Affinity profile system and method
A computer-implemented method of using affinity profiles to determine at least one audience category that is expected to consume a selected content item type, the method comprises: obtaining affinity profiles for a plurality of users of a content distribution system, wherein each affinity profile comprises at least one selected affinity category or affinity category score, and the affinity categories are selected from a stored set of affinity categories, each representing a user's affinity for a respective subject area; monitoring consumption of selected items of content of the selected type to determine which of the users consumed the items of content of the selected type; determine an audience that is expected to consume the items of content of the selected type based on the affinity profiles of the users that were determined to have consumed the selected items of content.
1 . A computer-implemented method of using affinity profiles to determine at least one audience category that is expected to consume a selected content item type, the method comprising:
for each of a plurality of user devices, monitoring user activity including identifying selected items of content selected for viewing by users of the plurality of user devices;
obtaining content metadata concerning the selected items of content, the content metadata representing at least some properties of the selected items of content;
generating or updating user records for the users, the user records comprising or representing the user activity and the content metadata associated with the user activity;
processing the user records to generate affinity profiles for the users based on the user records;
wherein each of the affinity profiles comprises at least one selected affinity category associated with an affinity category score, and the selected affinity categories are selected from a stored set of affinity categories, each representing a user's affinity for a respective subject area, and
wherein the affinity profiles do not include data representing socio-economic or demographic status of the user;
monitoring consumption of the selected items of content of the selected content item type to determine which of the users consumed the selected items of content of the selected content item type; and
determining an audience that is expected to consume items of content of the selected content item type, based on the affinity profiles of the users that were determined to have consumed the selected items of content, by:
defining a bespoke user segment comprising the users that were determined to have consumed the selected items of content of the selected content item type; and
categorizing each user into one or more of a plurality of user segments based on the affinity profile of the user, and
determining the audience that is expected to consume the items of content of the selected content item type based on the user segments to which the users in the bespoke user segment, who consumed the selected items of content, belong.
2 . The method of claim 1 , wherein the selected content item type comprises at least one of a selected genre of television programme, movie or other audio-visual content; a selected genre of computer game; a selected genre of music; a selected genre of books, music, spoken word content, other audio content, newspapers, or magazines; television programmes, movies, other audio-visual content, computer games, music, books, spoken word content, other audio content, newspapers, or magazines with at least one selected property.
3 . The method of claim 1 , wherein the selected items of content are provided to user devices of the users using a content distribution system, wherein each user device displays an electronic programme guide (EPG) or other user interface that is operable by a user to select one or more items of television or other content, and in response to the selections the distribution system distributes the selected items of television content or other content to the user devices for viewing by the users during content viewing sessions.
4 . The method of claim 1 , wherein the selected items of content are provided to user devices of the users using a content distribution system, wherein each user device displays an electronic programme guide (EPG) or other user interface that is operable by a user to select one or more items of television or other content, and in response to the selections the distribution system distributes the selected items of television content or other content to the user devices for viewing by the users during content viewing sessions, wherein the user interface is operable by a user to select one or more other items of content of types other than television content,
the obtaining metadata, the generating of the user record or the updating of the user record, and the processing of the user record to generate the affinity profile are performed using the content metadata obtained for both selected items of television content and the selected items of content of other content types, and
the other content types comprises at least one of computer games, books, music, spoken word content, other audio content, newspapers, or magazines.
5 . The method of claim 1 , wherein the determining of the audience for the selected content item type comprises providing at least one of the affinity profiles or user records of the users determined to have consumed the selected items of content of the selected content item type as inputs to a machine learning model that is trained to output an audience based on at least one of the affinity profiles or user records of the users.
6 . The method of claim 1 , wherein the obtaining of the affinity profiles is independent of, or is performed without taking into account, data representing socio-economic or demographic status of the users.
7 . The method of claim 1 , wherein at least one of a), b) or c):
a) the user record for each user does not include any data representing socio-economic or demographic status of the user;
b) the user record for each user is anonymous;
c) the obtaining of metadata, the generating or updating of user records, and the processing of the user records to generate the affinity profiles are performed by processing circuitry that does not have access to at least one of or all of data representing socio-economic or demographic status of the users or identity of the users.
8 . The method of claim 1 , wherein at least one of:
the stored set of affinity categories comprises at least 100 affinity categories or sub-categories;
the metadata concerning the selected items of content is obtained from a stored ontology that includes at least 10,000 features that can be used as meta data to represent the selected items of content.
9 . The method of claim 8 , wherein the ontology includes enriched versions of metadata obtained for the selected items of content.
10 . The method of claim 8 , wherein the processing of the user record to generate the affinity profile comprises applying a mapping process to map between the metadata in the user record and the affinity categories, the mapping process including applying weightings or confidence scores for mappings between metadata in the user record and items in the affinity categories.
11 . The method of claim 1 , wherein the user record comprises or represent user activity for different time windows during a day or week, and the method comprises generating different of the affinity profiles for the user for the different time windows.
12 . The method of claim 1 , further comprising categorizing a user into one of a plurality of segments based on the affinity profile.
13 . The method of claim 1 , wherein the affinity profile for each user comprises a set of scores, each score being for a respective one of the affinity categories.
14 . The method of claim 1 , wherein at least one of: each user is a user account, a plurality of individuals may have access to the user account or a plurality of user devices may be associated with the user account, and wherein at least one of: the affinity profile for the user account is based on selection of content by the plurality of individuals or using the plurality of user devices.
15 . The method according to claim 1 , further comprising selecting additional television content or other content to push to the user based on the affinity profile for the user.
16 . The method according to claim 1 , further comprising outputting the affinity profiles for at least one of the plurality of users or the user segments, via an API or operator interface thereby making at least one of the affinity profiles or the user segments available to a third party external to the content distribution system.
17 . A system comprising processing circuitry configured to:
for each of a plurality of user devices, monitor user activity including identifying selected items of content selected for viewing by users of the plurality of user devices;
obtain content metadata concerning the selected items of content, the content metadata representing at least some properties of the selected items of content;
generate or update user records for the users, the user records comprising or representing the user activity and the content metadata associated with the user activity;
process the user records to generate affinity profiles for the users based on the user records;
wherein each of the affinity profiles comprises at least one selected affinity category associated with an affinity category score, and the selected affinity categories are selected from a stored set of affinity categories, each representing a user's affinity for a respective subject area, and
wherein the affinity profiles do not include data representing socio-economic or demographic status of the user;
monitor consumption of the selected items of content of the selected content item type to determine which of the users consumed the selected items of content of the selected content item type; and
determine an audience category that is expected to consume items of content of the selected content item type based on the affinity profiles of the users that were determined to have consumed the selected items of content, by:
defining a bespoke user segment comprising the users that were determined to have consumed the selected items of content of the selected content item type; and
categorizing each user into one or more of a plurality of user segments based on the affinity profile of the user, and
determining the audience that is expected to consume the items of content of the selected content item type based on the user segments to which the users in the bespoke user segment, who consumed the selected items of content, belong.
18 . A non-transitory computer-readable medium that comprises computer-readable instructions that are executable to perform a method according to claim 1 .