KR101817342B1 - Method for making and selling a photo imoticon - Google Patents

Abstract

The present invention relates to a method for generating and selling a photo emoticon, and more particularly, to a method for generating and selling a photo emoticon, which includes the steps of: tagging a photo after automatically extracting a tag expressing a representative emotion of the photo based on contents written in a user comment if a user post composed of the photo and the user comment is registered; determining tag reliability for the photo based on response results of a plurality of interested parties after inquiring a matching degree between the photo and the tag of the plurality of interested parties; and registering an emoticon in an emoticon sale market after generating the photo emoticon corresponding to the tag and the photo if the tag reliability for the photo is equal to or greater than a predetermined value. Accordingly, the present invention can further enhance the interest of a user by using the emotion.

Description

{METHOD FOR MAKING AND SELLING A PHOTO IMOTICON}

The present invention relates to a method and apparatus for generating and selling photographic emoticons, and more particularly, to a method and system for automatically generating a photographic emoticon by automatically extracting a tag indicating representative emotion of the photographic image on the basis of content described in the user comment Tagging the photo; Determining a tag reliability for the photograph based on a response result of the plurality of persons after inquiring a plurality of parties about the degree of correspondence between the photograph and the tag; And registering the photo and the photo emoticons corresponding to the tag in the emoticon sale market when the tag reliability for the photo is equal to or greater than a predetermined value.

With the recent development of communication technologies, users of communication devices are increasingly using community services by linking with unspecified number of users online. In order to meet the desire of users who want to perform their emotions or expressions more clearly and positively in the community service, community service providers use emotional expression images such as emoticons, It provides a means to communicate more clearly.

In the conventional community service, any one of the emoticons provided as a basis in text creation is selected and used. However, these emoticons can not realistically convey the emotional state of the user, and the user can not arbitrarily change the image, There are problems that it is difficult to satisfy.

As a prior art document for meeting such needs, Korean Unexamined Patent Application Publication No. 2014-0010525 (Apr. 21, 2014) is related to an emoticon service system and a method for providing emoticon service thereof, Receiving facial feature points from the received facial image and then changing the facial features of the facial image similar to the detected facial feature points, And an emoticon service device for providing at least one image effect to the terminal, generating a plurality of caricature samples, and providing the generated caricature samples to the terminal.

In addition, U.S. Published Patent Application No. 2012/0130717 A1 (May 24, 2012) is intended to provide real-time assimilation for personalized cartoon avatars, in which a motion set of one or more upper parts based on voice and motion data And training at least one or more animated models to provide at least one animated model. The process links one or more predefined statements representing an emotional state with one or more animated models. After creating the model, the process receives the speech in real time and then identifies the emotional state expressed based on one or more predefined phrases that matched the context to the real-time speech input. And the process generates an animated motion sequence of one or more upper body portions by applying one or more animated models in response to the real-time voice input.

The present invention relates to a method of selling representative emotions corresponding to a photograph in which the representative emotions are tagged by determining representative emotions of the photographs and then selling the emoticones. In providing and selling photographs to the SNS, To increase the interest of the.

The present invention provides the following means for solving the above problems.

Automatically extracting a tag indicating representative emotion of the photograph based on the content described in the user comment and tagging the user's photograph on the photograph,

Determining a tag reliability for the photograph based on a response result of the plurality of persons after inquiring a plurality of parties about the degree of correspondence between the photograph and the tag; And

And registering the photo and the photo emoticons corresponding to the tag in the emoticon sale market when the tag reliability for the photo is equal to or greater than a predetermined value.

Wherein the step of tagging the photographs representative of the representative emotions of the photographs comprises: classifying words constituting sentences of the user comments by parts of speech using a morpheme analyzer;

Extracting emotional characteristics for the word using a per-part emotional dictionary; And

And classifying the representative emotions of the sentence through the emotion classifier trained in advance using the extracted emotion characteristics.

The step of determining the tag reliability of the photograph may include determining the tag reliability for the photograph based on the percentage of correct answers of the plurality of persons after inquiring of the plurality of persons about the representative sensitivity associated with the photograph, do.

The step of determining the tag reliability for the photograph may include determining at least two photographs having the same representative sensitivity to the plurality of photographers and then determining the tag reliability for the photograph based on the selectivity of the plurality of photographers .

In particular, the method may further include a step of collecting and analyzing tag reliability for each photograph and calculating a credit rating for each user.

