Unidirectional trust based decision making for information technology conversation agents

• US 10,419,489 B2
• Filed: 05/04/2017
• Issued: 09/17/2019
• Est. Priority Date: 05/04/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kalia, Anup K., Vukovic, Maja, Wu, Frederick Y., Xiao, Jin
• Primary Examiner(s): Avery, Jeremiah L
• Application Number:
  US15/587,370
• Publication Number:
  US 20180324215A1
• Time in Patent Office: 866 Days
• Field of Search: None
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: H04L 63/102 Entity profiles
• CPC Class Codes: H04L 63/1433 Vulnerability analysis
• CPC Class Codes: H04L 63/20 for managing network security; network security policies in general filtering policies H04L63/0227

Abstract

A method and system of processing an information technology (IT) electronic request is provided. The electronic request is received in natural language from a user. Parameters of the electronic request are extracted. A risk of the electronic request is determined. A policy based on the parameters and the risk of the electronic request is determined and executed. A level of trust between the user and the computer device is calculated based on the determined risk and an outcome of the execution of the policy. A conversation pattern of the computer device toward the user is adjusted based on the calculated level of trust.

Claims

1. A computing device comprising:

a processor;

a network interface coupled to the processor to enable communication over a network;

a storage device coupled to the processor;

a conversation agent software stored in the storage device, wherein an execution of the software by the processor configures the computing device to perform acts comprising;

receiving an information technology (IT) electronic request in natural language from a user, via a user device, over the network;

extracting parameters of the electronic request;

determining a risk of the electronic request;

determining a policy based on the parameters and the risk of the electronic request;

executing the policy;

calculating a level of trust between the user and the conversation agent based on the determined risk and an outcome of the execution of the policy; and

adjusting a conversation pattern of the conversation agent toward the user based on the calculated level of trust.

2. The computing device of claim 1, wherein extracting parameters of the electronic request comprises:

performing speech recognition to determine a textual representation of the electronic request;

performing speech segmentation on the textual representation of the electronic request; and

applying concept expansion on the textual representation of the electronic request to determine an intent of the electronic request.

3. The computing device of claim 1, wherein determining the risk of the electronic request comprises determining how fulfillment of the electronic request would affect one or more resources of an IT network of a business enterprise.

4. The computing device of claim 1, wherein determining the policy comprises determining whether the user is authorized to submit the electronic request.

5. The computing device of claim 1, wherein calculating the level of trust between the user and the conversation agent comprises calculating a level of trust of the conversation agent toward the user.

6. The computing device of claim 5, wherein calculating the level of trust of the conversation agent toward the user is further based on a relevance of the electronic request with respect to resources of a private network of the computing device.

7. The computing device of claim 1, wherein calculating a level of trust between the user and the conversation agent comprises calculating a level of trust of the user toward the conversation agent.

8. The computing device of claim 1:

wherein calculating the level of trust between the user and the conversation agent comprises;

calculating a first level of trust of the conversation agent toward the user; and

calculating a second level of trust of the user toward the conversation agent; and

wherein the adjustment of the behavioral approach of the conversation agent toward the user is based on the calculated first level of trust and the calculated second level of trust.

9. The computing device of claim 1, wherein execution of the conversation agent by the processor further configures the computing device to perform acts comprising:

soliciting a satisfaction feedback regarding the execution of the electronic request, from the user via the user device, wherein calculating a level of trust between the user and the conversation agent is further based on the satisfaction feedback.

10. The computing device of claim 1, wherein execution of the conversation agent by the processor further configures the computing device to perform acts comprising:

retrieving a prior level of trust between the user and the conversation agent, wherein calculating the level of trust between the user and the conversation agent is further based on the prior level of trust between the user and the conversation agent.

11. A non-transitory computer readable storage medium tangibly embodying a computer readable program code having computer readable instructions that, when executed, causes a computer device to carry out a method of processing an information technology (IT) electronic request, the method comprising:

receiving the electronic request in natural language from a user;

extracting parameters of the electronic request;

determining a risk of the electronic request;

determining a policy based on the parameters and the risk of the electronic request;

executing the policy;

calculating a level of trust between the user and the computer device based on the determined risk, and an outcome of the execution of the policy; and

adjusting a conversation pattern of the computer device toward the user based on the calculated level of trust.

12. The non-transitory computer readable storage medium of claim 11, wherein extracting parameters of the electronic request comprises:

performing speech recognition to determine a textual representation of the electronic request;

performing speech segmentation on the textual representation of the electronic request; and

applying concept expansion on the textual representation of the electronic request to determine an intent of the electronic request.

13. The non-transitory computer readable storage medium of claim 11, wherein determining the risk of the electronic request comprises determining how fulfillment of the electronic request would affect one or more resources of an IT network of a business enterprise.

14. The non-transitory computer readable storage medium of claim 11, wherein determining the policy comprises determining whether the user is authorized to submit the electronic request.

15. The non-transitory computer readable storage medium of claim 11, wherein calculating the level of trust between the user and the computer device comprises calculating a level of trust of the computer device toward the user.

16. The non-transitory computer readable storage medium of claim 15, wherein calculating the level of trust of the computer device toward the user is further based on a relevance of the electronic request with respect to resources of a private network of the computing device.

17. The non-transitory computer readable storage medium of claim 11, wherein calculating a level of trust between the user and the computer device comprises calculating a level of trust of the user toward the computer device.

18. The non-transitory computer readable storage medium of claim 11:

wherein calculating the level of trust between the user and the computer device comprises;

calculating a first level of trust of the computer device toward the user; and

calculating a second level of trust of the user toward the computer device; and

wherein the adjustment of the behavioral approach of the computer device toward the user is based on the calculated first level of trust and the calculated second level of trust.

19. The non-transitory computer readable storage medium of claim 11, wherein execution of the computer device by the processor further configures the computing device to perform acts comprising:

soliciting a satisfaction feedback regarding the execution of the electronic request, from the user via the user device, wherein calculating a level of trust between the user and the computer device is further based on the satisfaction feedback.

20. The non-transitory computer readable storage medium of claim 11, wherein execution of the computer device by the processor further configures the computing device to perform acts comprising:

retrieving a prior level of trust between the user and the computer device, wherein calculating the level of trust between the user and the computer device is further based on the prior level of trust between the user and the computer device.