US8352319B2
Active / In Force
US
⏱️ 2.4 years remaining
Generating user profiles
Assignee: Google LLC
•
Filing: 2009-03-10
•
Granted: 2013-01-08
•
Expires: 2029-03-10
Abstract
Abstract Methods, systems, and apparatus, including computer program products, for generating user identifier profiles. A user identifier profile characterizes a user based on events that occurred during past user sessions for a user (e.g., past online activities). An event is an action that occurs during a user session, such as a web page view, an advertisement click-through, and a conversion. A user identifier profile can be used, for example, to select advertisements targeted to the user. A user identifier profile includes information about inferred user interests and inferred user demographics.
Inventors
- 👤 Xuefu Wang
- 👤 Sarah Sirajuddin
- 👤 Oren E. Zamir
- 👤 Aitan Weinberg
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 18:17
CPC Classifications
G; G06; G06Q; G06Q30/00; G06Q30/02; G06Q30/0201; G06Q30/0204; G06Q30/0241; G06Q30/0251; G06Q30/0255; G06Q30/0269; G06Q30/06; G06Q30/0601
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
160 words
A computer-implemented method, comprising: identifying event data for a user identifier based on past user sessions associated with the user identifier, the event data specifying events that occurred during the past user sessions; categorizing each of the events as belonging to one or more vertical categories; for each vertical category, determining a user identifier interest weight for the user identifier based on the events associated with the vertical category; generating user identifier demographics data for the user identifier based on population demographics for each site visited during the past user sessions as specified by the event data, the population demographics for each site identifying one or more demographic features of visitors to the site; generating, by one or more computer processors, user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data; and selecting advertisements for user sessions associated with the user identifier based on the user identifier profile data.
Claim 2
Dependent Claim
160 words
A computer-implemented method, comprising: identifying event data for a user identifier based on past user sessions associated with the user identifier, the event data specifying events that occurred during the past user sessions; categorizing each of the events as belonging to one or more vertical categories; for each vertical category, determining a user identifier interest weight for the user identifier based on the events associated with the vertical category; generating user identifier demographics data for the user identifier based on population demographics for each site visited during the past user sessions as specified by the event data, the population demographics for each site identifying one or more demographic features of visitors to the site; generating, by one or more computer processors, user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data; and selecting advertisements for user sessions associated with the user identifier based on the user identifier profile data.
Claim 3
Dependent Claim
19 words
The method of claim 1 , wherein the events include page views of web pages, advertisement click-throughs, or conversions.
Claim 4
Dependent Claim
53 words
The method of claim 2 , wherein categorizing each of the events as belonging to one or more vertical categories comprises: categorizing each of the events as belonging to one or more vertical categories based on subject matter associated with the event and subject matter associated with the one or more vertical categories.
Claim 5
Dependent Claim
206 words
The method of claim 2 , wherein for each vertical category, determining a user identifier interest weight for the user identifier based on the events that belong to the vertical category comprises: determining a weight of the vertical category for the web page; for each of the page views, generating a web page weight based on the weight of the vertical category for the web page and an inverse document frequency of the viewed web page; for each of the advertisement click-throughs: identifying an advertisement of the advertisement click-through; determining a weight of the vertical category for the advertisement; identifying a landing page of the advertisement; determining a weight of the vertical category for the landing page; determining a duration with which the landing page was presented on a user device; and generating an advertisement click-through weight based on the weight of the vertical category for the landing page and the duration; for each of the conversions, generating an advertisement conversion weight based on the weight of the vertical category for the landing page and a conversion weight associated with the advertisement; and aggregating the web page weights, the weights of the vertical category for the advertisements, the advertisement click-through weights, and the advertisement conversion weights.
Claim 6
Dependent Claim
48 words
The method of claim 1 , wherein a portion of the event data are associated with a publisher, and generating the user identifier profile data for the user identifier comprises: generating the user identifier profile data only from the portion of the event data associated with the publisher.
Claim 7
Dependent Claim
101 words
The method of claim 1 , wherein the event data are based on past user sessions that occurred during a first time period, and generating user identifier profile data comprises: generating long-term user identifier profile data for the user identifier from the event data that are based on past user sessions that occurred during the first time period; and generating short-term user identifier profile data for the user identifier from the event data that are based on past user sessions that occurred during a second time period, the second time period being a most recent sub-period of the first time period.
