Granted Patent B2

US 9,848,239 · App. 14/628,106 · Granted Dec 19, 2017

Abstract

Claims (58)

1. A computer-implemented method comprising:

accessing tuning data representing television tuning events associated with particular households, each tuning event in the tuning data including an identification of a particular television program associated with the tuning event and a household minutes value representing a number of minutes the particular television program was played at a particular household in association with the tuning event;

accessing panelist viewing data representing television viewing events associated with panelists, each viewing event in the viewing data including an identification of a particular television program associated with the viewing event and a panelist minutes value representing a number of minutes a panelist was exposed to the particular television program during the viewing event, each panelist associated with panelist information; and

for at least one tuning event represented by the tuning data:

accessing household member data representing member information on individual members of a particular household associated with the tuning event, wherein the individual members are persons associated with the particular household;

for at least one individual member of the particular household for the tuning event:

identifying matching panelist viewing data for the individual member, the matching panelist viewing data including at least a portion of the panelist viewing data associated with members of panelist households whose panelist information matches at least a portion of the member information of the individual member;

determining a member minutes value associated with the individual member of the particular household for the tuning event, the member minutes value based at least in part on the matching panelist viewing data;

determining a fractional viewership value for the individual member of the particular household associated with the tuning event, the fractional viewership value representing a probability that the individual member watched the television program associated with the tuning event, the fractional viewership value based at least in part on the matching panelist viewing data.

2. The method of claim 1 , further comprising:

before determining the member minutes values and fractional viewership values, applying a weighting factor to the panelist viewing data based on a distribution of demographic information associated with the members of panelist households.

3. The method of claim 1 , wherein the panelist viewing data is based on monitoring viewing behavior of the members of panelist households.

4. The method of claim 1 , wherein determining fractional viewership values for each individual member of the particular household for the tuning event comprises, for at least one of the individual members:

determining that a particular episode of a television program is associated with the tuning event; and

determining a fraction of members of panelist households that watched the particular episode that have panelist information matching the member information for the individual member.

5. The method of claim 1 , wherein determining fractional viewership values for each individual member of the particular household for the tuning event comprises, for at least one of the individual members:

determining that a particular television network is associated with the tuning event; and

determining a fraction of members of panelist households that watched the particular television network that have panelist information matching the member information for the individual member.

6. The method of claim 1 , wherein determining fractional viewership values for each individual member of the particular household for the tuning event comprises, for at least one of the individual members:

determining that a particular television entity is associated with the tuning event; and

determining a fraction of members of panelist household that watched the particular television entity that have panelist information matching the member information for the individual member.

7. The method of claim 1 , wherein:

the tuning data includes a time, date, and television network for each tuning event; and

determining fractional viewership values for the individual members of the particular household comprises, for at least one of the individual members, determining a fraction of panelist members of other households with panelist information matching the member information for the individual member that watch the television network at the time and date associated with the tuning event.

8. The method of claim 1 , wherein the member information includes one or more demographic groups to which the individual member belongs, and the panelist information includes one or more demographic groups to which the panelist member belongs.

9. The method of claim 1 , wherein the member information includes a geographic area for the individual member, and the panelist information includes a geographic area for the panelist member.

10. The method of claim 1 , wherein the household member data representing member information on the individual members of the particular household associated with the tuning event includes information provided by at least one individual member of the particular household.

11. A computer-implemented method comprising:

accessing tuning data representing television tuning events associated with particular households, each tuning event in the tuning data including an identification of a television program played in association with the tuning event, and a household minutes value representing a number of minutes the television program was played at a particular household in association with the tuning event;

accessing panelist viewing data representing television viewing events associated with panelists, each viewing event in the viewing data including an identification of a television program associated with the viewing event, and a panelist minutes value representing a number of minutes a particular panelist was exposed to the television program during the viewing event, each panelist associated with panelist information;

identifying group subsets within the tuning data, each group subset including tuning data having matching values for a group criteria including attributes included in the tuning data and the panelist viewing data, wherein the group criteria includes at least one attribute of households associated with tuning data included in the group subset;

identifying a particular television program for which to calculate unique viewers and person-level minutes; and

for at least one particular group subset from the identified group subsets within the tuning data:

identifying matching panelist viewing data for the particular group subset, the matching panelist viewing data including panelist viewing data having matching values for the group criteria associated with the particular group subset;

calculating a unique viewers value for the particular group subset based on the matching panelist viewing data, wherein the unique viewers value represents an estimated number of individual members of households associated with the tuning data included in the group subset that watched the particular television program, and wherein the individual members are persons associated with the particular household;

calculating a person-level minutes value for the group subset based on the matching panelist viewing data, wherein the person-level minutes value represents an estimated number of minutes individual members of households associated with the tuning data included in the group subset watched the particular television program.

