Data transformation of performance statistics and ticket information for network devices for use in machine learning models

• US 10,693,740 B2
• Filed: 12/07/2017
• Issued: 06/23/2020
• Est. Priority Date: 12/07/2017
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: Coccia, Davide, Bellini, Davide Guglielmo
• Primary Examiner(s): Harrell, Robert B
• Application Number:
  US15/834,845
• Publication Number:
  US 20190182120A1
• Time in Patent Office: 929 Days
• Field of Search: 706 12, 709224
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/5074 Handling of user complaints or trouble tickets
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters

Abstract

A device may receive one or more data models that have been trained using a first set of values that are in a format capable of being processed by the one or more data models. The first set of values may be associated with a set of historical network performance indicators relating to a set of network devices. The device may receive network data that includes network ticket information and performance statistics for the one or more network devices. The device may determine a set of network performance indicators relating to the one or more network devices. The device may convert the set of network performance indicators into a second set of values that are in the format capable of being processed by the one or more data models. The device may use the second set of values to generate one or more recommendations associated with improving network performance.

Claims

1. A device, comprising:

one or more memories; and

one or more processors communicatively coupled to the one or more memories to;

obtain historical network data associated with a set of network devices,

the historical network data being associated with a first set of values that are in a format capable of being processed by one or more data models, and

the historical network data including at least one of;

historical network ticket information, or

historical performance statistics relating to the set of network devices;

determine a set of historical network performance indicators for one or more groups of network devices, of the set of network devices, by analyzing the historical network data;

train the one or more data models based on the set of historical network performance indicators;

receive, after training the one or more data models, new network data for one or more network devices of the set of network devices,

the new network data being received periodically over an interval and including at least one of;

network ticket information, or

performance statistics relating to the one or more network devices;

determine a set of other network performance indicators that are associated with the one or more network devices, of the set of network devices, by analyzing the new network data;

convert the set of other network performance indicators into a second set of values that are in the format capable of being processed by the one or more data models,

wherein the one or more processors, when converting the set of other network performance indicators into the second set of values, are to;

execute a data mining technique to identify, by analyzing information associated with a set of data sources, a set of threshold ranges of values,

 

the set of threshold ranges of values being associated with a network performance indicator of the set of other network performance indicators;

compare the network performance indicator, of the set of other network performance indicators, to the set of threshold ranges of values; and

convert the network performance indicator to a value included in the second set of values based on a particular threshold range of values, of the set of threshold ranges of values, with which the network performance indicator is associated;

generate, based on the set of other network performance indicators and the one or more data models, one or more recommendations associated with improving network performance; and

perform, based on the one or more recommendations, one or more actions associated with improving network performance.

2. The device of claim 1, where the historical network ticket information is associated with a set of historical network tickets, and

where the network ticket information is associated with a set of network tickets,

where each historical network ticket of the set of historical network tickets and each network ticket of the set of network tickets includes at least one of:

a first field identifying a particular performance issue of a network device of the set of network devices,

a second field describing the particular performance issue,

a third field indicating a time at which a historical network ticket of the set of historical network tickets or a network ticket of the set of network tickets was created, or

a fourth field indicating a network device identifier for the network device.

3. The device of claim 1, where the one or more processors are further to:

convert the set of historical network performance indicators to the first set of values that are in the format capable of being processed by the one or more data models; and

where the one or more processors, when training the one or more data models, are to;

train the one or more data models using the first set of values.

4. The device of claim 1, where the one or more processors, when training the one or more data models, are to:

train the one or more data models using one or more machine learning or artificial intelligence techniques.

5. The device of claim 1, where the one or more processors, when training the one or more data models, are to:

train a data model of the one or more data models with the first set of values and at least one of;

a location identification technique,

a path-finding technique, or

a forecasting technique,

where the location identification technique, the path-finding technique, or the forecasting technique includes a set of rules that allow the device to process the first set of values.

6. The device of claim 1,

where the one or more processors, when generating the one or more recommendations, are to:

generate the one or more recommendations by providing the second set of values as input to the one or more data models.

7. The device of claim 1, where the one or more processors, when generating the one or more recommendations, are to:

generate a recommendation, of the one or more recommendations, to reroute traffic flow from a first network device of the set of network devices to a second network device of the set of network devices; and

where the one or more processors, when performing the one or more actions, are to;

modify, using an application programming interface (API), one or more network routing paths to allow the traffic flow to be rerouted based on the recommendation.

8. A method, comprising:

receiving, by a device, one or more data models that have been trained using a first set of values that are in a format capable of being processed by the one or more data models,

the first set of values being associated with a set of historical network performance indicators that relate to a set of network devices;

receiving, by the device, network data for one or more network devices of the set of network devices,

the network data including network ticket information and performance statistics relating to the one or more network devices;

determining, by the device, a set of other network performance indicators that are associated with the one or more network devices by analyzing the network data;

converting, by the device, the set of other network performance indicators into a second set of values that are in the format capable of being processed by the one or more data models,

wherein converting the set of other network performance indicators into the second set of values comprises;

executing a data mining technique to identify, by analyzing information associated with a set of data sources, a set of threshold ranges of values,

the set of threshold ranges of values being associated with a network performance indicator of the set of other network performance indicators,

comparing the network performance indicator to the set of threshold ranges of values, and

converting the network performance indicator to a value included in the second set of values based on a particular threshold range of values, of the set of threshold ranges of values, with which the network performance indicator is associated;

generating, by the device and by providing the second set of values as input to the one or more data models, one or more recommendations associated with improving network performance; and

performing, by the device and based on the one or more recommendations, one or more actions associated with improving network performance.

