# -*- coding: utf-8 -*- # @Author: privacy # @Date: 2024-08-30 11:17:21 # @Last Modified by: privacy # @Last Modified time: 2024-12-04 11:17:17 """ 商务部分 """ import re from typing import List, Optional from celery_tasks.LLMAgent import get_proj from celery_tasks.project_loc import extract_project from celery_tasks.text_extractor import similar_match from celery_tasks.extract_financial_report import extract_financial_report def get_score(comment: str, standard: str): if re.findall(r'A~D|A～D|A、B、C', standard): try: return re.findall('([A-D])级', comment).pop() except Exception: return 'B' elif re.findall(r'\d+\s?分', standard): try: return re.findall(r'(\d+)\s?分', comment).pop() except Exception: return "60" def busi_loc(scrutinize_dict: dict, outline_dict: List[dict], title_list: List[dict], table_list: List[dict], image_list: List[dict], supplier: str, project: str = None, file_name: str = None) -> Optional[List[dict]]: """ 投标商务部分定位 Args: scrutinize_dict: 详细评审 tender_file: 投标文件 Returns: result: 商务部分详审结果 """ part = None # 从详审大纲中获取商务评分方法 for key in scrutinize_dict.keys(): if '商务' in key: part = key break # 没有找到商务评审方法则直接返回 if not part: return None result = { 'writeName': '', 'scoringCriteria': [] } for item in scrutinize_dict[key]: if '信用' in item['评分因素']: result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': get_score(comment="B级（70分）", standard=item['评分标准']), 'pages': [] }] }) elif '业绩' in item['评分因素']: # 项目业绩表查询 proj_list = extract_project(table_list, instances=['合同金额', '合同价格', '发包人名称', '项目规模', '合同时间']) # 定位信息格式化 title_sims = [{'fileName': file_name, 'conformFlag': 1, 'pageKey': '', 'pageStart': str(proj['page_numbers'][-1]), 'pageEnd': str(proj['page_numbers'][-1])} for proj in proj_list] # # 打分 comment = get_proj(input_json=proj_list, standard=item['评分标准']) # 结果回传 result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': get_score(comment=comment, standard=item['评分标准']), 'pages': title_sims }] }) elif '财务' in item['评分因素']: financial_list = extract_financial_report( title_list=title_list, table_list=table_list, image_list=image_list, year=2022 ) title_sims = [] starts = [] for _ in financial_list: for page in _['pages']: starts.append(page[0]) for page in set(starts): title_sims.append({ "fileName": file_name, "conformFlag": 1, "pageKey": "", "pageEnd": page, "pageStart": page, }) result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': 'B', 'supplier': '3个关键的财务指标', 'pages': title_sims }] }) elif '报价' in item['评分因素']: result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': 'B', 'pages': [] }] }) elif '完整性' in item['评分因素']: result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': 'B', 'pages': [] }] }) elif '涉密' in item['评分因素']: result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': get_score(comment="A级（100分）", standard=item['评分标准']), 'pages': [] }] }) else: title_sims = similar_match(outline_dict, [item['评分因素']], key='title') pages = [{'fileName': file_name, 'conformFlag': 1, 'pageStart': str(sim['page_number']), 'pageEnd': str(sim['page_number']), 'pageKey': '', 'text': sim['title'], 'score': sim['相似度']} for sim in title_sims] result['scoringCriteria'].append({ 'scoringFactors': item['评分因素'], 'scoringStandard': item['评分标准'], 'percentage': item['权重'], 'expertAdvice': '', 'writeName': '', 'suppliers': [{ 'expertAdvice': '', 'writeName': '', 'name': supplier, 'grade': get_score(comment="B级（70分）", standard=item['评分标准']), 'pages': pages, }] }) return result if __name__ == '__main__': import os import json from glob import glob from pprint import pprint with open('bidding_dataset.json', 'r', encoding='utf-8') as fp: scrutinizes = json.load(fp) for project in scrutinizes.keys(): scrutinize_dict = scrutinizes[project] for file in glob(f'./data/0预审查初审详审测试数据/{project}/*/*-outline.json'): with open(file, 'r', encoding='utf-8') as fp: outline_dict = json.load(fp) if outline_dict == []: os.remove(file) continue with open(file.replace('outline.json', 'title.json'), 'r', encoding='utf-8') as fp: title_list = json.load(fp) with open(file.replace('outline.json', 'table.json'), 'r', encoding='utf-8') as fp: table_list = json.load(fp) with open(file.replace('outline.json', 'image.json'), 'r', encoding='utf-8') as fp: image_list = json.load(fp) supplier = file.split('\\')[-2] pprint( busi_loc( scrutinize_dict=scrutinize_dict, outline_dict=outline_dict, title_list=title_list, table_list=table_list, image_list=image_list, supplier=supplier, project=project, file_name=file ) ) exit(0)