# US 12,223,457 B2 · Intelligent scoring systems and methods for scoring a level of performance of a business unit of a plurality of business units in an organization

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

- Number: US 12,223,457 B2
- Document ID: US12223457B2
- Status: Granted
- Kind: B2
- Application number: 17/526,749
- Filed: 2021-11-15
- Published: 2023-05-18
- Granted: 2025-02-11
- Earliest claimed: 2021-11-15
- Assignees: Allstate Solutions Private Limited
- Applicants: Allstate Solutions Private Limited
- Inventors: Sarish Paul; Anupam Adhikari; Siddharth Gaur; Sheeba Bano; Kamalnath KV
- Web page: https://patentgrep.com/patent/US12223457B2

## CPC

- G06Q 10/06395: {Quality analysis or management}
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/09: Supervised learning
- G06Q 10/0637: Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An intelligent scoring system includes a scorecard tool, a user input device, a memory component, a processor; and machine-readable instructions. The scorecard tool includes a scorecard and a neural network model. The machine-readable instructions stored in the memory component cause the intelligent scoring system to: receive a parameter rating for the scorecard for a first portion of a plurality of business performance parameters; automatically input the parameter rating for the scorecard for a second portion of the plurality of business performance parameters; associate a weighting with each parameter rating; estimate a parameter outcome score for each of the first portion and the second portion of the plurality of business performance parameters based on each parameter rating and weighting; automatically estimate an overall outcome score; and automatically generate a recommendation for improving the level of performance of the business unit.

## Claims

### Claim 1

An intelligent scoring system for scoring a level of performance of a business unit of a plurality of business units in an organization, comprising:
a scorecard tool comprising a scorecard and a neural network model;
one or more user input devices;
one or more memory components;
one or more processors communicatively coupled to the scorecard tool, the one or more user input devices, and the one or more memory components; and
machine-readable instructions stored in the one or more memory components that cause the intelligent scoring system to perform at least the following when executed by the one or more processors:
receive from the one or more user input devices a parameter rating for the scorecard of the business unit for each of a first portion of a plurality of business performance parameters;
automatically input the parameter rating for the scorecard of the business unit for each of a second portion of the plurality of business performance parameters;
automatically determine, via the neural network model, a weighting associated with each parameter rating;
automatically estimate, via the neural network model, a parameter outcome score for each of the first portion and the second portion of the plurality of business performance parameters based on each respective parameter rating and each associated weighting;
automatically estimate, via the neural network model, an overall outcome score indicating the level of performance of the business unit of the plurality of business units of the organization based on each parameter outcome score;
automatically generate one or more recommendations for improving the level of performance of the business unit based on the overall outcome score;
automatically display one or more portions of the scorecard including the weighting applied to each parameter rating as an indicator of an impact of each parameter to the overall outcome score;
store, to a training data server, at least one of the parameter rating, the weighting, the parameter outcome score, the overall outcome score, and/or the one or more recommendations as a historical parameter rating, a historical weighting, a historical parameter outcome score, a historical overall outcome score, and/or a historical recommendation;
update the neural network model, wherein the neural network model is retrained with the historical parameter rating, the historical weighting, the historical parameter outcome score, the historical overall outcome score, and/or the historical recommendation;
adjust the weighting, via the neural network model, of each parameter rating; and
generate one or more micro-organizational scores for one or more subgroups of the business unit, wherein the one or more recommendations for improving the level of performance of the business unit comprises a recommendation to at least one micro-organizational entity including a first sub group selected from the one or more subgroups and focused on a product or a geographic location.

### Claim 2 (depends on 1)

The intelligent scoring system of claim 1, wherein:
the machine-readable instructions stored in the one or more memory components further cause the intelligent scoring system to retrieve business data stored on the one or more memory components,
the parameter rating for the scorecard of the business unit for each of the second portion of the plurality of business performance parameters is generated, via the neural network model, based on the business data.

### Claim 3 (depends on 2)

The intelligent scoring system of claim 2, wherein the machine-readable instructions stored in the one or more memory components further cause the intelligent scoring system to automatically generate, via the neural network model, the parameter rating for each of the second portion of the plurality of business performance parameters based on a rating parameter received from the one or more user input devices and the business data.

### Claim 4 (depends on 1)

The intelligent scoring system of claim 1, further comprising a display communicatively coupled to the one or more processors, wherein the machine-readable instructions stored in the one or more memory components further cause the intelligent scoring system to display the one or more recommendations for improving the level of performance of the business unit on the display.

### Claim 5 (depends on 1)

The intelligent scoring system of claim 1, wherein the plurality of business performance parameters include value to core business, leadership, delivery responsibility, ownership, participation, responsibility, footprint, collaboration, employee band mix, number of subordinates, employee survey inputs, retention, process maturity/adoption, tool usage, or innovation culture.

