From 1e8350963dc4dd790056f5053778215b8f4e20fe Mon Sep 17 00:00:00 2001
From: zeyu <zeyu@unifisoftware.com>
Date: Mon, 20 Apr 2020 20:09:42 -0700
Subject: [PATCH] initial commit
---
.DS_Store | Bin 0 -> 6148 bytes
.ipynb_checkpoints/Untitled-checkpoint.ipynb | 391 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Readme.txt | 3 +++
__MACOSX/._project2_greedy_upload | Bin 0 -> 220 bytes
__MACOSX/project2_greedy_upload/._.DS_Store | Bin 0 -> 120 bytes
__MACOSX/project2_greedy_upload/._Readme.txt | Bin 0 -> 484 bytes
__MACOSX/project2_greedy_upload/._data_train.xlsx | Bin 0 -> 334 bytes
__MACOSX/project2_greedy_upload/._project2_main.py | Bin 0 -> 176 bytes
__MACOSX/project2_greedy_upload/._票务对话机器人项目说明.pdf | Bin 0 -> 343 bytes
data_train.xlsx | Bin 0 -> 17277 bytes
project2_main.py | 272 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
stopword.txt | 13 +++++++++++++
12 files changed, 679 insertions(+)
create mode 100644 .DS_Store
create mode 100644 .ipynb_checkpoints/Untitled-checkpoint.ipynb
create mode 100644 Readme.txt
create mode 100755 __MACOSX/._project2_greedy_upload
create mode 100644 __MACOSX/project2_greedy_upload/._.DS_Store
create mode 100644 __MACOSX/project2_greedy_upload/._Readme.txt
create mode 100644 __MACOSX/project2_greedy_upload/._data_train.xlsx
create mode 100644 __MACOSX/project2_greedy_upload/._project2_main.py
create mode 100644 __MACOSX/project2_greedy_upload/._票务对话机器人项目说明.pdf
create mode 100644 data_train.xlsx
create mode 100644 project2_main.py
create mode 100644 stopword.txt
diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000..0003bba
Binary files /dev/null and b/.DS_Store differ
diff --git a/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/.ipynb_checkpoints/Untitled-checkpoint.ipynb
new file mode 100644
index 0000000..a749903
--- /dev/null
+++ b/.ipynb_checkpoints/Untitled-checkpoint.ipynb
@@ -0,0 +1,391 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/zeyusu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+ " _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
+ "/Users/zeyusu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+ " _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
+ "/Users/zeyusu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+ " _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
+ "/Users/zeyusu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+ " _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
+ "/Users/zeyusu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+ " _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
+ "/Users/zeyusu/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+ " np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
+ ]
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "import fool\n",
+ "import time\n",
+ "import re\n",
+ "import random\n",
+ "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+ "from sklearn.linear_model import LogisticRegression"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "stopwords = {}\n",
