NETWORK BASED CONTENT TRANSMISSION BASED ON CLIENT DEVICE PARAMETERS

• US 20170097982A1
• Filed: 12/14/2016
• Published: 04/06/2017
• Est. Priority Date: 08/29/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhang, Xiaonan, Ponnekanti, Shankar, Zamir, Oren Eli, Liu, Ting
• Granted Patent: US 10,789,276 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/303 Terminal profiles
• CPC Class Codes: H04L 67/53 using third party service providers

Abstract

Systems and methods for predicting content performance with interest data include receiving a content selection request that includes a client identifier. One or more topical interest categories associated with the client identifier may be used as inputs to a prediction model to predict the likelihood of an online action occurring as a result of third-party content being selected. The predicted likelihood may be used to select third-party content.

Claims

1-20. -20. (canceled)

21. A system for network based content transmission based on client device parameters, comprising:

a data processing system having one or more processors to;

receive, from a client device, a request for content for insertion into a content source, the request including a device identifier corresponding to the client device, keywords of the content source associated with a first category identifier;

identify, from a device profile database, input values for a prediction model, the input values including;

a second category identifier associated with the device identifier, the second category identifier extracted from keywords of a previous content source accessed by the client device,

an interaction frequency metric associated with the device identifier, and

a time length associated with the second category identifier for the device identifier;

select a content item based on the first category identifier, the second category identifier, and a third category identifier associated with the content item;

estimate a predicted likelihood of interaction for the content item based on the prediction model and using the input values of the second category identifier, the interaction frequency metric, and the time length associated with the second category for the device identifier;

select the content item based on the predicted likelihood of interaction estimated based on the prediction model; and

provide, to the client device, the content item for presentation on the content source.

22. The system of claim 21, wherein the data processing system estimates the predicted likelihood of interaction for the content item based on the prediction model, the prediction model using the input values of the second category identifier, the interaction frequency metric, and the time length associated with the second category as a set of coefficients in the prediction model.

23. The system of claim 21, comprising the data processing system configured to:

perform an image recognition to the content source to determine the first category identifier; and

perform at least one of the image recognition and a text recognition to the content item to determine the third category identifier.

24. The system of claim 21, comprising the data processing system configured to:

parse the content source to identify a keyword of the content source;

match the keyword to a keyword set, the keyword set associated with one category identifier; and

identify the first category identifier based on the match of the keyword to the keyword set.

25. The system of claim 21, comprising the data processing system configured to:

select a plurality of candidate content items based on a match between the first category identifier, the second category identifier, and the third category identifier, the plurality of content items numbering a predetermined limit; and

select, from the plurality of candidate content items, the content item based on the predicted likelihood of interaction estimated based on the prediction model.

26. The system of claim 21, comprising the data processing system configured to:

receive, from the device, an indication of an interaction by the client device with the content item on the content source; and

update the prediction model based on the receipt of the indication of the interaction by the client device.

27. The system of claim 21, comprising the data processing system configured to:

receive, from the device, an indication of an interaction by the client device with the content item on the content source; and

update a set of coefficients for the prediction model, the set of weights corresponding to the input values of the second category identifier, the interaction frequency metric, and the time length associated with the second category.

28. The system of claim 21, comprising the data processing system configured to:

determine a frequency for a keyword on the content source, the frequency indicating a number of occurrence of the keyword on the content source; and

identify the frequency for the keyword as one of the input values for the prediction model to estimate the predicted likelihood of interaction for the content item.

29. The system of claim 21, wherein the predicted likelihood of interaction includes at least one of a predicted conversion rate and a predicted click-through rate.

30. The system of claim 21, wherein the predicted likelihood of interest for the content item is determined based on at least one of a logistic regression technique, a linear regression technique, an artificial neural network technique, and a Bayesian classifier technique.

31. A method of estimating likelihood of interaction with content items on webpages in a computer networked environment, comprising:

receiving, by a data processing system having one or more processors, from a client device, a request for content for insertion into a content source, the request including a device identifier corresponding to the client device, keywords of the content source associated with a first category identifier;

identifying, by the data processing system, from a device profile database, input values for a prediction model, the input values including;

a second category identifier associated with the device identifier, the second category identifier extracted from keywords of a previous content source accessed by the client device,

an interaction frequency metric associated with the device identifier, and

a time length associated with the second category identifier for the device identifier;

selecting, by the data processing system, a content item based on the first category identifier, the second category identifier, and a third category identifier associated with the content item;

estimating, by the data processing system, a predicted likelihood of interaction for the content item based on the prediction model, the prediction model using the input values of the second category identifier, the interaction frequency metric, and the time length associated with the second category for the device identifier;

selecting, by the data processing system, the content item based on the predicted likelihood of interaction estimated based on the prediction model; and

providing, by the data processing system, to the client device, the content item for presentation on the content source.

32. The method of claim 31, comprising:

estimating, by the data processing system, the predicted likelihood of interaction for the content item based on the prediction model, the prediction model using the input values of the second category identifier, the interaction frequency metric, and the time length associated with the second category as a set of coefficients in the prediction model.

33. The method of claim 31, comprising:

performing, by the data processing system, an image recognition to the content source to determine the first category identifier; and

performing, by the data processing system, at least one of the image recognition and a text recognition to the content item to determine the third category identifier.

34. The method of claim 31, comprising:

parsing, by the data processing system, the content source to identify a keyword of the content source;

matching, by the data processing system, the keyword to a keyword set, the keyword set associated with one category identifier; and

identifying, by the data processing system, the first category identifier based on the match of the keyword to the keyword set.

35. The method of claim 31, comprising:

selecting, by the data processing system, a plurality of candidate content items based on a match between the first category identifier, the second category identifier, and the third category identifier, the plurality of content items numbering a predetermined limit; and

selecting, by the data processing system, from the plurality of candidate content items, the content item based on the predicted likelihood of interaction estimated based on the prediction model.

36. The method of claim 31, comprising:

receiving, by the data processing system, from the device, an indication of an interaction by the client device with the content item on the content source; and

updating, by the data processing system, the prediction model based on the receipt of the indication of the interaction by the client device.

37. The method of claim 31, comprising:

receiving, by the data processing system, from the device, an indication of an interaction by the client device with the content item on the content source; and

updating, by the data processing system, a set of coefficients for the prediction model, the set of weights corresponding to the input values of the second category identifier, the interaction frequency metric, and the time length associated with the second category.

38. The method of claim 31, comprising:

determining, by the data processing system, a frequency for a keyword on the content source, the frequency indicating a number of occurrence of the keyword on the content source; and

identifying, by the data processing system, the frequency for the keyword as one of the input values for the prediction model for estimating the predicted likelihood of interaction for the content item.

39. The method of claim 31, comprising:

estimating, by the data processing system, the predicted likelihood of interaction for the content item, the predicted likelihood of interaction including at least one of a predicted conversion rate and a predicted click-through rate.

40. The method of claim 31, comprising:

estimating, by the data processing system, the predicted likelihood of interaction for the content item based on the prediction model, the prediction model including at least one of a logistic regression, a linear regression, an artificial neural network technique, and a Bayesian classifier.