In addition, the method may further include providing an incentive corresponding to the user-specific credit rating.

The present invention relates to a method of selling representative emotions corresponding to a photograph in which the representative emotions are tagged by determining representative emotions of the photographs and then selling the emoticones. In providing and selling photographs to the SNS, The effect of the present invention is further enhanced.

1 is a diagram of a method for generating and selling photographic emoticons according to the present invention;
2 is a diagram of a method for generating and selling photographic emoticons according to the present invention

Hereinafter, embodiments and examples of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art to which the present invention pertains.

It should be understood, however, that the present invention may be embodied in many different forms and is not limited to the embodiments and examples described herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout this specification, when an element is referred to as "including " an element, it is understood that the element may include other elements as well, without departing from the other elements unless specifically stated otherwise.

As used herein, the terms "about," " substantially, "and the like are used herein to refer to or approximate the numerical value of manufacturing and material tolerances inherent in the stated sense, Accurate or absolute numbers are used to prevent unauthorized exploitation by unauthorized intruders of the mentioned disclosure. Also, throughout the present specification, the phrase " step "or" step "does not mean" step for.

Throughout this specification, the term "combination thereof" included in the expression of the machine form means one or more combinations or combinations selected from the group consisting of the constituents described in the expression of the machine form, And the like.

Throughout this specification, the description of "A and / or B" means "A or B, or A and B".

According to the present invention, the present invention provides the following means for solving the above problems.

Figure 1 is a representative diagram of a system in which a method for generating and selling photographic emoticons is implemented.

The present invention includes a first step of automatically extracting a tag indicating representative emotions of a photograph based on a content described in the user comment and tagging the user's photograph, A second step of determining a tag reliability for the photograph based on a result of a response of the plurality of parties after inquiring the plurality of parties of the photograph and the degree of correspondence between the tags; And a third step of generating a photo emoticon corresponding to the photo and the tag and registering the photo emoticon in an emoticon sale market when the tag reliability for the photo is equal to or greater than a preset value.

The first step will be described as follows. The present invention is implemented in a server 1 and a provision environment of a terminal 10 used by a user and connected to the server 1 through network communication.

The data in the present invention is data of a picture 30 provided as an image form file and data 31 of a character posted together with the picture 30 and provided as character type information. The server 1 is provided with a sensitivity determination unit 2 for extracting words from the character data 31 provided in synchronization with the photograph 30 to determine the sensibility. The emotion judgment unit (2) matches the emotion of each word in the DB (3). If there are many words matching the specific emotion in the character 31 data, the corresponding photo 30 judges that the emotion has the emotion, and judges it as the current emotion of the user. Then, the emotional state is automatically tagged in the photograph 30 and stored together with the photograph 30 as information.

For example, in the word "travel" in DB (3), the emotional states such as "happiness", "joy", and "comfort" Are matched. Emotional states such as "sorrow", "emptiness" and "pain" are included in the word "farewell", and emotional states such as "sorrow" and "pain" are matched to the word "tear".

For example, when the character 31 data includes the words "travel" and "gift ", the number of emotion states corresponding to each word is counted. Once, "Comfort" is once, and "Joy" is once. In this case, "happiness", which is the emotion state counted most, is tagged in the representative emotion state. Of course, it is also possible that a plurality of emotion states of up to two positions are tagged in addition to one emotion state.

After performing the above operation in the emotion determination unit 2, the photograph 30 and the corresponding representative emotion are uploaded to the data server 4.

The user uses the terminal 10 to increase the SNS. In general, when uploading a picture, the emotional state of the user may be raised, but in many cases, the emotional state is often raised. In addition, the user can request the search using the emotional tag for the photographs that the user has previously taken, and utilize the desired photo by utilizing the search result list.

In this case, the emotion determination unit 2 searches for a post that the user has uploaded to the SNS, for example, around a specific time based on a time point at which the user registered the picture in the SNS. Then, the process of finding the representative emotion described above is performed based on the words included in the letters of the article. The representative emotion obtained as a result is inferred from the representative emotion of the photograph. It describes the step of deriving the user's current emotion based on the newly registered posts in the SNS.

Without such a process, the emotion determination unit 2 may send a question to the user's terminal 10 inquiring about the current emotion state, and the user may infer the photograph and the representative emotion in response thereto.

The steps of extracting and tagging the representative emotions of the photographs described above will be described in more detail as follows.