+ "with open(r'stopword.txt', 'r', encoding='utf-8') as fr:\n",
+ " for word in fr:\n",
+ " stopwords[word.strip()] = 0"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 119,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "class CLF_MODEL:\n",
+ " # 类目标：该类将所有模型训练、预测、数据预处理、意图识别的函数包括其中\n",
+ "\n",
+ " # 初始化模块\n",
+ " def __init__(self):\n",
+ " self.model = \"\" # 成员变量，用于存储模型\n",
+ " self.vectorizer = \"\" # 成员变量，用于存储tfidf统计值\n",
+ "\n",
+ " # 训练模块\n",
+ " def train(self):\n",
+ " # 函数目标：读取训练数据，训练意图分类模型，并将训练好的分类模型赋值给成员变量self.model\n",
+ " # input：无\n",
+ " # output：无\n",
+ "\n",
+ " # 从excel文件读取训练样本\n",
+ " d_train = pd.read_excel(\"data_train.xlsx\")\n",
+ " # 对训练数据进行预处理\n",
+ " d_train.sentence_train = d_train.sentence_train.apply(self.fun_clean)\n",
+ " print(\"训练样本 = %d\" % len(d_train))\n",
+ "\n",
+ " \"\"\"\n",
+ " TODO：利用sklearn中的函数进行训练，将句子转化为特征features\n",
+ " \"\"\"\n",
+ " self.vectorizer = TfidfVectorizer()\n",
+ " X = self.vectorizer.fit_transform(d_train.sentence_train)\n",
+ " self.model = LogisticRegression(penalty='l1', solver='liblinear')\n",
+ "\n",
+ " self.model.fit(X, d_train.label)\n",
+ "\n",
+ " # 预测模块（使用模型预测）\n",
+ " def predict_model(self, sentence):\n",
+ " # 函数目标：使用意图分类模型预测意图\n",
+ " # input：sentence（用户输入）\n",
+ " # output：clf_result（意图类别），score（意图分数）\n",
+ "\n",
+ " # --------------\n",
+ " # 对样本中没有的特殊情况做特别判断\n",
+ " if sentence in [\"好的\", \"需要\", \"是的\", \"要的\", \"好\", \"要\", \"是\"]:\n",
+ " return 1, 0.8\n",
+ " # --------------\n",
+ "\n",
+ " \"\"\"\n",
+ " TODO：利用已训练好的意图分类模型进行意图识别\n",
+ " \"\"\"\n",
+ " sentence = self.fun_clean(sentence)\n",
+ " x = self.vectorizer.transform([sentence])\n",
+ " clf_result = self.model.predict(x)[0]\n",
+ " score = self.model.predict_proba(x)[0][clf_result]\n",
+ "\n",
+ "\n",
+ " return clf_result, score\n",
+ "\n",
+ " # 预测模块（使用规则）\n",
+ " def predict_rule(self, sentence):\n",
+ " # 函数目标：如果模型训练出现异常，可以使用规则进行预测，同时也可以让学员融合\"模型\"及\"规则\"的预测方式\n",
+ " # input：sentence（用户输入）\n",
+ " # output：clf_result（意图类别），score（意图分数）\n",
+ "\n",
+ " sentence = sentence.replace(' ', '')\n",
+ " if re.findall(r'不需要|不要|停止|终止|退出|不买|不定|不订', sentence):\n",
+ " return 2, 0.8\n",
+ " elif re.findall(r'订|定|预定|买|购', sentence) or sentence in [\"好的\",\"需要\",\"是的\",\"要的\",\"好\",\"要\",\"是\"]:\n",
+ " return 1, 0.8\n",
+ " else:\n",
+ " return 0, 0.8\n",
+ "\n",
+ " # 预处理函数\n",
+ " def fun_clean(self, sentence):\n",
+ " # 函数目标：预处理函数，将必要的实体转换成统一符号（利于分类准确），去除停用词等\n",
+ " # input：sentence（用户输入语句）\n",
+ " # output：sentence（预处理结果）\n",
+ "\n",
+ " \"\"\"\n",
+ " TODO：预处理函数，将必要的实体转换成统一符号（利于分类准确），去除停用词等\n",
+ " \"\"\"\n",
+ " words, ners = fool.analysis(sentence)\n",
+ "\n",
+ " res = []\n",
+ " ner_idx = 0\n",
+ " cur_idx = 0\n",
+ " for word in words[0]:\n",
+ " if ner_idx < len(ners[0]) and cur_idx == ners[0][ner_idx][0]:\n",
+ " if ners[0][ner_idx][0] == 'time':\n",
+ " res.append('DATE')\n",
+ " elif ners[0][ner_idx][0] == 'location':\n",
+ " res.append('CITY')\n",
+ " elif word[0] not in stopwords:\n",
+ " res.append(word[0])\n",
+ " ner_idx += 1\n",