### Claim 6

A method for intelligent assessment of a business unit of a plurality of business units of an organization, the method comprising:
receiving with one or more processors of an intelligent scoring system, a parameter rating for a scorecard of the business unit for each of a first portion of a plurality of business performance parameters;
automatically inputting the parameter rating for the scorecard of the business unit for each of a second portion of the plurality of business performance parameters;
automatically determining, via a neural network model, a weighting associated with each parameter rating;
automatically estimating, via the neural network model, a parameter outcome score for each of the first portion and the second portion of the plurality of business performance parameters based on each respective parameter rating and each associated weighting;
automatically estimating, via the neural network model, an overall outcome score indicating a level of performance of the business unit of the plurality of business units of the organization based on each parameter outcome score;
automatically generating one or more recommendations for improving the level of performance of the business unit based on the overall outcome score;
automatically displaying one or more portions of the scorecard including the weighting applied to each parameter rating as an indicator of an impact of each parameter to the overall outcome score;
storing, to a training data server, at least one of the parameter rating, the weighting, the parameter outcome score, the overall outcome score, and/or the one or more recommendations as a historical parameter rating, a historical weighting, a historical parameter outcome score, a historical overall outcome score, and/or a historical recommendation;
updating the neural network model by retraining the neural network model with the historical parameter rating, the historical weighting, the historical parameter outcome score, the historical overall outcome score, and/or the historical recommendation;
adjusting the weighting, via the neural network model, of each parameter rating; and
generating one or more micro-organizational scores for one or more subgroups of the business unit, wherein the one or more recommendations for improving the level of performance of the business unit comprises a recommendation to at least one micro-organizational entity including a first sub group selected from the one or more subgroups and focused on a product or a geographic location.

### Claim 7 (depends on 6)

The method of claim 6, further comprising retrieving, with the one or more processors, business data stored on one or more memory components, wherein the parameter rating for the scorecard of the business unit for each of the second portion of the plurality of business performance parameters is generated, via the neural network model, based on the business data.

### Claim 8 (depends on 7)

The method of claim 7, further comprising generating, via the neural network model, the parameter rating for each of the second portion of the plurality of business performance parameters based on a rating parameter received from one or more user input devices and the business data.

### Claim 9 (depends on 6)

The method of claim 6, further comprising displaying, on a display communicatively coupled to the one or more processors, the one or more recommendations for improving the level of performance of the business unit.

### Claim 10 (depends on 6)

The method of claim 6, wherein the plurality of business performance parameters include value to core business, leadership, delivery responsibility, ownership, participation, responsibility, footprint, collaboration, employee band mix, number of subordinates, employee survey inputs, retention, process maturity/adoption, tool usage, or innovation culture.

### Claim 11 (depends on 6)

The method of claim 6, wherein the plurality of business performance parameters include at least two or more of value to core business, leadership, delivery responsibility, delivery responsibility, ownership, participation, responsibility, footprint, collaboration, employee band mix, number of subordinates, employee survey inputs, retention, process maturity/adoption, tool usage, or innovation culture.

### Claim 12

A method for intelligent assessment of a business unit of a plurality of business units of an organization, the method comprising:
retrieving, with one or more processors, business data stored on one or more memory components communicatively coupled to the one or more processors;
automatically generating, via a neural network model, a rating parameter for one or more business performance parameters based the business data;
automatically determining, via the neural network model, a weighting associated with each parameter rating;
automatically estimating, via the neural network model, a parameter outcome score for each of the one or more business performance parameters based on each respective parameter rating and each associated weighting;
automatically estimating, via the neural network model, an overall outcome score indicating a level of performance of the business unit of the plurality of business units of the organization based on each parameter outcome score;
automatically displaying a scorecard including the rating parameter, the weighting applied to each parameter rating, the parameter outcome score and the overall outcome score as an indicator of an impact of each parameter to the overall outcome score;
storing, to a training data server, at least one of the parameter rating, the weighting, the parameter outcome score, and/or the overall outcome score as a historical parameter rating, a historical weighting, a historical parameter outcome score, and/or a historical overall outcome score;
updating the neural network model by retraining the neural network model with the historical parameter rating, the historical weighting, the historical parameter outcome score, and/or the historical overall outcome score;
adjusting the weighting, via the neural network model, of each parameter rating;
automatically generating, via a neural network recommendation model, one or more recommendations for improving the level of performance of the business unit; and
generating one or more micro-organizational scores for one or more subgroups of the business unit, wherein the one or more recommendations for improving the level of performance of the business unit comprises a recommendation to at least one micro-organizational entity including a first sub group selected from the one or more subgroups and focused on a product or a geographic location.

### Claim 13 (depends on 12)

The method of claim 12, further comprising displaying the one or more recommendations for improving the level of performance of the business unit on a display communicatively coupled to the one or more processors.

### Claim 14 (depends on 12)

The method of claim 12, wherein the one or more recommendations for improving the level of performance of the business unit are based on the weightage of each of the one or more business performance parameters to the overall outcome score.

### Claim 15 (depends on 12)

The method of claim 12, wherein the one or more business performance parameters include value to core business, leadership, delivery responsibility, ownership, participation, responsibility, footprint; collaboration, employee band mix, number of subordinates, employee survey inputs, retention, process maturity/adoption, tool usage, or innovation culture.

### Claim 16 (depends on 1)

The intelligent scoring system of claim 1, wherein the business performance parameters are customized for the first sub-group of the business unit based on goals, needs, and organization structure, and includes one or more global capability parameters and one or more execution capability parameters.