KR20200021663A - Recording Midium - Google Patents

Abstract

The present invention relates to a recording medium, and more particularly, to a recording medium recording a computer program for providing a chat service. If a user-written text written for a chat by a service user using a chat service includes a phrase corresponding to a specific emotion, the expression of an icon character displayed on an input icon of an intension expression image item is changed to an expression corresponding to the specific emotion. After selecting one or more intention expression image items corresponding to the specific emotion from a plurality of pre-stored intension expression image items, a list of intension expression image items including only one or more intension expression image items is generated. The service user using the chat service scores the intension expression image item or the list of the intension expression image item, and efficiently expresses various emotions through the intension expression image item or the list of the intension expression image item rearranged in the order of the intension expression image items preferred by the service user.

Description

Recording medium {Recording Midium}

The present invention relates to a recording medium, and more particularly to a recording medium recording a computer program for providing a chat service.

 The expression image item is a symbol used to express emotions of service users in a chat service, and is a term in which emotions and icons are synthesized.

These expressive image items serve as a supplementary element of communication to help enrich human emotions, and because the emotions are transmitted through a complex signal that reveals human emotions without speaking to the other party, You can also communicate easily.

Early expressional image items were made of simple combinations of symbols and characters on the keyboard or in the form of fixed icons, but recently, various types of characters used to express the emotions of the user using responsive pseudo-expression image items. Developed into.

As the demands of the service users for such expressive image items increase, it has become common to provide various types of expressive image items to the service users in the chat service.

Here, in the conventional chat service, in order for a service user to deliver a pseudo-expression image item for expressing an emotion to a chat partner, the service user first inputs a chat message for expressing his or her feelings into the message display window of the chat window as shown in FIG. Select the Enter Pseudo Image Item icon after or before input.

Then, as shown in FIG. 16, a list of the expression image items corresponding to various kinds of expression image items provided by the chat service is displayed on a part of the chat window, and the service user expresses his or her feelings in the expression image item list. You can select specific expressive image items.

Through this, a specific expression image item corresponding to the specific expression image item may be displayed on the chat window as shown in FIG. 17 and transmitted to the chat partner.

Here, since the pseudo-expression image item list provided by the conventional chat service is irregularly listed with a plurality of pseudo-expression image items expressing various types of expressions or actions as shown in FIG. There was a problem in that a lot of time and effort should be devoted to finding a specific expressive image item for expressing the feelings of the child.

In addition, despite the different expressions of the pseudo-expression image items which are preferred according to the emotional expressions among the expression-expression image items, the same expression expression item items that the user prefers are efficiently used because the list of the pseudo-expression image items is always arranged identically. It was not used.

In addition, the conventional chat service is difficult to express various emotions of the user who transmits the text-based data in real time, and after the text input in the semantic unit is completed or the user additionally selects and transmits the pseudo-expression image item to express the emotion. There was an inconvenience in doing this.

Against this background, it is an object of the present invention to provide an expression of an icon character displayed on a pseudo-expression image item input icon when a user-written text written for chatting by a service user using a chat service includes a phrase corresponding to a specific emotion. Changes to the expression corresponding to a specific emotion, selects one or more pseudo-expression image items corresponding to a specific emotion from among a plurality of pre-stored pseudo-expression image items, and then generates a list of the pseudo-expression image items including only one or more expression items The purpose is to provide a recording medium recording a computer program.

Another object of the present invention is to provide a pseudo-expression image item or a pseudo-rearranged order of pseudo-expression image items or pseudo-expression image items by a service user using a chat service in order of the pseudo-expression image items preferred by the service user. It is an object of the present invention to provide a recording medium on which a computer program is recorded to efficiently express various emotions through a list of expression image items.

Still another object of the present invention is to provide a recording medium for recording a computer program for providing a real-time pseudo-expression image item that can properly express the emotional state of the user while text is input from the user using the chat service. There is this.

In order to achieve the above object, in one aspect, the present invention is provided in the user terminal, the function of receiving the user-written text from the service user and the chat progress with one or more chat partner terminal through the relay of the chat service providing server And a function of displaying a chat window for chatting with the one or more chat partner terminals, storing a plurality of expression image items, and storing a list of a plurality of expression image items including the plurality of expression image items. Store frequency information of a service user's use of the user's expression image items, scoring information, and rescoring information of the service user for the plurality of expression items, and the expression of the icon character included in the plurality of expression items; Multiple emotional expressions children expressed by emotion type A function of storing the information, classifying and managing the plurality of expression expression image items according to element information, and processing a machine learning based on the classification management information to generate a customized image item learning model, and calculated using the learning model. An object of the present invention is to provide a recording medium recording a computer program including a function of acquiring customized setting information and generating recommended setting information based on the customized setting information to provide a customized service to a service user.

As described above, according to the present invention, if the user-written text created by the service user includes a phrase expressing a specific emotion, the expression of the icon character of the pseudo-expression image item input icon displayed on a part of the chat window by the user terminal is specified. Since the display is changed to an expression corresponding to the emotion, the service user may be interested in the chat service.

In addition, if the user-written text includes a phrase expressing a specific emotion, the N pseudo-expression image items corresponding to the specific emotion are selected from among a plurality of pre-stored pseudo-expression image items, and the pseudo-includes only N pseudo-expression image items. Since a list of expression image items can be generated and displayed on the screen, a service user using a chat service can easily select the expression image items for a specific emotion.

In addition, the service user scores a pseudo-expression image item or a list of the expression-expression image item to receive a recommendation of a specific emotion expression image item including a specific emotion expression image item that the service user prefers from the user terminal. The efficiency can be increased.

