Ontology based customer support techniques

• US 9,177,319 B1
• Filed: 03/21/2012
• Issued: 11/03/2015
• Est. Priority Date: 03/21/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Chheda, Mahendra M.
• Primary Examiner(s): Nguyen, Kira
• Application Number:
  US13/426,409
• Time in Patent Office: 1,322 Days
• Field of Search: 705/304
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

Methods and systems for providing customer support in response to support communication are disclosed. Such communications may be structured or unstructured, and unstructured communications may be subject to further processing. A determination is made at least as to one or more relevant support classes, as well as to whether further support action(s) should be initiated. When determined that at least a further support action should be initiated, aspects of the support action may be determined and initiated.

Claims

1. A computer-implemented method for processing customer communications, comprising:

generating, by a computer system, a tree associated with services of a resource provider, nodes of the tree indicative of the services and associated support classes of the resource provider, the services offered to a plurality of customers based at least in part on device configurations of the resource provider remotely usable by the plurality of customers;

obtaining, by the computer system, a plurality of structured customer communications over a period of time, a structured customer communication of the plurality of structured customer communications formatted based at least in part on a predefined field of an interface, by at least;

(a) receiving the structured customer communication that is at least directed, by a customer of the plurality of customers of the resource provider, to a support entity that is configured to receive the structured customer communication; and

(b) upon detection of a trigger indicating communication between the customer and a third party, at least;

(i) receiving an unstructured customer communication based at least in part on the trigger, the unstructured customer communication including a freeform communication; and

(ii) processing the received unstructured customer communication to generate the structured customer communication;

inferring, by the computer system, customer information indicating a potential device configuration of the resource provider associated with the obtained plurality of structured customer communications, the inferring comprising;

(a) comparing customer data from the generated structured customer communication to resource provider data within the nodes of the tree;

(b) identifying a node of the tree as representing a potential service provided to the customer based at least in part on the comparing; and

(c) identifying the potential device configuration based at least in part on the potential service;

setting a device configuration remotely utilized by the customer from the device configurations of the resource provider as the potential device configuration based at least in part on analyzing the obtained plurality of structured customer communications and the inferred customer information;

determining one or more support classes that are relevant to the analyzed obtained plurality of structured customer communications based at least in part on the device configuration and the node representing the potential service;

determining whether to initiate support workflows relevant to the determined one or more support classes; and

based at least in part on determining that the support workflows should be initiated;

(a) determining, using at least the analyzed plurality of structured customer communications, appropriate workflow sequences for the support workflows; and

(b) executing the determined appropriate workflow sequences; and

(c) notifying the customer of the executed workflow sequence.

2. The computer-implemented method of claim 1, wherein the trigger is detected by a listener computer system that is configured to track use, on public communications network presences, of handles or metadata tags, the handles including at least identities associated with the customer, the metadata tags including at least hashtags.

3. The computer-implemented method of claim 1, wherein the detected trigger is detected use of at least one metadata tag among a plurality of predetermined triggering metadata tags.

4. The computer-implemented method of claim 1, wherein the received unstructured customer communication is processed by applying at least one natural language processing technique.

5. The computer-implemented method of claim 1,

wherein the inferred information indicating the potential device configuration utilized is based at least in part on querying a customer master computer system that at least stores information about the customer.

21. The computer-implemented method of claim 1, wherein the inferred information indicating a resource configuration utilized by the customer is different than the information in the obtained structured customer communications and/or the one or more support classes.

22. The computer-implemented method of claim 1, further comprises, at a time after determining that the support workflows should be initiated, scheduling the determined workflow sequences.

23. The computer-implemented method of claim 1, wherein the appropriate workflow sequence comprises a number of device commands to be executed on a resource provided by the resource provider.

6. A computer-implemented method for processing customer communications, comprising:

generating a tree associated with services of a resource provider, nodes of the tree representative of the services and associated support classes of the resource provider, the services offered to a plurality customers based at least in part on device configurations of the resource provider remotely usable by the plurality of customers;

upon detection of a trigger indicating communication between a customer of the plurality of customers of the resource provider and a third party, at least;

(a) receiving, by a computer system, an unstructured communication relating to a support class based at least in part on the detection of the trigger, the support class associated with a service of the services of the resource provider; and

(b) processing the received unstructured communication to generate a structured communication;

inferring, by the computer system, customer information indicating a potential device configuration of the resource provider based at least in part on the generated structured communication, the inferring comprising;

(a) comparing customer data from the generated structured communication to resource provider data within the nodes of the tree;

(b) identifying a node of the tree as representing a potential service provided to the customer based at least in part on the comparing; and

(c) identifying the potential device configuration based at least in part on the potential service;

setting a device configuration remotely utilized by the customer from the device configurations of the resource provider as the potential device configuration based at least in part on analyzing the generated structured communication and the inferred customer information;

determining the support class that relates to the received unstructured communication based at least in part on the device configuration and the node representing the potential service;

determining whether to initiate a support workflow relevant to the support class based at least in part on determining the support class; and

based at least in part on determining that the support workflow should be initiated, at least;

(a) determining, using at least the analyzed structured communication, an appropriate workflow sequence for the support workflow; and

(b) executing the determined appropriate workflow sequence.

