System and method for creating a census hub in resource constrained regions

Patent metadata

Field	Value
Publication number	US-11468377-B2
Application number	US-201916458161-A
Country	US
Kind code	B2
Filing date	Jun 30, 2019
Priority date	Mar 2, 2016
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

The disclosure provides systems and methods for generating attendance census models using data received from a network of automated census sensors as well as various additional secondary data sources. The models may be generated and used in real time to provide attendance predictions, to efficiently allocate resources, and to detect fraud, among many other uses.

First claim

The invention claimed is:

1. A method comprising the steps of:
receiving, by a computer system via a network, one or more sensor signals that represent attendee information about one or more physical attributes of one or more students attending one or more schools remotely located with respect to the computer system, and storing the attendee information in an attendee data record in a database, wherein the attendee data record is dynamically annotated with predefined metadata values by an embedded unit;
receiving, by the computer system, one or more data signals from one or more secondary data sources and storing non-census data determined from the data signals in one or more non-census data records;
correlating the non-census data records with the attendee data records to create a census hub, the correlation using one or more of a time factor, a location factor, and an identity factor;
generating an attendance forecast for the school based on the correlated non-census data records and the attendee data records for one or more groups of students in one or more of the schools, the attendance forecast including past events and future predictions over a time scale; and
generating one or more notifications based on the attendance forecast that include a requisition order to a supplier and a public notice to enable transparent allocation and distribution of a resource, wherein any allocation and distribution based on fraudulent attendance data is detected based on profiles being defined by the identity factors for the students attending the school, the school being defined by the location factor, and the time attended being defined by the time factor, respectively.

2. The method of claim 1 , further comprising the step of generating an attendance model based on the correlated non-census data records and the attendee data records, and wherein the attendance forecast is part of the attendance model.

3. The method of claim 1 , wherein the census hub is a database structured to store historical census data from a plurality of schools, and further comprising generating an attendance model, wherein the attendance forecast is part of the attendance model.

4. The method of claim 1 , wherein the secondary data source is one or more of the following: a sensor, a social media network, a website, a manual input device, and a secondary database.

5. The method of claim 1 , wherein a secondary data is selected from one or more of the following: a weather report, a website usage report, a health report, an attendance report, an audio recording, and a news report.

6. The method of claim 1 , wherein the identity factor is obtained from one or more of the following sensors: a camera, a fingerprint reader, an identification (ID) scanner, a Radio Frequency ID (RFID) reader, an image, a photograph, an ID number, and a biometric indicator.

7. The method of claim 1 , where the metadata includes at least one local weather factors including one or more of a temperature, a humidity, and a barometric pressure.

8. The method of claim 1 , further comprising the step of receiving, by the computer system, one or more data signals representing a tertiary non-census data from one or more tertiary data sources, the tertiary data being specific to one of the schools.

9. The method of claim 8 , where the tertiary non-census data includes one or more of: one or more resources available at a school, one or more resources available per student, an historical school profile data, performance data of a school, performance data for one or more students at that school, historical fraud data, a neighborhood statistic, and time data for the foregoing.

10. A networked census system comprising:
a server comprising one or more computer processors and one or more memories coupled to the processor; and
a networked set of attendance census gathering sensors,
wherein each attendance census gathering sensor in the set of attendance census gathering sensors is in data communication with the server, and wherein the memory is configured to store program instructions executable by the processor to cause the server to perform the following:
receiving via the network, one or more sensor signals that represent attendee information about one or more physical attributes of one or more students attending one or more schools remotely located with respect to the system, and storing the attendee information in an attendee data record in a database;
receiving one or more data signals from one or more secondary data sources and storing non-census data determined from the data signals in one or more non-census data records;
correlating the non-census data records with the attendee data records to create a census hub, the correlation using one or more of a time factor, a location factor, and an identity factor;
generating an attendance model for the one or more of the schools based on the correlated non-census data records and the attendee data records in the census hub,
based on the attendance model, generating an attendance forecast for each of the schools based on the correlated non-census data records and the attendee data records for one or more groups of students in one or more schools, the attendance forecast including past events and future predictions over a time scale; and
generating one or more notifications based on the attendance forecast that include a requisition order to a supplier and a public notice to enable transparent allocation and distribution of a resource, wherein any allocation and distribution based on fraudulent attendance data is detected based on profiles being defined by the identity factors for the students attending the school, the school being defined by the location factor, and the time attended being defined by the time factor, respectively.

11. The system of claim 10 , wherein the processor is configured to receive a request from a user and provide an output based on the request and the attendance model.

12. The system of claim 10 , wherein the notification is an alert transmitted via the network to notify one or more remote users of resources that are needed at one or more of the schools.

13. The system of claim 10 , wherein the notification is a requisition order transmitted via the network to requisition resources needed at one or more of the schools.

14. The system, as in claim 13 , where the resources include one or more of the following: electrical power and water.

15. The system, as in claim 10 , where the notification is sent from an interactive platform.

16. The system, as in claim 10 , where the notification is a requisition for a resource.

17. The system, as in claim 16 , where the resource is one or more of food, water, books, and school supplies.

18. The system, as in claim 16 , where the notification is sent directly to a resource provider.

19. The system, as in claim 10 , where the notification is sent as a forecast of change in attendance from the attendance model due to a resource availability.

20. The system, as in claim 19 , where the attendance model uses one or more tertiary non-census data to make the forecast, the tertiary non-census data including one or more of: one or more resources available at a school, one or more resources available per student, an historical school profile data, performance data of a school, performance data for one or more students at that school, historical fraud data, neighbourhood statistics, and time data for the foregoing.

Assignees

• IBM

Inventors

• Bhattacharya Kamal
• Kalton Alan
• Weldemariam Komminist

Classifications

• G06Q10/0631 Primary

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G06Q50/20

  Education · CPC title