Methods and apparatus to estimate audience measurement metrics based on users represented in bloom filter arrays

A method for generating a modulo 2 Bloom filter array, the method comprising:

• receiving network-based impression requests indicative of accesses to digital media over the internet by respective client devices, wherein the respective client devices are operated by respective users that are registered with a database proprietor;
• based on receiving the network-based impression requests, logging media impressions in a database of the database proprietor;
• obtaining, by a computing system comprising a processor, a memory, and a network communication interface using the logged media impressions, a list of users that accessed the media;
• generating, by the computing system, an array of elements, each element in the array of the elements storing a same binary value;
• allocating, by the computing system, users of the list of users to respective ones of the elements in the array of the elements using a hash function, wherein allocating a user of the list of users to a respective element in the array comprises toggling a current binary value stored in the respective element in the array regardless of whether or not the current binary value stored in the respective element in the array has already been toggled;
• and
• after allocating the users of the list of users to the respective ones of the elements in the array, transmitting, by the computing system, the array of elements to another computing system using the network communication interface, the transmitting to facilitate deduplication between the list of users who accessed the media and another list of users who accessed the media via bit-wise modulo 2 addition of the array of elements and another array of elements corresponding to the other list of users.

A non-transitory computer-readable medium having stored therein instructions that when executed by a computing system cause the computing system to perform a set of acts to generate a modulo 2 Bloom filter array, the set of acts comprising:

• receiving network-based impression requests indicative of accesses to digital media over the internet by respective client devices, wherein the respective client devices are operated by respective users that are registered with a database proprietor;
• based on receiving the network-based impression requests, logging media impressions in a database of the database proprietor;
• obtaining, using the logged media impressions, a list of users that accessed the media;
• generating an array of elements, each element in the array of the elements storing a same binary value;
• allocating users of the list of users to respective ones of the elements in the array of the elements using a hash function, wherein allocating a user of the list of users to a respective element in the array comprises toggling a current binary value stored in the respective element in the array regardless of whether or not the current binary value stored in the respective element in the array has already been toggled;
• and
• after allocating the users of the list of users to the respective ones of the elements in the array, transmitting the array of elements to another computing system using a network communication interface, the transmitting to facilitate deduplication between the list of users who accessed the media and another list of users who accessed the media via bit-wise modulo 2 addition of the array of elements and another array of elements corresponding to the other list of users.