1 is a view briefly showing the configuration of a chat service providing system according to an embodiment of the present invention;
2 is a block diagram schematically showing the configuration of a chat service providing server according to an embodiment of the present invention;
3 is a view showing in more detail the customized image item providing unit according to an embodiment of the present invention;
4 is a diagram illustrating a plurality of emotional expression icons according to an embodiment of the present invention;
6 to 13 are views illustrating a process of providing a chat service in a user terminal according to an embodiment of the present invention.
14 is a flowchart illustrating a process of providing a chat service in a user terminal according to an embodiment of the present invention;
15 to 17 is a diagram illustrating a conventional process of providing a chat service.

The following merely illustrates the principles of the invention. Therefore, those skilled in the art, although not explicitly described or illustrated herein, may embody the principles of the present invention and invent various devices that fall within the spirit and scope of the present invention. In addition, all conditional terms and embodiments listed herein are in principle clearly intended for the purpose of understanding the concept of the invention and are not to be limited to the specifically listed embodiments and states. Should be.

In addition, it is to be understood that all detailed descriptions, including the principles, aspects, and embodiments of the present invention, as well as listing specific embodiments, are intended to include structural and functional equivalents of these matters. In addition, these equivalents should be understood to include not only equivalents now known, but also equivalents to be developed in the future, that is, all devices invented to perform the same function regardless of structure.

Thus, for example, the block diagrams herein should be understood to represent a conceptual aspect of exemplary circuitry embodying the principles of the invention. Similarly, all flowcharts, state transitions, pseudocodes, etc., are understood to represent various processes performed by the computer or processor, whether the computer may be substantially represented on a readable medium and whether the computer or processor is clearly shown. Should be.

In addition, the explicit use of terms presented in terms of processor, control, or similar concept should not be interpreted exclusively as a citation of hardware capable of executing software, and without limitation, ROM for storing digital signal processor (DSP) hardware, software. (ROM), RAM, and non-volatile memory are to be understood to implicitly include. Other hardware for the governor may also be included.

In addition, the term 'terminal' used in the present invention is a term used to describe the present invention, and the term 'terminal' may be replaced with 'device' or 'server', and has the same meaning and function.

The above objects, features and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, whereby those skilled in the art may easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram briefly illustrating a configuration of a chat service providing system according to an exemplary embodiment of the present invention.

The chat service providing system 100 according to an exemplary embodiment of the present invention includes a service user terminal 110, an internet communication network 120, and a chat service providing server 130.

The user terminal 110 is a terminal in which a chat application for using a chat service according to an embodiment of the present invention is installed. The user terminal 110 connects to the chat service providing server 130 through execution of a chat application, and provides a chat service providing server 130. Through the chat window 400 generated through the use of one or more chat terminal (not shown) and the chat service, that is, it is possible to send and receive chat messages and expression image items with one or more chat partners.

In this case, the pseudo-expression image item may include an image representing the user's emotions, moods, states, and other intentions to express, and the image may include, for example, a emoji format that matches specific expression information. Character emoticon format, or a separate designated picture file format, may be composed of data of the file format to allow movement. In addition, the expression information may include a text indicating the emotion, mood, state or other intention, keywords, additional descriptions, and the like, and one or more keywords and additional descriptions may be matched to one image.

In an embodiment of the present invention, the user terminal 110 stores a plurality of pseudo-expression image items, and stores a list of a plurality of pseudo-expression image items including a plurality of pseudo-expression image items.

In addition, the user terminal 110 may store the plurality of expression expression image items as a plurality of emotion expression icons in which the expression of the icon character is expressed for each emotion type as shown in FIG. 4. Here, the plurality of emotion types may be anger, sadness, fear, joy, depression, and the like.

Through this, the user terminal 110 may provide a chat service according to an embodiment of the present invention as follows.

First, when the message input window 410 of the chat window 400 is blank as shown in FIG. 5 while the user terminal 110 is chatting with at least one chat partner terminal (not shown) through the chat window 400. The user terminal 110 sets the expression of the icon character displayed on the pseudo-expression image item input icon located at a portion of the chat window 400 as the default expression.

Here, the user terminal 110 extracts a basic icon, which is a pseudo-expression image item input icon, in which a facial expression of an icon character is expressed as a basic expression (for example, an expressionless expression) from a plurality of previously stored emotion expression icons, and chats it. A portion of window 400 may be displayed.

Thereafter, the user terminal 110 may receive user-written text from a service user through a keypad or a touch screen provided in the user terminal 110, and the user-written text may be inputted into the message input window of the chat window 400. 410 may be indicated.

In this case, the user terminal 110 analyzes the user-written text through one or more of a plurality of natural language comprehension techniques such as morphological analysis, keyword recognition, speech act analysis, and semantic analysis. You can check whether it is included in the written text. Here, the user-written text refers to text written by a service user through a keypad or a touch screen of the user terminal 110.

As a result of analyzing the user-written text, if the user-created text includes a specific emotional expression phrase, the user terminal 110 expresses the expression of the icon character displayed on the pseudo-expression image item input icon in the basic expression. Can be changed.

Here, the user terminal 110 extracts a specific emotion expression icon, which is a pseudo-expression image item input icon in which the expression of the icon character is expressed with a specific expression, from a plurality of pre-stored emotion expression icons, and a part of the chat window 400. The displayed basic icon 430 may be replaced with the specific emotion expression icons 510 and 710.

