Providing machine learning assistance for technical support

• US 10,652,109 B1
• Filed: 10/29/2018
• Issued: 05/12/2020
• Est. Priority Date: 10/29/2018
• Status: Active Grant

• Current Assignee: Dell Products BV (Dell Technologies Inc.)
• Original Assignee: Dell Products BV (Dell Technologies Inc.)
• Inventors: Sethi, Parminder Singh, Shanthigodu, Mohith, Singh, Durai, Hegde, Vivekananda, Kapil, Smita, V, Elanjelian
• Primary Examiner(s): Wasel, Mohamed A.
• Application Number:
  US16/173,511
• Publication Number:
  US 20200136928A1
• Time in Patent Office: 561 Days
• 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 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 41/046 comprising network management agents or mobile agents therefor
• CPC Class Codes: H04L 41/0654 using network fault recovery ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 41/5032 Generating service level reports
• CPC Class Codes: H04L 41/5074 Handling of user complaints or trouble tickets

Abstract

In some examples, after a client system encounters a problem, a technical support specialist may connect to the client system via a console. The console may display a graphical representation of a client system that includes a plurality of components. The console may execute a machine learning module to determine one or more potential solutions to the particular problem. Each solution of the one or more solutions may correspond to a previously resolved problem that is similar to the particular problem and may have an associated confidence level determined based on: a similarity of the particular problem to the previously resolved problem, a similarity of the plurality of components to a second plurality of components included in a second client system associated with the previously resolved problem, a similarity of a network topology of the client system to a second network topology of the second client system.

Claims

1. A method comprising:

displaying, by one or more processors, a graphical representation of a client system experiencing a particular problem, wherein;

the client system comprises a plurality of components;

each component of the plurality of components has a corresponding set of attributes; and

the graphical representation of the client system comprises;

the plurality of components;

a device type of each component of the plurality of components;

a connection between at least a first device and a second device of the plurality of components; and

a status of the connection;

performing, by the one or more processors, a comparison of recently gathered data associated with the client system with previously gathered data associated with the client system;

providing, by the one or more processors, a comparison report identifying differences between the recently gathered data and the previously gathered data based on the comparison;

determining, by a machine learning module executed by the one or more processors, one or more solutions, each solution of the one or more solutions corresponding to a previously resolved problem that is similar to the particular problem; and

displaying, by the one or more processors, the one or more solutions, wherein a particular solution of the one or more solutions has an associated confidence level.

2. The method of claim 1, wherein:

each solution of the one or more solutions identifies a technician that resolved the previously resolved problem, an experience level of the technician, and contact information associated with the technician.

3. The method of claim 1, wherein the confidence level is determined based on:

a similarity of the particular problem of the client system to the previously resolved problem;

a similarity of the plurality of components of the client system to a second plurality of components included in a second client system associated with the previously resolved problem; and

a similarity of a network topology of the client system to a second network topology of the second client system associated with the previously resolved problem.

4. The method of claim 1, further comprising:

receiving a component selection selecting one or more components of the plurality of components;

receiving an attribute selection selecting a subset of the corresponding set of attributes associated with individual components of the one or more components; and

displaying a revised graphical representation of at least a portion of the client system based at least in part on the component selection and the attribute selection.

5. The method of claim 1, wherein the corresponding set of attributes comprises at least one of:

configuration information;

one or more error messages;

a currently installed firmware version;

a currently installed software version;

a hardware version;

one or more installation logs;

or

one or more error logs.

6. The method of claim 1, wherein the plurality of components comprises:

at least one server;

at least one network attached storage device; and

at least one of either a network switch or a network router.

7. The method of claim 1, further comprising:

determining data associated with the client system, the data identifying the plurality of components and a network topology of the client system;

performing a comparison of the data with other data associated with other client systems;

determining one or more similar client systems from the other client systems based on the comparison; and

determining a portion of the one or more similar client systems having problems similar to the particular problem.

