11.18 技术要求层级修改
This commit is contained in:
parent
4cde79be3c
commit
d77dde3f6e
@ -10,6 +10,7 @@ from flask_app.general.通义千问long import qianwen_long, upload_file
|
||||
from flask_app.general.json_utils import clean_json_string, combine_json_results
|
||||
from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main
|
||||
from flask_app.general.doubao import doubao_model, generate_full_user_query, pdf2txt
|
||||
from flask_app.货物标.技术参数要求提取后处理函数 import postprocess, all_postprocess
|
||||
|
||||
|
||||
def generate_key_paths(data, parent_key='', good_list=None, seen=None):
|
||||
@ -189,64 +190,6 @@ def combine_and_update_results(original_data, updates):
|
||||
recursive_update(original_data, key, value)
|
||||
|
||||
return original_data
|
||||
def postprocess(data):
|
||||
"""递归地转换字典中的值为列表，如果所有键对应的值都是'/', '{}' 或 '未知'"""
|
||||
def convert_dict(value):
|
||||
# 如果所有值是'/', '{}' 或 '未知'
|
||||
if all(v in ['/', '未知', {}] for v in value.values()):
|
||||
return list(value.keys())
|
||||
else:
|
||||
# 如果不满足条件，则递归处理嵌套的字典
|
||||
return {k: convert_dict(v) if isinstance(v, dict) else v for k, v in value.items()}
|
||||
|
||||
# 递归处理顶层数据
|
||||
return {key: convert_dict(val) if isinstance(val, dict) else val for key, val in data.items()}
|
||||
|
||||
def detect_depth(data):
|
||||
"""
|
||||
Detects the depth of the nested dictionary.
|
||||
"""
|
||||
if isinstance(data, dict):
|
||||
return 1 + max((detect_depth(v) for v in data.values()), default=0)
|
||||
elif isinstance(data, list):
|
||||
return 1 # Lists are considered the terminal layer
|
||||
else:
|
||||
return 0 # Base case for non-nested elements
|
||||
|
||||
|
||||
def restructure_data(data):
|
||||
"""
|
||||
Restructure data to normalize levels of nesting.
|
||||
If depth is 2 throughout, return as-is.
|
||||
If both 2 and 3 levels exist, restructure to align to 3-layer format.
|
||||
"""
|
||||
# Check if data contains mixed 2-layer and 3-layer structures
|
||||
has_two_layers = False
|
||||
has_three_layers = False
|
||||
|
||||
for key, value in data.items():
|
||||
if isinstance(value, dict):
|
||||
has_three_layers = True
|
||||
elif isinstance(value, list):
|
||||
has_two_layers = True
|
||||
else:
|
||||
raise ValueError(f"Unexpected data format for key '{key}': {type(value)}")
|
||||
|
||||
# If only 2-layer, return as-is
|
||||
if has_two_layers and not has_three_layers:
|
||||
return data
|
||||
|
||||
# If mixed or only 3-layer, normalize to 3-layer
|
||||
structured_data = {}
|
||||
for key, value in data.items():
|
||||
if isinstance(value, dict):
|
||||
# Already a 3-layer structure, keep as is
|
