Providing automatic self-support responses

• US 10,410,219 B1
• Filed: 09/30/2015
• Issued: 09/10/2019
• Est. Priority Date: 09/30/2015
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: El-Nakib, Eslam M.
• Primary Examiner(s): Vincent, David R
• Application Number:
  US14/871,471
• Time in Patent Office: 1,441 Days
• Field of Search: 706 15, 706 45
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

Providing automatic initial responses to service requests. An automated support engine receives a service request including a problem description from a client. A text analysis component analyzes the problem description to identify an issue. A search component searches response reference sources to identify a set of suggested solutions and a set of reference materials associated with the issue. The response reference sources include structured data materials and unstructured data materials. The automated support engine combines the set of suggested solutions and a set of links corresponding to the set of reference materials to generate an automatic initial response. The automated support engine sends the automatic initial response to the client to assist a user in resolving the identified issue.

Claims

1. A computer-implemented method executed by one or more processors, the method comprising:

receiving a service request from a user associated with the service request;

analyzing the service request, by the one or more processors, to identify at least one issue associated with the service request;

identifying (i) at least one suggested solution associated with resolving the at least one issue, and (ii) a set of reference materials associated with the at least one issue based on a search of a plurality of response reference sources;

generating an automatic initial response to the service request, by an automated support engine, the automatic initial response comprising the at least one suggested solution for resolving the at least one issue and at least one link corresponding to the set of reference materials;

sending the automatic initial response to the user associated with the service request;

receiving a score from the user associated with the service request, the received score rating a quality of the automatic initial response, the received score being associated with the at least one issue;

saving the received score to a database, the database comprising a plurality of other scores received from other users rating qualities of a plurality of other automatic initial responses;

analyzing at least some scores among the plurality of other scores in the database, each of the at least some scores being associated with a same issue as the at least one issue associated with the received score; and

modifying, by a training engine, a set of parameters associated with the automated support engine based on the analysis of the at least some scores to avoid generating new responses to the same issue, thereby increasing a speed in responding to service requests and reducing processor load.

2. The computer-implemented method of claim 1, wherein the service request comprises a problem description and further comprising:

parsing the problem description associated with the service request, by a text analyzer, to identify at least one keyword associated with the at least one issue; and

searching the plurality of response reference sources using the at least one keyword to identify the at least one suggested solution and the set of reference materials.

3. The computer-implemented method of claim 1, further comprising:

sending the automatic initial response to at least one technology service engineer associated with a service center.

4. The computer implemented method of claim 1, wherein searching the plurality of response reference sources further comprises:

searching a content of a text document to identify at least one reference material associated with the at least one issue.

5. The computer-implemented method of claim 1, wherein the plurality of response reference sources comprises a set of unstructured data materials, and further comprising:

searching the set of unstructured data materials by an unstructured data analyzer;

identifying a subset of the set of unstructured data materials associated with the at least one issue; and

adding at least one link corresponding to the subset of the set of unstructured data materials to the automatic initial response.

6. The computer-implemented method of claim 1, wherein generating the automatic initial response further comprises:

retrieving an automatic reply statement; and

adding the automatic reply statement to the automatic initial response.

7. A computing device comprising:

one or more processors;

a memory coupled to the one or more processors, the memory comprising a plurality of response reference materials;

a communications interface receiving a service request from a client, the service request comprising an issue to be resolved;

an automated support engine, the one or more processors executing the automated support engine to parse a problem description associated with the service request to identify the issue, search response history data to identify a pre-generated automatic initial response corresponding to the issue, and return the pre-generated automatic initial response to the client, the pre-generated automatic initial response comprising at least one suggested solution for resolving the issue associated with the service request and at least one link corresponding to a set of reference materials associated with the issue to be resolved, the set of reference materials comprising at least one unstructured data material associated with assisting a user in resolving the issue;

a scoring database comprising a plurality of user-generated scores, wherein a score comprises a rating of a quality of the pre-generated automatic initial response to a service request, a suggested solution to the issue, or a recommended reference material associated with the issue; and

a training engine, the training engine analyzing at least some scores among the plurality of user-generated scores, each of the at least some scores being associated with a same issue as the issue to be resolved, and modifying a set of parameters associated with the automated support engine based on the analysis of the at least some scores among the plurality of user-generated scores to avoid generating new responses to the same issue, thereby increasing a speed in responding to service requests and reducing processor load.

8. The computing device of claim 7, further comprising:

an unstructured data analyzer, wherein the unstructured data analyzer analyzes a set of unstructured data materials to identify the at least one unstructured data material in the set of unstructured data materials associated with the issue.

9. The computing device of claim 7, further comprising:

a text analyzer, wherein the text analyzer parses the problem description for a set of keywords; and

an advanced search engine, wherein the advanced search engine searches the plurality of response reference materials using the set of keywords to identify the set of reference materials.

10. The computing device of claim 7 further comprising:

a network connection, wherein the service request is received from the client via the network connection, and the pre-generated automatic initial response is sent to the client via the network connection.

11. The computing device of claim 7, wherein the plurality of response reference materials comprises at least one of documents, videos, knowledge base articles, community network data or response history data.

12. One or more computer storage media embodying computer executable instructions that, when executed, cause at least one processor to:

receive a service request from a user device;

parse the service request received from the user device to identify a set of keywords;

search a plurality of response reference sources based on the set of keywords to identify at least one suggested solution, the plurality of response reference sources comprising a set of unstructured data materials;

on condition of identifying at least one suggested solution, generate an automatic initial response to the service request, the automatic initial response comprising the at least one suggested solution to resolve an issue associated with the service request;

send the automatic initial response to the user device for display to a user to assist the user in resolving the issue;

on condition of receiving a score from the user device, save the received score with a plurality of other scores, the received score rating a quality of the automatic initial response, the plurality of other scores rating qualities of a plurality of other automatic initial responses;

analyze at least some scores among the plurality of other scores, each of the at least some scores being associated with a same issue as the issue associated with the service request; and

modify at least one parameter in a set of parameters associated with an automated support engine based on the analysis of the at least some scores to avoid generating new responses to the same issue, thereby increasing a speed in responding to service requests and reducing processor load.

13. The one or more computer storage media of claim 12, wherein the instructions are further executed to cause the at least one processor to:

on condition of identifying a set of reference materials in the plurality of response reference sources providing information associated with the issue, add at least one link corresponding to the set of reference materials to the automatic initial response.

14. The one or more computer storage media of claim 12, wherein the instructions are further executed to cause the at least one processor to:

retrieve an automatic reply statement; and

combine the automatic reply statement and the at least one suggested solution to generate the automatic initial response.

15. The one or more computer storage media of claim 12, wherein the plurality of response reference sources comprises at least one of documents, videos, knowledge base articles, community network data or response history data.