SEMANTIC INFERENCING IN CUSTOMER RELATIONSHIP MANAGEMENT

• US 20200134492A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: N3, LLC (Accenture PLC)
• Inventors: Copeland, Shannon L.
• Granted Patent: US 12,001,972 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

Customer relationship management (“CRM”) implemented in a computer system, including parsing, by a parsing engine of the computer system into parsed triples of a description logic, words of a CRM event from an incoming stream of CRM events, the CRM event characterized by an event type, the stream implemented in a CRM application of the computer system; and inferring, by an inference engine from the parsed triples according to inference rules specific to the event type, inferred triples.

Claims

1. A method of customer relationship management (“

CRM”

) implemented in a computer system, the method comprising;

parsing, by a parsing engine of the computer system into parsed triples of a description logic, words of a CRM event from an incoming stream of CRM events, the CRM event characterized by an event type, the stream implemented in a CRM application of the computer system; and

inferring, by an inference engine from the parsed triples according to inference rules specific to the event type, inferred triples.

2. The method of claim 1 wherein:

the method further comprises joining the parsed triples to triples of an event-related subgraph of an enterprise knowledge graph of the computer system; and

inferring further comprises inferring, by an inference engine from the joined triples according to inference rules specific to the event type, inferred triples.

3. The method of claim 1 wherein words of a CRM event further comprise words from a conversation between a tele-agent and a customer representative that are recognized by a natural language processing speech recognition (“

NLP-SR”

) engine into words of digitized speech.

4. The method of claim 1 wherein words of a CRM event further comprise a word from a text box widget of a CRM dashboard implemented in a graphical user interface of the computer system.

5. The method of claim 1 wherein words of a CRM event further comprise a word designated as an element of a parsed triple through a widget of a CRM dashboard implemented in a graphical user interface of the computer system.

6. The method of claim 1 wherein CRM events comprise activities that generate digitized words for parsing into triples that can be included in an enterprise knowledge graph.

7. The method of claim 1 wherein CRM events comprise activities that generate digital representations of new customers, new customer representatives, and new call notes.

8. The method of claim 1 further comprising storing a parsed triple in an enterprise knowledge graph of the computer system.

9. The method of claim 1 further comprising storing an inferred triple in an enterprise knowledge graph of the computer system.

10. The method of claim 1 further comprising:

determining whether the parsed triples and the inferred triples are already asserted in an enterprise knowledge graph of the computer system; and

storing in the enterprise knowledge graph only those parsed triples and inferred triples that are not already in the enterprise knowledge graph.

11. The method of claim 1 wherein the description logic is a member of a family of formal knowledge representation languages in which a query of the logic is decidable.

12. The method of claim 1 wherein the computer system comprises an enterprise knowledge graph composed of triples of the description logic comprising all CRM-related knowledge that is available to a tele-agent through the computer system.

13. A computer system that implements customer relationship management (“

CRM”

), the computer system comprising a computer processor operatively coupled to computer memory, the computer processor configured to function by;

parsing, by a parsing engine of the computer system into parsed triples of a description logic, words of a CRM event from an incoming stream of CRM events, the CRM event characterized by an event type, the stream implemented in a CRM application of the computer system; and

inferring, by an inference engine from the parsed triples according to inference rules specific to the event type, inferred triples.

14. The computer system of claim 13 wherein:

the computer processor configured to function by joining the parsed triples to triples of an event-related subgraph of an enterprise knowledge graph of the computer system; and

inferring further comprises inferring, by an inference engine from the joined triples according to inference rules specific to the event type, inferred triples.

15. The computer system of claim 13 wherein words of a CRM event further comprise words from a conversation between a tele-agent and a customer representative that are recognized by a natural language processing speech recognition (“

NLP-SR”

) engine into words of digitized speech.

16. The computer system of claim 13 wherein words of a CRM event further comprise a word from a text box widget of a CRM dashboard implemented in a graphical user interface of the computer system.

17. The computer system of claim 13 wherein words of a CRM event further comprise a word designated as an element of a parsed triple through a widget of a CRM dashboard implemented in a graphical user interface of the computer system.

18. The computer system of claim 13 wherein CRM events comprise activities that generate digitized words for parsing into triples that can be included in an enterprise knowledge graph.

19. The computer system of claim 13 with the computer processor further configured to function by storing parsed triples and inferred triples in an enterprise knowledge graph of the computer system.

20. The computer system of claim 13 with the computer processor further configured to function by:

determining whether the parsed triples and the inferred triples are already asserted in an enterprise knowledge graph of the computer system; and

storing in the enterprise knowledge graph only those parsed triples and inferred triples that are not already in the enterprise knowledge graph.