Methods and systems for partitioning documents having customer feedback and support content

• US 9,436,758 B1
• Filed: 06/22/2012
• Issued: 09/06/2016
• Est. Priority Date: 12/27/2011
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Lewis, Glenn M., Buryak, Kirill, Benbarak, Nadav, Ben-Artzi, Aner, Peng, Jun
• Primary Examiner(s): Dwivedi, Mahesh
• Application Number:
  US13/530,619
• Time in Patent Office: 1,537 Days
• Field of Search: 707/737
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/35 Clustering; Classification

Abstract

Methods and systems for use in partitioning documents having customer feedback and support content are provided. One exemplary computer-implemented method including executing instructions stored on a computer-readable medium includes receiving a plurality of documents, at least a portion of the plurality of documents including customer feedback related to an issue and support content responsive to the customer feedback, filtering the plurality of documents to retain one of the customer feedback and the support content within a plurality of filtered documents, partitioning the plurality of filtered documents into multiple clusters, receiving a new document, and partitioning the new document based on at least one keyword included in one of the multiple clusters of filtered documents.

Claims

1. A computer-implemented method including executing instructions stored on a non-transitory computer-readable storage medium, said method comprising:

receiving a plurality of documents from a plurality of different communication channels, at least a portion of the plurality of documents including a set of content representing an interaction between a user and a support entity, wherein the set of content includes both customer feedback content received from a user, and support content provided by the support entity and to the user responsive to the customer feedback content;

identifying, within each document of the portion of the received plurality of documents, the customer feedback content received from a user and the support content provided to the user responsive to the customer feedback;

filtering, by a processor executing the instructions, the portion of the received plurality of documents, including removing the customer feedback content and retaining the support content;

partitioning, after the filtering, the plurality of filtered documents, in which the customer feedback has been removed, into multiple clusters based on the support content of each of the plurality of filtered documents;

after the partitioning, for each filtered document in each cluster of the multiple clusters, associating the customer feedback content that was filtered from the filtered document with the cluster to which the filtered document belongs and the retained support content from that filtered document, and storing association information in memory;

receiving a new document including customer feedback related to an issue;

determining, using the association information in the memory, that the customer feedback of the new document matches the customer feedback content associated with one of the clusters; and

providing, over a communication connection with a user associated with the new document, the retained support content associated with the cluster based on the match between the customer feedback of the new document and the customer feedback content that was associated with the cluster after the partitioning.

2. The method of claim 1, wherein the support content of at least one of the filtered documents comprises a term descriptive of a product or a service.

3. The method of claim 1, wherein partitioning the plurality of filtered documents into multiple clusters comprises categorizing the support content of each of the plurality of filtered documents according to a topic associated with said one of the multiple clusters.

4. The method of claim 1, wherein the plurality of different communication channels includes at least one of an email thread, a chat thread, and a help forum thread between a user and a customer service representative.

5. The method of claim 1, wherein the support content includes at least one support solution, and wherein partitioning the plurality of filtered documents includes partitioning the plurality of filtered documents based on the at least one support solution.

6. The method of claim 1, further comprising generating a report indicating at least one topic associated with said one of the multiple clusters.

7. The method of claim 5, where the at least one support solution comprises predetermined response.

8. The method of claim 1, wherein receiving the plurality of documents includes retrieving the plurality of documents from a database configured to store the plurality of documents.

9. A computer system for use in partitioning a plurality of documents, said computer system comprising:

a plurality of processing engines; and

a non-transitory memory device accessible by said processing engines, said memory device for storing a plurality of documents, at least a portion of the plurality of documents including customer feedback content and support content responsive to the customer feedback content,

wherein said plurality of processing engines are configured to perform the operations of;

receiving a plurality of documents from a plurality of different communication channels, at least a portion of the plurality of documents including a set of content representing an interaction between a user and a support entity, wherein the set of content includes both customer feedback content received from a user, and support content provided by the support entity and to the user responsive to the customer feedback content;

identifying, within each document of the portion of the received plurality of documents, the customer feedback content received from a user and the support content provided to the user responsive to the customer feedback;

filtering, by a processor executing the instructions, the portion of the received plurality of documents, including removing the customer feedback content and retaining the support content;

partitioning, after the filtering, the plurality of filtered documents, in which the customer feedback has been removed, into multiple clusters based on the support content of each of the plurality of filtered documents;

after the partitioning, for each filtered document in each cluster of the multiple clusters, associating the customer feedback content that was filtered from the filtered document with the cluster to which the filtered document belongs and the retained support content from that filtered document, and storing association information in memory;

receiving a new document including customer feedback related to an issue;

determining, using the association information in the memory, that the customer feedback of the new document matches the customer feedback content associated with one of the clusters; and

providing, over a communication connection with a user associated with the new document, the retained support content associated with the cluster based on the match between the customer feedback of the new document and the customer feedback content that was associated with the cluster after the partitioning.

10. The system of claim 9, wherein partitioning the plurality of filtered documents into multiple clusters comprises categorizing the support content of each of the plurality of filtered documents according to a topic associated with said one of the multiple clusters.

11. The system of claim 9, wherein the support content includes at least one support solution, and wherein partitioning the plurality of filtered documents includes partitioning the plurality of filtered documents based on the at least one support solution.

12. The system of claim 9, wherein the plurality of documents comprises at least one of an email thread, a chat thread, and a help forum thread between a user and a customer service representative.

13. A non-transitory computer-readable storage device having encoded thereon computer readable instructions, which when executed by a processor, cause the processor to:

retrieve a plurality of documents from a database, at least a portion of the plurality of documents including a set of content representing an interaction between a user and a support entity, wherein the set of content includes both customer feedback content received from a user, and support content provided by the support entity and to the user responsive to the customer feedback content;

identify, within each document of the portion of the received plurality of documents, the customer feedback content received from a user and the support content provided to the user responsive to the customer feedback;

filter the portion of the plurality of documents, including removing the customer feedback content and retaining the support content;

partition, after the filtering, the plurality of filtered documents, in which the customer feedback has been removed, into multiple clusters based on the support content of each of the plurality of filtered documents;

after the partitioning, for each filtered document in each cluster of the multiple clusters, associate the customer feedback content that was filtered from the filtered document with the cluster to which the filtered document belongs and the retained support content from that filtered document, and storing association information in memory;

receive a new document including customer feedback related to an issue;

determine, using the association information the in memory, that the customer feedback of the new document matches the customer feedback content associated with one of the clusters; and

provide, over a communication connection with a user associated with the new document, the retained support content associated with the cluster based on the match between the customer feedback of the new document and the customer feedback content that was associated with the cluster after the partitioning.

14. The computer-readable storage device of claim 13, wherein the support content of at least one of the filtered documents comprises a term descriptive of a product or a service.

15. The computer-readable storage device of claim 13, wherein partitioning the plurality of filtered documents into multiple clusters comprises categorizing the support content of each of the plurality of filtered documents according to a topic associated with said one of the multiple clusters.

16. The computer-readable storage device of claim 13, wherein the plurality of different communication channels includes at least one of an email thread, a chat thread, and a help forum thread between a user and a customer service representative.

17. The computer-readable storage device of claim 13, wherein the support content includes at least one support solution, and wherein partitioning the plurality of filtered documents includes partitioning the plurality of filtered documents based on the at least one support solution.

18. The computer-readable storage device of claim 13, further comprising generating a report indicating at least one topic associated with said one of the multiple clusters.