In this case, the icon changed from the basic icon 430 to the specific emotion expression icons 510 and 710 is an animated icon that more vividly expresses the emotion expression of the user rather than the fixed icon, or the shaking function, the rotation function, and the larger icon. It may be an effect icon displayed by functions such as a small function, a flying function, an upload function, and a pulse function, and the animated icon and the effective icon may be animated or applied according to a time value set by a system administrator. The form may be repeated. Through the animated icon and the effect icon, the service user has an effect of easily identifying the representative recommendation icon. This may be applied to all of the specific emotion expression icons 510 and 710 described later.

On the other hand, if the user-written text does not include a specific emotional expression phrase, the user terminal 110 is to display the expression of the icon character displayed on the pseudo-expression image item input icon as a basic expression, that is, to continuously display the basic icon 430 The basic icon 430 may be a fixed icon rather than an animated or effect icon.

After changing the expression of the icon character displayed on the pseudo-expression image item input icon from the default expression to the specific expression as described above, if the send button (not shown) is selected by the service user, the user terminal 410 chats the user-written text. In addition to transmitting to the providing server 130, the user-written text displayed on the message input window 410 may be deleted, and the user-written text may be displayed on the message display window 420.

On the other hand, if a user expression text item input icon is selected by the service user while the user-written text is displayed on the message input window 410, the user terminal 110 corresponds to a specific emotion among a plurality of pre-stored pseudo expression image items. First select only N or more pseudo-expression image items, and check the frequency expression information of the service user for N or more pseudo-expression image items corresponding to the N or more pseudo-expression image items. After the second selection of N pseudo-expression image items corresponding to up to N frequently used pseudo-expression image items, a list of specific emotional expression image items including only N pseudo-expression image items is generated. Specific emotions, including only expressive image items. Multiple expressive image item lists may be generated. The user terminal 110 may display a specific emotional expression image item list on a part of the chat window 400 as shown in FIG. 7 or 9.

In this case, the specific emotional expression image item list generated after the above-described second screening process may be used to determine the expression of the pseudo expression image item according to the scoring of the service user described later, that is, the number of times of use of the user expression expression item and feedback information. Arrangements can be rearranged and can recommend a list of pseudo-expression image items to service users. The scoring may be learned through machine learning and deep artificial neural network models, which are pre-built in the user terminal 110, and the user terminal 110 may use the machine learning and artificial neural network models. It performs the function of recommending customized expression image items and item list to service users based on the learned data. Hereinafter, a description will be given of a process in which a service user is recommended a customized expression image item through scoring.

First, a long press of a pseudo-expression image item from a list of N specific emotional expression image items including only the frequently used N expression image items provided by the service user after the above-described second screening process is performed. Click through a click method that includes event features such as click method, double click click method. Thereafter, as shown in FIG. 10, a numeric icon is generated near (upward or downward) the pseudo-expression image item, and a short press click method and a double click on the pseudo-expression image item which the service user wants to prioritize. Click through a click method that includes event features such as click method. For example, the pseudo-expression image items that are sequentially clicked through the short press method are rearranged in the order in which they are clicked, and the numeric icons generated near the pseudo-expression image items are also rearranged in the ascending order. After the above-described process, when the service user closes the list window displayed on a part of the chat window 400, the pseudo-expression image item scoring information of the service user may be stored, and if the service user wants to rescor it, After repeating the above-described process, the pseudo-expression image item score may be recored by re-storing the score, and then, the rescoring information may be stored in the user terminal 110. The pseudo-expression image item scoring information stored through the above-described process may be displayed in a state in which the pseudo-expression image item is rearranged according to the scoring or rescoring information stored by the service user as shown in FIG. 11.

In the present invention, the click method is described only as a long press click method and a short press click method in order to easily explain the invention. However, the click method is not limited to the long press click method and the short press click method. Of course, any click method can be used as long as the method can select an icon or a button through the included click method. The same applies to the example of the click method described below.

Next, the service user may select a list of N specific emotional expression image items including only the frequently used N expression image items provided after the second screening process, or specific emotions in which the expression image items have been rearranged through the scoring. A list of pseudo-expression image items may be scored to receive a recommendation of a personalized expression image item from the user terminal 110. First, among the N specific emotional expression image item lists rearranged according to the above-described scoring, the service user randomly receives a specific emotional expression image item list including one representative icon 810 as shown in FIG. 12. Subsequently, when the service user clicks the representative icon 810 through the long press method, N specific emotional expression image item list scores are differentially arranged according to the long press input duration. Pseudo-expression image item list scoring information is stored. In this case, the pseudo-expression image item included in the N specific emotional expression image item list is generated based on the pre-stored pseudo-expression image item scoring information of the service user or based on a recommendation value preset in the user terminal 110. It may be a list of pseudo-expression image items. In addition, the N specific emotional expression image item list may be randomly generated until a user scores all of the N expression image item lists and stores a score, and the rescoring process may be performed after all of the scores are stored. It can be designed to be executed during the scoring process. In addition, when rescoring, the rescoring information may be stored in the user terminal 110. The pseudo-expression image item list scoring information stored through the above-described process may be displayed in a state in which the pseudo-expression image item list is rearranged according to the score stored by the service user as shown in FIG. 13.

Through the scoring method as described above, the user terminal 110 learns a pseudo-expression image item for a particular emotion preferred by the service user, thereby adding a new pseudo-expression image item in the user terminal 110 or having the same service user for a certain period of time. When using only the expression image items or when the service user clicks the refresh button etc. separately displayed in the expression image item list, the new expression image item and the new expression image that the service user would prefer based on the learned data. I can recommend a list of items. By doing so, the user terminal 110 can easily select and efficiently use the pseudo-expression image item from the list of specific emotional expression image items arranged by giving priority to the expression expression image item for the specific emotion preferred by the service user. do.