A task of classifying the words constituting the article by parts of speech is performed. At this time, the morpheme analyzer 6 is used. And the morphological analyzer are implemented in the server is a general description of the contents, so a detailed description will be omitted. In order to extract the emotion feature for the word by using the part-of-speech emotion dictionary (7), emotion is matched to the DB (3) and the corresponding data is used as described above.

Classifying the representative emotions of the sentence through the emotion classifier 8 in which the criterion is set in advance by using the extracted emotional characteristics may be in the order of emotions matched according to the words, It is also possible to do.

Thereafter, a process of evaluating the degree of matching between the photograph and the tag is required. The matching degree between the photograph and the tag is transmitted to the related party client terminal 11 registered in advance through the network in the server 1 and received as a numerical value as the matching value obtained from the related party client terminal 11. [ The reliability evaluation unit 8 adds up all of the feedback matching degrees to determine the tag reliability for the photograph. Here, it is determined whether or not such a tag reliability value is equal to or greater than a predetermined value.

When the tag reliability for the photograph is equal to or greater than a predetermined value, the photograph and the photo emoticons corresponding to the tag are generated and registered in the emoticon sale market 40. Here, market refers to online content trading platforms such as Google Play and App Store.

Here, an example of a step of determining the tag reliability for the photograph is as follows. After inquiring of the plurality of parties about the representative emotion reminded from the photograph, the tag reliability for the photograph may be determined based on the percentage of correct answers of the plurality of parties.

For example, while transmitting the photographs to a plurality of party client terminals, the representative emotions associated with the photographs can be asked in a supportive or multiple-choice manner. An answer is provided from a plurality of party's client terminals. Depending on whether it matches the representative emotion determined in the first step, a correct answer or an incorrect answer is determined, and the tag reliability is determined according to the correct answer rate. In this case, the predetermined reliability will be determined depending on how many percent or more of the percent correct is exceeded.

It is also possible to present at least two photographs having the same representative sensibility to the plurality of parties and then determine the tag reliability for the photograph based on the selectivity of the plurality of parties. A plurality of photographs determined to have the same representative emotion in the first step are transmitted to an interested party client terminal, and after receiving all the selection information for a photograph matching the representative emotion, It is an acceptable method.

And collecting and analyzing the tag reliability of the photograph for each user to calculate a credit rating for each user.

This constitutes a credit DB 9 for each user, and when the number of times the user sells a photograph increases, the user's credit rating also rises accordingly. The credit rating of the user may be stored in the credit DB 9 for each user, and an incentive corresponding to the user's credit rating may be provided as the sales are accumulated.

It will be understood by those of ordinary skill in the art that the foregoing description of the embodiments is for illustrative purposes and that those skilled in the art can easily modify the invention without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be interpreted as being included in the scope of the present invention .

1: Server
2:
3: DB
4: Data server
6: Morphological analyzer
7: Dictionary
8: Emotion classifier
9: Credit DB
10: User terminal
30: Photos
31: Character
40: Market

Claims (3)

When a user's post including a photograph and a user comment on the photo is registered in the server, a tag indicating the representative emotion of the photo is automatically extracted based on the content described in the user comment through the emotion determination unit provided in the server, ;
When the matching of the photographs is completed, the degree of matching between the photograph and the tag is transmitted to a plurality of client terminals registered in advance in the server through a network, and the matching degree Summing and determining a tag reliability for the photograph;
Collecting and analyzing tag reliability of the photographs for each user through a credit DB for each user provided in the server; And
And registering the photo and the photo emoticons corresponding to the tag in the emoticon sale market when the tag reliability for the photo is equal to or greater than a predetermined value,
Wherein the step of automatically tagging the tags representing the representative emotions of the photographs,
Classifying words constituting a sentence of the user comment by parts of speech using a morpheme analyzer;
Extracting emotional characteristics for the word using a per-part emotional dictionary; And
And classifying the representative emotions of the sentence through an emotion classifier in which a criterion is set in advance using the extracted emotion characteristic,
Determining a tag reliability for the photo,
A representative representative of the photographs is contacted to the plurality of persons in question on the basis of the representative emotion reminiscent of the photographs, and then the answers of the plurality of persons are automatically extracted from the tags representing the representative emotions of the photographs, And determining the tag reliability of the photograph based on the percentage of correct answers of the plurality of persons with respect to the matching of the emotions. delete delete

Images