System and method for warranty customization based on customer need and part failure rate

Patent metadata

Field	Value
Publication number	US-2024281821-A1
Application number	US-202418653822-A
Country	US
Kind code	A1
Filing date	May 2, 2024
Priority date	Jul 23, 2021
Publication date	Aug 22, 2024
Grant date	—

Abstract

Systems and methods provide customers with a need-based warranty using a deep learning neural network. After categorizing, a customer need is mapped to a warranty type based on the SLA needs. Warranties may then be suggested based on customer need. In another embodiment, systems and methods detect an optimal warranty based on part failure and performance of a server. A mean time to resolve or replace can be minimized in future failure instances by comparing the derived replacement time with available warranty offerings to identify potential deviations and thereby recommend an optimal warranty from the available offerings. In a further embodiment, systems and methods identify and offer additional service contracts for vender services. A warranty proposer looks for warranty types that are emitted by a warranty-types analyzer and by a technical-support analyzer. The overlapping warranty offers are provided to customers.

First claim

What is claimed is:

1 . A customized warranty system for providing a warranty based on device performance, comprising:
a processor; and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution by the processor, cause the system to:
collect data required to derive a current Mean Time To Resolve/Replace (MTTR);
build a model for MTTR derivation;
derive the MTTR using a machine learning algorithm;
identify a desired Service Level Agreement (SLA) that can minimize the current MTTR;
determine whether an existing warranty with the desired SLA is available; and
if a warranty with the desired SLA is available, then recommend the existing warranty to the customer.

2 . The customized warranty system of claim 1 , wherein the data required to derive a current MTTR comprises one or more of: a system inventory, a system serial number, a life cycle log, a part replacement history, and a time required to replace parts.

3 . The customized warranty system of claim 1 , wherein the model for MTTR derivation comprises: a time from part failure to service case creating, a time from service case creation to failed part identification, a shipping time for a replacement part, and an install time for a replacement part.

4 . The customized warranty system of claim 1 , wherein to derive the MTTR using a machine learning algorithm the instructions, upon execution by the processor, further cause the system to:
process the required data to filter life cycle logs; and calculate an MTTR for a plurality of devices.

5 . The customized warranty system of claim 4 , wherein the instructions, upon execution by the processor, further cause the system to:
collect alerts generated by the device; identify part replacements that occurred in a device environment; and compute a time required to resolve the alerts.

6 . The customized warranty system of claim 1 , wherein the instructions, upon execution by the processor, further cause the system to:
retrieve available warranty offers from a warranty server; compare a derived MTTR to SLAs in the available warranty offers; and identify one or more warranty offers that provide a lower MTTR than the derived MTTR.

7 . A customized warranty system for identifying warranty needs based on gaps in existing coverage, comprising:
a warranty-types analyzer comprising an artificial intelligence processor configured to analyze available warranty types and to identify gaps in the available warranty types; a technical-support analyzer comprising an artificial intelligence processor configured to analyze customer cases, part-replacement data, and application offers; and a warranty proposer configured to identify warranty types that are received from both the warranty-types analyzer and the technical-support analyzer.

8 . The customized warranty system of claim 7 , wherein the warranty-types analyzer is further configured to separate a warranty into a set of components using natural language processing.

9 . The customized warranty system of claim 8 , wherein the set of components comprises one or more of: a replacement type, an SLA, a support type, post support needs, a software level, an application, and a feature.

10 . The customized warranty system of claim 7 , the warranty-types analyzer is configured to emit any identified gaps in warranty types that are not offered by a vendor.

11 . The customized warranty system of claim 7 , wherein the technical-support analyzer is configured to emit possible warranty types and corresponding occurrences of the possible warranty types.

12 . The customized warranty system of claim 7 , wherein the technical-support analyzer is configured to assess warranty offers in view of case workloads.

13 . A method for providing a customized warranty based on device performance, comprising:
collecting data required to derive a current Mean Time To Resolve/Replace (MTTR); building a model for MTTR derivation; deriving the MTTR using a machine learning algorithm; identifying a desired Service Level Agreement (SLA) that can minimize the current MTTR; determining whether an existing warranty with the desired SLA is available; and if a warranty with the desired SLA is available, then recommend the existing warranty to the customer.

14 . The method of claim 13 , wherein the data required to derive a current MTTR comprises one or more of: a system inventory, a system serial number, a life cycle log, a part replacement history, and a time required to replace parts.

15 . The method of claim 13 , wherein the model for MTTR derivation comprises: a time from part failure to service case creating, a time from service case creation to failed part identification, a shipping time for a replacement part, and an install time for a replacement part.

16 . The method of claim 13 , further comprising:
processing the required data to filter life cycle logs; and calculating an MTTR for a plurality of devices.

17 . The method of claim 16 , further comprising:
collecting alerts generated by the device; identifying part replacements that occurred in a device environment; and computing a time required to resolve the alerts.

18 . The method of claim 13 , further comprising:
retrieving available warranty offers from a warranty server; comparing a derived MTTR to SLAs in the available warranty offers; and identifying one or more warranty offers that provide a lower MTTR than the derived MTTR.

Assignees

• Dell Products Lp

Inventors

• Ganesan Vaideeswaran
• R chandrasekhar
• Ms Rekha
• Babu Harish
• Lalgoudar Praveen
• S Nikhil
• Varadharajan Pandiyan
• Velamuri Rushyendra
• Arora Nidhi Kant
• Pai Sandeep Venkatesh

Classifications

• G06Q30/0207 Primary

  Discounts or incentives, e.g. coupons or rebates · CPC title

• H04L41/5012

  determining service availability, e.g. which services are available at a certain point in time · CPC title

• H04L43/0805

  by checking availability · CPC title

• H04L41/5016

  based on statistics of service availability, e.g. in percentage or over a given time · CPC title

• G06Q30/012 Primary

  Providing warranty services · CPC title