For example, before the user inputs a written text through the message input window 410 of the chat window 400 as shown in FIG. 5, the expression of the icon character is the basic expression (the faceless face image of FIG. 5). The basic icon 430, which is a pseudo-expression image item input icon, may be displayed on a part of the chat window 400.

And when receiving the user-written text 'like ^^' from the service user through the keypad or touch screen, as shown in Figure 6, the user terminal 110 the user input text 'like ^^' the message input window 410 In addition to expressing certain emotions by expressing specific feelings by analyzing user-written text 'likes ^^' through one or more of many natural language understanding techniques such as morphological analysis, keyword analysis, speech act analysis, semantic analysis, etc. You can check whether is included in the user-written text.

Here, since "good" is an emotional expression phrase corresponding to pleasure among a plurality of emotion types such as anger, sadness, fear, and enjoyment, the user terminal 110 may determine a certain emotion that the service user feels as "pleasure". 5, the basic icon 430 of FIG. 5 may be replaced with a specific emotion expression icon 510 corresponding to pleasure as shown in FIG. 6.

Subsequently, when the service user selects a specific emotion expression icon 510, the user terminal 110 firstly stores only N or more expression image items corresponding to a 'emotion' which is a specific emotion among a plurality of pre-stored pseudo expression image items. Select. Thereafter, the service user expresses the frequency of use of the pseudo-expression image item for the N or more pseudo-expression image items corresponding to the N or more pseudo-expression image items, and up to N pseudo-expression image items having a high frequency of use of the pseudo-expression image item. After the N pseudo-expression image items corresponding to the second selection are generated, a specific emotional expression image item list including only N pseudo-expression image items is generated.

In this case, the service user may assign a priority to the pseudo expression image item included in the specific emotional expression image item list including only N or more expression image items. First, a service user clicks through a long press method any one expression image item from the list of N specific emotion expression image items including only the frequently used N expression image items provided after the second screening process. In this case, a number icon is created near the pseudo-expression image item. Subsequently, when the user first clicks on the pseudo-expression image items preferred by the short press method, the arrangement of the pseudo-expression image items is rearranged in order, and the number icon is also displayed according to the arrangement of the rearranged pseudo-expression image items. Reassigned in ascending order. Through the above-described process, the user terminal 110 displays a specific emotional expression image item list for pleasure on a portion of the chat window 400 as shown in FIG. 11, but the expression expression image items are arranged in the order preferred by the service user. By providing a list of specific emotional expression image items, the service user can easily select one expression image item corresponding to a specific emotion, 'pleasure', from the specific emotional expression image item list. Here, as shown in FIG. 11, the service user may select a specific emotion expression icon 510 disposed in the order of priority while the user-written text 'liked ^^' is displayed on the message input window 310.

For another example, in the state in which the user terminal 110 displays the basic icon 430 on a part of the chat window 400 as shown in FIG. When received through a keypad or a touch screen, the user terminal 110 displays the user-written text 'Feel by Me' on the message input window 410, and also includes a number of morphological analysis, keyword recognition, speech act analysis, semantic analysis, and the like. One or more of the natural language comprehension techniques of the user may analyze user-written text 'by mood,' and determine whether the user-written text includes a specific emotional expression phrase, a phrase expressing a specific emotion.

In this case, since the 'feeling not good' is an emotional expression phrase corresponding to 'depressed' among a plurality of emotion types such as anger, sadness, fear, pleasure, and depression, the user terminal 110 'depresses' certain emotions felt by the service user. 5, the basic icon 430 of FIG. 5 may be replaced with a specific emotional expression icon 710 corresponding to depression, as shown in FIG. 8.

Subsequently, when the service user selects a specific emotion expression icon 710, the user terminal 110 firstly stores only N or more expression expression image items corresponding to 'depression' which is a specific emotion among a plurality of pre-stored expression expression items. Select and express the service user's expression image item usage frequency information on the N or more expression image items corresponding to the N or more expression image items, and then use the expression expression items up to N frequently used. After the second selection of N pseudo-expression image items corresponding to the item, a list of specific emotional expression image items including only N pseudo-expression image items is generated.

In this case, the service user may assign a score to the specific emotional expression image item lists and receive a recommendation of the specific emotional expression image item list from the user terminal 110 later. In this case, the pseudo-expression image item included in the specific emotional expression image item list may be N pseudo-expression image items after the above-described second screening process or N pseudo-expression image items designated by the service user with priority. First, the service user is recommended from the user terminal 110 a specific emotional expression image item list including one representative icon 810. Thereafter, the service user clicks the representative icon 810 through a long press method, and gives a score to a specific emotional expression image item list by varying the length of the long press input. Here, the user terminal 110 may repeatedly recommend the specific emotion expression image item list until the service user has scored all of the N specific emotion expression image item lists, and the N specific emotion expression image items may be recommended. When all of the scores are assigned to the item list, the user terminal 110 learns a list of N specific emotional expression image items assigned by the service user and newly recommends a specific emotional expression image item list that the service user may prefer. . Through the above-described process, the user terminal 110 displays a specific emotional expression image item list corresponding to depression on a part of the chat window 400 as shown in FIG. 13, and includes the expression expression image item that the service user may prefer. By recommending the list of expressive expression image items, the service user can easily select any one of the expressive expression image items corresponding to the specific emotion 'depression' from the list of specific expressive expression image items recommended by the user terminal 110. . Here, as shown in FIG. 13, the service user may select a specific emotion expression icon 710 in a state where the user-written text of 'by the mood' is displayed on the message input window 410.

