Systems and methods for identifying users who watched a television advertisement

Patent metadata

Field	Value
Publication number	US-2016156972-A1
Application number	US-201414556317-A
Country	US
Kind code	A1
Filing date	Dec 1, 2014
Priority date	Dec 1, 2014
Publication date	Jun 2, 2016
Grant date	—

Abstract

An audience measurement service may monitor broadcasts in a region, ingesting closed captioning data, metadata, displayed text or logos, performing facial recognition on people, and/or generating audio/video fingerprints of broadcast content to create a database of content and associated keywords, along with times at which the content was broadcast. The audience measurement service may receive user search queries from a search provider and detect “spiking” queries. The audience measurement service may determine whether the spiking queries are related, contextually and temporally, to an item of content identified in the database, and infer that users generating the queries likely viewed the item of content. In some implementations, the audience measurement service may also infer that the users likely viewed other items of content (e.g. advertisements) displayed during the prior or subsequent few minutes on the same broadcast channel as the query-triggering item.

First claim

1 . A method for audience measurement, comprising:
receiving, by an audience measurement server from a broadcast monitoring system, a plurality of identifications of broadcast items of content and corresponding broadcast times of each item of content; receiving, by the audience measurement server from a search service, a log of search queries received by the search service and corresponding device identifiers of devices transmitting each search query; determining, by the audience measurement server from the received log of search queries, that a first search query has a query volume above a baseline query volume for the first search query at a first time; retrieving, by the audience measurement server from the received plurality of identifications of broadcast items of content, an identification of a first item of content broadcast at the first time, the identification corresponding to the first search query; and associating, by the audience measurement server, an identifier of a device that transmitted the first search query with the first item of content.

2 . The method of claim 1 , further comprising identifying a user of the device that transmitted the first search query as an audience member of the first item of content.

3 . The method of claim 1 , wherein each identification of a broadcast item of content comprises a caption transcript of the broadcast item of content, and wherein the identification of the first item of content corresponds to the first search query responsive to the caption transcript including the first search query.

4 . The method of claim 1 , wherein determining that the first search query has a query volume above the baseline query volume for the search query at the first time further comprises determining that the query volume at the first time exceeds an average query volume for the search query by at least a predetermined threshold.

5 . The method of claim 1 , further comprising retrieving an identification of a second item of content broadcast at a second time prior to the first time; and associating the identifier of the device that transmitted the first search query with the second item of content.

6 . The method of claim 5 , further comprising scoring the association of the identifier of the device with the first item of content with a first confidence score, and scoring the association of the identifier of the device with the second item of content with a second confidence score, the second score lower than the first score in proportion to a time difference between the second time and first time.

7 . The method of claim 6 , further comprising generating the first confidence score based on a difference between a peak query volume for the first search query and the baseline query volume for the first search query.

8 . The method of claim 6 , further comprising receiving a request for an audience measurement for the first item of content, and including the identifier of the device in the audience measurement responsive to the first confidence score being above a threshold.

9 . The method of claim 6 , further comprising receiving a request for an audience measurement for the second item of content, and excluding the identifier of the device from the audience measurement responsive to the second confidence score being below a threshold.

10 . The method of claim 1 , wherein retrieving the identification of the first item of content broadcast at the first time further comprises retrieving an entity related to the first search query in a semantic dictionary; and wherein the identification of the first item of content broadcast at the first comprises the retrieved entity.

11 . The method of claim 1 , further comprising selecting a second item of content for presentation to the device, responsive to the association of the identifier of the device with the first item of content.

12 . A system for audience measurement, comprising:
a broadcast receiver; an entity extractor connected to the broadcast receiver, configured to extract an entity associated with an item of broadcast content and record an identification of the entity, item of broadcast content, and a broadcast time to an entity log; and an audience measurement server, configured to:
receive an identification of a search query having a query volume above a baseline query volume for the search query at a first time, and an identifier of a device that transmitted the search query at the first time,
determine that the identified search query corresponds to the identified entity,
retrieve the identification of the entity and broadcast time from the entity log, responsive to the determination, and
add an association of the identifier of the device and item of broadcast content to a viewership database, responsive to the determination.

13 . The system of claim 12 , wherein the entity extractor comprises a closed captioning decoder, and wherein the audience measurement server is further configured to determine that the identified search query corresponds to the identified entity responsive to the search query being included in a closed captioning transcript of the item of broadcast content.

14 . The system of claim 12 , wherein the audience measurement server is further configured to determine that the query volume exceeds a threshold at the first time, the threshold comprising a multiple of the baseline query volume.

15 . The system of claim 12 , wherein the audience measurement server is further configured to determine that the identified search query corresponds to the identified entity responsive to the entity and search query being associated in a semantic dictionary.

16 . The system of claim 12 , wherein the audience measurement server is further configured to generate a confidence score for the association of the identifier of the device and item of broadcast content and store the generated confidence score in the viewership database.

17 . The system of claim 16 , wherein the audience measurement server is further configured to include the identifier of the device in an audience measurement for the item of broadcast content, responsive to the confidence score exceeding a threshold.

18 . The system of claim 16 , wherein the audience measurement server is further configured to add an association of the identifier of the device and a second item of broadcast content broadcast starting at a second time immediately prior to the broadcast time to the viewership database; and to generate a second confidence score for the association of the identifier of the device to the second item of broadcast, the second confidence score reduced from the confidence score for the association of the identifier of the device and item of broadcast content by an amount proportional to the difference between the second time and the broadcast time.

19 . A non-transitory computer-readable storage medium storing instructions that when executed by one or more data processors, cause the one or more data processors to perform operations including:
receiving, from a broadcast monitoring system, a plurality of identifications of broadcast items of content and corresponding broadcast times of each item of content; receiving, from a search service, a log of search queries received by the search service and corresponding identifiers of devices transmitting each search query, the search queries related to each other and having an aggregated query volume above a baseline query volume for the search queries at a first time; retrieving, from the received plurality of identi

Assignees

• Google Inc

Inventors

• Oztaskent Ant
• Volovich Yaroslav
• Trollope Ingrid Mcaulay
• Hollendoner Margaret

Classifications

• H04N21/44224 Primary

  Monitoring of user activity on external systems, e.g. Internet browsing · CPC title

• H04N21/812

  involving advertisement data (advertising per se G06Q30/02) · CPC title

• H04H60/63

  for services of sales {(data processing systems or methods specially adapted for electronic commerce G06Q30/00)} · CPC title

• H04H60/33

  Arrangements for monitoring the users' behaviour or opinions · CPC title

• G06Q30/0246 Primary

  Traffic · CPC title