1、简介

最近一直在研究NLP的文本相似度算法，本文将利用TF-IDF特征向量和Simhash指纹计算中文文本的相似度。

2、计算过程

准备测试数据
预处理读到的数据
加载数据到Map中
输入用户问题
利用TF特征向量和Simhash指纹计算出预处理的配置文件中的分值

3、效果图

在这里插入图片描述

4、核心代码

    try:
        text = re_test.run(question) # 通过正则 查找匹配数据
        doc_token = jt.tokens(text) # 预处理，分词
        doc_feat = fb.compute(doc_token)
        doc_fl = DocFeatLoader(smb, doc_feat) # 对象包含两个参数 # fingerprint   指纹分值 # feat_vec  包含元组的列表

        # 预处理后的配置文件
        contentFlListMap = nodeMap
        p_score_list = []
        if nodeId in contentFlListMap.keys():
            nodeFlList = contentFlListMap[nodeId]
            print("nodeFilist",nodeFlList)
            for i in range(len(nodeFlList)):
                p_score_dict={}
                dist = cosine_distance_nonzero(nodeFlList[i]["lableDataFeatureVector"].feat_vec, doc_fl.feat_vec, norm=False)
                p_score_dict["score"] = dist
                p_score_dict["labelData"] = nodeFlList[i]["labelData"]
                p_score_dict["targetNodeId"] = nodeFlList[i]["targetNodeId"]
                p_score_dict["conditionId"] = nodeFlList[i]["conditionId"]
                p_score_list.append(p_score_dict)
            p_score_list = sorted(p_score_list, key=lambda score : score["score"], reverse=True)

            print("Sorted：",p_score_list)

            Complete_MayBeL4 = []
            Complete_MayBeL4Score = []
            Complete_MayBeL4ID = []
            Complete_MayBeL4Max = 3
            for i, el in enumerate(p_score_list):
                p_label = p_score_list[i]["labelData"]
                p_score = p_score_list[i]["score"]
                p_conditionId = p_score_list[i]["conditionId"]
                if len(Complete_MayBeL4) < Complete_MayBeL4Max:
                    Complete_MayBeL4.append(p_label)
                    Complete_MayBeL4Score.append(p_score)
                    Complete_MayBeL4ID.append(p_conditionId)
                else:
                    break

            print("************************************")
            print("用户问题：", question)
            print("相似问(Max=%s)：%s"%(Complete_MayBeL4Max,Complete_MayBeL4))
            print("特征值(Max=%s)：%s"%(Complete_MayBeL4Max,Complete_MayBeL4Score))
            print("ID：",Complete_MayBeL4ID)
            return "", "", "", "", "", ""
    except Exception as e:
        print("************************************")
        print("Error textSimilarity：", str(e))
        print("************************************")