On the other hand, if the send a chat message button (not shown) by the service user is selected, the user terminal 110 generates a chat message transmission request information and transmits to the chat service providing server 130 and the message input window 410 The user-written text displayed on the screen may be displayed on the message display window 420.

In addition, the facial expression of the icon character displayed on the pseudo-expression image item input icon may be changed from a specific facial expression to the basic facial expression.

The Internet communication network 120 is a means for mediating data transmission and reception between the user terminal 110 and the chat service providing server 130 and data transmission and reception between the chat service providing server 130 and one or more chat counterpart terminals (not shown). Network, wireless LAN network, Wideband Code Division Multiple Access (WCDMA) network, High Speed Downlink Packet Access (HSDPA) network, Long Term Evolution (LTE) network, LTE Advanced (LTE-A) network, 5G mobile communication network, etc. Can be.

The chat service providing server 130 is a device for providing a chat service to the user terminal 110 and at least one chat counterpart terminal (not shown) according to an embodiment of the present invention, and may be configured as a single server or two or more servers. have.

The chat service providing server 130 provides a chat application to the user terminal 110 and one or more chat counterpart terminals (not shown).

In addition, the chat service providing server 130 relays a chat message transmission and reception between the user terminal 110 running the chat application and one or more chat counterpart terminals (not shown).

In other words, the chat service providing server 130 receives from the user terminal 110 in the message display window 420 of the chat window 400 for the chat proceeding between the user terminal 110 and one or more chat counterpart terminals (not shown). Post a chat message and a chat message received from one or more chat partner terminals (not shown), and post a pseudo-expression image item selected by the user terminal 110 to the message display window 420 of the chat window 400, or The pseudo-expression image item selected by the chat partner terminal (not shown) may be posted on the message display window 420 of the chat window 400.

As described above, in the embodiment of the present invention, if the user terminal 110 analyzes the user-written text and includes the phrase expressing a specific emotion in the user-written text, the pseudo-expression image item included in the chat window 400 is input. Since the facial expression of the icon is changed to a specific facial expression corresponding to a specific emotion, the service user may be interested in the chat service.

In addition, when the user terminal 110 analyzes the user-written text and includes the phrase expressing a specific emotion in the user-written text, the user terminal 110 selects one or more pseudo-expression image items corresponding to the specific emotion from a plurality of pre-stored pseudo-expression image items. Since the user can select and express a list of the expression image items including only one or more expression image items in the chat window 400, a user of the service using the chat service can easily select the expression image items for a particular emotion. Will be.

In addition, the user terminal 110 learns the scoring information scored by the service user and recommends a specific emotion expression image item list including the specific emotion expression image item that the user prefers to the service user to improve the efficiency of the chat service. You can increase it.

Hereinafter, the configuration of the user terminal 110 according to an embodiment of the present invention will be described in detail.

2 is a block diagram schematically illustrating a configuration of a user terminal according to an exemplary embodiment of the present invention.

The user terminal 110 according to an exemplary embodiment of the present invention includes a wireless communication unit 210, a display unit 220, a memory unit 230, an information input unit 240, a control unit 270, and a custom image item providing unit 260. It includes.

The wireless communication unit 210 performs data transmission and reception with the chat service providing server 130 connected through a mobile communication network or a Wi-Fi network.

In other words, the wireless communication unit 210 transmits one or more of the user-written text and the pseudo-expression image item inputted by the service user through the information input unit 240 to the chat service providing server 130, and at least one chat counterpart terminal ( One or more terminals (not shown) may receive one or more of a chat message or a pseudo-expression image item transmitted to the chat service providing server 130 from the chat service providing server 130.

The display 220 displays information processed by the user terminal 110. For example, when the user terminal 110 is in a voice call, a voice connection screen such as a voice call related user interface (UI), a graphic user interface (GUI), and the like is displayed. In addition, when the chat application is running in the user terminal 110, the display unit 220 may display a screen such as a UI or a GUI associated with the chat application.

In other words, the display 220 may display a chat window 400 for a chat progress between the user terminal 110 and one or more chat counterpart terminals (not shown).

The display unit 220 may include at least one of a liquid crystal display, a thin film transistor liquid crystal display, and an organic light emitting diode.

The memory unit 230 may store an operation program for controlling the operation of the controller 270, that is, the overall operation of the user terminal 110, an application installed in the user terminal 110, content, and the like.

In an embodiment of the present invention, the memory unit 230 stores a plurality of pseudo-expression image items, and stores a list of a plurality of pseudo-expression image items including a plurality of pseudo-expression image items.

In addition, the memory unit 230 may store information on the frequency of use of the pseudo-expression image item of the service user for each of the plurality of pseudo-expression image items, and may store scoring information and rescoring information of the service user.

The memory unit 230 may store a plurality of emotion expression icons in which the expressions of the icon characters included in the plurality of pseudo-expression image items are expressed for each of a plurality of emotion types. Here, the plurality of emotion types may be anger, sadness, fear, joy, depression, and the like.

The memory unit 230 may include a flash memory type, a card type memory (for example, SD or micro SD memory), a random access memory (RAM), and a static random access memory (SRAM) ROM. It may include at least one of -Only Memory (PROM), Programmable Read-Only Memory (PROM), Electrically Erasable Programmable Read-Only Memory (EEPROM).

