Methods, systems, articles of manufacture, and apparatus to estimate audience population

Patent metadata

Field	Value
Publication number	US-12361439-B2
Application number	US-202318495573-A
Country	US
Kind code	B2
Filing date	Oct 26, 2023
Priority date	Jun 22, 2020
Publication date	Jul 15, 2025
Grant date	Jul 15, 2025

Abstract

Methods, apparatus, systems, and articles of manufacture are disclosed to estimate an audience population. An example apparatus includes processor circuitry; characteristic identifier instructions to be executed by the processor circuitry to determine whether respective ones of respondents are associated with a characteristic; recapture probability estimator instructions to be executed by the processor circuitry to select a recapture probability of the respective ones of respondents; and population estimator instructions to be executed by the processor circuitry to in response to the recapture probability satisfying a recapture threshold, determine a population estimate having the characteristics based on a first model; and in response to the recapture probability not satisfying the recapture threshold, determine the population estimate having the characteristics based on a second model, the second model different than the first model.

First claim

What is claimed is:

1. An audience measurement computing system comprising:
at least one processor;
memory having stored therein computer readable instructions that, when executed by the at least one processor, cause the audience measurement computing system to:
count respective ones of respondents that are associated with a characteristic, wherein the characteristic corresponds to a population subset;
determine a recapture probability of the respective ones of respondents;
select from amongst multiple population estimation models based on the recapture probability; and
determine an estimate of the population subset based on a selected one of the multiple population estimation models.

2. The audience measurement computing system of claim 1 , wherein the computer readable instructions further cause, when executed by the at least one processor, the audience measurement computing system to select from amongst the multiple population estimation models by:
making a determination that the recapture probability varies in time; and
selecting the selected one of the multiple population estimation models in response to making the determination.

3. The audience measurement computing system of claim 1 , wherein the computer readable instructions further cause, when executed by the at least one processor, the audience measurement computing system to select from amongst the multiple population estimation models by:
making a determination that the recapture probability is constant; and
selecting the selected one of the multiple population estimation models in response to making the determination.

4. The audience measurement computing system of claim 1 , wherein the computer readable instructions further cause, when executed by the at least one processor, the audience measurement computing system to select from amongst the multiple population estimation models by determining whether the recapture probability satisfies a recapture threshold.

5. The audience measurement computing system of claim 1 , wherein the computer readable instructions further cause, when executed by the at least one processor, the audience measurement computing system to:
determine a seed population estimate based on a unique capture count for respective ones of the respondents based on the recapture probability; and
determine the estimate of the population subset based on the seed population estimate.

6. The audience measurement computing system of claim 1 , wherein the computer readable instructions further cause, when executed by the at least one processor, the audience measurement computing system to:
determine a first audience population estimate based on a sample count, the sample count based on a unique capture count, a total capture count, a seed population estimate, and a number of samples collected;
determine a second audience population estimate without the sample count; and
select one of the first audience population estimate or the second audience population estimate as the estimate of the population subset based on a difference between the first audience population estimate and the second audience population estimate relative to a population estimate threshold.

7. The audience measurement computing system of claim 6 , wherein the computer readable instructions further cause, when executed by the at least one processor, the audience measurement computing system to select the first audience population estimate as the estimate of the population subset when the difference between the first audience population estimate and the second audience population estimate is below the population estimate threshold.

8. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor of a computing system, cause at least:
counting respective ones of respondents that are associated with a characteristic, wherein the characteristic corresponds to a population subset;
determining a recapture probability of the respective ones of respondents;
selecting from amongst multiple population estimation models based on the recapture probability; and
determining an estimate of the population subset based on a selected one of the multiple population estimation models.

9. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause selecting from amongst multiple population estimation models by at least:
making a determination that the recapture probability varies in time; and
selecting the selected one of the multiple population estimation models in response to making the determination.

10. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause selecting from amongst multiple population estimation models by at least:
making a determination that the recapture probability is constant; and
selecting the selected one of the multiple population estimation models in response to making the determination.

11. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause selecting from amongst multiple population estimation models by at least determining whether the recapture probability satisfies a recapture threshold.

12. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause:
determining a seed population estimate based on a unique capture count for respective ones of the respondents based on the recapture probability; and
determining the estimate of the population subset based on the seed population estimate.

13. The non-transitory computer readable medium of claim 8 , wherein the instructions further cause:
determining a first audience population estimate based on a sample count, the sample count based on a unique capture count, a total capture count, a seed population estimate, and a number of samples collected;
determining a second audience population estimate without the sample count; and
selecting one of the first audience population estimate or the second audience population estimate as the estimate of the population subset based on a difference between the first audience population estimate and the second audience population estimate relative to a population estimate threshold.

14. A computer implemented method comprising:
counting respective ones of respondents that are associated with a characteristic, wherein the characteristic corresponds to a population subset;
determining a recapture probability of the respective ones of respondents;
selecting from amongst multiple population estimation models based on the recapture probability; and
determining an estimate of the population subset based on a selected one of the multiple population estimation models.

15. The computer implemented method of claim 14 , wherein the selecting from amongst multiple population estimation models includes:
making a determination that the recapture probability varies in time; and
selecting the selected one of the multiple population estimation models in response to making the determination.

16. The computer implemented method of claim 14 , wherein the selecting from amongst multiple population estimation models includes:
making a determination that the recapture probability is constant; and
selecting the selected one of the multiple population estimation models in response to making the determination.

17. The computer implemented method of claim 14 , wherein the selecting from amongst multiple population estimation models includes determining whether the recapture probability satisfies a recapture threshold.

Assignees

• Nielsen Co Us Llc

Inventors

• Sheppard Michael
• Murphy Edward
• Poppie Molly
• Daemen Ludo

Classifications

• H04N21/44222

  Analytics of user selections, e.g. selection of programmes or purchase activity (monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33) · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• H04H60/45

  for identifying users · CPC title

• H04H60/33

  Arrangements for monitoring the users' behaviour or opinions · CPC title

• H04H60/66

  for using the result on distributors' side · CPC title