Bagaimana ML membantu audit kualitas layanan pelanggan

Apakah mungkin untuk menganalisis permintaan pelanggan dan mengidentifikasi penyebab ulasan negatif dalam waktu singkat dan tanpa biaya tenaga kerja yang tinggi? Pada artikel ini, kami ingin memberi tahu Anda bagaimana kami berhasil menyelesaikan masalah ini dengan bantuan alat ML.

Dalam pekerjaan kami, kami dihadapkan pada kebutuhan untuk menilai kualitas layanan pelanggan. Kami dihadapkan pada tugas menganalisis permintaan pelanggan dan mengidentifikasi alasan terjadinya review negatif pada layanan purna jual produk asuransi.

. - .

, , . , , .

, , , :

def cl_text(text):
    c = text.lower()
    c = re.sub(r'crm[^\n]+', '', c)
    c = re.sub(r':\s*\d{2}\s?\d{2}\s?\d{6}\s*', '', c)
    c = re.sub(r':\s*\d{2}\s?\d{2}\s?\d{6}\s*', '', c)
    c = re.sub(r' (  )?:\s*\d{2}\.?\d{2}\.?\d{4}\s*', '', c)
    c = re.sub(r'  :\s*\d{2}\.?\d{2}\.?\d{4}\s*', '', c)
    c = re.sub(r'  :\s*\d{2}\.?\d{2}\.?\d{4}\s*', '', c)
    c = re.sub(r' :\s*\d{2}\.?\d{2}\.?\d{4}\s*', '', c)
    c = re.sub(r' :[\S\W]\w*', '', c)
    c = re.sub(r'\n+', ' ', c)
    c = re.sub(r'\s+', ' ', c)
    c = re.sub(r"[A-Za-z!#$%&'()*+,./:;<=>?@[\]^_`{|}~—\"\-]+", ' ', c)
    return c.strip()
      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

, , . - NLTK stopwords:

import pymorphy2
import nltk
morph = pymorphy2.MorphAnalyzer()
stopwords = nltk.corpus.stopwords.words('russian')
stopwords.extend(['','','','','',''])

def lemmatize(text):
    text = re.sub(r"\d+", '', text.lower()) #   
    for token in text.split():
        token = token.strip()
        token = morph.normal_forms(token)[0].replace('', '')
        if token and token not in stopwords: tokens.append(token)
    if len(tokens) > 2: ' '.join(tokens)
    return None
      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

:

, , -. OneHotEncoding TF-IDF. , , – . , , , « » « » , .. .

Universal Sentence Embedder, , . . .

import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_text

model = hub.load(r'/UniverseSentenseEmbeddings/USEv3')
embedding = model(‘    ’)
      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

, 5 . , :

input1, input2 = [' '], [' ', ' ', ' ', ' ', ' ']
emb1, emb2 = model(input1), model(input2)
results_cosine = pairwise.cosine_similarity(emb1, emb2).tolist()[0]
for i, res in enumerate(results_cosine):
    print('"{}" <> "{}", cos_sim={:.3f}'.format(input1[0],input2[i],results_cosine[i]))
      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

:

" " <> " ", cos_sim = 0.860
" " <> " ", cos_sim = 0.769
" " <> " ", cos_sim = 0.748
" " <> " ", cos_sim = 0.559
" " <> " ", cos_sim = 0.192

      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

, , .

4 : DBSCAN, , kMeans MiniBatchKMeans. , .., , :

from sklearn.cluster import AgglomerativeClustering
num_clusters = 5
agglo1 = AgglomerativeClustering(n_clusters=num_clusters, affinity='euclidean') #cosine, l1, l2, manhattan
get_ipython().magic('time answer = agglo1.fit_predict(sent_embs)')
      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

5 , , . – 10 :

cl = {}
for cluster, data in tqdm(report.groupby('AGGLOM'), desc=method):
    arr = ' '.join(data[''].values).split()
    arr_morph = []
    for k in arr:
        arr_morph.append(morph.parse(k)[0].normal_form) 
    cl[method+'_'+str(cluster)] = Counter([x.replace('', '') for x in arr_morph if x not in stopwords]).most_common(10) 
      
      

        
        
        
      

    
        
        
        
      
      

        
        
        
      

    
    

- :

, , .

  , , .

, .