The information input unit 240 is a means for receiving information from a service user and may be configured as a keypad, a touch screen, or the like.

In an embodiment of the present invention, the information input unit 240 may receive a user-written text from a service user.

The image item manager 250 may match and store the pseudo-expression image items stored through the memory 230 according to the classification information.

The classification information may include attribute information for each element of the image item, and the attribute information for each element may include, for example, pseudo expression type information, image type information, scoring information (user count information and feedback information), and the like. May be exemplified.

In addition, the image item manager 250 may receive the feedback information received from the user terminal 110 through the information input unit 240 and apply the classification information of the pseudo-expression image item. For example, the information may include at least one of element-specific evaluation information, report information, or utilization information corresponding to the intentional expression image item.

In particular, when the report information is received, the image item management unit 250 may perform a process of correcting or deleting a pseudo-expression image item corresponding to the report information, such that the update of the memory unit 230 is processed in real time. User feedback corresponding to each expression image item may be actively reflected.

The customized image item providing unit 260 learns the data scored by the service user through machine learning and deep artificial neural network model, and based on the learned information, a doctor who may prefer the service user. The expression image item and the expression image item list are recommended to the service user.

More specifically, the customized image item providing unit 260 may include a user customized recommendation unit 261, a machine learning processing unit 263, and a feedback information weight applying unit 265, and the customized pseudo expression generated according to machine learning. A customized image item learning model 262 including an image item and a list of customized pseudo-expression image items may be provided through the memory unit 230.

The machine learning processing unit 263 processes the machine learning of the expression image item and the item list based on the classification management information of the image item management unit 250 to generate a customized image item learning model 262, and generates the generated image item learning model 262. The customized image item learning model 262 is processed to be stored in the memory 230.

Here, the custom image item learning model 262 may include a learning model for deriving a custom setting information matching algorithm for generating an image item, and may include classification information of an image item as an input variable, and an output variable. May include recommendation setting information for recommendation between the pseudo-expression image items. The customized setting information may include customized expressive image item information and customized expressive image item list information based on the scoring information of the service user, and the recommended setting information is a mobile communication terminal 110 set based on the customized setting information. ) May include recommending expression image item information and recommendation expression image item list information recommended to the service user.

One or more processing methods may be used for the machine learning algorithm in the machine learning processing unit 263. Further, the input variable and the target variable may be applied to a combination of the plurality of machine learning algorithms and the plurality of machine learning algorithms to pre-learn and learn. The optimal machine learning algorithm may be determined in consideration of at least one of the accuracy of each algorithm, the calculation time compared to the accuracy, the performance ratio, and the fitness of the model.

Machine learning algorithms processed by the machine learning processing unit 263 include, for example, Ridge Regression, Logistic Regression, Generalized Linear Model, Random Forest, and Change. A gradient boosting model, a neural network, or the like can be used.

Ridge regression is a basic linear model that provides additional parameters to handle extremes or outliers. Logistic regression analysis is a basic linear model and is effective to use when the target variable, that is, the target to be predicted, shows a binomial distribution. The generalized linear model is a basic linear model and it is effective to use it when the target variable shows Poisson distribution. A random forest ensemble model that consists of multiple decision trees. Each decision tree is developed individually considering the correlation between input variables and target variables and has more flexible characteristics than the upper linear model. The change stimulus model, also called the Generalized Boosting Model or GBM, is an ensemble model that has a similar tendency to a random forest, or that each decision tree is opened considering the accuracy of the decision tree that has already been created. It is also considered.

Neural networks are highly flexible models that can predict virtually any target, so parameter tuning needs to be fine-tuned because they can encompass both linear and non-linear patterns. In particular, the neural network is a statistical learning algorithm inspired by the neural network of biology in machine learning and cognitive science, and the deep learning method can be implemented by combining such neural networks.

For example, a neural network may include a convolutional neural network (CNN) that is optimized along with overall fully connected (FC), max pooling, and convolution, and recurrent neural networks (RNNs) useful for time-series data.

When the neural network learning process is used, for example, the machine learning processor 263 generates a predicted value of the customized image item learning model 262 generated according to the customized setting information from the classification information of the image item memory unit 230. In order to minimize the difference between the process and the prediction value and the actual classification information value, a learning process (backpropagation) may be performed to update the weight of the connection. To this end, the machine learning processor 263 inclines the cost function by dividing the cost function with respect to the weight and then repeatedly shifts the weight little by little in the direction of the slope to find a weight that minimizes the difference between the actual value and the predicted value. Gradient descent, etc., can be used to learn the optimal customized configuration information similar to the real world.

When the machine learning is processed as described above, the user-customized recommendation unit 261 determines and generates a recommendation expression image item and a recommendation expression image item list based on the scoring information of the service user to display the recommended setting information to the service user. Can provide customized service.

The image item manager 250 receives feedback information corresponding to the customized pseudo-expression image item and the customized pseudo-expression image item list generated from the user terminal 110 and stores data corresponding to the feedback information. The update process may be performed through the unit 230.

On the other hand, the feedback information weight applying unit 265 is based on at least one of the element-specific evaluation information and the utilization information obtained from the feedback information, the customized setting information corresponding to the feedback target customized image item list and the feedback target customized image item list Weight tuning can be handled.

The controller 270 controls the overall operation of the user terminal 110.

The controller 270 may be an application processor unit that performs control and processing related to a voice call, data communication, and execution of an application program.

In an embodiment of the present invention, the control unit 270 may provide a chat service according to an embodiment of the present invention when chatting with one or more chat counterpart terminals (not shown) through the chat service providing server 130 as follows. .