8. A computing device comprising:

one or more processors; and

one or more non-transitory computer readable media storing instructions executable by the one or more processors to perform operations comprising;

displaying a graphical representation of a client system experiencing a particular problem, wherein;

the client system comprises a plurality of components;

each component of the plurality of components has a corresponding set of attributes; and

the graphical representation of the client system comprises;

the plurality of components;

a device type of each component of the plurality of components;

a connection between at least a first device and a second device of the plurality of components; and

a status of the connection;

performing a comparison of recently gathered data associated with the client system with previously gathered data associated with the client system;

providing a comparison report identifying differences between the recently gathered data and the previously gathered data based on the comparison;

determining, by a machine learning module, one or more solutions, each solution of the one or more solutions corresponding to a previously resolved problem that is similar to the particular problem; and

displaying the one or more solutions, wherein each solution of the one or more solutions has an associated confidence level.

9. The computing device of claim 8, wherein:

each solution of the one or more solutions identifies a technician that resolved the previously resolved problem, an experience level of the technician, and contact information associated with the technician.

10. The computing device of claim 8, wherein the confidence level is determined based on:

a similarity of the particular problem of the client system to the previously resolved problem;

a similarity of the plurality of components of the client system to a second plurality of components included in a second client system associated with the previously resolved problem; and

a similarity of a network topology of the client system to a second network topology of the second client system associated with the previously resolved problem.

11. The computing device of claim 8, the operations further comprising:

receiving a component selection selecting one or more components of the plurality of components;

receiving an attribute selection selecting a subset of the corresponding set of attributes associated with individual components of the one or more components; and

displaying a revised graphical representation of at least a portion of the client system based at least in part on the component selection and the attribute selection.

12. The computing device of claim 8, wherein the plurality of components comprises:

at least one server;

at least one network attached storage device; and

at least one of either a network switch or a network router.

13. The computing device of claim 8, the operations further comprising:

determining data associated with the client system, the data identifying the plurality of components and a network topology of the client system;

performing a comparison of the data with other data associated with other client systems;

determining one or more similar client systems from the other client systems based on the comparison; and

determining a portion of the one or more similar client systems having problems similar to the particular problem.

14. One or more non-transitory computer readable media storing instructions executable by one or more processors to perform operations comprising:

displaying a graphical representation of a client system experiencing a particular problem, wherein;

the client system comprises a plurality of components;

each component of the plurality of components has a corresponding set of attributes; and

the graphical representation of the client system comprises;

the plurality of components;

a device type of each component of the plurality of components;

a connection between at least a first device and a second device of the plurality of components; and

a status of the connection;

performing a comparison of recently gathered data associated with the client system with previously gathered data associated with the client system;

providing a comparison report identifying differences between the recently gathered data and the previously gathered data based on the comparison;

determining, by a machine learning module, one or more solutions, each solution of the one or more solutions corresponding to a previously resolved problem that is similar to the particular problem; and

displaying the one or more solutions, wherein each solution of the one or more solutions has an associated confidence level.

15. The one or more non-transitory computer readable media of claim 14, wherein:

each solution of the one or more solutions identifies a technician that resolved the previously resolved problem, an experience level of the technician, and contact information associated with the technician.

16. The one or more non-transitory computer readable media of claim 14, wherein the confidence level is determined based on:

a similarity of the particular problem of the client system to the previously resolved problem;

a similarity of the plurality of components of the client system to a second plurality of components included in a second client system associated with the previously resolved problem; and

a similarity of a network topology of the client system to a second network topology of the second client system associated with the previously resolved problem.

17. The one or more non-transitory computer readable media of claim 14, the operations further comprising:

receiving a component selection selecting one or more components of the plurality of components;

receiving an attribute selection selecting a subset of the corresponding set of attributes associated with individual components of the one or more components; and

displaying, by the one or more processors, a revised graphical representation of at least a portion of the client system based at least in part on the component selection and the attribute selection.

18. The one or more non-transitory computer readable media of claim 14, wherein the graphical representation of the client system comprises:

a network topology of the client system.

19. The one or more non-transitory computer readable media of claim 14, wherein the plurality of components comprises:

at least one server;

at least one network attached storage device; and

at least one of either a network switch or a network router.

20. The one or more non-transitory computer readable media of claim 14, the operations further comprising:

determining data associated with the client system, the data identifying the plurality of components and a network topology of the client system;

performing a comparison of the data with other data associated with other client systems;

determining one or more similar client systems from the other client systems based on the comparison; and

determining a portion of the one or more similar client systems having problems similar to the particular problem.