2])
print(f'总门票价格：{total_cost}元')