Claim 8
Dependent Claim
56 words
The method of claim 6 , wherein selecting advertisements for user sessions associated with the user identifier based on the user identifier profile data comprises: selecting a candidate advertisement set based on the long-term user identifier profile data; and adjusting a ranking order of the candidate advertisement set based on the short-term user identifier profile data.
Claim 9
Dependent Claim
36 words
The method of claim 1 , wherein generating user identifier demographics data for the user identifier based on population demographics comprises: aggregating the population demographics for each of the sites visited during the past user sessions.
Claim 10
Dependent Claim
181 words
The method of claim 1 , wherein generating user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data comprises: determining an order of the vertical categories according to the corresponding user identifier interest weights; and determining a highest-ordered subset of the ordered vertical categories for use in generating the user identifier profile data, the highest-ordered subset based on the corresponding user identifier interest weights, a first threshold and a second threshold, wherein: the first threshold defines an upper limit for a quotient of the user identifier interest weight of a first-ordered vertical category in a subset and the user identifier interest weight of a last-ordered vertical category in the subset; the second threshold defines a lower limit for a quotient of the user identifier interest weight of the last-ordered vertical category in the subset and the user identifier interest weight of a next-ordered vertical category external to the subset; and wherein the highest-ordered subset of vertical categories are the only vertical categories used to generate the user identifier profile data.
Claim 11
Dependent Claim
75 words
The method of claim 1 , comprising: allocating profits from advertisement auctions associated with the selected advertisements based on publisher data contributions to the event data; and wherein an amount of the profits allocated to a publisher is based on: a revenue paid by an auction-winning advertiser associated with an advertisement in the selected advertisements; a publisher revenue share percentage; and a publisher data contribution factor quantifying the publisher data contribution to the event data.
Claim 12
Independent Claim
209 words
A system, comprising: one or more data processors; and a data storage apparatus encoded with instructions that when executed by the one or more data processors cause the one or more data processors to define: a user interest module configured to: identify event data for a user identifier based on past user sessions associated with the user identifier, the event data specifying events that occurred during the past user sessions; categorize each of the events as belonging to one or more vertical categories; for each vertical category, determine a user identifier interest weight for the user identifier based on the events associated with the vertical category; a user demographics module configured to: generate user identifier demographics data for the user identifier based on population demographics for each site visited during the past user sessions as specified by the event data, the population demographics for each site identifying one or more demographic features of visitors to the site; a user profile module configured to: generate user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data; and an advertisement selection module configured to: select advertisements for user sessions associated with the user identifier based on the user identifier profile data.
Claim 13
Independent Claim
209 words
A system, comprising: one or more data processors; and a data storage apparatus encoded with instructions that when executed by the one or more data processors cause the one or more data processors to define: a user interest module configured to: identify event data for a user identifier based on past user sessions associated with the user identifier, the event data specifying events that occurred during the past user sessions; categorize each of the events as belonging to one or more vertical categories; for each vertical category, determine a user identifier interest weight for the user identifier based on the events associated with the vertical category; a user demographics module configured to: generate user identifier demographics data for the user identifier based on population demographics for each site visited during the past user sessions as specified by the event data, the population demographics for each site identifying one or more demographic features of visitors to the site; a user profile module configured to: generate user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data; and an advertisement selection module configured to: select advertisements for user sessions associated with the user identifier based on the user identifier profile data.
Claim 14
Dependent Claim
19 words
The system of claim 11 , wherein the events include page views of web pages, advertisement click-throughs, or conversions.
Claim 15
Dependent Claim
46 words
The system of claim 12 , wherein the user interest module is configured to: categorize each of the events as belonging to one or more vertical categories based on subject matter associated with the event and subject matter associated with the one or more vertical categories.
Claim 16
Dependent Claim
188 words
The system of claim 12 , wherein the user interest module is configured to: determine a weight of the vertical category for the web page; for each of the page views, generate a web page weight based on the weight of the vertical category for the web page and an inverse document frequency of the viewed web page; for each of the advertisement click-throughs: identify an advertisement of the advertisement click-through; determine a weight of the vertical category for the advertisement; identify a landing page of the advertisement; determine a weight of the vertical category for the landing page; determine a duration with which the landing page was presented on a user device; and generate an advertisement click-through weight based on the weight of the vertical category for the landing page and the duration; for each of the conversions, generate an advertisement conversion weight based on the weight of the vertical category for the landing page and a conversion weight associated with the advertisement; and aggregate the web page weights, the weights of the vertical category for the advertisements, the advertisement click-through weights, and the advertisement conversion weights.