||||
structured_data[key] = value
|
||||
elif isinstance(value, list):
|
||||
# Convert 2-layer structure to 3-layer
|
||||
structured_data[key] = {key: value}
|
||||
|
||||
return structured_data
|
||||
|
||||
# user_query1 = """
|
||||
# 请你首先定位该采购文件中的采购清单或采购需求部分，请告诉我需要采购的货物，如果有采购清单，请直接根据清单上的货物（或系统）名称给出结果，注意不要返回'说明'或'规格'或'技术参数'列中的内容；若没有采购清单，你要从表格中或文中摘取需要采购的系统和货物，采购需求中可能包含层次关系，例如采购的某系统中可能包含几种货物，那么你需要用嵌套键值对表示这种关系，且不要遗漏该系统中包含的货物，你的输出请以json格式返回，最外层键名为'采购需求'，嵌套键名为对应的系统名称或货物名称，需与原文保持一致，无需给出采购数量和单位。以下为需要考虑的特殊情况：如果采购清单中同一层级(或同一系统)下存在同名货物且它们的采购要求有所不同，请你以'货物名-编号'区分多种型号，编号为从 1 开始的自然数，依次递增,例如若采购清单中有两种型号的'交换机'，那么你应返回两个键名，'交换机-1'和'交换机-2'；如有未知内容，在对应键值处填'未知'。以下为考虑了特殊情况的示例输出：
|
||||
@ -493,7 +436,7 @@ def get_technical_requirements(file_path,invalid_path):
|
||||
"""根据所有键是否已添加处理技术要求"""
|
||||
# 更新原始采购需求字典
|
||||
final_res=combine_and_update_results(cleaned_res['采购需求'], technical_requirements_combined_res)
|
||||
ffinal_res=restructure_data(final_res)
|
||||
ffinal_res=all_postprocess(final_res)
|
||||
# final_res = postprocess(cleaned_res)
|
||||
ffinal_res["货物列表"] = good_list
|
||||
# 输出最终的 JSON 字符串
|
||||
|
||||
127
flask_app/货物标/技术参数要求提取后处理函数.py
Normal file
127
flask_app/货物标/技术参数要求提取后处理函数.py
Normal file
@ -0,0 +1,127 @@
|
||||
import json
|
||||
def postprocess(data):
|
||||
"""递归地转换字典中的值为列表，如果所有键对应的值都是'/', '{}' 或 '未知'"""
|
||||
def convert_dict(value):
|
||||
# 如果所有值是'/', '{}' 或 '未知'
|
||||
if all(v in ['/', '未知', {}] for v in value.values()):
|
||||
return list(value.keys())
|
||||
else:
|
||||
# 如果不满足条件，则递归处理嵌套的字典
|
||||
return {k: convert_dict(v) if isinstance(v, dict) else v for k, v in value.items()}
|
||||
|
||||
# 递归处理顶层数据
|
||||
return {key: convert_dict(val) if isinstance(val, dict) else val for key, val in data.items()}
|
||||
|
||||
def all_postprocess(data):
|
||||
temp=restructure_data(data)
|
||||
processed_data = {}
|
||||
for key, value_list in temp.items():
|
||||
processed_data[key] = remove_common_prefixes(value_list)
|
||||
return processed_data
|
||||
def detect_depth(data):
|
||||
"""
|
||||
Detects the depth of the nested dictionary.
|
||||
"""
|
||||
if isinstance(data, dict):
|
||||
return 1 + max((detect_depth(v) for v in data.values()), default=0)
|
||||
elif isinstance(data, list):
|
||||
return 1 # Lists are considered the terminal layer
|
||||
else:
|
||||
return 0 # Base case for non-nested elements
|
||||
|
||||
|
||||
def restructure_data(data):
|
||||
"""
|
||||
Restructure data to normalize levels of nesting.
|
||||
If depth is 2 throughout, return as-is.
|
||||
If both 2 and 3 levels exist, restructure to align to 3-layer format.