7. The computer-implemented method of claim 6, wherein the determination of whether to initiate the support workflow further includes at least an analysis of the inferred customer information and wherein the determination of the appropriate workflow sequence further includes at least an analysis of the inferred customer information.

8. The computer-implemented method of claim 7, wherein the customer information is inferred by querying a customer master entity that stores the customer information for a plurality of customers, and further comprising submitting information at least relating to the executed workflow sequence to the customer master entity, such that the workflow sequence-related information is correlated with the associated customer by the customer master entity.

9. The computer-implemented method of claim 6, wherein the determined support class is selected, based on the analysis of the structured communication, from among a plurality of support classes organized into the tree.

10. The computer-implemented method of claim 6, wherein the determination of whether to initiate the support workflow is further determined by analyzing outcomes of past determinations of whether to initiate support workflows.

24. The computer-implemented method of claim 6, wherein processing the unstructured communication comprises applying one or more of linguistic stemming, determination of word weights, or determination of word proximities to generate the structured communication according to a format for traversing the tree, and wherein determining the device configuration utilized by the customer comprises selecting a node from the one or more nodes based at least in part on a relationship between the customer data from the generated structured communication.

11. A computer system for processing customer communications, comprising:

one or more processors; and

memory, including instructions executable by the one or more processors to cause the computer system to at least;

generate a tree associated with services of a resource provider, nodes of the tree representative of the services and associated support categories of the resource provider, the services offered to a plurality of customers based at least in part on device configurations of the resource provider remotely usable by the plurality of customers;

detect triggers that indicate an existence of a freeform communication of a customer of the plurality of customers of the resource provider with a third party provider relevant to a support entity;

upon detecting a trigger of the triggers that indicates a communication between a customer of the resource provider and the third party provider, process the freeform communication, by at least applying at least one data cleansing technique, to generate support data;

infer information indicating a potential device configuration of the resource provider associated with the generated support data, the inference causing the computer system to at least;

(a) compare customer data from the generated support data to resource provider data from the nodes of the tree;

(b) identify a node of the tree as representing a potential service provided to the customer based at least in part on the compare; and

(c) identify the potential device configuration based at least in part on the potential service;

set a device configuration remotely utilized by the customer from the device configurations of the resource provider as the potential device configuration based at least in part on analyze an analysis of the generated support data and the inferred information;

determine a support category related to the generated support data based at least in part on the device configuration and the node representing the potential service;

determine whether to initiate a support action based at least in part on the support category; and

based at least in part on determining that the support action should be initiated, at least;

(a) analyze the generated support data to define the support action; and

(b) perform the defined support action.

12. The computer system of claim 11, wherein the instructions further cause the computer system to provide, to the customer, information related to at least one of the generated support data or the support action.

13. The computer system of claim 11, wherein the instructions further cause the computer system to at least perform the defined support action by submitting information related to the defined support action to an entity associated with the determined support category.

14. The computer system of claim 13, wherein the instructions further cause the computer system to receive, from the entity associated with the determined support category, data related to the performed support action.

15. The computer system of claim 14, wherein the instructions further cause the computer system to provide, to the customer, data related to the performed support action.

16. The computer system of claim 13, wherein the performed support action is a response, to the customer, indicating at least operational metrics of the determined support category.

17. One or more non-transitory computer-readable storage media having collectively stored thereon executable instructions that, when executed by one or more processors of a computing resource provider'"'"'s computer system, cause the computer system to at least:

generate a tree associated with services of a resource provider, nodes of the tree representative of the services and associated support categories of the resource provider, the services offered to a plurality of customers based at least in part on resource configurations of the resource provider remotely usable by the plurality of customers;

receive information from a customer of the plurality of customers of the resource provider that relates to a support category based at least in part on detecting a trigger indicating communication of the customer with a third party;

infer information indicating a potential resource configuration of the resource provider, the inference comprising;

(a) comparing customer data associated with the received information to resource provider data from the nodes of the tree;

(b) identifying a node of the tree as representing a potential service provided to the customer based at least in part on the comparing; and

(c) identifying the potential resource configuration based at least in part on the potential service;

set a resource configuration remotely utilized by the customer from the resource configurations of the resource provider as the potential resource configuration based at least in part on analyzing the received information from the customer and the inferred information;

determine the support category related to the received information from the customer based at least in part on the resource configuration and the node representing the potential service;

determine whether the received information from the customer relates to customer support needs that are related to the determined support category;

based at least in part on determining that the received information from the customer relates to customer support needs, determine whether the customer support needs necessitate support action sequences that are at least related to the support category; and

based at least in part on determining that the customer support needs necessitate the support action sequences, at least;

(a) determine support steps of the support action sequences; and

(b) execute the support steps.

18. The computer-readable storage media of claim 17, wherein the determined support steps are, at least in part, automatically executed by an entity of the computer system.

19. The computer-readable storage media of claim 17, wherein the determined support steps are, at least in part, executed by entities related to the support categories.

20. The computer-readable storage media of claim 17, wherein the received information from a customer is submitted by a listener computer system associated with a public communications network presence.