Claim 17
Dependent Claim
44 words
The system of claim 11 , wherein a portion of the event data are associated with a publisher, and the user profile module is configured to: generate the user identifier profile data only from the portion of the event data associated with the publisher.
Claim 18
Dependent Claim
104 words
The system of claim 11 , wherein the event data are based on past user sessions that occurred during a first time period, and the user profile module is configured to: generate a long-term user identifier profile data for the user identifier from the event data that are based on past user sessions that occurred during the first time period; and generate a short-term user identifier profile data for the user identifier from the event data that are based on past user sessions that occurred during a second time period, the second time period being a most recent sub-period of the first time period.
Claim 19
Dependent Claim
45 words
The system of claim 16 , wherein the advertisement selection module is configured to: select a candidate advertisement set based on the long-term user identifier profile data; and adjust a ranking order of the candidate advertisement set based on the short-term user identifier profile data.
Claim 20
Dependent Claim
185 words
A computer program product, encoded on one or more memory devices, including instructions that when executed by one or more data processing apparatuses cause the one or more data processing apparatuses to perform operations comprising: identifying event data for a user identifier based on past user sessions associated with the user identifier, the event data specifying events that occurred during the past user sessions; categorizing each of the events as belonging to one or more vertical categories; for each vertical category, determining a user identifier interest weight for the user identifier based on the events associated with the vertical category; generating user identifier demographics data for the user identifier based on population demographics for each site visited during the past user sessions as specified by the event data, the population demographics for each site identifying one or more demographic features of visitors to the site; generating user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data; and selecting advertisements for user sessions associated with the user identifier based on the user identifier profile data.
Claim 21
Dependent Claim
185 words
A computer program product, encoded on one or more memory devices, including instructions that when executed by one or more data processing apparatuses cause the one or more data processing apparatuses to perform operations comprising: identifying event data for a user identifier based on past user sessions associated with the user identifier, the event data specifying events that occurred during the past user sessions; categorizing each of the events as belonging to one or more vertical categories; for each vertical category, determining a user identifier interest weight for the user identifier based on the events associated with the vertical category; generating user identifier demographics data for the user identifier based on population demographics for each site visited during the past user sessions as specified by the event data, the population demographics for each site identifying one or more demographic features of visitors to the site; generating user identifier profile data for the user identifier based on the user identifier interest weights and the user identifier demographics data; and selecting advertisements for user sessions associated with the user identifier based on the user identifier profile data.
Claim 22
Dependent Claim
21 words
The computer program product of claim 18 , wherein the events include page views of web pages, advertisement click-throughs, or conversions.
Claim 23
Dependent Claim
55 words
The computer program product of claim 19 , wherein categorizing each of the events as belonging to one or more vertical categories comprises: categorizing each of the events as belonging to one or more vertical categories based on subject matter associated with the event and subject matter associated with the one or more vertical categories.
References Cited (Backward Citations)
US5848396A
Cited
US6421675B1
Cited
US6839680B1
Cited
US20050288954A1
Cited
US20020111994A1
Cited
US20030074252A1
Cited
US7330828B2
Cited
US20040024777A1
Cited
US20070011039A1
Cited
US20050021397A1
Cited
US20050222989A1
Cited
WO2005065229A2
Cited
US20050131762A1
Cited
US20070061195A1
Cited
US7734632B2
Cited
US7904448B2
Cited
US20110161331A1
Cited
US20070239680A1
Cited
US20080126176A1
Cited
US20080103897A1
Cited
US20080154717A1
Cited
US20080209350A1
Cited
US20080306830A1
Cited
US20090216616A1
Cited
US20100125505A1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2016-01-08 | 2016-07-09 | 2017-01-08 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2020-01-08 | 2020-07-09 | 2021-01-08 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2024-01-08 | 2024-07-09 | 2025-01-08 | $7700.00 | Window Closed / Lapsed |