# US 2017/0286970 A1 · Answer-suggestion system for automatically resolving customer requests

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0286970 A1
- Document ID: US20170286970A1
- Status: Published application
- Kind: A1
- Application number: 15/087,755
- Filed: 2016-03-31
- Published: 2017-10-05
- Earliest claimed: 2016-03-31
- Assignees: Zendesk, Inc.
- Applicants: Zendesk, Inc.
- Inventors: Thomas Pelletier
- Web page: https://patentgrep.com/patent/US20170286970A1

## CPC

- G06Q 30/016: After-sales
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The disclosed embodiments relate to a system that suggests helpful articles to automatically resolve a customer request. During operation, the system receives the customer request, wherein the customer request is associated with a product or a service used by the customer. Next, the system determines whether the customer request matches one or more similar previously received customer requests. If so, the system identifies one or more helpful articles that were useful in resolving the one or more previously received customer requests, and then uses the one or more helpful articles to generate a set of suggested articles. Finally, the system presents the set of suggested articles to the customer to facilitate automatically resolving the customer request.

## Claims

### Claim 1

A method for suggesting helpful articles to automatically resolve a customer request, comprising:
receiving the customer request, wherein the customer request is associated with a product or a service used by the customer;
using a search engine to select a preliminary set of suggested articles from a set of possible articles based on correlations between words in the customer request and words in the set of possible articles;
determining whether the customer request matches one or more similar previously received customer requests;
if the customer request matches one or more previously received customer requests,
identifying one or more helpful articles that were useful in resolving the one or more previously received customer requests, and
modifying the preliminary set of suggested articles based on the one or more helpful articles to produce the set of suggested articles;
if the customer request does not match any of the previously received customer requests, using the preliminary set of suggested articles as the set of suggested articles; and
presenting the set of suggested articles to the customer to facilitate automatically resolving the customer request.

### Claim 2 (depends on 1)

The method of claim 1, wherein modifying the preliminary set of suggested articles based on the one or more helpful articles includes re-ranking the preliminary set of suggested articles based on whether any of the preliminary set of articles also appears in the one or more helpful articles.

### Claim 3 (depends on 1)

The method of claim 1, wherein modifying the preliminary set of suggested articles based on the one or more helpful articles includes inserting at least one of the one or more helpful articles into the preliminary set of suggested articles.

### Claim 4 (depends on 1)

The method of claim 1, wherein the method further comprises:
receiving feedback from the customer regarding whether the one or more suggested articles were helpful in resolving the customer request; and
using the feedback to update a model used to identify helpful articles to resolve future customer requests.

### Claim 5 (depends on 4)

The method of claim 4, wherein receiving the feedback from the customer includes receiving the feedback through a user interface that displays a suggested article along with user interface elements that enable the customer to provide feedback.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining whether the customer request matches one or more similar previously received customer requests includes:
using words from the customer request to generate a vector of numerical values representing the customer request; and
comparing the vector representing the customer request against vectors representing previously received customer requests to determine whether the customer request matches one or more similar previously received customer requests.

### Claim 7 (depends on 6)

The method of claim 6, wherein generating the vector includes using the Doc2Vec technique to generate the vector to represent the customer request.

### Claim 8 (depends on 1)

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.

### Claim 9 (depends on 1)

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

### Claim 10 (depends on 9)

The method of claim 9, wherein the method is performed asynchronously by the help desk system after the ticket is initially processed by the help desk ticketing system.

### Claim 11

A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for suggesting helpful articles to automatically resolve a customer request, the method comprising:
receiving the customer request, wherein the customer request is associated with a product or a service used by the customer;
using a search engine to select a preliminary set of suggested articles from a set of possible articles based on correlations between words in the customer request and words in the set of possible articles;
determining whether the customer request matches one or more similar previously received customer requests;
if the customer request matches one or more previously received customer requests,
identifying one or more helpful articles that were useful in resolving the one or more previously received customer requests; and
modifying the preliminary set of suggested articles based on the one or more helpful articles to produce the set of suggested articles;
if the customer request does not match any of the previously received customer requests, using the preliminary set of suggested articles as the set of suggested articles; and
presenting the set of suggested articles to the customer to facilitate automatically resolving the customer request.

