IP Library › Granted Patent US 11,869,024
Granted Patent B2
US 11,869,024 · App. 18/147,513 · Granted Jan 9, 2024

Methods and apparatus to analyze and adjust demographic information

Inventors: Albert R. Perez (San Francisco, CA); Josh Gaunt (Sunnyvale, CA)
Assignee: The Nielsen Company (US), LLC
G06Q30/0204G06Q10/067G06Q30/0201G06Q30/0246
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,869,024
App. No.
18/147,513
Granted
Jan 9, 2024
Kind
B2
Abstract

A disclosed example includes accessing computer-generated impression records, the computer-generated impression records based on network communications received at a server of a database proprietor from client devices, the computer-generated impression records indicative of accesses to media at the client devices; accessing self-reported demographic data and behavioral data from a database of the database proprietor, the self-reported demographic data and the behavioral data corresponding to user accounts registered with the database proprietor and associated with the client devices; comparing the self-reported demographic data with a probability distribution of higher-accuracy demographic data; determining different adjustments for corresponding ones of self-reported demographics of the self-reported demographic data based on the comparison; adjusting the corresponding ones of the self-reported demographics based on corresponding ones of the different adjustments to generate adjusted user demographic data; and assigning the adjusted user demographic data to corresponding ones of the computer-generated impression records.

Claims (36)

1. A system comprising:

memory;

instructions; and

programmable circuitry to be programmed by the instructions to:

access computer-generated impression records, the computer-generated impression records based on network communications received at a server of a database proprietor from client devices, the computer-generated impression records indicative of accesses to media at the client devices;

access self-reported demographic data from a database of the database proprietor, the self-reported demographic data corresponding to user accounts registered with the database proprietor and associated with the client devices;

determine different adjustments for corresponding ones of self-reported demographics of the self-reported demographic data based on an adjustment model and based on a comparison of the ones of the self-reported demographics with a probability distribution of higher-accuracy demographic data, the adjustment model selected based on an evaluation process of a first training model and a second training model;

adjust the corresponding ones of the self-reported demographics based on corresponding ones of the different adjustments to generate adjusted user demographic data; and

assign the adjusted user demographic data to corresponding ones of the computer-generated impression records.

2. The system of claim 1 , wherein the probability distribution of the higher-accuracy demographic data is located in the adjustment model.

3. The system of claim 1 , wherein the media is accessed at the client devices via the Internet.

4. The system of claim 1 , wherein the programmable circuitry is to perform the comparison of the ones of the self-reported demographics with the probability distribution of the higher-accuracy demographic data based on: (a) the probability distribution of the higher-accuracy demographic data being grouped into first categories, and (b) the first categories matched to second categories of the ones of the self-reported demographics.

5. The system of claim 1 , wherein the evaluation process includes comparisons of demographic buckets between the first training model and the second training model to determine which of the first training model and the second training model produces acceptable results based on a threshold.

6. The system of claim 1 , wherein the programmable circuitry is to assign the adjusted user demographic data to the corresponding ones of the computer-generated impression records to improve an accuracy of the computer-generated impression records.

7. A non-transitory computer readable medium comprising instructions to to cause programmable circuitry to at least:

access computer-generated impression records, the computer-generated impression records based on network communications received at a server of a database proprietor from client devices, the computer-generated impression records indicative of accesses to media at the client devices;

access self-reported demographic data from a database of the database proprietor, the self-reported demographic data corresponding to user accounts registered with the database proprietor and associated with the client devices;

determine different adjustments for corresponding ones of self-reported demographics of the self-reported demographic data based on an adjustment model and based on a comparison of the ones of the self-reported demographics with a probability distribution of higher-accuracy demographic data, the adjustment model selected based on an evaluation process of a first training model and a second training model;

adjust the corresponding ones of the self-reported demographics based on corresponding ones of the different adjustments to generate adjusted user demographic data; and

assign the adjusted user demographic data to corresponding ones of the computer-generated impression records.

8. The non-transitory computer readable medium of claim 7 , wherein the probability distribution of the higher-accuracy demographic data is located in the adjustment model.

9. The non-transitory computer readable medium of claim 7 , wherein the media is accessed at the client devices via the Internet.

10. The non-transitory computer readable medium of claim 7 , wherein the instructions are to cause the programmable circuitry to perform the comparison of the ones of the self-reported demographics with the probability distribution of the higher-accuracy demographic data based on: (a) the probability distribution of the higher-accuracy demographic data being grouped into first categories, and (b) the first categories matched to second categories of the ones of the self-reported demographics.

11. The non-transitory computer readable medium of claim 7 , wherein the evaluation process includes comparisons of demographic buckets between the first training model and the second training model to determine which of the first training model and the second training model produces acceptable results based on a threshold.

12. The non-transitory computer readable medium of claim 7 , wherein the instructions are to cause the programmable circuitry to assign the adjusted user demographic data to the corresponding ones of the computer-generated impression records to improve an accuracy of the computer-generated impression records.

13. A method comprising:

accessing computer-generated impression records, the computer-generated impression records based on network communications received at a server of a database proprietor from client devices, the computer-generated impression records indicative of accesses to media at the client devices;

accessing self-reported demographic data from a database of the database proprietor, the self-reported demographic data corresponding to user accounts registered with the database proprietor and associated with the client devices;

determining, by executing an instruction with a processor, different adjustments for corresponding ones of self-reported demographics of the self-reported demographic data based on an adjustment model and based on a comparison of the ones of the self-reported demographics with a probability distribution of higher-accuracy demographic data, the adjustment model selected based on an evaluation process of a first training model and a second training model;

adjusting, by executing an instruction with the processor, the corresponding ones of the self-reported demographics based on corresponding ones of the different adjustments to generate adjusted user demographic data; and

assigning, by executing an instruction with the processor, the adjusted user demographic data to corresponding ones of the computer-generated impression records.

14. The method of claim 13 , wherein the probability distribution of the higher-accuracy demographic data is located in the adjustment model.

15. The method of claim 13 , wherein the media is accessed at the client devices via the Internet.

16. The method of claim 13 , wherein the comparison of the ones of the self-reported demographics with the probability distribution of the higher-accuracy demographic data is based on: (a) the probability distribution of the higher-accuracy demographic data being grouped into first categories, and (b) the first categories matched to second categories of the ones of the self-reported demographics.

17. The method of claim 13 , wherein the evaluation process includes comparisons of demographic buckets between the first training model and the second training model to determine which of the first training model and the second training model produces acceptable results based on a threshold.

18. The method of claim 13 , wherein the assigning of the adjusted user demographic data to the corresponding ones of the computer-generated impression records is to improve an accuracy of the computer-generated impression records.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 5, 2023
From: PEREZ, ALBERT R.; GAUNT, JOSH
To: THE NIELSEN COMPANY (US), LLC
Reel/Frame 062636/0990 →
Continuity (8)
Continuation 17163533 · Jan 31, 2021
Continuation 16051055 · Jul 31, 2018
Continuation 15420861 · Jan 31, 2017
Continuation 14809888 · Jul 27, 2015
Continuation 13209292 · Aug 12, 2011
Provisional Application 61386543 · Sep 26, 2010
Provisional Application 61385553 · Sep 22, 2010
Related Publication 20230132878A1 · May 4, 2023
Cited By (2)
US 12,223,520 US 12,586,095