Through this, the user terminal 110 may provide a chat service according to an embodiment of the present invention as follows.

First, when the message input window 410 of the chat window 400 is blank as shown in FIG. 5 while the user terminal 110 is chatting with at least one chat partner terminal (not shown) through the chat window 400. The controller 270 sets the expression of the icon character displayed on the pseudo-expression image item input icon located at a portion of the chat window 400 as the default expression.

Here, the controller 270 extracts a basic icon, which is a pseudo-expression image item input icon, in which the expression of the icon character is expressed as a basic expression (for example, an expressionless expression) from a plurality of emotion expression icons stored in the memory 230. The display 220 may display a basic icon on a portion of the chat window 400.

Thereafter, the controller 270 may receive user-written text from the service user through the information inputter 240, and input the user-written text into the message input window 410 of the chat window 400.

At this time, the controller 270 analyzes the user-written text through one or more of a plurality of natural language understanding techniques such as morphological analysis, keyword recognition, speech act analysis, semantic analysis, and the like. You can check whether it is included in the text.

As a result of analyzing the user-written text, if the user-written text includes a specific emotional expression phrase, the controller 270 may change the expression of the icon character displayed on the pseudo expression image item input icon from the basic expression to the specific expression corresponding to the specific emotion. Change it.

Here, the controller 270 extracts a specific emotion expression icon, which is a pseudo expression image item input icon in which an expression of an icon character is expressed with a specific expression, from the plurality of emotion expression icons stored in the memory 230, and displays the display 220. The basic icon 430 displayed on a part of the chat window 400 may be replaced with specific emotion expression icons 510 and 710 to be displayed.

On the other hand, if a specific emotion expression phrase is not included in the user-written text, the controller 270 displays the expression of the icon character displayed on the pseudo-expression image item input icon as the basic expression, that is, the basic icon 430 on the display 220. Should be displayed continuously.

After the expression of the icon character displayed on the pseudo-expression image item input icon is changed from the default expression to the specific expression, when the send button (not shown) included in the chat window 400 is selected by the service user, the control unit 270. The user transmits the user-written text to the chat service providing server 130 through the wireless communication unit 210, deletes the user-written text input in the message input window 410, and transmits the user-written text to the message display window 420. You can enter

The control unit 270 controls to change the expression of the icon character displayed on the pseudo-expression image item input icon from the specific expression to the basic expression, that is, the display unit 220 changes the expression of the icon character from the specific expression to the basic expression. It can be changed and displayed again.

Meanwhile, when a pseudo expression image item input icon is selected by the service user while the user-written text is displayed on the message input window 410, the controller 270 may identify a specific expression image item among a plurality of pseudo expression image items stored in the memory 230. Only N or more pseudo-expression image items corresponding to the emotion are selected first.

Then, the service user expresses the frequency of use of the pseudo-expression image item for the N or more pseudo-expression image items corresponding to the N or more pseudo-expression image items, and up to N pseudo-expression image items having a high frequency of use of the pseudo-expression image item. After the N pseudo-expression image items corresponding to the second selection are generated, a specific emotion expression image item list including only N expression image items is generated, and a specific emotion expression image item list as shown in FIG. 7 or 9 is generated. It can be displayed on a portion of the chat window (400).

Through this, the service user can easily select the expression image item for the specific emotion from the specific emotion expression image item list.

In an embodiment of the present invention, the control unit 270 may arrange the N pseudo-expression image items in order of high frequency when generating a specific emotional expression image item list.

In addition, the controller 270 may provide the service user with the customized image item providing unit 260 to the service user based on the scoring information of the service user stored in the memory unit 230. Allows the user to recommend a list of specific emotional expression image items and specific emotional expression image items that the user would prefer.

First, any one of the expressive image items in the list of N specific emotional expressive image items including only the frequently used N expressive image items provided by the service user after the above-described second screening process displayed on the display 220 Click through the long press method. Subsequently, a numeric icon is generated in the vicinity of the pseudo-expression image item (upper or lower) as shown in FIG. 10, and the short press method of the pseudo-expression image item to be prioritized by the service user is performed. Click in turn. The pseudo expression image items that are sequentially clicked through the short press method are stored in the memory unit 230 as specific emotional expression image item scoring information, and the arrangement is rearranged in the order in which the service user clicks as shown in FIG. Numerical icons created near the representation image item are also rearranged in ascending order in the order in which the service user clicks.

Next, the controller 270 services the customized image item providing unit 260 based on the specific emotional expression image item scoring information stored in the memory unit 230 machined through the customized image item providing unit 260. Allows the user to recommend a list of specific emotional expression image items.

First, the controller 270 of the N specific emotional expression image item list in which the pseudo expression image item is rearranged according to the specific emotional expression image item scoring information stored in the memory unit 230 is represented by a representative icon 810. The display unit 220 randomly displays a specific emotional expression image item list including a). Subsequently, when the service user clicks on the representative icon 810 displayed on the display unit 220 through the long press method, the N specific emotional expression image item list scores are differentially differentiated according to the duration of the long press input. This is stored in the memory unit 230 as specific emotional expression image item list scoring information.

In this case, the service user may re-correlate the score and the list score by repeating the above-described process, and the re-cored information may be stored in the memory unit 230 as re-coring information.

Hereinafter, a process of providing a chat service by the user terminal 110 according to an exemplary embodiment of the present invention will be described.

14 is a flowchart illustrating a process of providing a chat service in a user terminal according to an embodiment of the present invention.

