# US 2022/0012654 A1 · Solution architecture prediction

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0012654 A1
- Document ID: US20220012654A1
- Status: Published application
- Kind: A1
- Application number: 16/998,696
- Filed: 2020-08-20
- Published: 2022-01-13
- Earliest claimed: 2020-07-08
- Assignees: Accenture Global Solutions Limited
- Applicants: Accenture Global Solutions Limited
- Inventors: Balaji JANARTHANAM; Anil KUMAR; Abhishek PATNI; Vinu VARGHESE; Hari Kumar KARNATI; Saran PRASAD; Nirav Jagdish SAMPAT
- Web page: https://patentgrep.com/patent/US20220012654A1

## CPC

- G06Q 10/0633: Workflow analysis
- G06F 18/2113: by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
- G06F 18/213: Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis}
- G06Q 10/06334: {using forecasting or predicting}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system for solution architecture prediction may identify a previous solution from a data source and may create a historical solution evaluation matrix by mapping a plurality of concern categories with the previous solution. The system may identify a plurality of solution components preponderant to deriving a solution associated with the solution architecture prediction and create a potential solution evaluation matrix therefrom. The system may evaluate the historical solution evaluation matrix and the potential solution evaluation matrix to determine a credibility score for each solution comprised therein. Based on the evaluation, a solution prediction data may be generated including a previous solution, a potential solution, and the associated credibility score. A service solution may be selected from the solution prediction data to resolve the solution prediction requirement.

## Claims

### Claim 1

A system comprising:
a processor;
a data extractor coupled to the processor, the data extractor to:
receive a solution prediction requirement associated with a service provided to a user, the solution prediction requirement being related to a solution to an issue pertaining to the service;
obtain historical data and infrastructure data pertaining to processing of the solution prediction requirement from a data source, the historical data comprising information regarding a previous solution for resolving the issue, and the infrastructure data comprising infrastructure information associated with processing the solution prediction requirement; and
implement an artificial intelligence component to determine a requirement fulfillment index for the previous solution associated with processing the solution prediction requirement to create a historical solution evaluation matrix;
a data analyzer coupled to the processor, the data analyzer to implement an artificial intelligence model to:
identify, from the data source, a plurality of solution components preponderant to deriving the solution associated with the issue;
obtain solution component data from the data source, the solution component data comprising information pertaining to each of the plurality of solution components; and
map solution component data with each of a pre-existing plurality of solution attributes to determine a performance score indicative of a performance of each of the plurality of solution components associated with each of the solution attributes; and
a modeler coupled to the processor, the modeler to implement the artificial intelligence model to:
map the solution component data and the infrastructure data with the performance score to create a solution database comprising a potential solution for the issue, the potential solution being based on a technical solution available in market;
map the potential solution with each of a plurality of concern categories associated with processing the solution prediction requirement to create a potential solution evaluation matrix;
evaluate the historical solution evaluation matrix and the potential solution evaluation matrix to determine a credibility score indicative of preponderance for each of the previous solution and the potential solution;
based on the evaluation, generate solution prediction data including the solution for the issue associated with the service user, the solution for issue including the previous solution, the potential solution, and the associated credibility score; and
select a service solution from the solution prediction data to process the solution prediction requirement, the selected service solution being implemented to resolve the solution prediction requirement.

### Claim 2 (depends on 1)

The system as claimed in claim 1, wherein the data extractor is to:
obtain the historical data including information associated with at least one of a defect, an incident, a concern, and a risk associated with the previous solution;
compute a requirement similarity parameter for the solution prediction requirement and the previous solution;
determine a number of occurrences of at least one of the defect, the incident, the concern, the risk corresponding to the requirement similarity parameter for each occurrence level category, the occurrence level category including at least one a high occurrence level category, a medium occurrence level category, and a low occurrence level category;
determine a final score for the previous solution based on the number of occurrences of the defect, the incident, the concern, the risk for each occurrence level category, and a weightage value assigned to the each occurrence level category; and
compute the requirement fulfillment index for the previous solution, based on the requirement similarity parameter and a corresponding predefined score reduction associated with the final score, the historical evolution solution matrix being based on the requirement fulfillment index.

### Claim 3 (depends on 1)

The system as claimed in claim 1, wherein the modeler is to:
obtain solution component data including information associated with at least one of a component defect, a component incident, a component concern, and a component risk associated with the potential solution; and
determine an occurrence probability for a second event associated with one of the component defect, the component incident, the component concern, and the component risk based on implementation of the artificial intelligence model on the solution component data; and
map the occurrence probability for the second event with the plurality of concern categories to create the potential solution evaluation matrix.