+ " elif word[0] not in stopwords:\n",
+ " res.append(word[0])\n",
+ " cur_idx += len(word)\n",
+ " \n",
+ " return ' '.join(res)\n",
+ "\n",
+ " # 分类主函数\n",
+ " def fun_clf(self, sentence):\n",
+ " # 函数目标：意图识别主函数\n",
+ " # input：sentence（ 用户输入语句）\n",
+ " # output：clf_result（意图类别），score（意图分数）\n",
+ "\n",
+ " # 对用户输入进行预处理\n",
+ " sentence = self.fun_clean(sentence)\n",
+ " # 得到意图分类结果（0为“查询”类别，1为“订票”类别，2为“终止服务”类别）\n",
+ " clf_result, score = self.predict_model(sentence) # 使用训练的模型进行意图预测\n",
+ " # clf_result, score = self.predict_rule(sentence) # 使用规则进行意图预测（可与用模型进行意图识别的方法二选一）\n",
+ " return clf_result, score"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 120,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "sentence = '帮 我 查 一下 DATE 去 CITY 的 票'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 121,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "训练样本 = 99\n"
+ ]
+ }
+ ],
+ "source": [
+ "clf_obj = CLF_MODEL()\n",
+ "# 完成意图识别模型的训练\n",
+ "clf_obj.train()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 122,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "clf_result, score = clf_obj.predict_model(sentence)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 123,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def fun_replace_num(sentence):\n",
+ " # 函数目标：替换时间中的数字（目的是便于实体识别包fool对实体的识别）\n",
+ " # input：sentence\n",
+ " # output：sentence\n",
+ "\n",
+ " # 定义要替换的数字\n",
+ " time_num = {\"一\":\"1\",\"二\":\"2\",\"三\":\"3\",\"四\":\"4\",\"五\":\"5\",\"六\":\"6\",\"七\":\"7\",\"八\":\"8\",\"九\":\"9\",\"十\":\"10\",\"十一\":\"11\",\"十二\":\"12\"}\n",
+ " for k, v in time_num.items():\n",
+ " sentence = sentence.replace(k, v)\n",
+ " return sentence"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 126,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def slot_fill(sentence, key=None):\n",
+ " # 函数目标：填槽函数（该函数从sentence中寻找需要的内容，完成填槽工作）\n",
+ " # input：sentence（用户输入）, key（指定槽位，只对该句话提取指定槽位的信息）\n",
+ " # output：slot（返回填槽的结果，以json格式返回，key为槽位名，value为值）\n",
+ "\n",
+ " slot = {}\n",
+ " # 进行实体识别\n",
+ " slot_lst = {\"time\":\"time\", \"date\":\"time\", \"from_city\":'location', \"to_city\":'location'}\n",
+ " words, ners = fool.analysis(sentence)\n",
+ " \"\"\"\n",
+ " TODO：从sentence中寻找需要的内容，完成填槽工作\n",
+ " \"\"\"\n",
+ " if not key:\n",
+ " keys = [\"time\", \"date\", \"from_city\", \"to_city\"]\n",
+ " else:\n",
+ " keys = [key]\n",
+ " for key in keys:\n",
+ " print(key)\n",
+ " if ners != [[]]:\n",
+ " for i in range(len(ners[0])):\n",
+ " if ners[0][i][2] == slot_lst[key]:\n",
+ " if key == \"time\" and not isTimeFormat(ners[0][i][3]):\n",
+ " continue\n",
+ " slot[key] = ners[0][i][3]\n",
+ " del ners[0][i]\n",
+ " break\n",
+ " return slot\n",
+ "\n",
+ "\n",
+ "def fun_wait(clf_obj):\n",
+ " # 函数目标：等待，获取用户输入问句\n",
+ " # input：CLF_MODEL类实例化对象\n",
+ " # output：clf_result（用户输入意图类别）, score（意图识别分数）, sentence（用户输入）\n",
+ "\n",
+ " # 等待用户输入\n",
+ " print(\"\\n\\n\\n\")\n",
+ " print(\"-------------------------------------------------------------\")\n",