Before the user-written text is input into the message input window 410 of the chat window 400 displayed on the user terminal 110 during a chat between the user terminal 110 and at least one chat partner terminal (not shown), that is, If the message input window 410 is blank, the user terminal 110 sets the expression of the icon character displayed on the pseudo-expression image item input icon located at a portion of the chat window 400 as the default expression (S910). Here, the user terminal 110 extracts a basic icon, which is a pseudo-expression image item input icon, in which an expression of an icon character is expressed as a basic expression (for example, an expressionless expression) from a plurality of previously stored emotion expression icons, and the chat icon is used as a chat window. A portion of 400 may be displayed.

Thereafter, the user terminal 110 may receive a user-written text from a service user through a keypad or a touch screen provided in the user terminal 110 (S920).

In addition, the user terminal 110 displays the user-written text in the message input window 410 of the chat window 400 and at least one of a plurality of natural language understanding technologies such as morphological analysis, keyword recognition, speech act analysis, semantic analysis, and the like. Through the analysis of the user-written text, it is possible to check whether the specific emotional expression phrase, which is a phrase expressing a specific emotion, is included in the user-written text (S930).

As a result of analyzing the user-written text, if the user-created text includes a specific emotional expression phrase, the user terminal 110 expresses the expression of the icon character displayed on the pseudo-expression image item input icon in the basic expression. Change to (S950).

Here, the user terminal 110 extracts a specific emotion expression icon, which is a pseudo-expression image item input icon in which the expression of the icon character is expressed with a specific expression, from a plurality of pre-stored emotion expression icons, and a part of the chat window 400. The displayed basic icon 430 may be replaced with the specific emotion expression icons 510 and 710.

On the other hand, if the user-written text does not include a specific emotional expression phrase, the user terminal 110 is to display the expression of the icon character displayed on the pseudo-expression image item input icon as a basic expression, that is, to continuously display the basic icon 430 Can be.

When the expression of the expression expression item item is selected by the service user in a state where the expression of the icon character is changed to a specific expression, the user terminal 110 selects N or more corresponding to a specific emotion from among a plurality of stored expression expression image items. The first screening of only the expressive expression image items, and the frequency of use of the expressive expression item items of the service user for the N or more expression expression image items corresponding to the N or more expression expression image items is checked. N pseudo expression image items corresponding to up to N pseudo expression image items are secondarily selected. Thereafter, the user terminal 110 generates and stores a specific emotional expression image item list including only N pseudo expression image items, and also displays the specific emotional expression image item list as shown in FIG. 7 or 9 in the chat window 400. A portion can be displayed (S960, S970).

The specific emotion expression image item list displayed on a portion of the chat window 400 may be included in the expression expression image item and the expression expression item list based on the scoring information of the service user, that is, the classification management information of the image item management unit 250. Accordingly, the machine learning process in the machine learning processing unit 263 may arrange the pseudo-expression image items as shown in FIG. 11 or 13. Here, the scoring information may be stored in the user terminal 110 as the service user selects a pseudo-expression image item through a click method including an event property function, and the machine learning processing unit 263 , Ridge Regression and Logistic Regression, which are pre-built in the user terminal 110, for the machine learning of the expression image item and the item list based on the classification management information of the image item manager 250. Learn a list of pseudo-expression image items scored by service users through machine learning algorithms such as, Generalized Linear Model, Random Forest, GradientBoosting Model, and Neural Network To create a custom image item learning model (262), And processing system that learning model 262 is stored in the memory unit 230, obtains the customized configuration information that is calculated from the customized image items learning model 262 (S980).

Subsequently, the mobile terminal 110 generates and displays recommendation setting information including the recommendation expression image item information and the recommendation expression image item list information recommended by the mobile terminal 110 based on the customized setting information, thereby customizing the service user. Provides (S990).

By doing so, the user terminal 110 can easily select and efficiently use the pseudo-expression image item from the list of specific emotional expression image items arranged by giving priority to the expression expression image item for the specific emotion preferred by the service user. do.

In the above description, all the components constituting the embodiments of the present invention are described as being combined or operating in combination, but the present invention is not necessarily limited to the embodiments. In other words, within the scope of the present invention, all of the components may be selectively operated in combination with one or more. The above description is merely illustrative of the technical idea of the present invention, and those skilled in the art may make various modifications and changes without departing from the essential characteristics of the present invention. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

Claims (4)

A function provided in the user terminal to receive a user-written text from a service user;
Displaying a chat window for chatting with at least one chat partner terminal when chatting with at least one chat partner terminal through a relay of a chat service providing server;
Store a plurality of expression image items, store a list of expression images items including the plurality of expression image items, and use frequency information of a service expression of the service user for the plurality of expression images items. And storing score information and rescoring information of the service user, and storing a plurality of emotion expression icons in which the expressions of the icon characters included in the plurality of pseudo-expression image items are expressed for each emotion type.
Classifying and managing the plurality of pseudo-expression image items according to element information;
Machine learning based on the classification management information is generated to generate a customized image item learning model, obtain customized setting information calculated using the learning model, and generate recommended setting information based on the customized setting information to a service user. A computer-readable recording medium comprising a program for executing a function of providing a customized service.
The method of claim 1,
The scoring information is configured through a function of storing a score by a service user clicking on one of the pseudo-expression image item through a click method including an event property function.
The method of claim 1,
The custom setting information may include personalized expression image item information and personalized expression image item list information.
The method of claim 1,
The recommendation setting information may include recommendation expression image item information and recommendation expression image item list information recommended by a mobile communication terminal set based on the customized setting information.

Images