12. The method of claim 11 , wherein the panelist viewing data includes observed viewing data obtained through monitoring viewing behavior of a plurality of panelists, and modeled viewing data obtained by applying statistical projections to household-level data.

13. The method of claim 11 , wherein the group criteria includes at least one of geographic area, or number of set-top-boxes.

14. The method of claim 11 , wherein calculating the unique viewers value includes determining a members per household number for the matching panelist viewing data, wherein the unique viewers value for the particular group subset is based at least in part on the members per household number.

15. The method of claim 11 , wherein calculating the person-level minutes value for the group subset includes determining a co-viewing factor for the matching panelist viewing data representing a ratio of household-level viewing minutes to person-level viewing minutes for the group subset, wherein the person-level minutes value for the group subset is based at least in part on the co-viewing factor.

16. The method of claim 11 , wherein calculating the unique viewers value includes calculating a set of demographic unique viewers values, wherein each demographic unique viewers values is associated with a particular one of a plurality of demographic groups and represents an estimated number of individual members in the particular demographic group from households associated with the tuning data included in the group subset that watched the particular television program.

17. The method of claim 16 , wherein the plurality of demographic groups are associated with a demographic criteria including at least one of age, gender, race, or income.

18. The method of claim 11 , wherein calculating the person-level minutes value includes calculating a set of demographic person-level minutes values, wherein each demographic person-level minutes value is associated with a particular one of a plurality of demographic groups and represents an estimated number of minutes individual members in the particular demographic group from households associated with the tuning data included in the group subset watched the particular television program.

19. A computer-implemented method comprising:

accessing tuning data representing tuning events associated with particular households, each tuning event in the tuning data including an identification of a particular television program watched during the tuning event, and a household minutes value representing a number of minutes the particular television program was played at a particular household in association with the tuning event, the tuning data divided into rostered tuning data for particular households associated with household member data and non-rostered tuning data for particular households not associated with household member data, wherein the household member data includes information about individual members of the particular household, and wherein the individual members are persons associated with the particular household;

accessing panelist viewing data representing television viewing events associated with panelists, each viewing event in the viewing data including an identification of a particular television program watched during the viewing event, and a panelist minutes value representing a number of minutes a particular panelist member was exposed to the particular television program during the viewing event, each panelist associated with panelist information;

generating person-level viewing data for tuning events represented by the rostered tuning data, the person-level viewing data based at least in part on the panelist viewing data and including second viewing events, each second viewing event including a member minutes value and a fractional viewership value associated with an individual member of a household associated with household member data; and

calculating unique viewers values and person-level minutes values for the non-rostered tuning data based on the panelist viewing data and the person-level viewing data.

20. The method of claim 19 , wherein generating person-level viewing data includes:

for at least one tuning event represented by the rostered tuning data:

determining a member minutes value associated with each individual member of the particular household for the tuning event, the member minutes value based at least in part on panelist minutes values from a portion of the panelist viewing data associated with panelists associated with panelist information matching at least a portion of the member information of the individual member;

determining a fractional viewership value for each individual member of the particular household representing a probability that the individual member watched the tuning event, the fractional viewership value based at least in part on the portion of the panelist viewing data associated with panelists associated with panelist information matching at least a portion of the member information of the individual member.

21. The method of claim 19 , wherein calculating unique viewers values and person-level minutes values for the non-rostered tuning data includes:

identifying a particular television program for which to calculate unique viewers and person-level minutes;

for at least one particular group subset in a plurality of group subsets of the non-rostered tuning data defined by group criteria:

identifying matching person-level viewing data including panelist and person-level viewing data that matches values for the group criteria associated with the particular group subset;

calculating a unique viewers value for the group subset based on the matching person-level viewing data, wherein the unique viewers value represents an estimated number of individual members of households associated with the non-rostered tuning data included in the group subset that watched the particular television program;

calculating a person-level minutes value for the group subset based on the matching person-level viewing data, wherein the person-level minutes value represents an estimated number of minutes individual members of households associated with the non-rostered tuning data included in the group subset watched the particular television program.

Assignments (8)