+ " print(\"----*------*-----*-----*----*-----*-----*-----*-----*------\")\n",
+ " print(\"Starting ...\")\n",
+ " sentence = input(\"客服：请问需要什么服务？(时间请用12小时制表示）\\n\")\n",
+ " # 对用户输入进行意图识别\n",
+ " clf_result, score = clf_obj.fun_clf(sentence)\n",
+ " return clf_result, score, sentence\n",
+ "\n",
+ "\n",
+ "def fun_search(clf_result, sentence):\n",
+ " # 函数目标：为用户查询余票\n",
+ " # input：clf_result（意图分类结果）, sentence（用户输入问句）\n",
+ " # output：是否有票\n",
+ "\n",
+ " # 定义槽存储空间\n",
+ " name = {\"time\":\"出发时间\", \"date\":\"出发日期\", \"from_city\":\"出发城市\", \"to_city\":\"到达城市\"}\n",
+ " slot = {\"time\":\"\", \"date\":\"\", \"from_city\":\"\", \"to_city\":\"\"}\n",
+ " # 使用用户第一句话进行填槽\n",
+ " sentence = fun_replace_num(sentence)\n",
+ " slot_init = slot_fill(sentence)\n",
+ " for key in slot_init.keys():\n",
+ " slot[key] = slot_init[key]\n",
+ " # 对未填充对槽位，向用户提问，进行针对性填槽\n",
+ " while \"\" in slot.values():\n",
+ " for key in slot.keys():\n",
+ " if slot[key]==\"\":\n",
+ " sentence = input(\"客服：请问%s是？\\n\"%(name[key]))\n",
+ " sentence = fun_replace_num(sentence)\n",
+ " slot_cur = slot_fill(sentence, key)\n",
+ " for key in slot_cur.keys():\n",
+ " if slot[key]==\"\":\n",
+ " slot[key] = slot_cur[key]\n",
+ "\n",
+ " # 查询是否有票，并答复用户（本次查询是否有票使用随机数完成，实际情况可查询数据库返回）\n",
+ " if random.random()>0.5:\n",
+ " print(\"客服：%s%s从%s到%s的票充足\"%(slot[\"date\"], slot[\"time\"], slot[\"from_city\"], slot[\"to_city\"]))\n",
+ " # 返回1表示有票\n",
+ " return 1\n",
+ " else:\n",
+ " print(\"客服：%s%s从%s到%s无票\" % (slot[\"date\"], slot[\"time\"], slot[\"from_city\"], slot[\"to_city\"]))\n",
+ " print(\"End !!!\")\n",
+ " print(\"----*------*-----*-----*----*-----*-----*-----*-----*------\")\n",
+ " print(\"-------------------------------------------------------------\")\n",
+ " # 返回0表示无票\n",
+ " return 0\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<_sre.SRE_Match object; span=(0, 3), match='4pm'>\n"
+ ]
+ }
+ ],
+ "source": [
+ "time='4pm' \n",
+ "print(re.match('^\\d{1,2}([:.]?\\d{1,2})?([ ]?[a|p]m)?$',time))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[[('4', 'm'), ('pm', 'nx')]]\n",
+ "[[]]\n"
+ ]
+ }
+ ],
+ "source": [
+ "s = '4pm'\n",
+ "words, ners = fool.analysis(s)\n",
+ "print(words)\n",
+ "print(ners)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.6.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Readme.txt b/Readme.txt
new file mode 100644
index 0000000..49258d5
--- /dev/null
+++ b/Readme.txt
@@ -0,0 +1,3 @@
+project2_main.py python执行脚本（所有的代码位置）
+data_train.xlsx 意图分类训练数据
+stopword.txt 停用词
diff --git a/__MACOSX/._project2_greedy_upload b/__MACOSX/._project2_greedy_upload
new file mode 100755
index 0000000..b5ea4b8
Binary files /dev/null and b/__MACOSX/._project2_greedy_upload differ
diff --git a/__MACOSX/project2_greedy_upload/._.DS_Store b/__MACOSX/project2_greedy_upload/._.DS_Store
new file mode 100644
index 0000000..a5b28df
Binary files /dev/null and b/__MACOSX/project2_greedy_upload/._.DS_Store differ
diff --git a/__MACOSX/project2_greedy_upload/._Readme.txt b/__MACOSX/project2_greedy_upload/._Readme.txt
