Browse Prior Art Database

Method for Advanced Resource Planning Utilizing Local Health Data and Patterns

IP.com Disclosure Number: IPCOM000248125D
Publication Date: 2016-Oct-28
Document File: 5 page(s) / 80K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a process for advanced resource planning utilizing local health data and patterns. The proposed method finds recommendations about how to staff businesses taking into account local health patterns.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 45% of the total text.

Page 01 of 5

Method for Advanced Resource Planning Utilizing Local Health Data and Patterns


Businesses in both the developing and developed countries face problems with trying to adequately staff at optimal levels. Over-staffing can reduce profit margins, while under-staffing can negatively impact customer service and demand fulfillment.

Some of the factors that increase the staffing demands are based on relatively static data and are therefore easy to predict, for example peak vacations periods, peak shopping seasons, etc. However, not all situations have a defined factor to reliably predict the need to increase staffing.

For example, in some situations the needed staffing increase may be due to health conditions in the local community, either because employees are more likely to get sick or an increased risk that an employee will need to call in sick to take care of another sick family member.

With today's advances in cognitive methods, an algorithm to utilize growing data sets and predict the overstaff requirement is needed help to do a better planning and provide better service level.

The disclosed method describes a process for advanced resource planning utilizing local health data and patterns. The proposed method finds recommendations about how to staff businesses (e.g., large retail, grocery stores, local pizza shop, etc.) taking into account local health patterns.

The method can use a number of data sets to find the potential overstaff requirements, including a combination of proprietary and existing open data sets: Center for Disease Control (CDC) data, local government website health data, hospital check-ins and symptoms, doctor visits, school data about the number of students out sick, etc.).

The process establishes baselines. When the baselines are crossed, the system sends a warning to employers to increase staff allocated per shift/day. The number of employees with school-aged children could be included, in order to account for parents calling in sick to tend to sick children.

In one example, after local data analysis, the method could suggest that a business should overstaff by 10% next week to take into account an increase in people likely to call in sick.

1


Page 02 of 5

Figure: System diagram

Following are the components and process, as depicted in the system diagram, above: 100 Advance Resource Planning Processor

110 Data Collector component gathers information form external data sources (e.g., CDC data, local government health data, hospital check-ins, school data, etc.).
120 Data Analytics component analyzes the information collected and finds patterns that could be used to predict a potential overstaff requirement.
130 Staff Recommendations component uses the data patterns found by the Data Analytics component to make estimates about the recommended overstaff required by the local business.
140 Data store component saves historical information that can be used to predict overstaff. This component can also customize the outp...