intentparser.py 文件源码

def getTextConfidence(self, text):
        if self.typeOfSim == 'jaccard':
            intend_confidenceList = []
            for i in self.know_words:
                intend_confidenceList.append(jaccard_compare(text, i))
            if len(self.know_words) > 0:
                return max(intend_confidenceList)
            else :
                return 0
        elif self.typeOfSim == 'gensim':
            try:
                from gensim import corpora, models, similarities
            except Exception as e:
                print(e)
            dictionary = corpora.Dictionary(self.know_words_remove_stopwords)
            corpus = [dictionary.doc2bow(text) for text in self.know_words_remove_stopwords]
            lsi = models.LsiModel(corpus, id2word=dictionary, num_topics=2)
            new_doc = text
            vec_bow = dictionary.doc2bow(new_doc.lower().split())
            vec_lsi = lsi[vec_bow]
            index = similarities.MatrixSimilarity(lsi[corpus])
            sims = index[vec_lsi]
            sims = sorted(enumerate(sims), key=lambda item: -item[1])
            most_sim = sims[0]
            return most_sim[1]