Article-suggestion system for automatically resolving customer-service requests

1. A method for automatically suggesting helpful articles to resolve a customer request, comprising:

receiving, by a ticketing system, the customer request, wherein the customer request is associated with a product or a service;

feeding words from the customer request through a model to generate a request vector representing words in the customer request;

wherein generating the request vector comprises,

obtaining a set of words from the customer request by combining a subject field and a description field from the customer request into a blob of text, feeding the blob of text through a regex processor to remove text that does not comprise words to produce a refined blob of text, and selecting a new set of words from the refined blob of text,

producing a set of word vectors by generating a word vector for each word in the new set of words,

feeding the set of word vectors through a recurrent neural network to produce a preliminary request vector representing the customer request, and

feeding the preliminary request vector through a feed-forward neural network to generate the request vector;

comparing the request vector against article vectors representing articles in a set of help center articles to determine whether the customer request matches one or more help center articles; and

presenting the one or more help center articles to a customer to facilitate automatically resolving the customer request when the customer request matches one or more help center articles.

2. The method of claim 1 , wherein generating the word vector for each word in the new set of words involves using the Word2vec technique to generate the word vector for each word in the new set of words.

3. The method of claim 1 , wherein feeding the set of word vectors through the one or more neural networks comprises:

feeding the set of word vectors through a recurrent neural network to produce a preliminary request vector representing the customer request; and

feeding the preliminary request vector through a feed-forward neural network to produce the request vector.

4. The method of claim 3 , wherein the recurrent neural network comprises a long short-term memory (LSTM) network; and

wherein the feed-forward neural network modifies the preliminary request vector in a manner that moves request vectors and article vectors for responsive articles closer together.

5. The method of claim 1 , wherein comparing the request vector against the article vectors involves calculating cosine distances between the request vector and the article vectors.

6. The method of claim 1 , wherein prior to receiving the customer request, the method further comprises training the model used to generate the request vector and the article vectors, by:

initially training the model on a first set of customer requests and responsive textual responses from customer support agents that successfully resolved the first set of customer requests; and

refining the initially trained model based on a second set of customer requests and responsive articles that successfully resolved the second set of customer requests.

7. The method of claim 1 , wherein the method further comprises:

upon receiving notice of a change to an article in the set of help center articles, including the changed article in the set of help center articles and updating the model used to generate the request vector and the article vectors based on the changed article.

8. The method of claim 1 , wherein the method further comprises:

upon receiving notice of a new article to be included in the set of help center articles, including the new article in the set of help center articles and updating the model used to generate the request vector and the article vectors based on the new article.

9. The method of claim 1 , wherein the method further comprises:

receiving feedback from the customer regarding whether the one or more help center articles were helpful in resolving the customer request; and

using the feedback to update the model used to generate the request vector and the article vectors.

10. The method of claim 1 , wherein the customer request includes a question from the customer about the product or the service used by the customer.

11. The method of claim 1 , wherein the customer request comprises a ticket associated with a customer issue in a help center ticketing system.

12. The method of claim 1 , wherein the set of help center articles comprises client-specific articles associated with a client's account.

13. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for automatically suggesting helpful articles to resolve a customer request, the method comprising:

receiving the customer request by the computer, wherein the customer request is associated with a product or a service;

feeding words from the customer request through a model to generate a request vector representing words in the customer request;

wherein generating the request vector comprises;

obtaining a set of words from the customer request, by combining a subject field and a description field from the customer request into a blob of text, feeding the blob of text through a regex processor to remove text that does not comprise words to produce a refined blob of text, and selecting a new set of words from the refined blob of text,

producing a set of word vectors by generating a word vector for each word in the new set of words,

feeding the set of word vectors through a recurrent neural network to produce a preliminary request vector representing the customer request, and

feeding the preliminary request vector through a feed-forward neural network to generate the request vector;

comparing the request vector against article vectors representing articles in a set of help center articles to determine whether the customer request matches one or more help center articles; and

presenting the one or more help center articles to a customer to facilitate automatically resolving the customer request when the customer request matches one or more help center articles.

14. The non-transitory computer-readable storage medium of claim 13 , wherein generating the word vector for each word in the new set of words involves using the Word2vec technique to generate the word vector for each word in the new set of words.

15. The non-transitory computer-readable storage medium of claim 13 , wherein feeding the set of word vectors through the one or more neural networks comprises:

feeding the set of word vectors through a recurrent neural network to produce a preliminary request vector representing the customer request; and

feeding the preliminary request vector through a feed-forward neural network to produce the request vector.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the recurrent neural network comprises a long short-term memory (LSTM) network; and

wherein the feed-forward neural network modifies the preliminary request vector in a manner that moves request vectors and article vectors for responsive articles closer together.

17. The non-transitory computer-readable storage medium of claim 13 , wherein comparing the request vector against the article vectors involves calculating cosine distances between the request vector and the article vectors.

18. The non-transitory computer-readable storage medium of claim 13 , wherein prior to receiving the customer request, the method further comprises training the model used to generate the request vector and the article vectors, by:

initially training the model on a first set of customer requests and responsive textual responses from customer support agents that successfully resolved the first set of customer requests; and

refining the initially trained model based on a second set of customer requests and responsive articles that successfully resolved the second set of customer requests.

19. The non-transitory computer-readable storage medium of claim 13 , wherein the method further comprises:

upon receiving notice of a change to an article in the set of help center articles, including the changed article in the set of help center articles and updating the model used to generate the request vector and the article vectors based on the changed article.

20. The non-transitory computer-readable storage medium of claim 13 , wherein the method further comprises:

upon receiving notice of a new article to be included in the set of help center articles including the new article in the set of help center articles; and

updating the model used to generate the request vector and the article vectors based on the new article.

21. The non-transitory computer-readable storage medium of claim 13 , wherein the method further comprises:

receiving feedback from the customer regarding whether the one or more help center articles were helpful in resolving the customer request; and

using the feedback to update the model used to generate the request vector and the article vectors.

22. The non-transitory computer-readable storage medium of claim 13 , wherein the customer request includes a question from the customer about the product or the service used by the customer.

23. The non-transitory computer-readable storage medium of claim 13 , wherein the customer request comprises a ticket associated with a customer issue in a help center ticketing system.

24. The non-transitory computer-readable storage medium of claim 13 , wherein the set of help center articles comprises client-specific articles associated with a client's account.

25. A system that suggests helpful articles to automatically resolve a customer request, comprising:

at least one processor and at least one associated memory; and

a request-processing mechanism that executes on the at least one processor, wherein during operation, the request-processing mechanism:

receives the customer request, wherein the customer request is associated with a product or a service;

feeds words from the customer request through a model to generate a request vector representing words in the customer request;

wherein generating the request vector comprises:

obtaining a set of words from the customer request, by combining a subject field and a description field from the customer request into a blob of text, feeding the blob of text through a regex processor to remove text that does not comprise words to produce a refined blob of text, and selecting a new set of words from the refined blob of text,

producing a set of word vectors by generating a word vector for each word in the new set of words,

feeding the set of word vectors through a recurrent neural network to produce a preliminary request vector representing the customer request, and

feeding the preliminary request vector through a feed-forward neural network to generate the request vector;

compares the request vector against article vectors representing articles in a set of help center articles to determine whether the customer request matches one or more help center articles; and

presents the one or more help center articles to the customer to facilitate automatically resolving the customer request when the customer request matches one or more help center articles.