Mobility enhanced advertising on internet protocol television

Patent metadata

Field	Value
Publication number	US-9584836-B2
Application number	US-201414476268-A
Country	US
Kind code	B2
Filing date	Sep 3, 2014
Priority date	Sep 3, 2014
Publication date	Feb 28, 2017
Grant date	Feb 28, 2017

Abstract

Enhanced personalized advertisements may be provided through media such as IPTV, for example, by analyzing data such as subscribers' mobility data (calling and movement data), television (TV) watching history, online browsing data (e.g., Internet, web site browsing), and subscribers' historical purchasing transactions. With the analysis, subscribers' contexts, any information that reflects subscribers' interests and activities, and intents, tendency to buy certain products, items, services, and/or travel to some locations may be inferred.

First claim

We claim:

1. A method of selecting advertisements to play on internet protocol television, comprising:
determining individual context and intent for a plurality of members of a household having internet protocol television subscription based on at least mobility data received from one or more mobile devices associated with the plurality of members of a household;
determining a program played on the internet protocol television;
predicting, by a processor, which individual in the household is watching the program based on current mobility data associated with the members of the household and user profiles associated with the members of the household, the predicting performed using a disambiguation predictive model built based on mobility data, calling data associated with the members of the household and television watching log associated with the household, the current mobility data determined based at least on information received from said one or more mobile devices associated with the plurality of members of a household, the predictive model built based on one or more of a machine learning technique and a decision tree technique; and
selecting, by the processor, an advertisement for delivery via the internet protocol television from a database of advertisements that matches an interest of the individual determined to be watching the program, the interest of the individual determined based on the individual context and intent associated with the individual,
the predicting comprising determining geographic location by longitude and latitude position of the household based on a subscription address of the household, and based on the mobility data comprising at least communication data between candidate members and an account owner associated with the subscription address, and geographic positions of the candidate members, and co-location pattern of the candidate members and the account owner, determining the members of the household, wherein the individual in the household predicted to be watching the program is determined among the members of the household.

2. The method of claim 1 , further comprising:
based on the predicting, determining whether multiple members in the household are watching the program, and performing the selecting an advertisement for delivery via the internet protocol television from a database of advertisements that match an interest of the individual determined to be watching the program based on the individual context and intent associated with the individual, responsive to determining that only one member of the household is watching the program.

3. The method of claim 2 , further comprising:
determining group context and intent associated with the household, wherein responsive to determining that multiple members are watching the program, selecting second advertisement for delivery that match an interest of the members of the household as a group based on the group context and intent.

4. The method of claim 1 , wherein the user profiles comprise an individual user's browsing profile disambiguated based on the user's mobility data, the user's calling data and the television watching log, the user profiles further comprising user's mobility profile, user's calling profile, and user's transaction profile generated based on user's historical transaction data.

5. The method of claim 4 , wherein the individual context and intent are determined for a member of the household by aggregating data associated with the member's categories of interest and locations from the user's mobility data and the user's calling data associated with the member of the household, and predicting the member's intent based on an intent predictive model.

6. The method of claim 5 , wherein the intent predictive model is trained based on a plurality of features in the user profiles and purchase transaction data, the intent predictive model predicting the member's intent to purchase an item given a set of features associated with the member.

7. The method of claim 6 , wherein a group context and intent are determined for the members of the household as a group based on a group intent predictive model, the group intent predictive model built based on a plurality of group features and purchase transaction data associated with a plurality of households.

8. A computer readable storage medium storing a program of instructions executable by a machine to perform a method of selecting advertisements to play on internet protocol television, comprising, the method comprising:
determining individual context and intent for a plurality of members of a household having internet protocol television subscription based on at least mobility data received from one or more mobile devices associated with the plurality of members of a household;
determining a program played on the internet protocol television;
predicting which individual in the household is watching the program based on current mobility data associated with the members of the household and user profiles associated with the members of the household, the predicting performed using a disambiguation predictive model built based on at least mobility data, calling data associated with the members of the household and television watching log associated with the household, the current mobility data determined based at least on information received from one or more mobile devices associated with the members of the household, the predictive model built based on one or more of a machine learning technique and a decision tree technique; and
selecting an advertisement for delivery via the internet protocol television from a database of advertisements that matches an interest of the individual determined to be watching the program, the interest of the individual determined based on the individual context and intent associated with the individual,
the predicting comprising determining geographic location by longitude and latitude position of the household based on a subscription address of the household, and based on the mobility data comprising at least communication data between candidate members and an account owner associated with the subscription address, and geographic positions of the candidate members and co-location pattern of the candidate members and the account owner, determining the members of the household, wherein the individual in the household predicted to be watching the program is determined among the members of the household.

9. The computer storage medium of claim 8 , further comprising:
based on the predicting, determining whether multiple members in the household are watching the program, and performing the selecting an advertisement for delivery via the internet protocol television from a database of advertisements that match an interest of the individual determined to be watching the program based on the individual context and intent associated with the individual, responsive to determining that only one member of the household is watching the program.

10. The computer storage medium of claim 9 , further comprising:
determining group context and intent associated with the household, wherein responsive to determining that multiple members are watching the program, selecting second advertisement for delivery that match an interest of the members of the household as a group based on the group context and intent.

11. The computer storage medium of claim 8 , wherein the user profiles comprise an individual user's browsing profile disambiguated based on the user's mobility data, the user's calling data and the television watching log, the user profiles further comprising user's mobility profile, user's calling profile, and user's transaction profile gene

Assignees

• IBM

Inventors

• Fei Hongliang
• Lei Kin H
• Li Ming
• Sahu Sambit

Classifications

• H04N21/23424

  involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement · CPC title

• 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

• H04N21/2668

  Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles {(information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063)} · CPC title

• H04N21/64322

  IP · CPC title

• H04N21/23109 Primary

  by placing content in organized collections, e.g. EPG data repository (details of retrieval of video data and associated meta data in video databases G06F16/739) · CPC title