# US 2022/0036390 A1 · Methods and apparatus to estimate audience measurement metrics based on users represented in bloom filter arrays

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

- Number: US 2022/0036390 A1
- Document ID: US20220036390A1
- Status: Published application
- Kind: A1
- Application number: 16/945,055
- Filed: 2020-07-31
- Published: 2022-02-03
- Earliest claimed: 2020-07-31
- Assignees: The Nielsen Company (US), LLC
- Applicants: The Nielsen Company (US), LLC
- Inventors: Michael Sheppard; Jake Ryan Dailey; Dongbo Cui; Jonathan Sullivan; Diane Morovati Lopez; Christie Nicole Summers; Molly Poppie
- Web page: https://patentgrep.com/patent/US20220036390A1

## CPC

- G06F 16/20: of structured data, e.g. relational data
- G06Q 30/0204: Market segmentation
- G06F 16/435: Filtering based on additional data, e.g. user or group profiles
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/20: Ensemble learning
- H04L 43/10: Active monitoring, e.g. heartbeat, ping or trace-route
- H04N 21/252: {Processing of multiple end-users' preferences to derive collaborative data}
- H04N 21/254: Management at additional data server, e.g. shopping server, rights management server {(arrangements for maintenance or administration in data networks H04L41/00; network services using third party service providers H04L67/53)}
- H04N 21/44224: {Monitoring of user activity on external systems, e.g. Internet browsing}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Methods, apparatus, systems, and articles of manufacture to estimate audience measurement metrics based on users represented in Bloom filter arrays are disclosed. An apparatus includes a communications interface to receive a first Bloom filter array from a first computer of a first database proprietor. The first Bloom filter array is representative of first users who accessed media. The first users are registered with the first database proprietor. The first Bloom filter array includes a first array of first elements. Values of respective ones of the first elements are either a 0 or a 1 based on whether quantities of the first users allocated to the respective ones of the first elements are even or odd. The apparatus further includes a Bloom filter array analyzer to estimate a first cardinality for the first Bloom filter array. The first cardinality is indicative of a total number of the first users who accessed the media.

## Claims

### Claim 1

An apparatus comprising:
a communications interface to receive a first Bloom filter array from a first computer of a first database proprietor, the first Bloom filter array representative of first users who accessed media, the first users registered with the first database proprietor, the first Bloom filter array including a first array of first elements, values of respective ones of the first elements being either a 0 or a 1 based on whether quantities of the first users allocated to the respective ones of the first elements are even or odd; and
a Bloom filter array analyzer to estimate a first cardinality for the first Bloom filter array, the first cardinality indicative of a total number of the first users who accessed the media.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the Bloom filter array analyzer is to:
determine a count of the first elements with a value of 1; and
estimate the first cardinality based on the count.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the count is a first count, the communications interface to receive a second Bloom filter array from the first computer of the first database proprietor, the second Bloom filter array representative of the first users who accessed media, the second Bloom filter array including a second array of second elements, the first users allocated to ones of the first elements of the first array based on a first hash function and allocated to ones of the second elements of the second array based on a second hash function different than the first has function, the Bloom filter array analyzer to
determine a second count of the second elements with a value of 1; and
estimate the first cardinality based on an average of the first and second counts.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the Bloom filter array analyzer is to:
determine a multiplicative constant based on a noise parameter, the noise parameter defining a probability at which ones of the values of respective ones of the first elements are flipped between 0 and 1 independent of an allocation of the first users to the respective ones of the first elements; and
estimate the first cardinality based on the multiplicative constant.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the communications interface is to receive a second Bloom filter array from a second computer of a second database proprietor, the second Bloom filter array representative of second users who accessed the media, the second users registered with the second database proprietor, the second Bloom filter array including a second array of second elements, values of respective ones of the second elements being either a 0 or a 1 based on whether quantities of the second users allocated to the respective ones of the second elements are even or odd, the Bloom filter array analyzer to estimate an overall cardinality across both the first and second Bloom filter arrays, the overall cardinality indicative of a total number of unique individuals corresponding to the first and second users who accessed the media.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the first array of first elements has a same length as the second array of second elements, the length corresponding to an odd number of elements.

### Claim 7 (depends on 5)

The apparatus of claim 5, wherein the Bloom filter array analyzer is to:
generate a third array of third elements based on a bit-wise union of the first array and the second array, the bit-wise union based on modulo 2 addition; and
estimate the overall cardinality based on the third array.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the communications interface is to receive a plurality of Bloom filter arrays including the first Bloom filter array, ones of the Bloom filter arrays representative of different users who accessed the media, the Bloom filter array analyzer to:
generate a plurality of arrays based on bit-wise unions between different sets of at least two of the plurality of Bloom filter arrays, the bit-wise unions based on modulo 2 addition, ones of the plurality of arrays representative of exclusive-or groupings of the different users included within datasets underlying respective ones of the plurality of Bloom filter arrays;
estimate a plurality of exclusive-or cardinalities for the plurality of arrays; and
estimate an overall cardinality across the plurality of Bloom filter arrays based on a summation of the exclusive-or cardinalities.