9. The method of claim 8, where receiving the network data comprises:

receiving the network data for the one or more network devices,

where the network data is reported periodically over an interval; and

where determining the set of other network performance indicators comprises;

determining a first group of other network performance indicators associated with each network device of the one or more network devices, and

determining a second group of other network performance indicators associated with the one or more network devices.

10. The method of claim 8, where converting the set of other network performance indicators into the second set of values comprises:

converting the set of other network performance indicators into the second set of values, where the first set of values is configurable by a user.

11. The method of claim 8, where receiving the one or more data models comprises:

receiving a data model, of the one or more data models, that has been trained using the set of historical network performance indicators and a forecasting technique;

where generating the one or more recommendations comprises;

generating a recommendation of the one or more recommendations,

the recommendation including information predicting a time period at

which a new network ticket will be opened; and

where performing the one or more actions comprises;

performing an action associated with correcting a performance issue of a network device, of the set of network devices, prior to the new network ticket being opened.

12. The method of claim 8, where generating the one or more recommendations comprises:

generating a recommendation, of the one or more recommendations, to allocate virtual resources assigned to a first network device of the set of network devices to a second network device of the set of network devices; and

where performing the one or more actions comprises;

removing, using an application programming interface (API), the virtual resources from the first network device of the set of network devices, and

adding, using the API, the virtual resources to the second network device of the set of network devices.

13. The method of claim 8, where generating the one or more recommendations comprises:

generating a recommendation, of the one or more recommendations, to add a first network device to a first location or to remove a second network device, of the set of network devices, from a second location,

the recommendation including;

information identifying the first network device or the second network device,

information identifying the first location or the second location, and

information associated with a set of installation or uninstallation instructions; and

where performing the one or more actions comprises;

analyzing, using information included in the recommendation, a data source that stores technician information to identify an available technician,

the technician information including;

technician schedule information identifying whether a technician is available,

technician location information, and

technician qualification information indicating one or more credentials of the technician, and

scheduling an appointment to an electronic calendar of an account associated with the available technician to allow the available technician to implement the recommendation.

14. The method of claim 8, where performing the one or more actions comprises:

providing at least one of the one or more recommendations for display.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to;

receive one or more data models that have been trained using one or more machine learning techniques and a first set of values that are in a format capable of being processed by the one or more data models,

the first set of values being associated with a set of historical network performance indicators that relate to a set of network devices;

receive network data for one or more network devices of the set of network devices,

the network data including at least one of;

network ticket information relating to the one or more network devices, or

performance statistics relating to the one or more network devices;

determine a set of other network performance indicators that are associated with the one or more network devices, of the set of network devices, by analyzing the network data;

convert the set of other network performance indicators into a second set of values that are in the format capable of being processed by the one or more data models,

wherein the one or more instructions, that cause the one or more processors to convert the set of other network performance indicators into the second set of values, cause the one or more processors to;

execute a data mining technique to identify, by analyzing information associated with a set of data sources, a set of threshold ranges of values,

 

the set of threshold ranges of values being associated with a network performance indicator of the set of other network performance indicators,

compare the network performance indicator, of the set of other network performance indicators, to the set of threshold ranges of values, and

convert the network performance indicator to a value included in the second set of values based on a particular threshold range of values, of the set of threshold ranges of values, with which the network performance indicator is associated;

generate, by providing the second set of values as input to the one or more data models, one or more recommendations associated with improving network performance,

the one or more recommendations including at least one of;

a first recommendation to modify a number of network devices used to support traffic flow,

a second recommendation to modify an allocation of resources associated with at least one of the one or more network devices, or

a third recommendation to reroute traffic flow associated with the set of network devices; and

perform, based on the one or more recommendations, one or more actions associated with improving network performance.

16. The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to receive the one or more data models, cause the one or more processors to:

receive the one or more data models,

where the one or more data models are trained on supplemental information,

the supplemental information including;

subscription information for user devices in a geographic region, or location information of a set of host servers; and

where the one or more instructions, that cause the one or more processors to generate the one or more recommendations, cause the one or more processors to;

generate the one or more recommendations based on the supplemental information.

17. The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to receive the one or more data models, cause the one or more processors to:

receive a data model, of the one or more data models, that has been trained using one or more historical network performance indicators of set of historical network performance indicators and an anomaly detection technique; and

where the one or more instructions, that cause the one or more processors to generate the one or more recommendations, cause the one or more processors to;

generate the first recommendation, the second recommendation, or the third recommendation based on information identifying a time at which an anomaly is likely to occur,

the anomaly being associated with a spike in network traffic.

18. The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to convert the set of other network performance indicators into the second set of values, cause the one or more processors to:

analyze, prior to comparing the network performance indicator to the set of threshold ranges of values, historical network ticket information using a natural language processing technique, and

determine the set of threshold ranges of values based on analyzing the historical network ticket information.

19. The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to generate the one or more recommendations, cause the one or more processors to:

generate the third recommendation to reroute traffic flow associated with the set of network devices,

the third recommendation to reroute traffic flow including information predicting that a particular network device will open up a new network ticket at a particular time period; and

where the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to;

modify, using an application programming interface (API), one or more network routing paths to allow the traffic flow to be rerouted based on the third recommendation.

20. The non-transitory computer-readable medium of claim 15, where the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to:

provide at least one of the one or more recommendations for display.