### Claim 12 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein modifying the preliminary set of suggested articles based on the one or more helpful articles includes re-ranking the preliminary set of suggested articles based on whether any of the preliminary set of articles also appears in the one or more helpful articles.

### Claim 13 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein modifying the preliminary set of suggested articles based on the one or more helpful articles includes inserting at least one of the one or more helpful articles into the preliminary set of suggested articles.

### Claim 14 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the method further comprises:
receiving feedback from the customer regarding whether the one or more suggested articles were helpful in resolving the customer request; and
using the feedback to update a model used to identify helpful articles to resolve future customer requests.

### Claim 15 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein receiving the feedback from the customer includes receiving the feedback through a user interface that displays a suggested article along with user interface elements that enable the customer to provide feedback.

### Claim 16 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein determining whether the customer request matches one or more similar previously received customer requests includes:
using words from the customer request to generate a vector of numerical values representing the customer request; and
comparing the vector representing the customer request against vectors representing previously received customer requests to determine whether the customer request matches one or more similar previously received customer requests.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein generating the vector includes using the Doc2Vec technique to generate the vector to represent the customer request.

### Claim 18 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the customer request includes a question from the customer about the product or the service used by the customer.

### Claim 19 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the customer request comprises a ticket associated with a customer issue in a help desk ticketing system.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the method is performed asynchronously by the help desk system after the ticket is initially processed by the help desk ticketing system.

### Claim 21

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 used by the customer;
uses a search engine to select a preliminary set of suggested articles from a set of possible articles based on correlations between words in the customer request and words in the set of possible articles;
determines whether the customer request matches one or more similar previously received customer requests;
if the customer request matches one or more previously received customer requests,
identifies one or more helpful articles that were useful in resolving the one or more previously received customer requests, and
modifies the preliminary set of suggested articles based on the one or more helpful articles to produce the set of suggested articles;
if the customer request does not match any of the previously received customer requests, uses the preliminary set of suggested articles as the set of suggested articles; and
presents the set of suggested articles to the customer to facilitate automatically resolving the customer request.

### Claim 22 (depends on 21)

The system of claim 21, wherein while modifying the preliminary set of suggested articles based on the one or more helpful articles, the request-processing mechanism re-ranks the preliminary set of suggested articles based on whether any of the preliminary set of articles also appears in the one or more helpful articles.

### Claim 23 (depends on 21)

The system of claim 21, wherein while modifying the preliminary set of suggested articles based on the one or more helpful articles, the request-processing mechanism inserts at least one of the one or more helpful articles into the preliminary set of suggested articles.

### Claim 24 (depends on 21)

The system of claim 21, wherein the request-processing mechanism additionally:
receives feedback from the customer regarding whether the one or more suggested articles were helpful in resolving the customer request; and
uses the feedback to update a model used to identify helpful articles to resolve future customer requests.

### Claim 25 (depends on 24)

The system of claim 24, wherein while receiving the feedback from the customer the request-processing mechanism receives the feedback through a user interface that displays a suggested article along with user interface elements that enable the customer to provide feedback.

### Claim 26 (depends on 21)

The system of claim 21, wherein while determining whether the customer request matches one or more similar previously received customer requests, the request-processing mechanism:
uses words from the customer request to generate a vector of numerical values representing the customer request; and
compares the vector representing the customer request against vectors representing previously received customer requests to determine whether the customer request matches one or more similar previously received customer requests.

### Claim 27 (depends on 26)

The system of claim 26, wherein while generating the vector, the request-processing mechanism uses the Doc2Vec technique to generate the vector to represent the customer request.

### Claim 28 (depends on 21)

The system of claim 21, wherein the customer request includes a question from the customer about the product or the service used by the customer.

### Claim 29 (depends on 21)

The system of claim 21, wherein the customer request comprises a ticket associated with a customer issue in a help desk ticketing system.

### Claim 30 (depends on 29)

The system of claim 29, wherein the request-processing system operates asynchronously after the ticket is initially processed by the help desk ticketing system.