### Claim 4 (depends on 1)

The system as claimed in claim 1, wherein the pre-existing plurality of solution attributes include at least one of an infrastructure index, a user experience index, a popularity index, a scalability index, a community support index, and the requirement fulfillment index.

### Claim 5 (depends on 4)

The system as claimed in claim 4, wherein the modeler is to map information from the historical solution evaluation matrix and the potential solution evaluation matrix with at least one of the infrastructure index, the user experience index, the popularity index, the scalability index, the community support index, and the requirement fulfillment index to create an upvote library.

### Claim 6 (depends on 5)

The system as claimed in claim 5, wherein the modeler is to assign a solution rank to each of the previous solution and the solution prediction data, based on respective credibility scores.

### Claim 7 (depends on 6)

The system as claimed in claim 6, wherein the modeler is to:
compare the credibility score for each of the solution in the solution prediction data to identify a conflicting solution rank in the solution prediction data, the conflicting solution rank indicative of a similar credibility score for the previous solution and the potential solution; and
elevate the solution rank for at least one solution associated with the conflicting solution rank, based on comparing the solution associated with the conflicting solution rank with the upvote library.

### Claim 8

A method comprising:
receiving, by a processor, a solution prediction requirement associated with a service provided to a user, the solution prediction requirement being related to a solution to an issue pertaining to the service;
obtaining, by the processor, historical data and infrastructure data pertaining to processing of the solution prediction requirement from a data source, the historical data comprising information regarding a previous solution for resolving the issue, and the infrastructure data comprising infrastructure information associated with processing the solution prediction requirement;
implementing, by the processor, an artificial intelligence component to determine a requirement fulfillment index for the previous solution associated with processing the solution prediction requirement to create a historical solution evaluation matrix; and
implementing, by the processor, an artificial intelligence model to:
identify, from the data source, a plurality of solution components preponderant to deriving the solution associated with the issue;
obtain solution component data from the data source, the solution component data comprising information pertaining to each of the plurality of solution components;
map solution component data with each of a pre-existing plurality of solution attributes to determine a performance score indicative of a performance of each of the plurality of solution components associated with each of the solution attributes;
map the solution component data and the infrastructure data with the performance score to create a solution database comprising a potential solution for the issue, the potential solution being based on a technical solution available in market;
map the potential solution with each of a plurality of concern categories associated with processing the solution prediction requirement to create a potential solution evaluation matrix;
evaluate the historical solution evaluation matrix and the potential solution evaluation matrix to determine a credibility score indicative of preponderance for each of the previous solution and the potential solution;
based on the evaluation, generate solution prediction data including the solution for the issue associated with the service user, the solution for issue including the previous solution, the potential solution, and the associated credibility score; and
select a service solution from the solution prediction data to process the solution prediction requirement, the selected service solution being implemented to resolve the solution prediction requirement.

### Claim 9 (depends on 8)

The method as claimed in claim 8, wherein the method further comprises:
obtaining the historical data including information associated with at least one of a defect, an incident, a concern, and a risk associated with the previous solution;
computing a requirement similarity parameter for the solution prediction requirement and the previous solution;
determining a number of occurrences of at least one of the defect, the incident, the concern, the risk corresponding to the requirement similarity parameter for each occurrence level category, the occurrence level category including at least one a high occurrence level category, a medium occurrence level category, and a low occurrence level category;
determining a final score for the previous solution based on the number of occurrences of the defect, the incident, the concern, the risk for each occurrence level category, and a weightage value assigned to the each occurrence level category; and
computing the requirement fulfillment index for the previous solution, based on the requirement similarity parameter and a corresponding predefined score reduction associated with the final score, the historical evolution solution matrix being based on the requirement fulfillment index.

### Claim 10 (depends on 8)

The method as claimed in claim 8, wherein the method further comprises:
obtaining, by the processor, the solution component data including information associated with at least one of a component defect, a component incident, a component concern, and a component risk associated with the potential solution; and
determining, by the processor, an occurrence probability for a second event associated with one of the component defect, the component incident, the component concern, and the component risk based on implementation of the artificial intelligence model on the solution component data; and
mapping, by the processor, the occurrence probability for the second event with the plurality of concern categories to create the potential solution evaluation matrix.

### Claim 11 (depends on 8)

The method as claimed in claim 8, wherein the pre-existing plurality of solution attributes include at least one of an infrastructure index, a user experience index, a popularity index, a scalability index, a community support index, and a requirement fulfillment index.

