Domain-driven feedback data analysis in information processing system

Patent metadata

Field	Value
Publication number	US-12450501-B2
Application number	US-202217870942-A
Country	US
Kind code	B2
Filing date	Jul 22, 2022
Priority date	Jul 22, 2022
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

Techniques are disclosed for domain-driven intent-based feedback data analysis. For example, a method comprises obtaining a feedback data set, and classifying the feedback data set into at least one domain of a plurality of domains. The feedback data set is mapped to a domain data set corresponding to the at least one domain, and a root cause is computed for the feedback data set to enable one or more actions to be taken in response to the feedback data set based on the root cause. By way of further example, computing the root cause for the feedback data set may further comprise utilizing at least one computed intent attribute, at least one computed sentiment attribute, and the domain data set to compute a decision on the root cause for the feedback data set.

First claim

What is claimed is:

1. An apparatus, comprising:
a processing platform comprising at least one processor and at least one memory storing computer program instructions wherein, when the at least one processor executes the computer program instructions, the apparatus is configured to:
obtain a feedback data set;
classify, based on a plurality of domains, the feedback data set into at least one domain of the plurality of domains;
map the feedback data set to a domain data set corresponding to the at least one domain; and
compute a root cause for the feedback data set to enable one or more actions to be taken in response to the feedback data set based on the root cause.

2. The apparatus of claim 1 , wherein obtaining the feedback data set further comprises obtaining the feedback data set from an entity engaged with an enterprise through one or more transactions, and the plurality of domains comprise a plurality of domains associated with the one or more transactions.

3. The apparatus of claim 2 , wherein obtaining the feedback data set further comprises converting input from the entity in one or more modalities into the feedback data set.

4. The apparatus of claim 1 , wherein classifying the feedback data set into at least one domain of the plurality of domains further comprises computing at least one intent attribute from the feedback data set.

5. The apparatus of claim 4 , wherein computing the at least one intent attribute from the feedback data set further comprises utilizing a machine learning model in the computation.

6. The apparatus of claim 1 , wherein classifying the feedback data set into at least one domain of the plurality of domains further comprises computing at least one sentiment attribute from the feedback data set.

7. The apparatus of claim 6 , wherein computing the at least one sentiment attribute from the feedback data set further comprises utilizing a machine learning model in the computation.

8. The apparatus of claim 1 , wherein computing the root cause for the feedback data set further comprises utilizing at least one intent attribute, at least one sentiment attribute, and the domain data set to compute a decision on the root cause for the feedback data set.

9. The apparatus of claim 8 , wherein computing the decision on the root cause for the feedback data set further comprises utilizing a supervised machine learning algorithm in the computation.

10. The apparatus of claim 1 , wherein when the at least one processor executes the computer program instructions, the apparatus is further configured to cause the one or more actions to be taken in response to the feedback data set based on the root cause.

11. The apparatus of claim 1 , wherein when the at least one processor executes the computer program instructions, the apparatus is further configured to learn over time at least a portion of the domain data set corresponding to the at least one domain.

12. The apparatus of claim 1 , wherein obtaining the feedback data set further comprises obtaining the feedback data set from a customer engaged with an enterprise through one or more transactions, and the plurality of domains comprise a plurality of supply-chain domains such that the computed root cause is used to enable one or more actions to be taken in a supply chain managed by the enterprise to address one of a customer intent and a customer sentiment extracted from the feedback data set.

13. A method, comprising:
obtaining a feedback data set;
classifying, based on a plurality of domains, the feedback data set into at least one domain of the plurality of domains;
mapping the feedback data set to a domain data set corresponding to the at least one domain; and
computing a root cause for the feedback data set to enable one or more actions to be taken in response to the feedback data set based on the root cause;
wherein the steps are performed by a processing platform comprising at least one processor coupled to at least one memory executing program code.

14. The method of claim 13 , wherein obtaining the feedback data set further comprises obtaining the feedback data set from an entity engaged with an enterprise through one or more transactions, and the plurality of domains comprise a plurality of domains associated with the one or more transactions.

15. The method of claim 13 , wherein classifying the feedback data set into at least one domain of the plurality of domains further comprises computing one or more of:
at least one intent attribute from the feedback data set; and
at least one sentiment attribute from the feedback data set.

16. The method of claim 13 , wherein computing the root cause for the feedback data set further comprises utilizing at least one intent attribute, at least one sentiment attribute, and the domain data set to compute a decision on the root cause for the feedback data set.

17. The method of claim 13 , further comprising causing the one or more actions to be taken in response to the feedback data set based on the root cause.

18. A computer program product stored on a non-transitory computer-readable medium and comprising machine executable instructions, the machine executable instructions, when executed, causing a processing device to perform steps of:
obtaining a feedback data set;
classifying, based on a plurality of domains, the feedback data set into at least one domain of the plurality of domains;
mapping the feedback data set to a domain data set corresponding to the at least one domain; and
computing a root cause for the feedback data set to enable one or more actions to be taken in response to the feedback data set based on the root cause.

19. The computer program product of claim 18 , wherein classifying the feedback data set into at least one domain of the plurality of domains further comprises computing at least one intent attribute from the feedback data set, and computing at least one sentiment attribute from the feedback data set, and further wherein computing the root cause for the feedback data set further comprises utilizing the at least one intent attribute, the at least one sentiment attribute, and the domain data set to compute a decision on the root cause for the feedback data set.

20. The computer program product of claim 19 , further comprising causing the one or more actions to be taken in response to the feedback data set based on the root cause.

Assignees

• Dell Products Lp

Inventors

• Kumar Dhilip S
• Sahoo Sujit Kumar
• Maikhuri Ajay
• Marappa Devaraj

Classifications

• G06F11/079

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G06F16/35

  Clustering; Classification · CPC title

• G06N20/00

  Machine learning · CPC title