new file mode 100644
index 0000000..bdaae4b
Binary files /dev/null and b/__MACOSX/project2_greedy_upload/._Readme.txt differ
diff --git a/__MACOSX/project2_greedy_upload/._data_train.xlsx b/__MACOSX/project2_greedy_upload/._data_train.xlsx
new file mode 100644
index 0000000..395d34b
Binary files /dev/null and b/__MACOSX/project2_greedy_upload/._data_train.xlsx differ
diff --git a/__MACOSX/project2_greedy_upload/._project2_main.py b/__MACOSX/project2_greedy_upload/._project2_main.py
new file mode 100644
index 0000000..ce1c222
Binary files /dev/null and b/__MACOSX/project2_greedy_upload/._project2_main.py differ
diff --git "a/__MACOSX/project2_greedy_upload/._\347\245\250\345\212\241\345\257\271\350\257\235\346\234\272\345\231\250\344\272\272\351\241\271\347\233\256\350\257\264\346\230\216.pdf" "b/__MACOSX/project2_greedy_upload/._\347\245\250\345\212\241\345\257\271\350\257\235\346\234\272\345\231\250\344\272\272\351\241\271\347\233\256\350\257\264\346\230\216.pdf"
new file mode 100644
index 0000000..d79570e
Binary files /dev/null and "b/__MACOSX/project2_greedy_upload/._\347\245\250\345\212\241\345\257\271\350\257\235\346\234\272\345\231\250\344\272\272\351\241\271\347\233\256\350\257\264\346\230\216.pdf" differ
diff --git a/data_train.xlsx b/data_train.xlsx
new file mode 100644
index 0000000..86f353b
Binary files /dev/null and b/data_train.xlsx differ
diff --git a/project2_main.py b/project2_main.py
new file mode 100644
index 0000000..c51a7df
--- /dev/null
+++ b/project2_main.py
@@ -0,0 +1,272 @@
+# coding=utf-8
+
+import pandas as pd
+import fool
+import re
+import random
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LogisticRegression
+
+
+# -----------------------------------------------------
+# 加载停用词词典
+stopwords = {}
+with open(r'stopword.txt', 'r', encoding='utf-8') as fr:
+ for word in fr:
+ stopwords[word.strip()] = 0
+# -----------------------------------------------------
+
+
+# 定义类
+class CLF_MODEL:
+ # 类目标：该类将所有模型训练、预测、数据预处理、意图识别的函数包括其中
+
+ # 初始化模块
+ def __init__(self):
+ self.model = "" # 成员变量，用于存储模型
+ self.vectorizer = "" # 成员变量，用于存储tfidf统计值
+
+ # 训练模块
+ def train(self):
+ # 函数目标：读取训练数据，训练意图分类模型，并将训练好的分类模型赋值给成员变量self.model
+ # input：无
+ # output：无
+
+ # 从excel文件读取训练样本
+ d_train = pd.read_excel("data_train.xlsx")
+ # 对训练数据进行预处理
+ d_train.sentence_train = d_train.sentence_train.apply(self.fun_clean)
+ print("训练样本 = %d" % len(d_train))
+
+ """
+ TODO：利用sklearn中的函数进行训练，将句子转化为特征features
+ """
+ self.vectorizer = TfidfVectorizer()
+ X = self.vectorizer.fit_transform(d_train.sentence_train)
+ self.model = LogisticRegression(penalty='l1', solver='liblinear')
+
+ self.model.fit(X, d_train.label)
+
+ # 预测模块（使用模型预测）
+ def predict_model(self, sentence):
+ # 函数目标：使用意图分类模型预测意图
+ # input：sentence（用户输入）
+ # output：clf_result（意图类别），score（意图分数）
+
+ # --------------
+ # 对样本中没有的特殊情况做特别判断
+ if sentence in ["好的", "需要", "是的", "要的", "好", "要", "是"]:
+ return 1, 0.8
+ # --------------
+
+ """
+ TODO：利用已训练好的意图分类模型进行意图识别
+ """
+ x = self.vectorizer.transform([sentence])