|
||||
"""
|
||||
# Check if data contains mixed 2-layer and 3-layer structures
|
||||
has_two_layers = False
|
||||
has_three_layers = False
|
||||
|
||||
for key, value in data.items():
|
||||
if isinstance(value, dict):
|
||||
has_three_layers = True
|
||||
elif isinstance(value, list):
|
||||
has_two_layers = True
|
||||
else:
|
||||
raise ValueError(f"Unexpected data format for key '{key}': {type(value)}")
|
||||
|
||||
# If only 2-layer, return as-is
|
||||
if has_two_layers and not has_three_layers:
|
||||
return data
|
||||
|
||||
# If mixed or only 3-layer, normalize to 3-layer
|
||||
structured_data = {}
|
||||
for key, value in data.items():
|
||||
if isinstance(value, dict):
|
||||
# Already a 3-layer structure, keep as is
|
||||
structured_data[key] = value
|
||||
elif isinstance(value, list):
|
||||
# Convert 2-layer structure to 3-layer
|
||||
structured_data[key] = {key: value}
|
||||
|
||||
return structured_data
|
||||
|
||||
# 定义获取所有以'：'结尾的前缀的函数
|
||||
def get_prefixes(s):
|
||||
prefixes = []
|
||||
for i in range(len(s)):
|
||||
if s[i] == '：':
|
||||
prefixes.append(s[:i+1])
|
||||
return prefixes
|
||||
|
||||
# 定义删除公共前缀的函数
|
||||
def remove_common_prefixes(string_list):
|
||||
# 构建前缀到字符串集合的映射
|
||||
prefix_to_strings = {}
|
||||
for s in string_list:
|
||||
prefixes = get_prefixes(s)
|
||||
unique_prefixes = set(prefixes)
|
||||
for prefix in unique_prefixes:
|
||||
if prefix not in prefix_to_strings:
|
||||
prefix_to_strings[prefix] = set()
|
||||
prefix_to_strings[prefix].add(s)
|
||||
# 找出至少在两个字符串中出现的前缀
|
||||
prefixes_occuring_in_multiple_strings = [prefix for prefix, strings in prefix_to_strings.items() if len(strings) >=2]
|
||||
# 对每个字符串，找到其匹配的最长前缀并删除
|
||||
new_string_list = []
|
||||
for s in string_list:
|
||||
applicable_prefixes = [prefix for prefix in prefixes_occuring_in_multiple_strings if s.startswith(prefix)]
|
||||
if applicable_prefixes:
|
||||
# 找到最长的前缀
|
||||
longest_prefix = max(applicable_prefixes, key=len)
|
||||
# 删除前缀
|
||||
new_s = s[len(longest_prefix):]
|
||||
new_string_list.append(new_s)
|
||||
else:
|
||||
new_string_list.append(s)
|
||||
return new_string_list
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 示例数据
|
||||
sample_data = {
|
||||
"交通信号机": [
|
||||
"★应采用区域控制信号机，并应与广水市交通信号控制系统兼容，信号机能接入已有系统平台，实现联网优化功能。",
|
||||
"1、控制功能：（1）区域协调控制：可对单个孤立交叉口、干道多个交叉口和关联性较强的交叉口群进行综合性地信号控制。",
|
||||
"1、控制功能：（2）线性协调控制：可对干道多个相邻交叉口进行协调控制。",
|
||||
"1、控制功能：（3）多时段控制：可根据交叉口的交通状况，将每天划分为多个不同的时段，每个时段配置不同的控制方案，能设置至少 10个时段、10种以上不同控制方案，能根据不同周日类型对方案进行调整。信号机能够根据内置时钟选择各个时段的控制方案，实现交叉口的合理控制。",
|
||||
"2、采集功能：（1）信号机支持接入线圈、地磁、视频、微波、超声波检测器、RFID等多种检测方式。",
|
||||
"2、采集功能：（2）信号机支持交通信息采集与统计,并支持交通流量共享。",
|
||||
"3、运维功能：（1）信号机能够自动检测地磁故障，若故障，能够自动上传故障信息至监控中心。"
|
||||
],
|
||||
"高清视频抓拍像机": [
|
||||
"1：摄像机：有效像素：≥900W像素",
|
||||
"1：摄像机：最低照度：彩色≤0.001lx",
|
||||
"1：摄像机：传感器类型：≥1英寸全局曝光 COMS/GMOS/GS COMS",
|
||||
"1：摄像机：电子快门：至少满足 1/25s至 1/100,000s，可调",
|
||||
"2：视频图像：视频压缩标准：至少支持 H264、H265等",
|
||||
"2：视频图像：视频分辨率：≥4096×2160，向下可设置",
|
||||
],
|
||||
}
|
||||
# 处理数据
|
||||
result = all_postprocess(sample_data)
|
||||
# 输出处理结果
|
||||
print(json.dumps(result,ensure_ascii=False,indent=4))
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user