### Claim 12 (depends on 11)

The method as claimed in claim 11, wherein the method further comprises mapping, by the processor, information from the historical solution evaluation matrix and the potential solution evaluation matrix with at least one of the infrastructure index, the user experience index, the popularity index, the scalability index, the community support index, and the requirement fulfillment index to create an upvote library.

### Claim 13 (depends on 12)

The method as claimed in claim 12, wherein the method further comprises assigning, by the processor, a solution rank to each of the previous solution and the potential solution in the solution prediction data, based on respective credibility scores.

### Claim 14 (depends on 13)

The method as claimed in claim 13, wherein the method further comprises:
comparing, by the processor, the credibility score for each of the solution in the solution prediction data to identify a conflicting solution rank in the solution prediction data, the conflicting solution rank indicative of a similar credibility score for the previous solution and the potential solution; and
elevating, by the processor, the solution rank for at least one solution associated with the conflicting solution rank, based on comparing the solution associated with the conflicting solution rank with the upvote library.

### Claim 15

A non-transitory computer-readable medium including machine readable instructions that are executable by a processor to:
receive a solution prediction requirement associated with a service provided to a user, the solution prediction requirement being related to a solution to an issue pertaining to the service;
obtain historical data and infrastructure data pertaining to processing of the solution prediction requirement from a data source, the historical data comprising information regarding a previous solution for resolving the issue, and the infrastructure data comprising infrastructure information associated with processing the solution prediction requirement;
implement an artificial intelligence component to determine a requirement fulfillment index for the previous solution associated with processing the solution prediction requirement to create a historical solution evaluation matrix; and
implement an artificial intelligence model to:
identify, from the data source, a plurality of solution components preponderant to deriving the solution associated with the issue;
obtain solution component data from the data source, the solution component data comprising information pertaining to each of the plurality of solution components;
map solution component data with each of a pre-existing plurality of solution attributes to determine a performance score indicative of a performance of each of the plurality of solution components associated with each of the solution attributes;
map the solution component data and the infrastructure data with the performance score to create a solution database comprising a potential solution for the issue, the potential solution being based on a technical solution available in market;
map the potential solution with each of a plurality of concern categories associated with processing the solution prediction requirement to create a potential solution evaluation matrix;
evaluate the historical solution evaluation matrix and the potential solution evaluation matrix to determine a credibility score indicative of preponderance for each of the previous solution and the potential solution;
based on the evaluation, generate solution prediction data including the solution for the issue associated with the service user, the solution for issue including the previous solution, the potential solution, and the associated credibility score; and
select a service solution from the solution prediction data to process the solution prediction requirement, the selected service solution being implemented to resolve the solution prediction requirement.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the processor is to:
obtain the historical data including information associated with at least one of a defect, an incident, a concern, and a risk associated with the previous solution;
compute a requirement similarity parameter for the solution prediction requirement and the previous solution;
determine a number of occurrences of at least one of the defect, the incident, the concern, the risk corresponding to the requirement similarity parameter for each occurrence level category, the occurrence level category including at least one a high occurrence level category, a medium occurrence level category, and a low occurrence level category;
determine a final score for the previous solution based on the number of occurrences of the defect, the incident, the concern, the risk for each occurrence level category, and a weightage value assigned to the each occurrence level category;
compute the requirement fulfillment index for the previous solution, based on the requirement similarity parameter and a corresponding predefined score reduction associated with the final score, the historical evolution solution matrix being based on the requirement fulfillment index.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the processor is to:
obtain the solution component data including information associated with at least one of a component defect, a component incident, a component concern, and a component risk associated with the potential solution; and
determine an occurrence probability for a second event associated with one of the component defect, the component incident, the component concern, and the component risk based on implementation of the artificial intelligence model on the solution component data; and
map the occurrence probability for the second event with the plurality of concern categories to create the potential solution evaluation matrix.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the processor is to pre-existing plurality of solution attributes include at least one of an infrastructure index, a user experience index, a popularity index, a scalability index, a community support index, and a requirement fulfillment index.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the processor is to:
map information from the historical solution evaluation matrix and the potential solution evaluation matrix with at least one of the infrastructure index, the user experience index, the popularity index, the scalability index, the community support index, and the requirement fulfillment index to create an upvote library; and
assign a solution rank to each of the previous solution and the potential solution in the solution prediction data, based on respective credibility scores.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein the processor is to:
compare the credibility score for each of the solution in the solution prediction data to identify a conflicting solution rank in the solution prediction data, the conflicting solution rank indicative of a similar credibility score for the previous solution and the potential solution; and
elevate the solution rank for at least one solution associated with the conflicting solution rank, based on comparing the solution associated with the conflicting solution rank with the upvote library.