### Claim 9

A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:
access a first Bloom filter array generated by a first computer of a first database proprietor, the first Bloom filter array representative of first users who accessed media, the first users registered with the first database proprietor, the first Bloom filter array including a first array of first elements, values of respective ones of the first elements being either a 0 or a 1 based on whether quantities of the first users allocated to the respective ones of the first elements are even or odd; and
estimate a first cardinality for the first Bloom filter array, the first cardinality indicative of a total number of the first users who accessed the media.

### Claim 10 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the instructions further cause the machine to:
determine a count of the first elements with a value of 9; and
estimate the first cardinality based on the count.

### Claim 11 (depends on 10)

The non-transitory computer readable medium of claim 10, wherein the count is a first count, and the instructions further cause the machine to:
access a second Bloom filter array generated by the first computer of the first database proprietor, the second Bloom filter array representative of the first users who accessed media, the second Bloom filter array including a second array of second elements, the first users allocated to ones of the first elements of the first array based on a first hash function and allocated to ones of the second elements of the second array based on a second hash function different than the first has function;
determine a second count of the second elements with a value of 1; and
estimate the first cardinality based on an average of the first and second counts.

### Claim 12 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the instructions further cause the machine to:
determine a multiplicative constant based on a noise parameter, the noise parameter defining a probability at which ones of the values of respective ones of the first elements are flipped between 0 and 1 independent of an allocation of the first users to the respective ones of the first elements; and
estimate the first cardinality based on the multiplicative constant.

### Claim 13 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the instructions further cause the machine to:
access a second Bloom filter array generated by a second computer of a second database proprietor, the second Bloom filter array representative of second users who accessed the media, the second users registered with the second database proprietor, the second Bloom filter array including a second array of second elements, values of respective ones of the second elements being either a 0 or a 1 based on whether quantities of the second users allocated to the respective ones of the second elements are even or odd; and
estimate an overall cardinality across both the first and second Bloom filter arrays, the overall cardinality indicative of a total number of unique individuals corresponding to the first and second users who accessed the media.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the first array of first elements has a same length as the second array of second elements, the length corresponding to an odd number of elements.

### Claim 15 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the instructions further cause the machine to:
generate a third array of third elements based on a bit-wise union of the first array and the second array, the bit-wise union based on modulo 2 addition; and
estimate the overall cardinality based on the third array.

### Claim 16 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein the instructions further cause the machine to:
access a plurality of Bloom filter arrays including the first Bloom filter array, ones of the Bloom filter arrays representative of different users who accessed the media;
generate a plurality of arrays based on bit-wise unions between different sets of at least two of the plurality of Bloom filter arrays, the bit-wise unions based on modulo 2 addition, ones of the plurality of arrays representative of exclusive-or groupings of the different users included within datasets underlying respective ones of the plurality of Bloom filter arrays;
estimate a plurality of exclusive-or cardinalities for the plurality of arrays; and
estimate an overall cardinality across the plurality of Bloom filter arrays based on a summation of the exclusive-or cardinalities.

### Claim 17

A method comprising:
accessing a first Bloom filter array generated by a first computer of a first database proprietor, the first Bloom filter array representative of first users who accessed media, the first users registered with the first database proprietor, the first Bloom filter array including a first array of first elements, values of respective ones of the first elements being either a 0 or a 1 based on whether quantities of the first users allocated to the respective ones of the first elements are even or odd; and
estimating, by executing an instruction with a processor, a first cardinality for the first Bloom filter array, the first cardinality indicative of a total number of the first users who accessed the media.

### Claim 18 (depends on 17)

The method of claim 17, further including:
determining a count of the first elements with a value of 1; and
estimating the first cardinality based on the count.

### Claim 19 (depends on 18)

The method of claim 18, wherein the count is a first count, and further including:
accessing a second Bloom filter array generated by the first computer of the first database proprietor, the second Bloom filter array representative of the first users who accessed media, the second Bloom filter array including a second array of second elements, the first users allocated to ones of the first elements of the first array based on a first hash function and allocated to ones of the second elements of the second array based on a second hash function different than the first has function;
determining a second count of the second elements with a value of 1; and
estimating the first cardinality based on an average of the first and second counts.

### Claim 20 (depends on 17)

The method of claim 17, further including:
determining a multiplicative constant based on a noise parameter, the noise parameter defining a probability at which ones of the values of respective ones of the first elements are flipped between 0 and 1 independent of an allocation of the first users to the respective ones of the first elements; and
estimating the first cardinality based on the multiplicative constant.

### Claim at position 21

21-27. (canceled)