+ clf_result = self.model.predict(x)[0]
+ score = self.model.predict_proba(x)[0][clf_result]
+ return clf_result, score
+
+ # 预测模块（使用规则）
+ def predict_rule(self, sentence):
+ # 函数目标：如果模型训练出现异常，可以使用规则进行预测，同时也可以让学员融合"模型"及"规则"的预测方式
+ # input：sentence（用户输入）
+ # output：clf_result（意图类别），score（意图分数）
+
+ sentence = sentence.replace(' ', '')
+ if re.findall(r'不需要|不要|停止|终止|退出|不买|不定|不订', sentence):
+ return 2, 0.8
+ elif re.findall(r'订|定|预定|买|购', sentence) or sentence in ["好的","需要","是的","要的","好","要","是"]:
+ return 1, 0.8
+ else:
+ return 0, 0.8
+
+ # 预处理函数
+ def fun_clean(self, sentence):
+ # 函数目标：预处理函数，将必要的实体转换成统一符号（利于分类准确），去除停用词等
+ # input：sentence（用户输入语句）
+ # output：sentence（预处理结果）
+
+ """
+ TODO：预处理函数，将必要的实体转换成统一符号（利于分类准确），去除停用词等
+ """
+ words, ners = fool.analysis(sentence)
+ res = []
+ ner_idx = 0
+ cur_idx = 0
+ for word in words[0]:
+ if ner_idx < len(ners[0]) and cur_idx == ners[0][ner_idx][0]:
+ if ners[0][ner_idx][2] == 'time':
+ res.append('DATE')
+ elif ners[0][ner_idx][2] == 'location':
+ res.append('CITY')
+ elif word[0] not in stopwords:
+ res.append(word[0])
+ ner_idx += 1
+ elif word[0] not in stopwords:
+ res.append(word[0])
+ cur_idx += len(word[0])
+ return ' '.join(res)
+
+ # 分类主函数
+ def fun_clf(self, sentence):
+ # 函数目标：意图识别主函数
+ # input：sentence（ 用户输入语句）
+ # output：clf_result（意图类别），score（意图分数）
+
+ # 对用户输入进行预处理
+ sentence = self.fun_clean(sentence)
+ # 得到意图分类结果（0为“查询”类别，1为“订票”类别，2为“终止服务”类别）
+ clf_result, score = self.predict_model(sentence) # 使用训练的模型进行意图预测
+ # clf_result, score = self.predict_rule(sentence) # 使用规则进行意图预测（可与用模型进行意图识别的方法二选一）
+ return clf_result, score
+
+
+def fun_replace_num(sentence):
+ # 函数目标：替换时间中的数字（目的是便于实体识别包fool对实体的识别）
+ # input：sentence
+ # output：sentence
+
+ # 定义要替换的数字
+ time_num = {"一":"1","二":"2","三":"3","四":"4","五":"5","六":"6","七":"7","八":"8","九":"9","十":"10","十一":"11","十二":"12"}
+ for k, v in time_num.items():
+ sentence = sentence.replace(k, v)
+ return sentence
+
+
+def slot_fill(sentence, key=None):
+ # 函数目标：填槽函数（该函数从sentence中寻找需要的内容，完成填槽工作）
+ # input：sentence（用户输入）, key（指定槽位，只对该句话提取指定槽位的信息）
+ # output：slot（返回填槽的结果，以json格式返回，key为槽位名，value为值）
+
+ slot = {}
+ # 进行实体识别
+ slot_lst = {"time":"time", "date":"time", "from_city":'location', "to_city":'location'}
+ words, ners = fool.analysis(sentence)
+ """
+ TODO：从sentence中寻找需要的内容，完成填槽工作
+ """
+ if not key:
+ keys = ["time", "date", "from_city", "to_city"]
+ else:
+ keys = [key]
+ for key in keys:
+ if ners != [[]]:
+ for i in range(len(ners[0])):
+ if ners[0][i][2] == slot_lst[key]:
+ if key == "time" and not re.match('^\d{1,2}([:.]?\d{1,2})?([ ]?[a|p]m)?$',ners[0][i][3]):
+ continue
+ slot[key] = ners[0][i][3]
+ del ners[0][i]
+ break
+ return slot
+
+
+def fun_wait(clf_obj):
+ # 函数目标：等待，获取用户输入问句
+ # input：CLF_MODEL类实例化对象
+ # output：clf_result（用户输入意图类别）, score（意图识别分数）, sentence（用户输入）
+
+ # 等待用户输入
+ print("\n\n\n")
+ print("-------------------------------------------------------------")
+ print("----*------*-----*-----*----*-----*-----*-----*-----*------")
+ print("Starting ...")
