EXTRACTION DEVICE, EXTRACTION METHOD, AND NON-TRANSITORY COMPUTER READABLE STORAGE MEDIUM

• US 20160042403A1
• Filed: 08/03/2015
• Published: 02/11/2016
• Est. Priority Date: 08/08/2014
• Status: Active Grant

• Current Assignee: Yahoo Japan Corporation (A Holdings Corp.)
• Original Assignee: Yahoo Japan Corporation (A Holdings Corp.)
• Inventors: TASHIRO, Takashi, OKURA, Shumpei
• Granted Patent: US 11,455,660 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

The extraction device according to the present application includes an acquisition unit and an extraction unit. The acquisition unit acquires behavior histories of users being candidates to whom content is to be distributed. The extraction unit extracts target users expected to perform specified behavior, based on a behavior history designated by a content provider, of the behavior histories acquired by the acquisition unit. For example, the extraction unit uses a model for determining the degree of similarity between a user performing the specified behavior and a target user expected to perform specified behavior based on the behavior history designated by the content provider in order to extract the target users.

Claims

1. An extraction device comprising:

an acquisition unit configured to acquire behavior histories of users being candidates to whom content is to be distributed; and

an extraction unit configured to extract target users expected to perform specified behavior, based on a behavior history designated by a content provider, from the behavior histories acquired by the acquisition unit.

2. The extraction device according to claim 1, further comprising a generation unit configured to generate a model for determining a degree of similarity between users performing the specified behavior and target users expected to perform specified behavior, based on the behavior history designated by the content provider,

wherein the extraction unit extracts the target users expected to perform specified behavior, using a model generated by the generation unit.

3. The extraction device according to claim 2, wherein the acquisition unit acquires behavior histories of the users performing the specified behavior, and

the generation unit generates the model based on behavior histories for a predetermined period before the specified behavior is performed, attribute information of the users performing the specified behavior, and the behavior history designated by the provider from the behavior histories of the users performing the specified behavior.

4. The extraction device according to claim 2, further comprising a providing unit configured to provide a user interface configured to receive the designation of the behavior history from the provider, as explanatory behavior accounting for expectation of the specified behavior of the user,

wherein the generation unit generates the model based on the received behavior history designated by the provider through the user interface provided by the providing unit.

5. The extraction device according to claim 4, wherein the providing unit provides the user interface configured to receive the designation of a plurality of behavior histories from the provider, and

the generation unit generates the model based on a combination of the plurality of received behavior histories designated by the provider.

6. The extraction device according to claim 2, wherein the acquisition unit acquires behavior histories of the target users after extraction, after the target users are extracted by the extraction unit, and

the generation unit determines whether the specified behavior is included in the behavior histories of the target users after extraction, acquired by the acquisition unit, to evaluate the behavior history designated by the provider, and generates a learned model based on an evaluation result.

7. The extraction device according to claim 6, wherein, when the behavior histories of the target users after extraction, acquired by the acquisition unit, include the specified behavior, the generation unit generates a model by weighting the designated behavior history for the model used for extraction of the target users, relative to the designated behavior history for the model used for extraction of the users not having the specified behavior in the behavior histories after extraction.

8. An extraction method performed by a computer comprising:

acquiring behavior histories of users being candidates to whom content is to be distributed; and

extracting target users expected to perform specified behavior, based on a behavior history designated by the content provider, from the behavior histories acquired in the acquiring.

9. A non-transitory computer readable storage medium having stored therein an extraction program, the extraction program causing a computer to perform:

acquiring behavior histories of users being candidates to whom content is to be distributed; and

extracting target users expected to perform specified behavior, based on a behavior history designated by the content provider, from the behavior histories acquired in the acquiring.