Systems, media, and methods for automated response to queries made by interactive electronic chat

• US 9,785,715 B1
• Filed: 04/28/2017
• Issued: 10/10/2017
• Est. Priority Date: 04/29/2016
• Status: Active Grant

• Current Assignee: LivePerson Incorporated
• Original Assignee: Conversable, Inc. (LivePerson Incorporated)
• Inventors: Busey, Andrew Thomas, Chen, Anthony Dan, Jonas, Isao Uchida, Daniels, Jr., Douglas James, Lamm, Benjamin Edward
• Primary Examiner(s): Stevens, Robert
• Application Number:
  US15/582,209
• Time in Patent Office: 165 Days
• Field of Search: 707706
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Systems, media, and methods for automated response to social queries comprising: monitoring queries from users, each query submitted to a vendor via an interactive chat feature of an external electronic communication platform, monitoring human responses to the queries, monitoring subsequent communications conducted via the electronic communication platform until each query is resolved; applying a first machine learning algorithm to the monitored communications to identify a query susceptible to response automation; applying a second machine learning algorithm to the query susceptible to response automation to identify one or more responses likely to resolve the query; and either i) notifying a human to respond to the query susceptible to response automation with the one or more responses likely to resolve the query, or ii) instantiating an autonomous software agent configured to respond to the query susceptible to response automation with the one or more responses likely to resolve the query.

Claims

1. A computer-implemented system comprising:

a digital processing device comprising;

at least one processor, an operating system configured to perform executable instructions, a memory, and a computer program including instructions executable by the digital processing device to create a social query response application comprising;

a) a software module monitoring queries from users, each query submitted to a vendor via an interactive chat feature of an external electronic communication platform, monitoring human responses to the queries, and monitoring subsequent communications conducted via the electronic communication platform until each query is resolved;

b) a software module applying a first machine learning algorithm to the monitored communications to identify one or more queries susceptible to response automation; and

c) a software module applying a second machine learning algorithm to the queries susceptible to response automation to identify one or more responses likely to resolve the query.

2. The system of claim 1, wherein the interactive chat is typed or verbal.

3. The system of claim 1, wherein the application further comprises:

a) a software module receiving a query from a user, the query submitted to the vendor via an interactive chat feature of an external electronic communication platform;

b) a software module automatically responding to the query with the identified one or more responses likely to resolve the query;

c) a software module determining when the query is resolved; and

d) a software module transmitting the outcome of the resolution to an enterprise software system.

4. The system of claim 1, wherein the application further comprises a software module identifying a user sending each query and retrieving data pertaining to previous interactions between the user and the vendor.

5. The system of claim 4, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the data pertaining to previous interactions.

6. The system of claim 1, wherein the application further comprises a software module providing an administrative interface allowing an administrator to add, remove, and edit automated responses.

7. The system of claim 1, wherein the application further comprises a software module notifying a human to respond to a query susceptible to response automation with one or more responses likely to resolve the query.

8. The system of claim 7, wherein the software module notifying a human to respond provides suggested responses and, for each, a percentage of users who respond with the suggested response.

9. The system of claim 1, wherein the application further comprises a software module instantiating an autonomous software agent to respond to a query susceptible to response automation with one or more responses likely to resolve the query.

10. The system of claim 1, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the historic number of communications required to resolve similar queries.

11. Non-transitory computer-readable storage media encoded with a computer program including instructions executable by a processor to create a social query response application comprising:

a) a software module monitoring queries from users, each query submitted to a vendor via an interactive chat feature of an external electronic communication platform, monitoring human responses to the queries, and monitoring subsequent communications conducted via the electronic communication platform until each query is resolved;

b) a software module applying a first machine learning algorithm to the monitored communications to identify one or more queries susceptible to response automation; and

c) a software module applying a second machine learning algorithm to the queries susceptible to response automation to identify one or more responses likely to resolve the query.

12. The media of claim 11, wherein the interactive chat is typed or verbal.

13. The media of claim 11, wherein the application further comprises:

a) a software module receiving a query from a user, the query submitted to the vendor via an interactive chat feature of an external electronic communication platform;

b) a software module automatically responding to the query with the identified one or more responses likely to resolve the query;

c) a software module determining when the query is resolved; and

d) a software module transmitting the outcome of the resolution to an enterprise software system.

14. The media of claim 11, wherein the application further comprises a software module identifying a user sending each query and retrieving data pertaining to previous interactions between the user and the vendor.

15. The media of claim 14, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the data pertaining to previous interactions.

16. The media of claim 11, wherein the application further comprises a software module providing an administrative interface allowing an administrator to add, remove, and edit automated responses.

17. The media of claim 11, wherein the application further comprises a software module notifying a human to respond to a query susceptible to response automation with one or more responses likely to resolve the query.

18. The media of claim 17, wherein the software module notifying a human to respond provides suggested responses and, for each, a percentage of users who respond with the suggested response.

19. The media of claim 11, wherein the application further comprises a software module instantiating an autonomous software agent to respond to a query susceptible to response automation with one or more responses likely to resolve the query.

20. The media of claim 11, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the historic number of communications required to resolve similar queries.

21. A computer-implemented method of social query response comprising:

a) monitoring, by a computer, queries from users, each query submitted to a vendor via an interactive chat feature of an external electronic communication platform,

b) monitoring, by the computer, human responses to the queries,

c) monitoring, by the computer, subsequent communications conducted via the electronic communication platform until each query is resolved;

d) applying, by the computer, a first machine learning algorithm to the monitored communications to identify a query susceptible to response automation;

e) applying, by the computer, a second machine learning algorithm to the query susceptible to response automation to identify one or more responses likely to resolve the query; and

f) either i) notifying, by the computer, a human to respond to the query susceptible to response automation with the one or more responses likely to resolve the query, or ii) instantiating, by the computer, an autonomous software agent configured to respond to the query susceptible to response automation with the one or more responses likely to resolve the query.

22. The method of claim 21, wherein the interactive chat is typed or verbal.

23. The method of claim 21, further comprising:

a) receiving, by the computer, a query from a user, the query submitted to the vendor via an interactive chat feature of an external electronic communication platform;

b) automatically responding, by the computer, to the query with the identified one or more responses likely to resolve the query;

c) determining, by the computer, when the query is resolved; and

d) transmitting, by the computer, the outcome of the resolution to an enterprise software system.

24. The method of claim 21, wherein the method further comprises identifying, by the computer, a user sending each query and retrieving data pertaining to previous interactions between the user and the vendor.

25. The method of claim 24, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the data pertaining to previous interactions.

26. The method of claim 21, wherein the method further comprises providing, by the computer, an administrative interface allowing an administrator to add, remove, and edit automated responses.

27. The method of claim 21, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the historic number of communications required to resolve similar queries.

28. The method of claim 21, wherein the first machine learning algorithm or the second machine learning algorithm utilizes the historic number of communications required to resolve similar queries.

29. The method of claim 21, wherein the second machine learning algorithm utilizes a glossary, knowledge base, or enterprise database.

30. The method of claim 21, wherein the first machine learning algorithm or the second machine learning algorithm utilizes a user status.