+ sentence = input("客服：请问需要什么服务？(时间请用12小时制表示）\n")
+ # 对用户输入进行意图识别
+ clf_result, score = clf_obj.fun_clf(sentence)
+ return clf_result, score, sentence
+
+
+def fun_search(clf_result, sentence):
+ # 函数目标：为用户查询余票
+ # input：clf_result（意图分类结果）, sentence（用户输入问句）
+ # output：是否有票
+
+ # 定义槽存储空间
+ name = {"time":"出发时间", "date":"出发日期", "from_city":"出发城市", "to_city":"到达城市"}
+ slot = {"time":"", "date":"", "from_city":"", "to_city":""}
+ # 使用用户第一句话进行填槽
+ sentence = fun_replace_num(sentence)
+ slot_init = slot_fill(sentence)
+ for key in slot_init.keys():
+ slot[key] = slot_init[key]
+ # 对未填充对槽位，向用户提问，进行针对性填槽
+ while "" in slot.values():
+ for key in slot.keys():
+ if slot[key]=="":
+ sentence = input("客服：请问%s是？\n"%(name[key]))
+ sentence = fun_replace_num(sentence)
+ slot_cur = slot_fill(sentence, key)
+ for key in slot_cur.keys():
+ if slot[key]=="":
+ slot[key] = slot_cur[key]
+
+ # 查询是否有票，并答复用户（本次查询是否有票使用随机数完成，实际情况可查询数据库返回）
+ if random.random()>0.5:
+ print("客服：%s%s从%s到%s的票充足"%(slot["date"], slot["time"], slot["from_city"], slot["to_city"]))
+ # 返回1表示有票
+ return 1
+ else:
+ print("客服：%s%s从%s到%s无票" % (slot["date"], slot["time"], slot["from_city"], slot["to_city"]))
+ print("End !!!")
+ print("----*------*-----*-----*----*-----*-----*-----*-----*------")
+ print("-------------------------------------------------------------")
+ # 返回0表示无票
+ return 0
+
+
+def fun_book():
+ # 函数目标：执行下单订票动作
+ # input：无
+ # output：无
+
+ print("客服：已为您完成订票。\n\n\n")
+ print("End !!!")
+ print("----*------*-----*-----*----*-----*-----*-----*-----*------")
+ print("-------------------------------------------------------------")
+
+
+
+if __name__=="__main__":
+ # 实例化对象
+ clf_obj = CLF_MODEL()
+ # 完成意图识别模型的训练
+ clf_obj.train()
+ # 用户定义阈值（当分类器分类的分数大于阈值才采纳本次意图分类结果，目的是排除分数过低的意图分类结果）
+ threshold = 0.55
+
+ # 循环提供服务
+ while 1:
+ clf_result, score, sentence = fun_wait(clf_obj)
+ # -------------------------------------------------------------------------------
+ # 状态转移条件（等待-->等待）：用户输入未达到“查询”、“订票”类别的阈值 OR 意图被分类为“终止服务”
+ # -------------------------------------------------------------------------------
+ if score<threshold or clf_result==2:
+ continue
+
+ # -------------------------------------------------------------------------------
+ # 状态转移条件（等待-->查询）：用户输入分类为“查询” OR “订票”
+ # -------------------------------------------------------------------------------
+ else:
+ # 收集订票细节信息
+ search_result = fun_search(clf_result, sentence)
+ # 查询无票
+ # -------------------------------------------------------------------------------
+ # 状态转移条件（查询-->等待）：FUN_SEARCH执行完后用户输入意图为“终止服务” OR FUN_SEARCH返回无票
+ # -------------------------------------------------------------------------------
+ if search_result==0:
+ continue
+ # 查询有票
+ else:
+ # 等待用户输入
+ sentence = input("客服：需要为您订票吗？\n")
+ # 对用户输入进行意图识别
+ clf_result, score = clf_obj.fun_clf(sentence)
+ # -------------------------------------------------------------------------------
+ # 状态转移条件（查询-->订票）：FUN_SEARCH返回有票 AND 用户输入意图为“订票”
+ # -------------------------------------------------------------------------------
+ if clf_result == 1:
+ fun_book()
+ continue
+
diff --git a/stopword.txt b/stopword.txt
new file mode 100644
index 0000000..a2664c4
--- /dev/null
+++ b/stopword.txt
@@ -0,0 +1,13 @@
+的
+到
+一下
+我
+，
+帮
+去
+了
+？
+吧
+。
+请
+么
--
libgit2 0.26.0