Server and operating method thereof

Patent metadata

Field	Value
Publication number	US-11080325-B2
Application number	US-201916268924-A
Country	US
Kind code	B2
Filing date	Feb 6, 2019
Priority date	Feb 14, 2018
Publication date	Aug 3, 2021
Grant date	Aug 3, 2021

Abstract

A server may include a communicator for receiving an image from a subject terminal from among a plurality of terminals; and a controller for identifying a type of a content included in the received image, and for controlling two or more different image filters using a recommended algorithm regarding an image filter to be applied to the image, wherein the controller may select a first image filter predicted to have a highest probability to be selected by a user of the subject terminal and a second image filter predicted to have a second highest probability to be selected by the user of the subject terminal using the recommended algorithm, and the communicator may transmit information on the first image filter and information on the second image filter to the subject terminal.

First claim

What is claimed is:

1. An operating method of a server, the method comprising:
receiving a first image from a subject terminal among a plurality of terminals;
identifying a type of a first content included in the first image;
obtaining a recommended algorithm regarding an image filter applicable to the first image;
selecting two or more different image filters corresponding to the type of the first content using the recommended algorithm; and
transmitting information on the selected two or more different image filters to the subject terminal,
wherein the obtaining comprises obtaining:
image filter history information, on a type of an image filter that has been previously selected, by the subject terminal, to be applied to a second image including the first content and
image filter history information, on a type of an image filter that has been previously selected, by each of the plurality of terminals except the subject terminal, to be applied to a third image including the first content, and
wherein the selecting comprises:
obtaining image filter history information of a first terminal, the image filter history information of the first terminal being predicted to be preferred by a user of the subject terminal, based on a result of comparing the image filter history information of the subject terminal and the image filter history information of the plurality of terminals, respectively; and
selecting two or more different image filters based on a plurality of image filters included in the image filter history information of the first terminal.

2. A server comprising:
a communicator for receiving a first image from a subject terminal from among a plurality of terminals; and
a controller for identifying a type of a first content included in the first image, and for selecting two or more different image filters using a recommended algorithm regarding an image filter to be applied to the first image,
wherein the controller selects a first image filter predicted to have a highest probability to be selected by a user of the subject terminal and a second image filter predicted to have a second highest probability to be selected by the user of the subject terminal using the recommended algorithm, and
the communicator transmits information on the first image filter and information on the second image filter to the subject terminal,
wherein the controller obtains:
image filter history information, on a type of an image filter that has been previously selected, by the subject terminal, to be applied to a second image including the first content and
image filter history information, on a type of an image filter that has been previously selected, by each of the plurality of terminals except the subject terminal, to be applied to a third image including the first content,
wherein the controller obtains image filter history information of a first terminal, the image filter history information of the first terminal being predicted to be preferred by the user of the subject terminal, based on a result of comparing the image filter history information of the subject terminal and the image filter history information of the plurality of terminals, respectively; and selects two or more different image filters based on a plurality of image filters included in the image filter history information of the first terminal.

3. The operating method according to claim 1 , further comprising:
obtaining a learning model for the identifying the type of the first content included in the first image, the learning model being learned regarding a correlation between image data of numerous photographs and types of contents included in the numerous photographs, prior to the identifying the type of the first content included in the first image.

4. The operating method according to claim 1 , further comprising:
receiving, from the subject terminal, user information that includes at least one of hobby information, gender information, age information, and information on a type of a preferred image filter of the user of the subject terminal.

5. The operating method according to claim 1 , wherein the obtaining the image filter history information of the first terminal comprises:
obtaining the image filter history information of the first terminal from among the plurality of terminals except the subject terminal, based on information on image filters overlapping between the image filter history information of the subject terminal and the image filter history information of the plurality of terminals, and
wherein the selecting the two or more different image filters comprises: selecting the two or more different image filters based on image filters included in the image filter history information of the first terminal and not included in the image filter history information of the subject terminal.

6. The operating method according to claim 1 , wherein the identifying the type of the first content included in the first image comprises detecting whether the first content comprises at least one of a person, certain object, certain animal, certain scenery, certain pattern and certain color.

7. The operating method according to claim 1 , wherein the selecting the two or more different image filters corresponding to the type of the first content using the recommended algorithm comprises selecting a first image filter predicted to have a highest probability to be selected by the user of the subject terminal and a second image filter predicted to have a second highest probability to be selected by the user of the subject terminal using the recommended algorithm.

8. A non-transitory computer-readable record medium where a program for executing the operating method according to claim 1 is recorded.

9. The server according to claim 2 , wherein the controller obtains the image filter history information of the first terminal from among the plurality of terminals except the subject terminal, based on information on image filters overlapping between the image filter history information of the subject terminal and the image filter history information of the plurality of terminals,
wherein the controller selects the two or more different image filters based on image filters included in the image filter history information of the first terminal and not included in the image filter history information of the subject terminal.

10. The server according to claim 2 , wherein the communicator receives user information that includes at least one of hobby information, gender information, age information, and information on a type of a preferred image filter of the user of the subject terminal.

11. The operating method according to claim 4 , wherein the obtaining the recommended algorithm regarding the image filter to be applied to the first image further comprises:
receiving the user information and a fourth image from each of at least one terminal of the plurality of terminals except the subject terminal;
identifying a type of a content included in the fourth image received from each of the at least one terminal;
receiving, from each of the at least one terminal, information on a type of an image filter selected to be applied to the fourth image received from each of the at least one terminal; and
obtaining a learning model using the user information, information on the identified type of the content included in the fourth image, and the received information on the type of the image filter selected to be applied to the fourth image.

12. The server according to claim 10 , wherein the communicator receives, from each of at least one terminal of the plurality of terminals except the subject terminal, the user informati

Assignees

• Hyperconnect Inc

Inventors

• Ahn Sangil
• Shin Beomjun
• Oh Minsik
• Choi Eunhee

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06T5/60 Primary

  using machine learning, e.g. neural networks · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06N20/00

  Machine learning · CPC title