| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566 |
- """
- @author: luojunhui
- """
- from applications.match_algorithm.title_similarity import jcd_title_similarity
- from applications.functions.log import logging
- def jac_score(d1, d2):
- """
- 通过交并集来判断
- :param d1:
- :param d2:
- :return:
- """
- f1_keys = set(d1["key_words"])
- f2_keys = set(d2["key_words"])
- keys_union = f1_keys | f2_keys
- keys_intersection = f1_keys & f2_keys
- f1_search_keys = set(d1["search_keys"])
- f2_search_keys = set(d2["search_keys"])
- search_keys_union = f1_search_keys | f2_search_keys
- search_keys_intersection = f1_search_keys & f2_search_keys
- f1_extra_keys = set(d1["extra_keys"])
- f2_extra_keys = set(d2["extra_keys"])
- extra_keys_union = f1_extra_keys | f2_extra_keys
- extra_keys_intersection = f1_extra_keys & f2_extra_keys
- score_1 = len(keys_intersection) / len(keys_union)
- score_2 = len(search_keys_intersection) / len(search_keys_union)
- score_3 = len(extra_keys_intersection) / len(extra_keys_union)
- return score_1 * 0.4 + score_2 * 0.4 + score_3 * 0.2, d2['video_id']
- def title_similarity_rank(content_title, recall_list):
- """
- :param content_title:
- :param recall_list:
- :return:
- """
- include_title_list = []
- for item in recall_list:
- video_info = item['result']
- platform = item['platform']
- if platform in ['dy_search', 'baidu_search']:
- title = video_info['title']
- elif platform in ['xg_search']:
- title = video_info['video_title']
- else:
- continue
- item['title'] = title
- item['score'] = jcd_title_similarity(content_title, title)
- include_title_list.append(item)
- # # include_title_list加上相似度分
- # title_score_list = [
- # {
- # 'score': jcd_title_similarity(
- # content_title,
- # item['title']
- # ),
- # **item
- # }
- # for item in
- # include_title_list
- # ]
- sorted_list = sorted(include_title_list, key=lambda x: x['score'], reverse=True)
- return sorted_list
|
