新增询报价聊天识别

config.py

@@ -160,3 +160,5 @@ attr_regex = "F|H|K|A|W|KW"
 special_attr_regex = "Ω"
 
 replace_char = "|/。，或各和：:"
+
+interference_tupe = ("HK","week",)

utils/functions.py

@@ -16,6 +16,8 @@ pcs_num_pattern = re.compile('(\s|[\u4e00-\u9fa5])(\d+\.\d+|\d+)(pcs)', re.I)
 price_num_pattern = re.compile('(\d+\.\d+|\d+)')
 zh_pattern = re.compile('[\u4e00-\u9fa5]+')
 usd_num_pattern = re.compile('(\d+\.\d+|\d+)(usd)', re.I)
+time_pattern = re.compile(
+    '(\s|[\u4e00-\u9fa5])(\d+[-~到至]\d+|\d+|一|二|三|四|五|六|七|八|九|十|两|叁|贰)(日|周|月|weeks|week|天|DAY|工作日)')
 prefixchar = [i + j for i in split_char for j in legal_char]
 tailchar = [i + j for i in legal_char for j in split_char]
 prefixchar.extend(list(legal_char))
@@ -373,7 +375,7 @@ def check_k_num(kw_info):
             res = str(delete_extra_zero(float(res[0][1]) * 1000))
         else:
             res = str(int(res[0][1]) * 1000)
-        return res,res_num
+        return res, res_num
         # return res
 
 
@@ -396,11 +398,14 @@ def check_num(kw_info):
     :param kw_info:
     :return:
     '''
-    res = num_pattern.findall(kw_info)
+
+    res = num_pattern.findall(kw_info.replace(",", ""))
     if not res:
         return False
     else:
-        return res[0][1].strip()
+        if res[0][1][0] != "0":
+            return res[0][1].strip()
+        return False
 
 
 def check_price(kw_info):
@@ -445,3 +450,30 @@ def replace_symbol(kw):
     for replace_info in replace_char:
         kw = kw.replace(replace_info, " ")
     return kw
+
+
+def check_time(kw_info):
+    '''
+    匹配货期
+    :param kw_info:
+    :return:
+    '''
+
+    res = time_pattern.findall(kw_info)
+    if res:
+        return res[0][1].replace("到", "-").replace("至", "-") + res[0][2].replace("工作日", "天")
+    else:
+        return False
+
+
+def check_interference(kw_info):
+    '''
+    确认是否包含干扰词
+    :param kw_info:
+    :return:
+    '''
+    for str_info in interference_tupe:
+        print(str_info)
+        if str_info in kw_info:
+            return False
+    return True

valid_server.py

@@ -159,9 +159,11 @@ class ImHandler(tornado.web.RequestHandler):
                 data_obj["number"] = ""
                 data_obj["price"] = ""
                 data_obj["encap"] = ""
+                data_obj["delivery_time"] = ""
 
                 new_data_info = []
-                data_info = replace_symbol(data_info).replace("（", "(").replace("）", ")")  # 统一分隔符,替换中文括号
+                # print(data_info.decode("gbk").encode("utf-8"))
+                data_info = replace_symbol(data_info).replace("（", "(").replace("）", ")").replace("\xa0","").replace("\t"," ")  # 统一分隔符,替换中文括号
                 data_cut_list = data_info.split(" ")
                 new_cut_info = ""
                 for cut_info in data_cut_list:  # 第一遍过滤
@@ -174,8 +176,10 @@ class ImHandler(tornado.web.RequestHandler):
                     else:
                         resp1 = self.predic.predict(new_info, 'all')
                         resp2 = self.predic.predict(new_info, 'brand')
-                        zh_res = check_zh(new_info)
-                        if resp1['result'] == '品牌' and resp2['result'] and "HK" not in new_info and zh_res: #判断是否含有中文，若含有中文，且品牌集合里面没有录入，则不当型号
+                        # zh_res = check_zh(new_info)
+                        if resp1['result'] == '品牌' and resp2[
+                            'result'] and check_zh(new_info) and check_interference(
+                            new_info):  # 判断是否含有中文，若含有中文，且品牌集合里面没有录入，则不当型号
                             data_obj["brand"] = new_info
                         # elif resp1['result'] != '品牌' and resp2['result']:
                         #
@@ -188,9 +192,7 @@ class ImHandler(tornado.web.RequestHandler):
                                 gn_res = self.predic.predict(new_info, 'gn')
                                 k_res = check_k_num(" " + new_info)
                                 pcs_res = check_pcs_num(" " + new_info)
-                                if gn_res[
-                                    "result"] and not k_res and not new_info.strip().isdigit() and not pcs_res and check_zh(
-                                    new_info):  # 剔除纯数字带K、pcs结尾的特殊情况，并且型号不能带有中文
+                                if gn_res["result"] and not k_res and not new_info.strip().isdigit() and not pcs_res and check_zh(new_info):  # 剔除纯数字带K、pcs结尾的特殊情况，并且型号不能带有中文
                                     data_obj["gn"].append(new_info)
 
                 if data_obj["brand"]:
@@ -224,9 +226,10 @@ class ImHandler(tornado.web.RequestHandler):
                             data_obj["price"] = price_res
                         if k_res or pcs_res or num_res or price_res:
                             new_cut_info = new_cut_info.replace(list_info, "")
-
-
-                        #第一种写法
+                        time_res = check_time(" " + kw_word + " ")
+                        if time_res:
+                            data_obj["delivery_time"] = time_res
+                        # 第一种写法
                         # kw_word = " " + list_info
                         # k_res = check_k_num(kw_word)
                         #
@@ -255,7 +258,7 @@ class ImHandler(tornado.web.RequestHandler):
                     end_cut_list = new_cut_info.split(" ")
                     len_lsit = []
                     for end_cut_info in end_cut_list:  # 将剩下的未知单词剔除包含中文的单词
-                        if end_cut_info.strip() and check_zh(end_cut_info.strip()) and len(end_cut_info.strip()) > 6:
+                        if end_cut_info.strip() and check_zh(end_cut_info.strip()) and len(end_cut_info.strip()) > 4:
                             len_lsit.append(end_cut_info)
                     if len_lsit and len(len_lsit) == 1 and not data_obj["gn"]:  # 若剔除完中文后，此时型号还未空，则剩下的词很大概率是型号，暂时按时型号处理
                         data_obj["gn"].append(len_lsit[0].strip())
@@ -265,7 +268,6 @@ class ImHandler(tornado.web.RequestHandler):
             res = {}
             res["data"] = data
 
-        # print(res)
         self.write(res)